diff --git a/CLAUDE.md b/CLAUDE.md index a3ca72d2..755710e3 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -294,6 +294,18 @@ not against a fixed cutoff; each reports that null in a gates table in `summary. frequency cutoff cannot substitute: it implicitly assumes a zero background, which holds in a simulation and in nothing else. +For `SC` the score is not what does most of the work on real data — the **strand** test is +(`--soft-clipping-fisher-strand-p-value-cutoff`, reject `FISHER_STRAND`). The dominant SC false +positive is a dark-cycle poly-G read tail, which is always the read's 3' end and therefore appears +on exactly one strand for a given clip direction, whereas reads clipped at a real breakpoint come +from both. Measured over 29 LTEE clones, 95% of accepted SC calls had every clipped read on one +strand. The tail-consensus test cannot see this at all, because poly-G tails agree with each other +perfectly; the companion `LOW_COMPLEXITY_TAIL` gate +(`--soft-clipping-maximum-tail-homopolymer-fraction`) catches the low-count positions where the +strand test has no power. The SC gates table in `summary.html` reports what fraction of the run's +clip events were one-strand — a value near 100% means the run's clipping is artifact, and it is the +first thing to check when a library predicts implausibly many SC items. + Validation/annotation types: `CURA`, `FPOS`, `PHYL`, `TSEQ`, `PFLP`, `RFLP`, `PFGE`, `NOTE`, `MASK` ### Key modules diff --git a/src/breseq/breseq_cmdline.cpp b/src/breseq/breseq_cmdline.cpp index be393c8f..528d0a0e 100644 --- a/src/breseq/breseq_cmdline.cpp +++ b/src/breseq/breseq_cmdline.cpp @@ -2843,7 +2843,7 @@ int breseq_default_action(int argc, char* argv[]) // record the final time and print summary table settings.record_end_time("Output"); - output::html_summary(settings.summary_html_file_name, settings, summary, ref_seq_info); + output::html_summary(settings.summary_html_file_name, settings, summary, ref_seq_info, gd); // Remove the individual evidence files now that everything is archived. // Skipped under --keep-intermediates so the raw evidence/ dir (plots, alignments) diff --git a/src/breseq/genome_diff_entry.cpp b/src/breseq/genome_diff_entry.cpp index 46679d41..e927c468 100644 --- a/src/breseq/genome_diff_entry.cpp +++ b/src/breseq/genome_diff_entry.cpp @@ -176,6 +176,10 @@ namespace breseq { const char* SC_AGREE_COUNT = "agree_read_count"; const char* SC_CONSENSUS_FRACTION = "consensus_fraction"; const char* SC_CONSENSUS_TAIL = "clipped_sequence"; + const char* SC_AGREE_COUNT_FORWARD = "agree_read_count_forward"; + const char* SC_AGREE_COUNT_REVERSE = "agree_read_count_reverse"; + const char* SC_SPANNING_COUNT_FORWARD = "spanning_read_count_forward"; + const char* SC_SPANNING_COUNT_REVERSE = "spanning_read_count_reverse"; //For CN const char* COPY_NUMBER = "copy_number"; diff --git a/src/breseq/genome_diff_entry.h b/src/breseq/genome_diff_entry.h index a1bbca18..4d958a59 100644 --- a/src/breseq/genome_diff_entry.h +++ b/src/breseq/genome_diff_entry.h @@ -188,6 +188,10 @@ namespace breseq { extern const char* SC_AGREE_COUNT; extern const char* SC_CONSENSUS_FRACTION; extern const char* SC_CONSENSUS_TAIL; + extern const char* SC_AGREE_COUNT_FORWARD; + extern const char* SC_AGREE_COUNT_REVERSE; + extern const char* SC_SPANNING_COUNT_FORWARD; + extern const char* SC_SPANNING_COUNT_REVERSE; //For CN extern const char* COPY_NUMBER; diff --git a/src/breseq/identify_mutations.cpp b/src/breseq/identify_mutations.cpp index 219eef8b..49788112 100644 --- a/src/breseq/identify_mutations.cpp +++ b/src/breseq/identify_mutations.cpp @@ -1036,6 +1036,64 @@ void identify_mutations_pileup::load_user_ra_evidence_from_gd() _user_evidence_ra_list = gd.get_list(make_vector(RA)); } +// Size the genome-wide spanning strand split is rescaled to when it stands in for a position's +// own (absent) read-through population in the SC strand test. Large enough that the resulting +// hypergeometric is numerically a binomial against that ratio, small enough to stay well inside +// the range where fisher_exact_test_2x2's lgamma arithmetic is exact. +const double kSCStrandFallbackScale = 10000.0; + +/*! Is a consensus clipped tail low-complexity enough to be an end-of-read artifact rather than + donor sequence? + + Two ways to fail, because the same artifact shows up in both shapes. A dark-cycle poly-G tail + is one unbroken run (GGGGGGGGGGGG, or CCCCCCCCCCCC once stored reference-forward for a leading + clip); a tail that straddles the start of the dark cycles is broken but still nearly all one + base (AAAAAACCCCCC, GGGGGGGGTTTT). Measured over 29 LTEE clones, 929 of 1040 accepted SC calls + had a run of >= 8 in 12 bases, and no plausible real breakpoint did. + + Both thresholds are fractions of the compared length rather than absolute counts, so they hold + when --soft-clipping-minimum-bases changes. Either fraction at 0 turns that half off. + */ +static bool sc_tail_is_low_complexity(const string& tail, + double maximum_homopolymer_fraction, + double maximum_base_fraction) +{ + if (tail.empty() || (tail == ".")) return false; + + // Non-ACGT columns are not evidence of anything either way, so they are excluded from both + // the numerators and the denominator. + map counts; + uint32_t informative = 0; + uint32_t longest_run = 0, run = 0; + char run_base = '\0'; + for (size_t i = 0; i < tail.size(); i++) { + char b = static_cast(toupper(static_cast(tail[i]))); + if ((b != 'A') && (b != 'C') && (b != 'G') && (b != 'T')) { run = 0; run_base = '\0'; continue; } + informative++; + counts[b]++; + if (b == run_base) run++; else { run_base = b; run = 1; } + if (run > longest_run) longest_run = run; + } + if (informative == 0) return false; + + // The epsilon is not cosmetic: the intended reading of the 0.66 default at 12 compared bases is + // "8 of 12", and a fraction that multiplies out to exactly the integer count must include it + // rather than fall on the wrong side of a rounding step. + const double kEpsilon = 1e-9; + double n = static_cast(informative); + if ((maximum_homopolymer_fraction > 0.0) && + (static_cast(longest_run) >= maximum_homopolymer_fraction * n - kEpsilon)) return true; + + uint32_t most_common = 0; + for (map::const_iterator it = counts.begin(); it != counts.end(); it++) { + if (it->second > most_common) most_common = it->second; + } + if ((maximum_base_fraction > 0.0) && + (static_cast(most_common) >= maximum_base_fraction * n - kEpsilon)) return true; + + return false; +} + void identify_mutations_pileup::add_sc_evidence(const Summary& summary, const cReferenceSequences& ref_seq_info) { if (!file_exists(_settings.soft_clipping_counts_file_name.c_str())) return; @@ -1076,14 +1134,21 @@ void identify_mutations_pileup::add_sc_evidence(const Summary& summary, const cR uint32_t clipped_count; uint32_t total_count; uint32_t agree_count; + uint32_t agree_count_fw; // agree_count split by the strand of the clipped read + uint32_t agree_count_rv; + uint32_t spanning_fw; // read-through reads here, split the same way + uint32_t spanning_rv; string consensus_tail; double score; double frequency; double consensus_fraction; + double fisher_strand_p_value; bool suppressed; sc_candidate() : position(0), direction(0), clipped_count(0), total_count(0), - agree_count(0), score(0.0), frequency(0.0), consensus_fraction(0.0), + agree_count(0), agree_count_fw(0), agree_count_rv(0), + spanning_fw(0), spanning_rv(0), score(0.0), frequency(0.0), + consensus_fraction(0.0), fisher_strand_p_value(1.0), suppressed(false) {} static bool by_seq_direction_position(const sc_candidate& a, const sc_candidate& b) { @@ -1104,7 +1169,7 @@ void identify_mutations_pileup::add_sc_evidence(const Summary& summary, const cR + _settings.soft_clipping_counts_file_name + "\nDelete 07_error_calibration/error_counts.done and re-run to regenerate it."); { - string expected = "#sc_format=2\tsoft_clipping_minimum_bases=" + to_string(_settings.soft_clipping_minimum_bases); + string expected = "#sc_format=3\tsoft_clipping_minimum_bases=" + to_string(_settings.soft_clipping_minimum_bases); ASSERT(line.substr(0, expected.size()) == expected, "Soft-clipping counts file was tabulated with different settings than the current run:\n " + line + "\nDelete 07_error_calibration/error_counts.done and re-run to regenerate it."); @@ -1121,7 +1186,7 @@ void identify_mutations_pileup::add_sc_evidence(const Summary& summary, const cR while (getline(in, line)) { vector fields = split(line, "\t"); - ASSERT(fields.size() >= 7, + ASSERT(fields.size() >= 11, "Soft-clipping counts file has too few columns and is probably from an older run:\n " + _settings.soft_clipping_counts_file_name + "\nDelete 07_error_calibration/error_counts.done and re-run to regenerate it."); @@ -1133,6 +1198,10 @@ void identify_mutations_pileup::add_sc_evidence(const Summary& summary, const cR uint32_t total_count = from_string(fields[4]); uint32_t agree_count = from_string(fields[5]); string consensus_tail = fields[6]; + uint32_t agree_count_fw = from_string(fields[7]); + uint32_t agree_count_rv = from_string(fields[8]); + uint32_t spanning_fw = from_string(fields[9]); + uint32_t spanning_rv = from_string(fields[10]); if (clipped_count == 0 || total_count == 0) continue; @@ -1172,10 +1241,59 @@ void identify_mutations_pileup::add_sc_evidence(const Summary& summary, const cR c.clipped_count = clipped_count; c.total_count = total_count; c.agree_count = agree_count; + c.agree_count_fw = agree_count_fw; + c.agree_count_rv = agree_count_rv; + c.spanning_fw = spanning_fw; + c.spanning_rv = spanning_rv; c.consensus_tail = consensus_tail; c.score = score; c.frequency = static_cast(test_count) / static_cast(total_count); c.consensus_fraction = static_cast(agree_count) / static_cast(clipped_count); + + /* + * Strand test. Same 2x2 as the RA polymorphism one (see _add_polymorphism_bias_statistics): + * the agreeing clipped reads are the "minor allele" and the reads that read through the + * position are the "major allele", so a clip population drawn from a different strand mix + * than the local coverage is what gets rejected. + * + * This is the discriminator that matters on real Illumina data. A dark-cycle poly-G tail -- + * the dominant SC false positive -- is always the 3' end of the read, so for a given clip + * direction it can only come from one strand: direction +1 clips from forward reads, + * direction -1 clips from reverse reads. Over 29 LTEE clones, 993 of 1040 accepted SC calls + * had every clipped read on a single strand, while every real-looking breakpoint was + * balanced. The consensus test cannot see this at all, because poly-G tails agree with each + * other perfectly. + * + * Comparing against the LOCAL spanning strand split rather than against 50/50 is what keeps + * a genuinely strand-skewed pileup from being read as a strand-skewed clip. Where there is + * no local read-through at all -- exactly the frequency == 1.000 positions, which carry the + * highest clip counts -- the contingency row is empty and Fisher returns 1 for anything; + * falling back to the genome-wide spanning split restores the test there (it becomes, in + * effect, a binomial test against the run's overall strand ratio). + */ + uint32_t major_fw = spanning_fw; + uint32_t major_rv = spanning_rv; + if (major_fw + major_rv == 0) { + // Rescaled to kSCStrandFallbackScale rather than passed at full size: the genome-wide + // totals run into the hundreds of millions, where the lgamma differences inside + // fisher_exact_test_2x2 lose precision and row1 + row2 can overflow its uint32_t. At this + // size the hypergeometric is already indistinguishable from the binomial the fallback is + // meant to be, so only the ratio matters. + const double scale = kSCStrandFallbackScale; + double gw_fw = static_cast(summary.soft_clipping.total_spanning_read_bases_forward); + double gw_rv = static_cast(summary.soft_clipping.total_spanning_read_bases_reverse); + double gw_total = gw_fw + gw_rv; + if (gw_total > 0.0) { + major_fw = static_cast(floor(scale * gw_fw / gw_total + 0.5)); + major_rv = static_cast(scale) - major_fw; + } + } + // With no reference population at all -- neither local nor genome-wide -- there is nothing to + // compare against, so leave the p-value at 1 rather than inventing a 50/50 expectation. + c.fisher_strand_p_value = (major_fw + major_rv > 0) + ? fisher_exact_test_2x2(c.agree_count_fw, c.agree_count_rv, major_fw, major_rv) + : 1.0; + candidates.push_back(c); } @@ -1246,6 +1364,16 @@ void identify_mutations_pileup::add_sc_evidence(const Summary& summary, const cR sc_entry[SC_CONSENSUS_FRACTION] = formatted_double(c.consensus_fraction, 4).to_string(); if (c.consensus_tail != ".") sc_entry[SC_CONSENSUS_TAIL] = c.consensus_tail; sc_entry[SC_LOG10_E_VALUE] = formatted_double(c.score, kMutationScorePrecision).to_string(); + // Strand split of the reads the score was computed from, and of the read-through population + // they were compared against. Reported whether or not the test rejected, because "all on one + // strand" is the first thing to look at when judging an SC call by eye. + sc_entry[SC_AGREE_COUNT_FORWARD] = to_string(c.agree_count_fw); + sc_entry[SC_AGREE_COUNT_REVERSE] = to_string(c.agree_count_rv); + sc_entry[SC_SPANNING_COUNT_FORWARD] = to_string(c.spanning_fw); + sc_entry[SC_SPANNING_COUNT_REVERSE] = to_string(c.spanning_rv); + // Spelled out rather than using output.h's FISHER_STRAND_P_VALUE, matching how the RA + // polymorphism code in this file writes the same key. + sc_entry["fisher_strand_p_value"] = formatted_double(c.fisher_strand_p_value, 5, true).to_string(); //// TIER 2: soft reject. The entry is kept and shown as marginal evidence. @@ -1273,6 +1401,20 @@ void identify_mutations_pileup::add_sc_evidence(const Summary& summary, const cR (c.consensus_fraction < _settings.soft_clipping_consensus_fraction_cutoff - _settings.polymorphism_precision_decimal)) { sc_entry.add_reject_reason("CLIPPED_TAIL_CONSENSUS"); } + // Clipped reads drawn from a different strand mix than the reads that read through the + // position; see the computation above for why this is the strongest SC filter there is. + if ((_settings.soft_clipping_fisher_strand_p_value_cutoff > 0.0) && + (c.fisher_strand_p_value < _settings.soft_clipping_fisher_strand_p_value_cutoff)) { + sc_entry.add_reject_reason("FISHER_STRAND"); + } + // The clipped tail is a homopolymer or near-homopolymer: a dark-cycle or adapter artifact, + // not donor sequence. Independent of the strand test, and it reaches the low-count positions + // where the strand test has no power. + if (sc_tail_is_low_complexity(c.consensus_tail, + _settings.soft_clipping_maximum_tail_homopolymer_fraction, + _settings.soft_clipping_maximum_tail_base_fraction)) { + sc_entry.add_reject_reason("LOW_COMPLEXITY_TAIL"); + } _gd.add(sc_entry); } diff --git a/src/breseq/output.cpp b/src/breseq/output.cpp index 9cc1fdfb..77840c76 100644 --- a/src/breseq/output.cpp +++ b/src/breseq/output.cpp @@ -1159,7 +1159,7 @@ void html_compare( } -void html_summary(const string &file_name, const Settings& settings, Summary& summary, cReferenceSequences& ref_seq_info) +void html_summary(const string &file_name, const Settings& settings, Summary& summary, cReferenceSequences& ref_seq_info, cGenomeDiff& gd) { // Create stream and confirm it's open ofstream HTML(file_name.c_str()); @@ -1320,6 +1320,10 @@ void html_summary(const string &file_name, const Settings& settings, Summary& su HTML << html_missing_pair_gates_string(settings, summary); } + // Same reasoning for SC, and more so: its null is fitted to the run, so identical command lines + // give wildly different SC counts on different libraries. See the function for what the rows mean. + HTML << html_soft_clipping_gates_string(settings, summary, gd); + //// // Write reference sequence information //// @@ -2913,6 +2917,139 @@ string html_pair_distance_gates_string(const Settings& settings, Summary& summar return ss.str(); } +/* The SC counterpart of the DP/PD/MP gates tables. + * + * SC needs one more than they do. Its null is fitted to the run, so the same command line gives + * wildly different SC counts on different libraries -- across 29 clones of one LTEE population the + * accepted count ranged from 5 to 1708 with no visible reason. The reason is almost always the + * strand-purity row below: an end-of-read artifact (dark-cycle poly-G, adapter read-through) is + * always the read's 3' end, so for a given clip direction it comes from exactly one strand. A run + * whose clip population is mostly strand-pure is a run whose SC evidence is mostly artifact, and + * that is not otherwise visible anywhere in the report. + * + * The outcome tally is counted from the genome diff rather than carried in the summary, because + * add_sc_evidence() runs against a const Summary and this cannot then drift from what the tables + * on the other pages actually show. + */ +string html_soft_clipping_gates_string(const Settings& settings, Summary& summary, cGenomeDiff& gd) +{ + const SoftClippingSummary& d = summary.soft_clipping; + if (!settings.predict_soft_clipping) return ""; + if ((d.total_clipped_read_ends == 0) && (d.total_spanning_read_bases == 0)) return ""; + + uint32_t accepted = 0, rejected_score = 0, rejected_strand = 0, + rejected_low_complexity = 0, rejected_other = 0; + // get_list, not show_list: the point of this tally is to say how many were rejected, and + // show_list has already dropped the rejected ones. + diff_entry_list_t sc_list = gd.get_list(make_vector(SC)); + for (diff_entry_list_t::iterator it = sc_list.begin(); it != sc_list.end(); it++) { + cDiffEntry& e = **it; + if (!e.entry_exists(REJECT)) { accepted++; continue; } + vector reasons = e.get_reject_reasons(); + bool score = false, strand = false, low_complexity = false, other = false; + for (vector::const_iterator r = reasons.begin(); r != reasons.end(); r++) { + if (*r == "SCORE_CUTOFF") score = true; + else if (*r == "FISHER_STRAND") strand = true; + else if (*r == "LOW_COMPLEXITY_TAIL") low_complexity = true; + else other = true; + } + // An item can fail several gates at once; count it under the most specific one so the + // columns add up to the number of rejected items. + if (strand) rejected_strand++; + else if (low_complexity) rejected_low_complexity++; + else if (score) rejected_score++; + else if (other) rejected_other++; + } + + stringstream ss; + ss << "

" << endl; + ss << start_table("border=\"0\" cellspacing=\"1\" cellpadding=\"3\"") << endl; + ss << tr(th("colspan=\"3\" align=\"left\" class=\"soft_clipping_header_row\"", + "Soft clipping (SC) evidence gates")) << endl; + ss << tr(th("gate") + th("value") + th("width=\"100%\"", "basis")) << endl; + + ss << tr(td("clipped bases required") + + td(to_string(settings.soft_clipping_minimum_bases) + " bases") + + td("also how much aligned reference a read must have on BOTH sides of a position to" + " count as reading through it")) << endl; + + { + string basis = "agreeing clip events over read opportunities, measured across the whole" + " reference rather than assumed"; + ss << tr(td("clipping background") + + td(to_string(100.0 * d.soft_clipping_null_rate, 4, false) + "%") + + td(basis)) << endl; + } + + { + string basis = "Pearson φ = " + to_string(d.soft_clipping_pearson_phi, 2, false) + + " over " + to_string(d.soft_clipping_tested_positions) + " (position, direction)" + + " pairs (mean " + to_string(d.soft_clipping_mean_tested_reads, 0, false) + + " reads), " + to_string(d.soft_clipping_trimmed_positions) + + " trimmed at a clipped fraction of " + + to_string(settings.soft_clipping_dispersion_trim_frequency, 2, false) + + " or above so that real breakpoints cannot define their own background"; + ss << tr(td("background unevenness") + + td(d.soft_clipping_dispersion > 0.0 + ? "ρ = " + to_string(d.soft_clipping_dispersion, 5, false) + : string("none (binomial)")) + + td(basis)) << endl; + } + + // The row that explains an artifact-dominated run. + if (d.total_agreeing_clipped_read_ends > 0) { + double pure_fraction = static_cast(d.total_strand_pure_agreeing_clipped_read_ends) + / static_cast(d.total_agreeing_clipped_read_ends); + ss << tr(td("one-strand clip events") + + td(to_string(100.0 * pure_fraction, 1, false) + "%") + + td(to_string(d.total_strand_pure_agreeing_clipped_read_ends) + " of " + + to_string(d.total_agreeing_clipped_read_ends) + " agreeing clip events sit at" + " positions that saw only one read strand. Reads clipped at a real breakpoint" + " come from both strands; an end-of-read artifact (dark-cycle poly-G, adapter" + " read-through) can only come from one. A high value here means most of this" + " run's clipping is artifact — the strand gate below is what removes it.")) << endl; + } + + ss << tr(td("strand gate") + + td(settings.soft_clipping_fisher_strand_p_value_cutoff > 0.0 + ? "p ≥ " + to_string(settings.soft_clipping_fisher_strand_p_value_cutoff, 3, false) + : string("OFF")) + + td("Fisher's exact test of the clipped reads' strand split against the strand split" + " of the reads that read through the same position, so a genuinely strand-skewed" + " pileup is not mistaken for a strand-skewed clip")) << endl; + + ss << tr(td("clipped tail complexity") + + td(settings.soft_clipping_maximum_tail_homopolymer_fraction > 0.0 + ? "run < " + to_string(settings.soft_clipping_maximum_tail_homopolymer_fraction, 3, false) + + ", one base < " + to_string(settings.soft_clipping_maximum_tail_base_fraction, 2, false) + : string("OFF")) + + td("as fractions of the compared clipped bases. Homopolymer tails agree with each" + " other perfectly, so the consensus test cannot see them.")) << endl; + + ss << tr(td("score cutoff") + + td(settings.soft_clipping_log10_e_value_cutoff > 0.0 + ? to_string(settings.soft_clipping_log10_e_value_cutoff, 1, false) + : string("OFF")) + + td("−log10 of the expected number of positions in this reference where this many" + " reads would be clipped with the same tail by chance, given the background rate" + " and its unevenness")) << endl; + + { + string tally = to_string(accepted) + " accepted"; + if (rejected_strand) tally += ", " + to_string(rejected_strand) + " rejected (strand)"; + if (rejected_low_complexity) + tally += ", " + to_string(rejected_low_complexity) + " rejected (clipped tail complexity)"; + if (rejected_score) tally += ", " + to_string(rejected_score) + " rejected (score)"; + if (rejected_other) tally += ", " + to_string(rejected_other) + " rejected (other gates)"; + ss << tr(td("outcome") + + td(to_string(sc_list.size()) + " reported") + + td(tally)) << endl; + } + + ss << "" << endl; + return ss.str(); +} + string html_missing_pair_gates_string(const Settings& settings, Summary& summary) { const MissingPairSummary& d = summary.missing_pair; @@ -3467,7 +3604,7 @@ string html_soft_clipping_table_string(diff_entry_list_t& list_ref, bool show_de ss << "

" << endl; ss << start_table("border=\"0\" cellspacing=\"1\" cellpadding=\"3\"") << endl; - size_t total_cols = link ? 14 : 13; + size_t total_cols = link ? 16 : 15; ss << "" << endl; if (title != "") { @@ -3481,10 +3618,15 @@ string html_soft_clipping_table_string(diff_entry_list_t& list_ref, bool show_de ss << th("direction") << endl; ss << th("clipped") << endl; ss << th("agree") << endl; + // Strand split of the agreeing clipped reads. An end-of-read artifact (dark-cycle poly-G, + // adapter read-through) can only produce one of these for a given direction, so a zero here + // is the fastest way to spot one by eye. + ss << th(nonbreaking("agree +/-")) << endl; ss << th("total") << endl; ss << th("freq") << endl; ss << th("range") << endl; ss << th("score") << endl; + ss << th(nonbreaking("strand p")) << endl; ss << th(nonbreaking("clipped seq")) << endl; ss << th("annotation") << endl; ss << th("gene") << endl; @@ -3510,6 +3652,10 @@ string html_soft_clipping_table_string(diff_entry_list_t& list_ref, bool show_de ss << td(ALIGN_RIGHT, nonbreaking(c[SC_READ_COUNT])) << endl; ss << td(ALIGN_RIGHT, nonbreaking(c.entry_exists(SC_AGREE_COUNT) ? c[SC_AGREE_COUNT] : " ")) << endl; + if (c.entry_exists(SC_AGREE_COUNT_FORWARD) && c.entry_exists(SC_AGREE_COUNT_REVERSE)) + ss << td(ALIGN_CENTER, nonbreaking(c[SC_AGREE_COUNT_FORWARD] + "/" + c[SC_AGREE_COUNT_REVERSE])) << endl; + else + ss << td(" ") << endl; ss << td(ALIGN_RIGHT, nonbreaking(c[SC_TOTAL_COUNT])) << endl; ss << td(string(CLASS_FREQ) + " " + string(ALIGN_RIGHT), Html_Mutation_Table_String::freq_to_string(c[FREQUENCY])) << endl; // "range" column: the confidence limits the frequency cutoff is actually applied to, which is @@ -3517,6 +3663,14 @@ string html_soft_clipping_table_string(diff_entry_list_t& list_ref, bool show_de ss << td(ALIGN_RIGHT, Html_Mutation_Table_String::freq_range_to_string(c[FREQUENCY_LOWER], c[FREQUENCY_UPPER])) << endl; ss << td(ALIGN_RIGHT, nonbreaking(c[SC_LOG10_E_VALUE])) << endl; + // Fisher's exact p for the clipped reads' strand split against the read-through population's. + if (c.entry_exists(FISHER_STRAND_P_VALUE)) { + stringstream ssf; + ssf << scientific << setprecision(1) << from_string(c[FISHER_STRAND_P_VALUE]); + ss << td(ALIGN_RIGHT, nonbreaking(ssf.str())) << endl; + } else { + ss << td(" ") << endl; + } // The consensus of the clipped read tails: the sequence that would have continued // the reference here. Always stored reference-forward regardless of clip direction. if (c.entry_exists(SC_CONSENSUS_TAIL)) @@ -3888,6 +4042,10 @@ string decode_reject_reason(const string& reject) { return "Stronger soft-clipping evidence in the same direction within a few bases; probably the same breakpoint."; } + else if (reject == "LOW_COMPLEXITY_TAIL") + { + return "Clipped read tails are a homopolymer or nearly one base; typical of dark-cycle (poly-G) or adapter read-through, not of donor sequence."; + } return "Unknown rejection reason."; } diff --git a/src/breseq/output.h b/src/breseq/output.h index 5786a24f..51d9879d 100644 --- a/src/breseq/output.h +++ b/src/breseq/output.h @@ -180,7 +180,7 @@ void mark_gd_entries_no_show(const Settings& settings, cGenomeDiff& gd); void html_marginal_predictions(const string& file_name, const Settings& settings, Summary& summary, cReferenceSequences& ref_seq_info, cGenomeDiff& gd); -void html_summary(const string& file_name, const Settings& settings, Summary& summary, cReferenceSequences& ref_seq_info); +void html_summary(const string& file_name, const Settings& settings, Summary& summary, cReferenceSequences& ref_seq_info, cGenomeDiff& gd); void html_compare( const Settings& settings, @@ -294,6 +294,7 @@ string html_discordant_pair_table_string(diff_entry_list_t& dp, string html_discordant_pair_gates_string(const Settings& settings, Summary& summary); string html_pair_distance_gates_string(const Settings& settings, Summary& summary); string html_missing_pair_gates_string(const Settings& settings, Summary& summary); +string html_soft_clipping_gates_string(const Settings& settings, Summary& summary, cGenomeDiff& gd); // summary.html block reporting how CNery's copy number analysis went for each reference sequence: // the replication bias it fit and divided out, how much flatter each correction stage made the diff --git a/src/breseq/settings.cpp b/src/breseq/settings.cpp index a1713789..b57b15b8 100644 --- a/src/breseq/settings.cpp +++ b/src/breseq/settings.cpp @@ -521,6 +521,9 @@ namespace breseq ("soft-clipping-minimum-read-count", "Minimum number of consensus-supporting clipped reads required for a position to be reported at all (DEFAULT = 3). 0 = OFF.", 3, NORMAL_OPTION) ("soft-clipping-frequency-cutoff", "Minimum fraction of reads that must be clipped at a position for the evidence to be accepted rather than rejected. Defaults to --polymorphism-frequency-cutoff, the same frequency used for predicting mutations, and follows it if you change it (DEFAULT = consensus mode, 0.10; polymorphism mode, 0.05). 0 = OFF.", "", NORMAL_OPTION) ("soft-clipping-consensus-fraction-cutoff", "Minimum fraction of the clipped reads at a position that must agree on the consensus clipped sequence for the evidence to be accepted rather than rejected (DEFAULT = 0.5). 0 = OFF.", "", NORMAL_OPTION) + ("soft-clipping-fisher-strand-p-value-cutoff", "Reject soft-clipping evidence whose clipped reads are distributed across the two read strands differently from the reads that read through the position, at this Fisher's exact test p-value. Reads clipped at a real breakpoint come from both strands; the common artifacts (dark-cycle poly-G tails, adapter read-through) are always the 3' end of the read and so appear on only one strand for a given clip direction (DEFAULT = 0.05). 0 = OFF.", "", NORMAL_OPTION) + ("soft-clipping-maximum-tail-homopolymer-fraction", "Reject soft-clipping evidence whose consensus clipped sequence contains a single-base run at least this fraction of its length. Catches dark-cycle poly-G/poly-C tails, which agree with each other perfectly and so pass the consensus test (DEFAULT = 0.66, which rejects a run of 8 or more of the 12 bases compared at the default --soft-clipping-minimum-bases). 0 = OFF.", "", NORMAL_OPTION) + ("soft-clipping-maximum-tail-base-fraction", "Reject soft-clipping evidence whose consensus clipped sequence is at least this fraction a single base, even when that base is not in one run (DEFAULT = 0.75). 0 = OFF.", "", NORMAL_OPTION) ; options.addUsage("", NORMAL_OPTION); @@ -855,6 +858,18 @@ namespace breseq this->soft_clipping_consensus_fraction_cutoff = from_string(options["soft-clipping-consensus-fraction-cutoff"]); ASSERT((this->soft_clipping_consensus_fraction_cutoff >= 0) && (this->soft_clipping_consensus_fraction_cutoff <= 1), "Argument --soft-clipping-consensus-fraction-cutoff must be in the range [0,1]") + if (options.count("soft-clipping-fisher-strand-p-value-cutoff")) + this->soft_clipping_fisher_strand_p_value_cutoff = from_string(options["soft-clipping-fisher-strand-p-value-cutoff"]); + ASSERT((this->soft_clipping_fisher_strand_p_value_cutoff >= 0) && (this->soft_clipping_fisher_strand_p_value_cutoff <= 1), + "Argument --soft-clipping-fisher-strand-p-value-cutoff must be in the range [0,1]") + if (options.count("soft-clipping-maximum-tail-homopolymer-fraction")) + this->soft_clipping_maximum_tail_homopolymer_fraction = from_string(options["soft-clipping-maximum-tail-homopolymer-fraction"]); + ASSERT((this->soft_clipping_maximum_tail_homopolymer_fraction >= 0) && (this->soft_clipping_maximum_tail_homopolymer_fraction <= 1), + "Argument --soft-clipping-maximum-tail-homopolymer-fraction must be in the range [0,1]") + if (options.count("soft-clipping-maximum-tail-base-fraction")) + this->soft_clipping_maximum_tail_base_fraction = from_string(options["soft-clipping-maximum-tail-base-fraction"]); + ASSERT((this->soft_clipping_maximum_tail_base_fraction >= 0) && (this->soft_clipping_maximum_tail_base_fraction <= 1), + "Argument --soft-clipping-maximum-tail-base-fraction must be in the range [0,1]") // Soft-clipping evidence needs partially-aligned reads to be kept so their clipped // ends are visible for tabulation, so loosen the match-fraction requirement when @@ -1452,6 +1467,13 @@ namespace breseq // Overwritten per prediction mode in the cmdline constructor to track polymorphism_frequency_cutoff. this->soft_clipping_frequency_cutoff = 0.1; this->soft_clipping_consensus_fraction_cutoff = 0.5; + // Same cutoff as polymorphism_fisher_strand_p_value_cutoff, and the same test: the clipped + // reads play the minor allele and the reads that read through play the major one. + this->soft_clipping_fisher_strand_p_value_cutoff = 0.05; + // 0.66 lands between 7/12 and 8/12, so at the default --soft-clipping-minimum-bases this + // rejects a run of 8 or more of the 12 compared bases and keeps a run of 7. + this->soft_clipping_maximum_tail_homopolymer_fraction = 0.66; + this->soft_clipping_maximum_tail_base_fraction = 0.75; this->polymorphism_prediction = false; this->mixed_base_prediction = true; diff --git a/src/breseq/settings.h b/src/breseq/settings.h index 9f788263..19f15426 100644 --- a/src/breseq/settings.h +++ b/src/breseq/settings.h @@ -464,6 +464,9 @@ namespace breseq uint32_t soft_clipping_minimum_read_count; // Default = 3 COMMAND-LINE OPTION 0 = OFF double soft_clipping_frequency_cutoff; // Default = tracks polymorphism_frequency_cutoff (0.10/0.05); COMMAND-LINE OPTION 0 = OFF double soft_clipping_consensus_fraction_cutoff; // Default = 0.5 COMMAND-LINE OPTION 0 = OFF + double soft_clipping_fisher_strand_p_value_cutoff; // Default = 0.05 COMMAND-LINE OPTION 0 = OFF + double soft_clipping_maximum_tail_homopolymer_fraction; // Default = 0.66 COMMAND-LINE OPTION 0 = OFF + double soft_clipping_maximum_tail_base_fraction; // Default = 0.75 COMMAND-LINE OPTION 0 = OFF //! These are mutually exclusive settings (polymorphism prediction overrides mixed_base_prediction) diff --git a/src/breseq/soft_clipping.cpp b/src/breseq/soft_clipping.cpp index 06e5a435..89b74342 100644 --- a/src/breseq/soft_clipping.cpp +++ b/src/breseq/soft_clipping.cpp @@ -37,6 +37,10 @@ namespace breseq { // a std::string -- on a 4 Mb genome at 150x there are ~200,000 clip events. const uint32_t kSoftClippingMaxConsensusBases = 21; +// 21 bases x 3 bits fills bits 0-62, leaving the top bit free. The read's strand rides +// there so that per-strand agree counts cost nothing beyond the tail itself. +const uint64_t kSoftClippingTailStrandBit = (1ULL << 63); + // Base <-> 3-bit code. 4 means "not A/C/G/T"; it never wins a consensus column // and always counts as a mismatch. static inline uint32_t base_to_code(char b) @@ -56,11 +60,18 @@ static inline char code_to_base(uint32_t c) return (c < 4) ? bases[c] : 'N'; } +// column <= 20, so the shift is at most 60 and the 3-bit mask reads bits 60-62 -- +// kSoftClippingTailStrandBit (bit 63) is never part of any base code. static inline uint32_t tail_code_at(uint64_t packed, uint32_t column) { return static_cast((packed >> (3 * column)) & 0x7ULL); } +static inline bool tail_is_reversed(uint64_t packed) +{ + return (packed & kSoftClippingTailStrandBit) != 0; +} + /* * Per-column consensus over the clipped tails at one (seq_id, position, direction), and the * number of reads agreeing with it. @@ -87,6 +98,17 @@ static inline uint32_t tail_code_at(uint64_t packed, uint32_t column) * the group consensus is the per-column consensus), and on noisy positions the simpler rule * here is the more conservative one. * + * The agreeing reads are also counted separately by the strand of the read they came from + * (agree_count_out == agree_forward_out + agree_reverse_out, always). This is what the + * strand test in add_sc_evidence() runs on, and it is the discriminator that matters most on + * real Illumina data: the dominant false positive is a dark-cycle poly-G tail, which is always + * the 3' end of the read, so it produces direction +1 clips only from forward-strand reads and + * direction -1 clips only from reverse-strand reads. Measured over 29 LTEE clones, 993 of 1040 + * accepted SC calls had every clipped read on one strand, while every plausible real breakpoint + * was strand-balanced. Note that a poly-G tail is stored reference-forward, so it reads as + * poly-C for direction -1 -- the tails agree with each other perfectly and the consensus test + * above cannot see anything wrong with them. + * * base_fraction == 0 turns the whole test off: every clipped read counts and no sequence * is reported. consensus_out is returned in column order; the caller reverses it for * direction -1 so the stored sequence is always reference-forward. @@ -96,13 +118,22 @@ static void compute_clipped_tail_consensus( uint32_t K, double base_fraction, string& consensus_out, - uint32_t& agree_count_out + uint32_t& agree_count_out, + uint32_t& agree_forward_out, + uint32_t& agree_reverse_out ) { consensus_out.clear(); agree_count_out = static_cast(tails.size()); + agree_forward_out = 0; + agree_reverse_out = 0; + for (vector::const_iterator it = tails.begin(); it != tails.end(); it++) { + if (tail_is_reversed(*it)) agree_reverse_out++; else agree_forward_out++; + } if (tails.empty()) return; + // With the consensus test off every clipped read counts, and the strand split above is + // already the split of all of them. if (base_fraction <= 0.0) return; // Per-column plurality consensus over every clipped tail at this position. @@ -128,6 +159,8 @@ static void compute_clipped_tail_consensus( if (informative_columns == 0) { consensus_out.clear(); agree_count_out = 0; + agree_forward_out = 0; + agree_reverse_out = 0; return; } @@ -138,13 +171,18 @@ static void compute_clipped_tail_consensus( if (required_matches < 1) required_matches = 1; agree_count_out = 0; + agree_forward_out = 0; + agree_reverse_out = 0; for (vector::const_iterator it = tails.begin(); it != tails.end(); it++) { uint32_t matches = 0; for (uint32_t col = 0; col < K; col++) { if (consensus_codes[col] >= 4) continue; // uninformative column if (tail_code_at(*it, col) == consensus_codes[col]) matches++; } - if (matches >= required_matches) agree_count_out++; + if (matches >= required_matches) { + agree_count_out++; + if (tail_is_reversed(*it)) agree_reverse_out++; else agree_forward_out++; + } } } @@ -353,11 +391,19 @@ void tabulate_soft_clipping_counts( // NOTE: a read with a large internal deletion (CIGAR D/N) is credited with spanning positions it // does not actually align to. Pre-existing behavior of the difference-array approach, but this // is now the only denominator, so it matters more. - map > spanning_diff; + // + // Kept split by the strand of the read, because that is the reference the strand test compares + // the clipped reads against: coverage itself is not always 50/50, and a locally strand-skewed + // pileup must not be read as evidence of a strand-skewed clip. The two arrays sum to what a + // single array held before, so every genome-wide total below is unchanged. + map > spanning_diff_fw; + map > spanning_diff_rv; uint64_t total_clipped_read_ends = 0; // total clip events, both directions (a read clipped at // both ends counts twice) uint64_t total_agreeing_clipped_read_ends = 0; // subset whose tail matches its position consensus + uint64_t total_strand_pure_agreeing_clipped_read_ends = 0; // ...of those, the ones at positions + // where every agreeing clipped read was on one strand uint64_t total_tested_positions = 0; // N: (position, direction) pairs with n_i > 0 for (vector::const_iterator bam_it = bam_file_names.begin(); bam_it != bam_file_names.end(); bam_it++) { @@ -400,8 +446,14 @@ void tabulate_soft_clipping_counts( // evaluated in 64 bits so it cannot wrap; inside it ref_end - min_bases >= ref_start + // min_bases >= 1, so neither index underflows, and the high index is at most // seq_length + 1, which is in bounds for a seq_length + 2 array. - vector& sd = spanning_diff[seq_id]; - if (sd.empty()) sd.resize(seq_length + 2, 0); + const bool read_reversed = a.reversed(); + const uint64_t strand_bit = read_reversed ? kSoftClippingTailStrandBit : 0ULL; + + vector& sd_fw = spanning_diff_fw[seq_id]; + vector& sd_rv = spanning_diff_rv[seq_id]; + if (sd_fw.empty()) sd_fw.resize(seq_length + 2, 0); + if (sd_rv.empty()) sd_rv.resize(seq_length + 2, 0); + vector& sd = read_reversed ? sd_rv : sd_fw; if (static_cast(ref_end) >= static_cast(ref_start) + 2ULL * minimum_clipped_bases) { sd[ref_start + minimum_clipped_bases] += 1; @@ -416,7 +468,8 @@ void tabulate_soft_clipping_counts( // Column 0 is the clipped base adjacent to the wall (just before // query_start_1); columns then run backwards, away from the reference. - uint64_t packed = 0; + // Bit 63 carries the read's strand; see kSoftClippingTailStrandBit. + uint64_t packed = strand_bit; for (uint32_t col = 0; col < consensus_bases; col++) { uint32_t q = a.query_start_1() - 1 - col; // >= 1, guaranteed by the clip length test packed |= static_cast(base_to_code(a.read_base_char_1(q))) << (3 * col); @@ -433,7 +486,8 @@ void tabulate_soft_clipping_counts( // Column 0 is the clipped base adjacent to the wall (just after query_end_1); // columns run forward, already reference-forward. - uint64_t packed = 0; + // Bit 63 carries the read's strand; see kSoftClippingTailStrandBit. + uint64_t packed = strand_bit; for (uint32_t col = 0; col < consensus_bases; col++) { uint32_t q = a.query_end_1() + 1 + col; // <= read_length, guaranteed by the clip length test packed |= static_cast(base_to_code(a.read_base_char_1(q))) << (3 * col); @@ -455,27 +509,39 @@ void tabulate_soft_clipping_counts( // // which the Pearson chi-square expansion below depends on, and it keeps // summary.total_spanning_read_bases in the same units as previous versions. - map > spanning; + map > spanning_fw; + map > spanning_rv; uint64_t total_spanning_read_bases = 0; + uint64_t total_spanning_read_bases_fw = 0; + uint64_t total_spanning_read_bases_rv = 0; for (map::iterator seq_it = seq_lengths.begin(); seq_it != seq_lengths.end(); seq_it++) { const string& seq_id = seq_it->first; uint32_t seq_length = seq_it->second; - if (spanning_diff.count(seq_id) == 0) continue; // no reads on this sequence - - vector& sd = spanning_diff[seq_id]; - vector& sp = spanning[seq_id]; - sp.resize(sd.size(), 0); - - int32_t running = 0; - for (uint32_t p = 1; p < sd.size(); p++) { - running += sd[p]; - sp[p] = (running > 0) ? static_cast(running) : 0; + if (spanning_diff_fw.count(seq_id) == 0) continue; // no reads on this sequence + + vector& sd_fw = spanning_diff_fw[seq_id]; + vector& sd_rv = spanning_diff_rv[seq_id]; + vector& sp_fw = spanning_fw[seq_id]; + vector& sp_rv = spanning_rv[seq_id]; + sp_fw.resize(sd_fw.size(), 0); + sp_rv.resize(sd_rv.size(), 0); + + int32_t running_fw = 0; + int32_t running_rv = 0; + for (uint32_t p = 1; p < sd_fw.size(); p++) { + running_fw += sd_fw[p]; + running_rv += sd_rv[p]; + sp_fw[p] = (running_fw > 0) ? static_cast(running_fw) : 0; + sp_rv[p] = (running_rv > 0) ? static_cast(running_rv) : 0; + uint32_t sp = sp_fw[p] + sp_rv[p]; if (sc_position_is_testable(p, seq_length, minimum_clipped_bases)) { - total_spanning_read_bases += 2ULL * static_cast(sp[p]); + total_spanning_read_bases += 2ULL * static_cast(sp); + total_spanning_read_bases_fw += 2ULL * static_cast(sp_fw[p]); + total_spanning_read_bases_rv += 2ULL * static_cast(sp_rv[p]); // N counts (position, direction) pairs with n_i > 0. A non-zero spanning count makes // both directions testable; positions with clips but no spanning reads are added in // the loop below, which only fires when read_through == 0, so nothing double counts. - if (sp[p] > 0) total_tested_positions += 2; + if (sp > 0) total_tested_positions += 2; } } } @@ -495,6 +561,10 @@ void tabulate_soft_clipping_counts( uint32_t clipped_count; uint32_t total_count; uint32_t agree_count; + uint32_t agree_count_fw; // agree_count split by the strand of the clipped read; + uint32_t agree_count_rv; // agree_count_fw + agree_count_rv == agree_count + uint32_t spanning_fw; // read-through reads at this position, by strand; + uint32_t spanning_rv; // spanning_fw + spanning_rv == total_count - clipped_count string consensus_tail; // always stored reference-forward }; vector positions; @@ -512,7 +582,9 @@ void tabulate_soft_clipping_counts( for (map >::iterator seq_it = clipped.begin(); seq_it != clipped.end(); seq_it++) { const string& seq_id = seq_it->first; - const vector& cov = spanning[seq_id]; // same denominator for both directions + // Same denominator for both directions. + const vector& cov_fw = spanning_fw[seq_id]; + const vector& cov_rv = spanning_rv[seq_id]; map >& seq_tails = tails[seq_id]; for (map::iterator pos_it = seq_it->second.begin(); pos_it != seq_it->second.end(); pos_it++) { @@ -521,12 +593,15 @@ void tabulate_soft_clipping_counts( cp.position = pos_it->first; cp.direction = direction; cp.clipped_count = pos_it->second; - uint32_t read_through = (cp.position < cov.size()) ? cov[cp.position] : 0; + cp.spanning_fw = (cp.position < cov_fw.size()) ? cov_fw[cp.position] : 0; + cp.spanning_rv = (cp.position < cov_rv.size()) ? cov_rv[cp.position] : 0; + uint32_t read_through = cp.spanning_fw + cp.spanning_rv; cp.total_count = cp.clipped_count + read_through; compute_clipped_tail_consensus(seq_tails[cp.position], consensus_bases, settings.soft_clipping_consensus_base_fraction, - cp.consensus_tail, cp.agree_count); + cp.consensus_tail, cp.agree_count, + cp.agree_count_fw, cp.agree_count_rv); // Columns run outward from the wall. For a leading clip that is backwards // relative to the reference, so reverse it: the stored sequence is then always @@ -534,6 +609,12 @@ void tabulate_soft_clipping_counts( if (direction < 0) reverse(cp.consensus_tail.begin(), cp.consensus_tail.end()); total_agreeing_clipped_read_ends += cp.agree_count; + // Diagnostic only (reported in the SC gates table): how much of the agreeing clip + // population sits at positions that saw only one strand. A clean library runs a few + // percent; a run dominated by dark-cycle poly-G runs most of the way to 100%, which is + // the single number that says "the SC calls in this run are an artifact". + if ((cp.agree_count > 0) && ((cp.agree_count_fw == 0) || (cp.agree_count_rv == 0))) + total_strand_pure_agreeing_clipped_read_ends += cp.agree_count; // A position with clips but no read-through was not counted in the prefix-sum loop. if (read_through == 0) total_tested_positions++; @@ -547,8 +628,15 @@ void tabulate_soft_clipping_counts( // the *agreeing* rate, since agree_count is the numerator being tested. uint64_t total_opportunities = total_clipped_read_ends + total_spanning_read_bases; summary.soft_clipping.total_spanning_read_bases = total_spanning_read_bases; + // The genome-wide strand split of the read-through population. add_sc_evidence() falls back to + // this as the expected strand ratio at a position with no read-through of its own, which is + // exactly the frequency == 1.000 case -- otherwise those positions have an empty contingency + // row and the strand test silently has no power where the clip count is highest. + summary.soft_clipping.total_spanning_read_bases_forward = total_spanning_read_bases_fw; + summary.soft_clipping.total_spanning_read_bases_reverse = total_spanning_read_bases_rv; summary.soft_clipping.total_clipped_read_ends = total_clipped_read_ends; summary.soft_clipping.total_agreeing_clipped_read_ends = total_agreeing_clipped_read_ends; + summary.soft_clipping.total_strand_pure_agreeing_clipped_read_ends = total_strand_pure_agreeing_clipped_read_ends; summary.soft_clipping.soft_clipping_rate = (total_opportunities > 0) ? static_cast(total_clipped_read_ends) / static_cast(total_opportunities) : 0.0; @@ -636,17 +724,20 @@ void tabulate_soft_clipping_counts( // The leading format token exists so that a counts file written by an older binary fails // loudly rather than being silently reinterpreted. Bump it whenever the meaning of a column // or of the denominator changes, not just when a column is added. - out << "#sc_format=2" + out << "#sc_format=3" << "\tsoft_clipping_minimum_bases=" << minimum_clipped_bases << "\tconsensus_base_fraction=" << settings.soft_clipping_consensus_base_fraction << "\tnull_rate=" << p0 << "\tdispersion=" << rho << "\n"; - out << "seq_id\tposition\tdirection\tclipped_count\ttotal_count\tagree_count\tclipped_sequence\n"; + out << "seq_id\tposition\tdirection\tclipped_count\ttotal_count\tagree_count\tclipped_sequence" + "\tagree_count_forward\tagree_count_reverse\tspanning_forward\tspanning_reverse\n"; for (vector::const_iterator it = positions.begin(); it != positions.end(); it++) { out << it->seq_id << "\t" << it->position << "\t" << it->direction << "\t" << it->clipped_count << "\t" << it->total_count << "\t" << it->agree_count << "\t" - << (it->consensus_tail.empty() ? "." : it->consensus_tail) << "\n"; + << (it->consensus_tail.empty() ? "." : it->consensus_tail) << "\t" + << it->agree_count_fw << "\t" << it->agree_count_rv << "\t" + << it->spanning_fw << "\t" << it->spanning_rv << "\n"; } out.close(); @@ -654,6 +745,12 @@ void tabulate_soft_clipping_counts( cerr << " Soft-clipping summary: " << total_clipped_read_ends << " clip events (" << total_agreeing_clipped_read_ends << " agreeing with their position consensus) over " << total_opportunities << " read opportunities" << endl; + if (total_agreeing_clipped_read_ends > 0) { + cerr << " " << total_strand_pure_agreeing_clipped_read_ends << " (" + << (100.0 * static_cast(total_strand_pure_agreeing_clipped_read_ends) + / static_cast(total_agreeing_clipped_read_ends)) + << "%) of the agreeing clip events are at positions that saw only one read strand" << endl; + } cerr << " null rate p0 = " << p0; if (p0 != p0_raw) cerr << " (raised from " << p0_raw << " by --soft-clipping-minimum-rate)"; cerr << endl; diff --git a/src/breseq/summary.cpp b/src/breseq/summary.cpp index 8e58af08..8ea11c66 100644 --- a/src/breseq/summary.cpp +++ b/src/breseq/summary.cpp @@ -370,9 +370,12 @@ void to_json(json& j, const SoftClippingSummary& s) { j = json{ {"total_spanning_read_bases", s.total_spanning_read_bases}, + {"total_spanning_read_bases_forward", s.total_spanning_read_bases_forward}, + {"total_spanning_read_bases_reverse", s.total_spanning_read_bases_reverse}, {"total_clipped_read_ends", s.total_clipped_read_ends}, {"soft_clipping_rate", s.soft_clipping_rate}, {"total_agreeing_clipped_read_ends", s.total_agreeing_clipped_read_ends}, + {"total_strand_pure_agreeing_clipped_read_ends", s.total_strand_pure_agreeing_clipped_read_ends}, {"soft_clipping_null_rate", s.soft_clipping_null_rate}, {"soft_clipping_dispersion", s.soft_clipping_dispersion}, {"soft_clipping_pearson_phi", s.soft_clipping_pearson_phi}, @@ -388,7 +391,10 @@ void from_json(const json& j, SoftClippingSummary& s) s.total_clipped_read_ends = j.at("total_clipped_read_ends").get(); s.soft_clipping_rate = get_double_or_default(j, "soft_clipping_rate"); // Defaulted: a summary written before these fields existed must still load. + s.total_spanning_read_bases_forward = get_uint64_or_default(j, "total_spanning_read_bases_forward"); + s.total_spanning_read_bases_reverse = get_uint64_or_default(j, "total_spanning_read_bases_reverse"); s.total_agreeing_clipped_read_ends = get_uint64_or_default(j, "total_agreeing_clipped_read_ends"); + s.total_strand_pure_agreeing_clipped_read_ends = get_uint64_or_default(j, "total_strand_pure_agreeing_clipped_read_ends"); s.soft_clipping_null_rate = get_double_or_default(j, "soft_clipping_null_rate"); s.soft_clipping_dispersion = get_double_or_default(j, "soft_clipping_dispersion"); s.soft_clipping_pearson_phi = get_double_or_default(j, "soft_clipping_pearson_phi"); diff --git a/src/breseq/summary.h b/src/breseq/summary.h index 8c532996..9a80ee85 100644 --- a/src/breseq/summary.h +++ b/src/breseq/summary.h @@ -335,6 +335,9 @@ namespace breseq{ public: uint64_t total_spanning_read_bases; // read-through opportunities: reads spanning a position with // >= min_bases aligned on BOTH sides, counted once per direction + uint64_t total_spanning_read_bases_forward; // ...split by the strand of the spanning read. The strand + uint64_t total_spanning_read_bases_reverse; // test falls back to this ratio where a position has no + // read-through of its own (frequency == 1.000). uint64_t total_clipped_read_ends; // total soft-clip events; a read with both ends clipped counts twice double soft_clipping_rate; // raw clip rate: total_clipped_read_ends / total opportunities @@ -343,6 +346,10 @@ namespace breseq{ // zero-clip positions needed for these estimates are not recoverable later -- // they must be carried forward here. uint64_t total_agreeing_clipped_read_ends; // clip events whose tail matches the position consensus + // Diagnostic, not part of the null: how many of those sit at positions where every agreeing + // clipped read came from one strand. Near 100% means the run's clip population is dominated by + // an end-of-read artifact (dark-cycle poly-G, adapter read-through), not by breakpoints. + uint64_t total_strand_pure_agreeing_clipped_read_ends; double soft_clipping_null_rate; // p0 used (agreeing rate, after the minimum-rate floor) double soft_clipping_dispersion; // rho used; 0 => plain binomial double soft_clipping_pearson_phi; // diagnostic: Pearson chi2 / (N-1) over the fitted positions @@ -352,9 +359,12 @@ namespace breseq{ SoftClippingSummary() : total_spanning_read_bases(0) + , total_spanning_read_bases_forward(0) + , total_spanning_read_bases_reverse(0) , total_clipped_read_ends(0) , soft_clipping_rate(0.0) , total_agreeing_clipped_read_ends(0) + , total_strand_pure_agreeing_clipped_read_ends(0) , soft_clipping_null_rate(0.0) , soft_clipping_dispersion(0.0) , soft_clipping_pearson_phi(0.0) diff --git a/tests/lambda_polymorphism_soft_clipping/expected.gd b/tests/lambda_polymorphism_soft_clipping/expected.gd index b8289934..b66ea9da 100644 --- a/tests/lambda_polymorphism_soft_clipping/expected.gd +++ b/tests/lambda_polymorphism_soft_clipping/expected.gd @@ -1,8 +1,8 @@ #=GENOME_DIFF 1.0 #=TITLE header #=AUTHOR Jeffrey Barrick -#=CREATED 13:25:13 30 Jul 2026 -#=PROGRAM breseq 0.50.0 revision 2474edd9b66f +#=CREATED 14:26:05 23 Aug 2026 +#=PROGRAM breseq 0.50.0 revision 68145331ba14 #=COMMAND ./src/breseq/breseq -j 4 --predict-soft-clipping --polymorphism-prediction --header-genome-diff ./tests/lambda_polymorphism_soft_clipping/header.gd -o ./tests/lambda_polymorphism_soft_clipping -r ./tests/lambda_polymorphism_soft_clipping/../data/lambda/lambda.gbk ./tests/lambda_polymorphism_soft_clipping/../data/lambda/lambda_mixed_population.fastq.gz #=TIME 20 #=CLONE A @@ -132,4 +132,4 @@ JC 117 . NC_001416 21737 -1 NC_001416 27734 1 0 alignment_overlap=5 coverage_min UN 118 . NC_001416 1 8 UN 119 . NC_001416 21738 27731 UN 120 . NC_001416 48502 48502 -SC 121 . NC_001416 2915 1 agree_read_count=3 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.7500 frequency=0.2727 frequency_lower=0.0788 frequency_upper=0.5644 gene_name=B gene_position=coding (80/1602 nt) gene_product=capsid component gene_strand=> locus_tag=lambdap04 log10_e_value=0.8 read_count=4 reject=SCORE_CUTOFF total_count=11 +SC 121 . NC_001416 2915 1 agree_read_count=3 agree_read_count_forward=3 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.7500 fisher_strand_p_value=8.33333e-03 frequency=0.2727 frequency_lower=0.0788 frequency_upper=0.5644 gene_name=B gene_position=coding (80/1602 nt) gene_product=capsid component gene_strand=> locus_tag=lambdap04 log10_e_value=0.8 read_count=4 reject=SCORE_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=0 spanning_read_count_reverse=7 total_count=11 diff --git a/tests/long_ltee_ara_m1_40k_pe36/expected.gd b/tests/long_ltee_ara_m1_40k_pe36/expected.gd index ec1965bf..5c65d49e 100644 --- a/tests/long_ltee_ara_m1_40k_pe36/expected.gd +++ b/tests/long_ltee_ara_m1_40k_pe36/expected.gd @@ -1,6 +1,6 @@ #=GENOME_DIFF 1.0 -#=CREATED 16:43:13 22 Aug 2026 -#=PROGRAM breseq 0.50.0 revision 77916ce0087c +#=CREATED 14:45:44 23 Aug 2026 +#=PROGRAM breseq 0.50.0 revision 68145331ba14 #=COMMAND ./src/breseq/breseq -j 7 -o ./tests/long_ltee_ara_m1_40k_pe36 -r ./tests/long_ltee_ara_m1_40k_pe36/../data/downloads/ltee_REL606/REL606.gbk --predict-copy-number --predict-discordant-pairs --predict-missing-pairs --predict-pair-distance --predict-soft-clipping ./tests/long_ltee_ara_m1_40k_pe36/../data/downloads/ena_SRR030258/SRR030258_1.fastq.gz ./tests/long_ltee_ara_m1_40k_pe36/../data/downloads/ena_SRR030258/SRR030258_2.fastq.gz #=REFSEQ ./tests/long_ltee_ara_m1_40k_pe36/../data/downloads/ltee_REL606/REL606.gbk #=READSEQ ./tests/long_ltee_ara_m1_40k_pe36/../data/downloads/ena_SRR030258/SRR030258_1.fastq.gz @@ -1930,11 +1930,11 @@ DP 1916 . REL606 16972 1 REL606 588495 1 background_e_value=7.109e-11 candidate_ DP 1917 . REL606 16974 -1 REL606 590471 -1 background_e_value=0.000e+00 candidate_discordant_count=61 concordant_count=0.0 discordant_count=63 distinct_discordant_count=62 expected_concordant_count=54.8 frequency=1.0000 frequency_lower=0.9528 frequency_upper=1.0000 neg_log10_discordance_p_value=0.2 side_1_annotate_key=gene side_1_concordant_count=0 side_1_discordant_count=63 side_1_gene_name=mokC/nhaA side_1_gene_position=intergenic (-16/-514) side_1_gene_product=regulatory protein for HokC, overlaps CDS of hokC/pH-dependent sodium/proton antiporter side_1_gene_strand= side_1_locus_tag=ECB_00017/ECB_00018 side_1_unpaired_count=85 side_2_annotate_key=repeat side_2_concordant_count=40 side_2_discordant_count=63 side_2_gene_name=IS150 side_2_gene_position=noncoding (1977/1977 nt) side_2_gene_product=repeat region side_2_gene_strand=> side_2_redundant=1 side_2_unpaired_count=595 DP 1918 . REL606 23291 1 REL606 555926 1 background_e_value=8.784e-05 candidate_discordant_count=22 concordant_count=NA discordant_count=22 distinct_discordant_count=22 expected_concordant_count=54.8 frequency=NA frequency_lower=NA frequency_upper=NA neg_log10_discordance_p_value=2.5 side_1_annotate_key=repeat side_1_concordant_count=60 side_1_discordant_count=22 side_1_gene_name=IS1 side_1_gene_position=noncoding (1/768 nt) side_1_gene_product=repeat region side_1_gene_strand=> side_1_redundant=1 side_1_unpaired_count=3259 side_2_annotate_key=repeat side_2_concordant_count=0 side_2_discordant_count=22 side_2_gene_name=ECB_00513 side_2_gene_position=coding (1211/2346 nt) side_2_gene_product=conserved hypothetical protein side_2_gene_strand=> side_2_locus_tag=ECB_00513 side_2_redundant=1 side_2_unpaired_count=73 DP 1919 . REL606 23291 1 REL606 1544689 1 background_e_value=0.000e+00 candidate_discordant_count=58 concordant_count=NA discordant_count=58 distinct_discordant_count=57 expected_concordant_count=54.8 frequency=NA frequency_lower=NA frequency_upper=NA neg_log10_discordance_p_value=0.3 side_1_annotate_key=repeat side_1_concordant_count=60 side_1_discordant_count=58 side_1_gene_name=IS1 side_1_gene_position=noncoding (1/768 nt) side_1_gene_product=repeat region side_1_gene_strand=> side_1_redundant=1 side_1_unpaired_count=3259 side_2_annotate_key=repeat side_2_concordant_count=43 side_2_discordant_count=58 side_2_gene_name=gadB side_2_gene_position=coding (1308/1401 nt) side_2_gene_product=glutamate decarboxylase B, PLP-dependent side_2_gene_strand=< side_2_locus_tag=ECB_01451 side_2_redundant=1 side_2_unpaired_count=159 -SC 1920 . REL606 48921 1 agree_read_count=7 clipped_sequence=GGGGGGGGGGGG consensus_fraction=1.0000 frequency=0.3889 frequency_lower=0.1990 frequency_upper=0.6078 gene_name=fixC gene_position=coding (547/1287 nt) gene_product=predicted oxidoreductase with FAD/NAD(P)-binding domain gene_strand=> locus_tag=ECB_00047 log10_e_value=2.9 read_count=7 reject=SCORE_CUTOFF total_count=18 -SC 1921 . REL606 122309 1 agree_read_count=7 clipped_sequence=GTGGTTTGTTTT consensus_fraction=0.7000 frequency=0.3043 frequency_lower=0.1525 frequency_upper=0.4964 gene_name=ampE gene_position=coding (225/855 nt) gene_product=predicted inner membrane protein gene_strand=> locus_tag=ECB_00110 log10_e_value=2.1 read_count=10 reject=SCORE_CUTOFF total_count=23 +SC 1920 . REL606 48921 1 agree_read_count=7 agree_read_count_forward=7 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGGGGG consensus_fraction=1.0000 fisher_strand_p_value=3.14228e-05 frequency=0.3889 frequency_lower=0.1990 frequency_upper=0.6078 gene_name=fixC gene_position=coding (547/1287 nt) gene_product=predicted oxidoreductase with FAD/NAD(P)-binding domain gene_strand=> locus_tag=ECB_00047 log10_e_value=2.9 read_count=7 reject=SCORE_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=0 spanning_read_count_reverse=11 total_count=18 +SC 1921 . REL606 122309 1 agree_read_count=7 agree_read_count_forward=7 agree_read_count_reverse=0 clipped_sequence=GTGGTTTGTTTT consensus_fraction=0.7000 fisher_strand_p_value=1.03199e-04 frequency=0.3043 frequency_lower=0.1525 frequency_upper=0.4964 gene_name=ampE gene_position=coding (225/855 nt) gene_product=predicted inner membrane protein gene_strand=> locus_tag=ECB_00110 log10_e_value=2.1 read_count=10 reject=SCORE_CUTOFF,FISHER_STRAND spanning_read_count_forward=1 spanning_read_count_reverse=12 total_count=23 DP 1922 . REL606 242024 -1 REL606 2137411 1 background_e_value=9.423e-14 candidate_discordant_count=52 concordant_count=0.0 discordant_count=52 distinct_discordant_count=52 expected_concordant_count=54.8 frequency=1.0000 frequency_lower=0.9440 frequency_upper=1.0000 neg_log10_discordance_p_value=0.4 side_1_annotate_key=repeat side_1_concordant_count=54 side_1_discordant_count=52 side_1_gene_name=IS1 side_1_gene_position=noncoding (768/768 nt) side_1_gene_product=repeat region side_1_gene_strand=> side_1_redundant=1 side_1_unpaired_count=3501 side_2_annotate_key=gene side_2_concordant_count=0 side_2_discordant_count=52 side_2_gene_name=yegX side_2_gene_position=coding (370/819 nt) side_2_gene_product=predicted hydrolase side_2_gene_strand=< side_2_locus_tag=ECB_02030 side_2_unpaired_count=37 DP 1923 . REL606 242024 -1 REL606 3595772 -1 background_e_value=6.125e-13 candidate_discordant_count=50 concordant_count=0.0 discordant_count=50 distinct_discordant_count=49 expected_concordant_count=54.8 frequency=1.0000 frequency_lower=0.9407 frequency_upper=1.0000 neg_log10_discordance_p_value=0.5 side_1_annotate_key=repeat side_1_concordant_count=54 side_1_discordant_count=50 side_1_gene_name=IS1 side_1_gene_position=noncoding (768/768 nt) side_1_gene_product=repeat region side_1_gene_strand=> side_1_redundant=1 side_1_unpaired_count=3501 side_2_annotate_key=gene side_2_concordant_count=0 side_2_discordant_count=50 side_2_gene_name=gadA side_2_gene_position=coding (1300/1401 nt) side_2_gene_product=glutamate decarboxylase A, PLP-dependent side_2_gene_strand=< side_2_locus_tag=ECB_03365 side_2_unpaired_count=82 -SC 1924 . REL606 342371 1 agree_read_count=7 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.6364 frequency=0.2800 frequency_lower=0.1395 frequency_upper=0.4622 gene_name=mhpA gene_position=coding (1205/1665 nt) gene_product=3-(3-hydroxyphenyl)propionate hydroxylase gene_strand=> locus_tag=ECB_00301 log10_e_value=1.8 read_count=11 reject=SCORE_CUTOFF total_count=25 +SC 1924 . REL606 342371 1 agree_read_count=7 agree_read_count_forward=7 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.6364 fisher_strand_p_value=8.59993e-06 frequency=0.2800 frequency_lower=0.1395 frequency_upper=0.4622 gene_name=mhpA gene_position=coding (1205/1665 nt) gene_product=3-(3-hydroxyphenyl)propionate hydroxylase gene_strand=> locus_tag=ECB_00301 log10_e_value=1.8 read_count=11 reject=SCORE_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=0 spanning_read_count_reverse=14 total_count=25 DP 1925 . REL606 498937 -1 REL606 1503759 1 background_e_value=9.792e-03 candidate_discordant_count=15 concordant_count=43.5 discordant_count=15 distinct_discordant_count=15 expected_concordant_count=54.8 frequency=0.2564 frequency_lower=0.1652 frequency_upper=0.3670 neg_log10_discordance_p_value=3.3 reject=CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=49 side_1_discordant_count=15 side_1_gene_name=rhsD side_1_gene_position=coding (3510/4281 nt) side_1_gene_product=rhsD element protein side_1_gene_strand=> side_1_locus_tag=ECB_00448 side_1_unpaired_count=214 side_2_annotate_key=gene side_2_concordant_count=38 side_2_discordant_count=15 side_2_gene_name=rhsE side_2_gene_position=coding (3483/4224 nt) side_2_gene_product=rhsE element core protein RshE side_2_gene_strand=> side_2_locus_tag=ECB_01414 side_2_unpaired_count=21 DP 1926 . REL606 555928 1 REL606 2035093 -1 background_e_value=7.549e-09 candidate_discordant_count=36 concordant_count=0.0 discordant_count=36 distinct_discordant_count=36 expected_concordant_count=54.8 frequency=1.0000 frequency_lower=0.9202 frequency_upper=1.0000 neg_log10_discordance_p_value=1.2 side_1_annotate_key=gene side_1_concordant_count=0 side_1_discordant_count=36 side_1_gene_name=ECB_00513 side_1_gene_position=coding (1213/2346 nt) side_1_gene_product=conserved hypothetical protein side_1_gene_strand=> side_1_locus_tag=ECB_00513 side_1_unpaired_count=73 side_2_annotate_key=repeat side_2_concordant_count=0 side_2_discordant_count=36 side_2_gene_name=IS1 side_2_gene_position=noncoding (1/768 nt) side_2_gene_product=repeat region side_2_gene_strand=< side_2_redundant=1 side_2_unpaired_count=3338 DP 1927 . REL606 588495 1 REL606 1270162 1 background_e_value=4.490e-05 candidate_discordant_count=23 concordant_count=NA discordant_count=23 distinct_discordant_count=21 expected_concordant_count=54.8 frequency=NA frequency_lower=NA frequency_upper=NA neg_log10_discordance_p_value=2.6 side_1_annotate_key=repeat side_1_concordant_count=62 side_1_discordant_count=23 side_1_gene_name=IS150 side_1_gene_position=noncoding (1/1977 nt) side_1_gene_product=repeat region side_1_gene_strand=> side_1_redundant=1 side_1_unpaired_count=1425 side_2_annotate_key=repeat side_2_concordant_count=25 side_2_discordant_count=23 side_2_gene_name=ldrB/ldrC side_2_gene_position=intergenic (-204/+224) side_2_gene_product=toxic polypeptide, small/toxic polypeptide, small side_2_gene_strand= side_1_redundant=1 side_1_unpaired_count=595 side_2_annotate_key=gene side_2_concordant_count=0 side_2_discordant_count=53 side_2_gene_name=ynjI side_2_gene_position=coding (573/1041 nt) side_2_gene_product=predicted inner membrane protein side_2_gene_strand=< side_2_locus_tag=ECB_01731 side_2_unpaired_count=104 DP 1935 . REL606 590471 -1 REL606 3015774 -1 background_e_value=0.000e+00 candidate_discordant_count=55 concordant_count=0.0 discordant_count=55 distinct_discordant_count=55 expected_concordant_count=54.8 frequency=1.0000 frequency_lower=0.9470 frequency_upper=1.0000 neg_log10_discordance_p_value=0.3 side_1_annotate_key=repeat side_1_concordant_count=40 side_1_discordant_count=55 side_1_gene_name=IS150 side_1_gene_position=noncoding (1977/1977 nt) side_1_gene_product=repeat region side_1_gene_strand=> side_1_redundant=1 side_1_unpaired_count=595 side_2_annotate_key=gene side_2_concordant_count=0 side_2_discordant_count=55 side_2_gene_name=ECB_02816 side_2_gene_position=coding (1195/1677 nt) side_2_gene_product=KpsD protein side_2_gene_strand=> side_2_locus_tag=ECB_02816 side_2_unpaired_count=83 DP 1936 . REL606 590471 -1 REL606 3901931 1 background_e_value=2.497e-12 candidate_discordant_count=48 concordant_count=0.0 discordant_count=48 distinct_discordant_count=47 expected_concordant_count=54.8 frequency=1.0000 frequency_lower=0.9382 frequency_upper=1.0000 neg_log10_discordance_p_value=0.6 side_1_annotate_key=repeat side_1_concordant_count=40 side_1_discordant_count=48 side_1_gene_name=IS150 side_1_gene_position=noncoding (1977/1977 nt) side_1_gene_product=repeat region side_1_gene_strand=> side_1_redundant=1 side_1_unpaired_count=595 side_2_annotate_key=gene side_2_concordant_count=0 side_2_discordant_count=48 side_2_gene_name=yieO side_2_gene_position=coding (489/1428 nt) side_2_gene_product=predicted multidrug or homocysteine efflux system side_2_gene_strand=< side_2_locus_tag=ECB_03640 side_2_unpaired_count=41 -SC 1937 . REL606 726917 -1 agree_read_count=5 clipped_sequence=CTAACCCCCCCC consensus_fraction=0.5556 frequency=0.2778 frequency_lower=0.1164 frequency_upper=0.4978 log10_e_value=0.3 no_show=1 read_count=9 reject=SCORE_CUTOFF total_count=18 -SC 1938 . REL606 742908 -1 agree_read_count=6 clipped_sequence=AAAAAACCCCCC consensus_fraction=0.7500 frequency=0.3750 frequency_lower=0.1778 frequency_upper=0.6090 gene_name=sucB gene_position=coding (596/1218 nt) gene_product=dihydrolipoamide acetyltransferase gene_strand=> locus_tag=ECB_00686 log10_e_value=1.9 read_count=8 reject=SCORE_CUTOFF total_count=16 -SC 1939 . REL606 1012575 1 agree_read_count=5 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.7143 frequency=0.4167 frequency_lower=0.1810 frequency_upper=0.6848 gene_name=ssuD gene_position=coding (505/1146 nt) gene_product=alkanesulfonate monooxygenase gene_strand=< locus_tag=ECB_00939 log10_e_value=1.3 read_count=7 reject=SCORE_CUTOFF total_count=12 -SC 1940 . REL606 1062852 -1 agree_read_count=6 clipped_sequence=AAAAAAAAAAAC consensus_fraction=0.5455 frequency=0.3158 frequency_lower=0.1475 frequency_upper=0.5300 gene_name=yccZ gene_position=coding (43/1140 nt) gene_product=predicted exopolysaccharide export protein gene_strand=< locus_tag=ECB_00986 log10_e_value=1.4 read_count=11 reject=SCORE_CUTOFF total_count=19 -SC 1941 . REL606 1073406 1 agree_read_count=5 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.4167 frequency=0.2632 frequency_lower=0.1099 frequency_upper=0.4758 log10_e_value=0.2 no_show=1 read_count=12 reject=SCORE_CUTOFF,CLIPPED_TAIL_CONSENSUS total_count=19 -SC 1942 . REL606 1168135 1 agree_read_count=5 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.6250 frequency=0.2632 frequency_lower=0.1099 frequency_upper=0.4758 log10_e_value=0.2 no_show=1 read_count=8 reject=SCORE_CUTOFF total_count=19 +SC 1937 . REL606 726917 -1 agree_read_count=5 agree_read_count_forward=0 agree_read_count_reverse=5 clipped_sequence=CTAACCCCCCCC consensus_fraction=0.5556 fisher_strand_p_value=4.99500e-04 frequency=0.2778 frequency_lower=0.1164 frequency_upper=0.4978 log10_e_value=0.3 no_show=1 read_count=9 reject=SCORE_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=9 spanning_read_count_reverse=0 total_count=18 +SC 1938 . REL606 742908 -1 agree_read_count=6 agree_read_count_forward=0 agree_read_count_reverse=6 clipped_sequence=AAAAAACCCCCC consensus_fraction=0.7500 fisher_strand_p_value=9.65701e-03 frequency=0.3750 frequency_lower=0.1778 frequency_upper=0.6090 gene_name=sucB gene_position=coding (596/1218 nt) gene_product=dihydrolipoamide acetyltransferase gene_strand=> locus_tag=ECB_00686 log10_e_value=1.9 read_count=8 reject=SCORE_CUTOFF,FISHER_STRAND spanning_read_count_forward=6 spanning_read_count_reverse=2 total_count=16 +SC 1939 . REL606 1012575 1 agree_read_count=5 agree_read_count_forward=5 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.7143 fisher_strand_p_value=7.93651e-03 frequency=0.4167 frequency_lower=0.1810 frequency_upper=0.6848 gene_name=ssuD gene_position=coding (505/1146 nt) gene_product=alkanesulfonate monooxygenase gene_strand=< locus_tag=ECB_00939 log10_e_value=1.3 read_count=7 reject=SCORE_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=0 spanning_read_count_reverse=5 total_count=12 +SC 1940 . REL606 1062852 -1 agree_read_count=6 agree_read_count_forward=0 agree_read_count_reverse=6 clipped_sequence=AAAAAAAAAAAC consensus_fraction=0.5455 fisher_strand_p_value=3.33000e-04 frequency=0.3158 frequency_lower=0.1475 frequency_upper=0.5300 gene_name=yccZ gene_position=coding (43/1140 nt) gene_product=predicted exopolysaccharide export protein gene_strand=< locus_tag=ECB_00986 log10_e_value=1.4 read_count=11 reject=SCORE_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=8 spanning_read_count_reverse=0 total_count=19 +SC 1941 . REL606 1073406 1 agree_read_count=5 agree_read_count_forward=5 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.4167 fisher_strand_p_value=1.26263e-03 frequency=0.2632 frequency_lower=0.1099 frequency_upper=0.4758 log10_e_value=0.2 no_show=1 read_count=12 reject=SCORE_CUTOFF,CLIPPED_TAIL_CONSENSUS,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=0 spanning_read_count_reverse=7 total_count=19 +SC 1942 . REL606 1168135 1 agree_read_count=5 agree_read_count_forward=5 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.6250 fisher_strand_p_value=2.28938e-04 frequency=0.2632 frequency_lower=0.1099 frequency_upper=0.4758 log10_e_value=0.2 no_show=1 read_count=8 reject=SCORE_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=0 spanning_read_count_reverse=11 total_count=19 PD 1943 . REL606 1297291 -1 REL606 1297292 1 ambiguous_pair_count=56 candidate_covering_count=73 distinct_pair_count=14 frequency=0.8235 frequency_lower=0.6044 frequency_upper=0.9501 normal_pair_count=3 position_range=1 reject=PAIR_DISTANCE_SCORE score=1.1 seed_z_score=-6.30 shifted_pair_count=14 side_1_annotate_key=gene side_1_gene_name=adhE/ychE side_1_gene_position=intergenic (-377/-100) side_1_gene_product=fused acetaldehyde-CoA dehydrogenase/iron-dependent alcohol dehydrogenase/pyruvate-formate lyase deactivase/predicted inner membrane protein side_1_gene_strand= side_1_locus_tag=ECB_01215/ECB_01216 side_2_annotate_key=gene side_2_gene_name=adhE/ychE side_2_gene_position=intergenic (-378/-99) side_2_gene_product=fused acetaldehyde-CoA dehydrogenase/iron-dependent alcohol dehydrogenase/pyruvate-formate lyase deactivase/predicted inner membrane protein side_2_gene_strand= side_2_locus_tag=ECB_01215/ECB_01216 size_shift=-14 size_shift_lower=-20 size_shift_upper=-10 total_pair_count=73 -SC 1944 . REL606 1475143 -1 agree_read_count=6 clipped_sequence=AAACCCCCCCCC consensus_fraction=0.6000 frequency=0.3750 frequency_lower=0.1778 frequency_upper=0.6090 gene_name=ydcO gene_position=coding (1048/1176 nt) gene_product=predicted benzoate transporter gene_strand=< locus_tag=ECB_01391 log10_e_value=1.9 read_count=10 reject=SCORE_CUTOFF total_count=16 -SC 1945 . REL606 1514080 -1 agree_read_count=6 clipped_sequence=CCCCCCCCCCCC consensus_fraction=0.8571 frequency=0.4615 frequency_lower=0.2240 frequency_upper=0.7130 gene_name=narZ gene_position=coding (2662/3741 nt) gene_product=nitrate reductase 2 (NRZ), alpha subunit gene_strand=< locus_tag=ECB_01426 log10_e_value=2.6 read_count=7 reject=SCORE_CUTOFF total_count=13 -SC 1946 . REL606 1674823 -1 agree_read_count=6 clipped_sequence=AAAAAACCCCCC consensus_fraction=0.8571 frequency=0.5455 frequency_lower=0.2712 frequency_upper=0.8004 gene_name=hdhA gene_position=coding (413/768 nt) gene_product=7-alpha-hydroxysteroid dehydrogenase gene_strand=< locus_tag=ECB_01588 log10_e_value=3.1 read_count=7 total_count=11 -SC 1947 . REL606 1716933 -1 agree_read_count=7 clipped_sequence=CCCCCCCCCCCC consensus_fraction=0.8750 frequency=0.3043 frequency_lower=0.1525 frequency_upper=0.4964 gene_name=ydhB gene_position=coding (133/933 nt) gene_product=predicted DNA-binding transcriptional regulator gene_strand=< locus_tag=ECB_01630 log10_e_value=2.1 read_count=8 reject=SCORE_CUTOFF total_count=23 -SC 1948 . REL606 1802331 -1 agree_read_count=5 clipped_sequence=AAAAAAAAAACC consensus_fraction=0.8333 frequency=0.3571 frequency_lower=0.1527 frequency_upper=0.6096 gene_name=ydjR/spy gene_position=intergenic (-129/+74) gene_product=hypothetical protein/envelope stress induced periplasmic protein gene_strand=/< side_1_locus_tag=ECB_01986/ECB_01987 side_1_unpaired_count=1 side_2_annotate_key=gene side_2_concordant_count=0 side_2_discordant_count=98 side_2_gene_name=ECB_02013 side_2_gene_position=coding (199/216 nt) side_2_gene_product=conserved hypothetical protein; putative exported protein side_2_gene_strand=< side_2_locus_tag=ECB_02013 side_2_unpaired_count=2 PD 1953 . REL606 2173252 -1 REL606 2173253 1 ambiguous_pair_count=56 candidate_covering_count=68 distinct_pair_count=9 frequency=0.6000 frequency_lower=0.3596 frequency_upper=0.8091 normal_pair_count=6 position_range=1 reject=PAIR_DISTANCE_SCORE score=0.6 seed_z_score=-6.02 shifted_pair_count=9 side_1_annotate_key=gene side_1_gene_name=bglX/dld side_1_gene_position=intergenic (-25/-171) side_1_gene_product=beta-D-glucoside glucohydrolase, periplasmic/D-lactate dehydrogenase, FAD-binding, NADH independent side_1_gene_strand= side_1_locus_tag=ECB_02062/ECB_02063 side_2_annotate_key=gene side_2_gene_name=bglX/dld side_2_gene_position=intergenic (-26/-170) side_2_gene_product=beta-D-glucoside glucohydrolase, periplasmic/D-lactate dehydrogenase, FAD-binding, NADH independent side_2_gene_strand= side_2_locus_tag=ECB_02062/ECB_02063 size_shift=-13 size_shift_lower=-19 size_shift_upper=-9 total_pair_count=71 -SC 1954 . REL606 2178048 1 agree_read_count=6 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.6667 frequency=0.2857 frequency_lower=0.1324 frequency_upper=0.4874 gene_name=yohF gene_position=coding (461/762 nt) gene_product=predicted oxidoreductase with NAD(P)-binding Rossmann-fold domain gene_strand=< locus_tag=ECB_02067 log10_e_value=1.1 read_count=9 reject=SCORE_CUTOFF total_count=21 -SC 1955 . REL606 2188147 -1 agree_read_count=5 clipped_sequence=CCCCCCCCCCCC consensus_fraction=1.0000 frequency=0.2778 frequency_lower=0.1164 frequency_upper=0.4978 log10_e_value=0.3 no_show=1 read_count=5 reject=SCORE_CUTOFF total_count=18 -SC 1956 . REL606 2480527 -1 agree_read_count=5 clipped_sequence=AAAAAACCCCCC consensus_fraction=0.8333 frequency=0.2500 frequency_lower=0.1041 frequency_upper=0.4556 log10_e_value=0.1 no_show=1 read_count=6 reject=SCORE_CUTOFF total_count=20 +SC 1954 . REL606 2178048 1 agree_read_count=6 agree_read_count_forward=6 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.6667 fisher_strand_p_value=5.38677e-05 frequency=0.2857 frequency_lower=0.1324 frequency_upper=0.4874 gene_name=yohF gene_position=coding (461/762 nt) gene_product=predicted oxidoreductase with NAD(P)-binding Rossmann-fold domain gene_strand=< locus_tag=ECB_02067 log10_e_value=1.1 read_count=9 reject=SCORE_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=0 spanning_read_count_reverse=12 total_count=21 +SC 1955 . REL606 2188147 -1 agree_read_count=5 agree_read_count_forward=0 agree_read_count_reverse=5 clipped_sequence=CCCCCCCCCCCC consensus_fraction=1.0000 fisher_strand_p_value=1.16713e-04 frequency=0.2778 frequency_lower=0.1164 frequency_upper=0.4978 log10_e_value=0.3 no_show=1 read_count=5 reject=SCORE_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=13 spanning_read_count_reverse=0 total_count=18 +SC 1956 . REL606 2480527 -1 agree_read_count=5 agree_read_count_forward=0 agree_read_count_reverse=5 clipped_sequence=AAAAAACCCCCC consensus_fraction=0.8333 fisher_strand_p_value=8.59993e-05 frequency=0.2500 frequency_lower=0.1041 frequency_upper=0.4556 log10_e_value=0.1 no_show=1 read_count=6 reject=SCORE_CUTOFF,FISHER_STRAND spanning_read_count_forward=14 spanning_read_count_reverse=0 total_count=20 PD 1957 . REL606 2488892 -1 REL606 2488997 1 ambiguous_pair_count=0 candidate_covering_count=28 distinct_pair_count=28 frequency=1.0000 frequency_lower=0.8985 frequency_upper=1.0000 normal_pair_count=0 position_range=23 score=8.3 seed_z_score=9.16 shifted_pair_count=28 side_1_annotate_key=gene side_1_gene_name=eutH/eutG side_1_gene_position=intergenic (-56/+261) side_1_gene_product=predicted inner membrane protein/predicted alcohol dehydrogenase in ethanolamine utilization side_1_gene_strand= locus_tag=ECB_02560 log10_e_value=1.9 read_count=10 reject=SCORE_CUTOFF total_count=24 +SC 1958 . REL606 2614598 -1 agree_read_count=5 agree_read_count_forward=0 agree_read_count_reverse=5 clipped_sequence=GACCGCCACCAC consensus_fraction=0.4545 fisher_strand_p_value=1.51515e-02 frequency=0.2941 frequency_lower=0.1238 frequency_upper=0.5219 log10_e_value=0.4 no_show=1 read_count=11 reject=SCORE_CUTOFF,CLIPPED_TAIL_CONSENSUS,FISHER_STRAND spanning_read_count_forward=5 spanning_read_count_reverse=1 total_count=17 +SC 1959 . REL606 2728387 1 agree_read_count=7 agree_read_count_forward=7 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.7000 fisher_strand_p_value=8.59993e-06 frequency=0.2917 frequency_lower=0.1457 frequency_upper=0.4787 gene_name=norV gene_position=coding (1052/1440 nt) gene_product=anaerobic nitric oxide reductase flavorubredoxin gene_strand=> locus_tag=ECB_02560 log10_e_value=1.9 read_count=10 reject=SCORE_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=0 spanning_read_count_reverse=14 total_count=24 PD 1960 . REL606 2792666 -1 REL606 2792726 1 ambiguous_pair_count=12 candidate_covering_count=44 distinct_pair_count=29 frequency=0.9062 frequency_lower=0.7752 frequency_upper=0.9740 normal_pair_count=3 position_range=11 score=13.3 seed_z_score=10.74 shifted_pair_count=29 side_1_annotate_key=gene side_1_gene_name=ECB_02621 side_1_gene_position=coding (158/849 nt) side_1_gene_product=conserved hypothetical protein side_1_gene_strand=> side_1_locus_tag=ECB_02621 side_2_annotate_key=gene side_2_gene_name=ECB_02621 side_2_gene_position=coding (218/849 nt) side_2_gene_product=conserved hypothetical protein side_2_gene_strand=> side_2_locus_tag=ECB_02621 size_shift=59 size_shift_lower=55 size_shift_upper=63 total_pair_count=44 -SC 1961 . REL606 2891719 1 agree_read_count=5 clipped_sequence=GGGGGTTTTTTA consensus_fraction=0.8333 frequency=0.3846 frequency_lower=0.1657 frequency_upper=0.6452 gene_name=ygeV/ygeW gene_position=intergenic (-178/-298) gene_product=predicted DNA-binding transcriptional regulator/hypothetical protein gene_strand= locus_tag=ECB_02702/ECB_02703 log10_e_value=1.1 read_count=6 reject=SCORE_CUTOFF total_count=13 -SC 1962 . REL606 2983214 1 agree_read_count=7 clipped_sequence=GGGGGGGGCGGG consensus_fraction=1.0000 frequency=0.4118 frequency_lower=0.2119 frequency_upper=0.6360 gene_name=yggW gene_position=coding (197/1137 nt) gene_product=coproporphyrinogen III oxidase gene_strand=> locus_tag=ECB_02785 log10_e_value=3.1 read_count=7 total_count=17 -SC 1963 . REL606 3006589 -1 agree_read_count=5 clipped_sequence=CCCCCCCCCCCC consensus_fraction=0.7143 frequency=0.2778 frequency_lower=0.1164 frequency_upper=0.4978 log10_e_value=0.3 no_show=1 read_count=7 reject=SCORE_CUTOFF total_count=18 +SC 1961 . REL606 2891719 1 agree_read_count=5 agree_read_count_forward=5 agree_read_count_reverse=0 clipped_sequence=GGGGGTTTTTTA consensus_fraction=0.8333 fisher_strand_p_value=1.26263e-03 frequency=0.3846 frequency_lower=0.1657 frequency_upper=0.6452 gene_name=ygeV/ygeW gene_position=intergenic (-178/-298) gene_product=predicted DNA-binding transcriptional regulator/hypothetical protein gene_strand= locus_tag=ECB_02702/ECB_02703 log10_e_value=1.1 read_count=6 reject=SCORE_CUTOFF,FISHER_STRAND spanning_read_count_forward=0 spanning_read_count_reverse=7 total_count=13 +SC 1962 . REL606 2983214 1 agree_read_count=7 agree_read_count_forward=7 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGCGGG consensus_fraction=1.0000 fisher_strand_p_value=5.14192e-05 frequency=0.4118 frequency_lower=0.2119 frequency_upper=0.6360 gene_name=yggW gene_position=coding (197/1137 nt) gene_product=coproporphyrinogen III oxidase gene_strand=> locus_tag=ECB_02785 log10_e_value=3.1 read_count=7 reject=FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=0 spanning_read_count_reverse=10 total_count=17 +SC 1963 . REL606 3006589 -1 agree_read_count=5 agree_read_count_forward=0 agree_read_count_reverse=5 clipped_sequence=CCCCCCCCCCCC consensus_fraction=0.7143 fisher_strand_p_value=2.28938e-04 frequency=0.2778 frequency_lower=0.1164 frequency_upper=0.4978 log10_e_value=0.3 no_show=1 read_count=7 reject=SCORE_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=11 spanning_read_count_reverse=0 total_count=18 PD 1964 . REL606 3289961 -1 REL606 3289978 1 ambiguous_pair_count=28 candidate_covering_count=36 distinct_pair_count=18 frequency=0.9000 frequency_lower=0.7174 frequency_upper=0.9819 normal_pair_count=2 position_range=12 reject=PAIR_DISTANCE_SCORE score=2.7 seed_z_score=7.03 shifted_pair_count=18 side_1_annotate_key=gene side_1_gene_name=gltB side_1_gene_position=coding (95/4554 nt) side_1_gene_product=glutamate synthase, large subunit side_1_gene_strand=> side_1_locus_tag=ECB_03077 side_2_annotate_key=gene side_2_gene_name=gltB side_2_gene_position=coding (112/4554 nt) side_2_gene_product=glutamate synthase, large subunit side_2_gene_strand=> side_2_locus_tag=ECB_03077 size_shift=16 size_shift_lower=15 size_shift_upper=25 snapped_to_junction=1 total_pair_count=48 -SC 1965 . REL606 3437328 1 agree_read_count=4 clipped_sequence=GGGGGGGGGGGG consensus_fraction=1.0000 frequency=0.5000 frequency_lower=0.1929 frequency_upper=0.8071 gene_name=yhfW gene_position=coding (1168/1227 nt) gene_product=predicted mutase gene_strand=< locus_tag=ECB_03232 log10_e_value=0.6 read_count=4 reject=SCORE_CUTOFF total_count=8 -SC 1966 . REL606 3624282 -1 agree_read_count=5 clipped_sequence=ACCGAGAACCAC consensus_fraction=1.0000 frequency=0.2778 frequency_lower=0.1164 frequency_upper=0.4978 log10_e_value=0.3 no_show=1 read_count=5 reject=SCORE_CUTOFF total_count=18 -SC 1967 . REL606 3722625 1 agree_read_count=5 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.6250 frequency=0.2941 frequency_lower=0.1238 frequency_upper=0.5219 log10_e_value=0.4 no_show=1 read_count=8 reject=SCORE_CUTOFF total_count=17 -SC 1968 . REL606 3728784 1 agree_read_count=8 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.7273 frequency=0.2963 frequency_lower=0.1568 frequency_upper=0.4714 gene_name=yibP gene_position=coding (1181/1260 nt) gene_product=protease with a role in cell division gene_strand=> locus_tag=ECB_03471 log10_e_value=2.6 read_count=11 reject=SCORE_CUTOFF total_count=27 -SC 1969 . REL606 3807908 -1 agree_read_count=5 clipped_sequence=CCCCCCCCCCCC consensus_fraction=0.7143 frequency=0.4167 frequency_lower=0.1810 frequency_upper=0.6848 gene_name=uhpC gene_position=coding (649/1320 nt) gene_product=membrane protein regulates uhpT expression gene_strand=< locus_tag=ECB_03551 log10_e_value=1.3 read_count=7 reject=SCORE_CUTOFF total_count=12 -SC 1970 . REL606 3917470 -1 agree_read_count=7 clipped_sequence=CCCCCCCCCCCC consensus_fraction=1.0000 frequency=0.3182 frequency_lower=0.1599 frequency_upper=0.5155 gene_name=ilvA gene_position=coding (338/1545 nt) gene_product=threonine dehydratase gene_strand=> locus_tag=ECB_03650 log10_e_value=2.2 read_count=7 reject=SCORE_CUTOFF total_count=22 -SC 1971 . REL606 3937196 -1 agree_read_count=6 clipped_sequence=CCTTTCCCCCCC consensus_fraction=0.6667 frequency=0.2000 frequency_lower=0.0909 frequency_upper=0.3570 log10_e_value=0.2 no_show=1 read_count=9 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=30 -SC 1972 . REL606 4123600 1 agree_read_count=5 clipped_sequence=GGGGGGGGGGGG consensus_fraction=1.0000 frequency=0.2500 frequency_lower=0.1041 frequency_upper=0.4556 log10_e_value=0.1 no_show=1 read_count=5 reject=SCORE_CUTOFF total_count=20 -SC 1973 . REL606 4312841 -1 agree_read_count=6 clipped_sequence=AAACCCCCCCCC consensus_fraction=0.7500 frequency=0.4286 frequency_lower=0.2061 frequency_upper=0.6750 gene_name=yjdB gene_position=coding (1464/1644 nt) gene_product=predicted metal dependent hydrolase gene_strand=< locus_tag=ECB_03985 log10_e_value=2.3 read_count=8 reject=SCORE_CUTOFF total_count=14 -SC 1974 . REL606 4313453 1 agree_read_count=5 clipped_sequence=CCTGCCGTTGCC consensus_fraction=1.0000 frequency=0.2778 frequency_lower=0.1164 frequency_upper=0.4978 log10_e_value=0.3 no_show=1 read_count=5 reject=SCORE_CUTOFF total_count=18 -SC 1975 . REL606 4509124 -1 agree_read_count=7 clipped_sequence=AAAAAACCCCCC consensus_fraction=0.6364 frequency=0.3043 frequency_lower=0.1525 frequency_upper=0.4964 gene_name=sgcC gene_position=coding (1258/1314 nt) gene_product=predicted phosphotransferase enzyme IIC component gene_strand=< locus_tag=ECB_04169 log10_e_value=2.1 read_count=11 reject=SCORE_CUTOFF total_count=23 -SC 1976 . REL606 4540220 -1 agree_read_count=7 clipped_sequence=CCTCCCCCCCCC consensus_fraction=0.8750 frequency=0.4118 frequency_lower=0.2119 frequency_upper=0.6360 gene_name=iadA gene_position=coding (221/1173 nt) gene_product=isoaspartyl dipeptidase gene_strand=< locus_tag=ECB_04197 log10_e_value=3.1 read_count=8 total_count=17 -SC 1977 . REL606 4542138 -1 agree_read_count=4 clipped_sequence=ACAAAAAAACCC consensus_fraction=0.8000 frequency=0.5000 frequency_lower=0.1929 frequency_upper=0.8071 log10_e_value=0.6 no_show=1 read_count=5 reject=SCORE_CUTOFF total_count=8 -SC 1978 . REL606 4560102 -1 agree_read_count=5 clipped_sequence=CCGCCCCCCCCC consensus_fraction=0.8333 frequency=0.2500 frequency_lower=0.1041 frequency_upper=0.4556 log10_e_value=0.1 no_show=1 read_count=6 reject=SCORE_CUTOFF total_count=20 +SC 1965 . REL606 3437328 1 agree_read_count=4 agree_read_count_forward=4 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGGGGG consensus_fraction=1.0000 fisher_strand_p_value=2.85714e-02 frequency=0.5000 frequency_lower=0.1929 frequency_upper=0.8071 log10_e_value=0.6 no_show=1 read_count=4 reject=SCORE_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=0 spanning_read_count_reverse=4 total_count=8 +SC 1966 . REL606 3624282 -1 agree_read_count=5 agree_read_count_forward=0 agree_read_count_reverse=5 clipped_sequence=ACCGAGAACCAC consensus_fraction=1.0000 fisher_strand_p_value=3.59477e-02 frequency=0.2778 frequency_lower=0.1164 frequency_upper=0.4978 log10_e_value=0.3 no_show=1 read_count=5 reject=SCORE_CUTOFF,FISHER_STRAND spanning_read_count_forward=8 spanning_read_count_reverse=5 total_count=18 +SC 1967 . REL606 3722625 1 agree_read_count=5 agree_read_count_forward=5 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.6250 fisher_strand_p_value=4.99500e-04 frequency=0.2941 frequency_lower=0.1238 frequency_upper=0.5219 log10_e_value=0.4 no_show=1 read_count=8 reject=SCORE_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=0 spanning_read_count_reverse=9 total_count=17 +SC 1968 . REL606 3728784 1 agree_read_count=8 agree_read_count_forward=8 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.7273 fisher_strand_p_value=1.35967e-06 frequency=0.2963 frequency_lower=0.1568 frequency_upper=0.4714 gene_name=yibP gene_position=coding (1181/1260 nt) gene_product=protease with a role in cell division gene_strand=> locus_tag=ECB_03471 log10_e_value=2.6 read_count=11 reject=SCORE_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=0 spanning_read_count_reverse=16 total_count=27 +SC 1969 . REL606 3807908 -1 agree_read_count=5 agree_read_count_forward=0 agree_read_count_reverse=5 clipped_sequence=CCCCCCCCCCCC consensus_fraction=0.7143 fisher_strand_p_value=7.93651e-03 frequency=0.4167 frequency_lower=0.1810 frequency_upper=0.6848 gene_name=uhpC gene_position=coding (649/1320 nt) gene_product=membrane protein regulates uhpT expression gene_strand=< locus_tag=ECB_03551 log10_e_value=1.3 read_count=7 reject=SCORE_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=5 spanning_read_count_reverse=0 total_count=12 +SC 1970 . REL606 3917470 -1 agree_read_count=7 agree_read_count_forward=0 agree_read_count_reverse=7 clipped_sequence=CCCCCCCCCCCC consensus_fraction=1.0000 fisher_strand_p_value=5.86359e-06 frequency=0.3182 frequency_lower=0.1599 frequency_upper=0.5155 gene_name=ilvA gene_position=coding (338/1545 nt) gene_product=threonine dehydratase gene_strand=> locus_tag=ECB_03650 log10_e_value=2.2 read_count=7 reject=SCORE_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=15 spanning_read_count_reverse=0 total_count=22 +SC 1971 . REL606 3937196 -1 agree_read_count=6 agree_read_count_forward=0 agree_read_count_reverse=6 clipped_sequence=CCTTTCCCCCCC consensus_fraction=0.6667 fisher_strand_p_value=9.45914e-05 frequency=0.2000 frequency_lower=0.0909 frequency_upper=0.3570 log10_e_value=0.2 no_show=1 read_count=9 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=19 spanning_read_count_reverse=2 total_count=30 +SC 1972 . REL606 4123600 1 agree_read_count=5 agree_read_count_forward=5 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGGGGG consensus_fraction=1.0000 fisher_strand_p_value=6.44995e-05 frequency=0.2500 frequency_lower=0.1041 frequency_upper=0.4556 log10_e_value=0.1 no_show=1 read_count=5 reject=SCORE_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=0 spanning_read_count_reverse=15 total_count=20 +SC 1973 . REL606 4312841 -1 agree_read_count=6 agree_read_count_forward=0 agree_read_count_reverse=6 clipped_sequence=AAACCCCCCCCC consensus_fraction=0.7500 fisher_strand_p_value=2.16450e-03 frequency=0.4286 frequency_lower=0.2061 frequency_upper=0.6750 gene_name=yjdB gene_position=coding (1464/1644 nt) gene_product=predicted metal dependent hydrolase gene_strand=< locus_tag=ECB_03985 log10_e_value=2.3 read_count=8 reject=SCORE_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=6 spanning_read_count_reverse=0 total_count=14 +SC 1974 . REL606 4313453 1 agree_read_count=5 agree_read_count_forward=1 agree_read_count_reverse=4 clipped_sequence=CCTGCCGTTGCC consensus_fraction=1.0000 fisher_strand_p_value=2.17087e-02 frequency=0.2778 frequency_lower=0.1164 frequency_upper=0.4978 log10_e_value=0.3 no_show=1 read_count=5 reject=SCORE_CUTOFF,FISHER_STRAND spanning_read_count_forward=11 spanning_read_count_reverse=2 total_count=18 +SC 1975 . REL606 4509124 -1 agree_read_count=7 agree_read_count_forward=0 agree_read_count_reverse=7 clipped_sequence=AAAAAACCCCCC consensus_fraction=0.6364 fisher_strand_p_value=1.98460e-05 frequency=0.3043 frequency_lower=0.1525 frequency_upper=0.4964 gene_name=sgcC gene_position=coding (1258/1314 nt) gene_product=predicted phosphotransferase enzyme IIC component gene_strand=< locus_tag=ECB_04169 log10_e_value=2.1 read_count=11 reject=SCORE_CUTOFF,FISHER_STRAND spanning_read_count_forward=12 spanning_read_count_reverse=0 total_count=23 +SC 1976 . REL606 4540220 -1 agree_read_count=7 agree_read_count_forward=0 agree_read_count_reverse=7 clipped_sequence=CCTCCCCCCCCC consensus_fraction=0.8750 fisher_strand_p_value=8.74126e-05 frequency=0.4118 frequency_lower=0.2119 frequency_upper=0.6360 gene_name=iadA gene_position=coding (221/1173 nt) gene_product=isoaspartyl dipeptidase gene_strand=< locus_tag=ECB_04197 log10_e_value=3.1 read_count=8 reject=FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=9 spanning_read_count_reverse=0 total_count=17 +SC 1977 . REL606 4542138 -1 agree_read_count=4 agree_read_count_forward=0 agree_read_count_reverse=4 clipped_sequence=ACAAAAAAACCC consensus_fraction=0.8000 fisher_strand_p_value=2.85714e-02 frequency=0.5000 frequency_lower=0.1929 frequency_upper=0.8071 log10_e_value=0.6 no_show=1 read_count=5 reject=SCORE_CUTOFF,FISHER_STRAND spanning_read_count_forward=3 spanning_read_count_reverse=0 total_count=8 +SC 1978 . REL606 4560102 -1 agree_read_count=5 agree_read_count_forward=0 agree_read_count_reverse=5 clipped_sequence=CCGCCCCCCCCC consensus_fraction=0.8333 fisher_strand_p_value=1.80599e-03 frequency=0.2500 frequency_lower=0.1041 frequency_upper=0.4556 log10_e_value=0.1 no_show=1 read_count=6 reject=SCORE_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=12 spanning_read_count_reverse=2 total_count=20 diff --git a/tests/long_ltee_ara_p1_50k_pe101/expected.gd b/tests/long_ltee_ara_p1_50k_pe101/expected.gd index cdae9450..bfa8ec9e 100644 --- a/tests/long_ltee_ara_p1_50k_pe101/expected.gd +++ b/tests/long_ltee_ara_p1_50k_pe101/expected.gd @@ -1,6 +1,6 @@ #=GENOME_DIFF 1.0 -#=CREATED 16:49:15 22 Aug 2026 -#=PROGRAM breseq 0.50.0 revision 77916ce0087c +#=CREATED 14:39:49 23 Aug 2026 +#=PROGRAM breseq 0.50.0 revision 68145331ba14 #=COMMAND ./src/breseq/breseq -j 7 -o ./tests/long_ltee_ara_p1_50k_pe101 -r ./tests/long_ltee_ara_p1_50k_pe101/../data/downloads/ltee_REL606/REL606.gbk --predict-copy-number --predict-discordant-pairs --predict-missing-pairs --predict-pair-distance --predict-soft-clipping ./tests/long_ltee_ara_p1_50k_pe101/../data/downloads/ena_SRR2584534/SRR2584534_1.fastq.gz ./tests/long_ltee_ara_p1_50k_pe101/../data/downloads/ena_SRR2584534/SRR2584534_2.fastq.gz #=REFSEQ ./tests/long_ltee_ara_p1_50k_pe101/../data/downloads/ltee_REL606/REL606.gbk #=READSEQ ./tests/long_ltee_ara_p1_50k_pe101/../data/downloads/ena_SRR2584534/SRR2584534_1.fastq.gz @@ -1032,7 +1032,7 @@ DP 1018 . REL606 24058 -1 REL606 1448695 1 background_e_value=3.536e-14 candidat DP 1019 . REL606 24058 -1 REL606 1982313 1 background_e_value=3.536e-14 candidate_discordant_count=27 concordant_count=0.0 discordant_count=27 distinct_discordant_count=27 expected_concordant_count=23.2 frequency=1.0000 frequency_lower=0.8950 frequency_upper=1.0000 neg_log10_discordance_p_value=0.2 side_1_annotate_key=repeat side_1_concordant_count=31 side_1_discordant_count=27 side_1_gene_name=IS1 side_1_gene_position=noncoding (768/768 nt) side_1_gene_product=repeat region side_1_gene_strand=> side_1_redundant=1 side_1_unpaired_count=3421 side_2_annotate_key=gene side_2_concordant_count=0 side_2_discordant_count=27 side_2_gene_name=yeeI side_2_gene_position=coding (664/798 nt) side_2_gene_product=hypothetical protein side_2_gene_strand=> side_2_locus_tag=ECB_01890 side_2_unpaired_count=79 DP 1020 . REL606 24058 -1 REL606 2815044 -1 background_e_value=1.951e-02 candidate_discordant_count=5 concordant_count=41.0 discordant_count=5 distinct_discordant_count=5 expected_concordant_count=23.2 frequency=0.1087 frequency_lower=0.0438 frequency_upper=0.2151 neg_log10_discordance_p_value=3.0 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=repeat side_1_concordant_count=31 side_1_discordant_count=5 side_1_gene_name=IS1 side_1_gene_position=noncoding (768/768 nt) side_1_gene_product=repeat region side_1_gene_strand=> side_1_redundant=1 side_1_unpaired_count=3421 side_2_annotate_key=gene side_2_concordant_count=41 side_2_discordant_count=5 side_2_gene_name=yqcD side_2_gene_position=coding (768/849 nt) side_2_gene_product=hypothetical protein side_2_gene_strand=> side_2_locus_tag=ECB_02639 side_2_unpaired_count=11 DP 1021 . REL606 24058 -1 REL606 4462655 1 background_e_value=3.536e-14 candidate_discordant_count=33 concordant_count=0.0 discordant_count=33 distinct_discordant_count=33 expected_concordant_count=23.2 frequency=1.0000 frequency_lower=0.9132 frequency_upper=1.0000 neg_log10_discordance_p_value=0.0 side_1_annotate_key=repeat side_1_concordant_count=31 side_1_discordant_count=33 side_1_gene_name=IS1 side_1_gene_position=noncoding (768/768 nt) side_1_gene_product=repeat region side_1_gene_strand=> side_1_redundant=1 side_1_unpaired_count=3421 side_2_annotate_key=gene side_2_concordant_count=0 side_2_discordant_count=33 side_2_gene_name=yjgM/yjgN side_2_gene_position=intergenic (-85/-108) side_2_gene_product=predicted acetyltransferase/conserved inner membrane protein side_2_gene_strand= side_2_locus_tag=ECB_04122/ECB_04123 side_2_unpaired_count=133 -SC 1022 . REL606 167451 1 agree_read_count=4 clipped_sequence=CCCCCCCCACCC consensus_fraction=0.8000 frequency=0.1026 frequency_lower=0.0358 frequency_upper=0.2195 gene_name=hrpB/mrcB gene_position=intergenic (+66/-130) gene_product=predicted ATP-dependent helicase/penicillin-binding protein 1b gene_strand=>/> locus_tag=ECB_00147/ECB_00148 log10_e_value=0.2 read_count=5 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=39 +SC 1022 . REL606 167451 1 agree_read_count=4 agree_read_count_forward=4 agree_read_count_reverse=0 clipped_sequence=CCCCCCCCACCC consensus_fraction=0.8000 fisher_strand_p_value=1.05019e-01 frequency=0.1026 frequency_lower=0.0358 frequency_upper=0.2195 gene_name=hrpB/mrcB gene_position=intergenic (+66/-130) gene_product=predicted ATP-dependent helicase/penicillin-binding protein 1b gene_strand=>/> locus_tag=ECB_00147/ECB_00148 log10_e_value=0.2 read_count=5 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,LOW_COMPLEXITY_TAIL spanning_read_count_forward=15 spanning_read_count_reverse=19 total_count=39 DP 1023 . REL606 183262 1 REL606 666130 -1 background_e_value=3.536e-14 candidate_discordant_count=37 concordant_count=0.0 discordant_count=37 distinct_discordant_count=37 expected_concordant_count=23.2 frequency=1.0000 frequency_lower=0.9222 frequency_upper=1.0000 neg_log10_discordance_p_value=0.0 side_1_annotate_key=gene side_1_concordant_count=0 side_1_discordant_count=37 side_1_gene_name=dgt side_1_gene_position=coding (1184/1518 nt) side_1_gene_product=deoxyguanosinetriphosphate triphosphohydrolase side_1_gene_strand=> side_1_locus_tag=ECB_00159 side_1_unpaired_count=115 side_2_annotate_key=repeat side_2_concordant_count=37 side_2_discordant_count=37 side_2_gene_name=IS150 side_2_gene_position=noncoding (1443/1443 nt) side_2_gene_product=repeat region side_2_gene_strand=> side_2_redundant=1 side_2_unpaired_count=14509 DP 1024 . REL606 183264 -1 REL606 664688 1 background_e_value=3.536e-14 candidate_discordant_count=20 concordant_count=0.0 discordant_count=20 distinct_discordant_count=20 expected_concordant_count=23.2 frequency=1.0000 frequency_lower=0.8609 frequency_upper=1.0000 neg_log10_discordance_p_value=0.5 side_1_annotate_key=gene side_1_concordant_count=0 side_1_discordant_count=20 side_1_gene_name=dgt side_1_gene_position=coding (1186/1518 nt) side_1_gene_product=deoxyguanosinetriphosphate triphosphohydrolase side_1_gene_strand=> side_1_locus_tag=ECB_00159 side_1_unpaired_count=134 side_2_annotate_key=repeat side_2_concordant_count=25 side_2_discordant_count=20 side_2_gene_name=IS150 side_2_gene_position=noncoding (1/1443 nt) side_2_gene_product=repeat region side_2_gene_strand=> side_2_redundant=1 side_2_unpaired_count=13342 DP 1025 . REL606 241257 1 REL606 555825 1 background_e_value=3.536e-14 candidate_discordant_count=31 concordant_count=0.0 discordant_count=31 distinct_discordant_count=31 expected_concordant_count=23.2 frequency=1.0000 frequency_lower=0.9079 frequency_upper=1.0000 neg_log10_discordance_p_value=0.1 side_1_annotate_key=repeat side_1_concordant_count=18 side_1_discordant_count=31 side_1_gene_name=IS1 side_1_gene_position=noncoding (1/768 nt) side_1_gene_product=repeat region side_1_gene_strand=> side_1_redundant=1 side_1_unpaired_count=3346 side_2_annotate_key=gene side_2_concordant_count=0 side_2_discordant_count=31 side_2_gene_name=ECB_00513 side_2_gene_position=coding (1110/2346 nt) side_2_gene_product=conserved hypothetical protein side_2_gene_strand=> side_2_locus_tag=ECB_00513 side_2_unpaired_count=58 @@ -1044,8 +1044,8 @@ DP 1030 . REL606 242024 -1 REL606 2405139 -1 background_e_value=3.536e-14 candid DP 1031 . REL606 263559 -1 REL606 588495 1 background_e_value=3.631e-06 candidate_discordant_count=8 concordant_count=NA discordant_count=8 distinct_discordant_count=8 expected_concordant_count=23.2 frequency=NA frequency_lower=NA frequency_upper=NA neg_log10_discordance_p_value=2.3 side_1_annotate_key=repeat side_1_concordant_count=23 side_1_discordant_count=8 side_1_gene_name=IS1 side_1_gene_position=noncoding (768/768 nt) side_1_gene_product=repeat region side_1_gene_strand=> side_1_redundant=1 side_1_unpaired_count=2998 side_2_annotate_key=repeat side_2_concordant_count=28 side_2_discordant_count=8 side_2_gene_name=IS150 side_2_gene_position=noncoding (1/1977 nt) side_2_gene_product=repeat region side_2_gene_strand=> side_2_redundant=1 side_2_unpaired_count=13791 DP 1032 . REL606 336055 1 REL606 664688 1 background_e_value=3.536e-14 candidate_discordant_count=16 concordant_count=0.0 discordant_count=16 distinct_discordant_count=16 expected_concordant_count=23.2 frequency=1.0000 frequency_lower=0.8293 frequency_upper=1.0000 neg_log10_discordance_p_value=0.9 side_1_annotate_key=gene side_1_concordant_count=0 side_1_discordant_count=16 side_1_gene_name=lacZ side_1_gene_position=coding (2807/3075 nt) side_1_gene_product=beta-D-galactosidase side_1_gene_strand=< side_1_locus_tag=ECB_00298 side_1_unpaired_count=101 side_2_annotate_key=repeat side_2_concordant_count=25 side_2_discordant_count=16 side_2_gene_name=IS150 side_2_gene_position=noncoding (1/1443 nt) side_2_gene_product=repeat region side_2_gene_strand=> side_2_redundant=1 side_2_unpaired_count=13342 DP 1033 . REL606 336057 -1 REL606 666130 -1 background_e_value=3.536e-14 candidate_discordant_count=34 concordant_count=0.0 discordant_count=34 distinct_discordant_count=34 expected_concordant_count=23.2 frequency=1.0000 frequency_lower=0.9157 frequency_upper=1.0000 neg_log10_discordance_p_value=0.0 side_1_annotate_key=gene side_1_concordant_count=0 side_1_discordant_count=34 side_1_gene_name=lacZ side_1_gene_position=coding (2805/3075 nt) side_1_gene_product=beta-D-galactosidase side_1_gene_strand=< side_1_locus_tag=ECB_00298 side_1_unpaired_count=108 side_2_annotate_key=repeat side_2_concordant_count=37 side_2_discordant_count=34 side_2_gene_name=IS150 side_2_gene_position=noncoding (1443/1443 nt) side_2_gene_product=repeat region side_2_gene_strand=> side_2_redundant=1 side_2_unpaired_count=14509 -SC 1034 . REL606 357604 -1 agree_read_count=7 clipped_sequence=GGGTGGGGGGGG consensus_fraction=0.7000 frequency=0.1842 frequency_lower=0.0898 frequency_upper=0.3183 gene_name=tauD/hemB gene_position=intergenic (+50/+57) gene_product=taurine dioxygenase/delta-aminolevulinic acid dehydratase gene_strand=>/< locus_tag=ECB_00318/ECB_00319 log10_e_value=4.3 read_count=10 reject=FREQUENCY_BELOW_CUTOFF total_count=38 -SC 1035 . REL606 412573 1 agree_read_count=9 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.6923 frequency=0.2143 frequency_lower=0.1166 frequency_upper=0.3442 gene_name=apbA gene_position=coding (365/912 nt) gene_product=2-dehydropantoate 2-reductase gene_strand=< locus_tag=ECB_00373 log10_e_value=6.5 read_count=13 total_count=42 +SC 1034 . REL606 357604 -1 agree_read_count=7 agree_read_count_forward=0 agree_read_count_reverse=7 clipped_sequence=GGGTGGGGGGGG consensus_fraction=0.7000 fisher_strand_p_value=2.89210e-03 frequency=0.1842 frequency_lower=0.0898 frequency_upper=0.3183 gene_name=tauD/hemB gene_position=intergenic (+50/+57) gene_product=taurine dioxygenase/delta-aminolevulinic acid dehydratase gene_strand=>/< locus_tag=ECB_00318/ECB_00319 log10_e_value=4.3 read_count=10 reject=FREQUENCY_BELOW_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=18 spanning_read_count_reverse=10 total_count=38 +SC 1035 . REL606 412573 1 agree_read_count=9 agree_read_count_forward=9 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.6923 fisher_strand_p_value=1.22813e-05 frequency=0.2143 frequency_lower=0.1166 frequency_upper=0.3442 gene_name=apbA gene_position=coding (365/912 nt) gene_product=2-dehydropantoate 2-reductase gene_strand=< locus_tag=ECB_00373 log10_e_value=6.5 read_count=13 reject=FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=5 spanning_read_count_reverse=24 total_count=42 DP 1036 . REL606 490483 -1 REL606 664688 1 background_e_value=3.536e-14 candidate_discordant_count=22 concordant_count=0.0 discordant_count=22 distinct_discordant_count=22 expected_concordant_count=23.2 frequency=1.0000 frequency_lower=0.8727 frequency_upper=1.0000 neg_log10_discordance_p_value=0.4 side_1_annotate_key=gene side_1_concordant_count=0 side_1_discordant_count=22 side_1_gene_name=ybbN/ybbO side_1_gene_position=intergenic (-36/+25) side_1_gene_product=predicted thioredoxin domain-containing protein/short chain dehydrogenase side_1_gene_strand= side_2_redundant=1 side_2_unpaired_count=13342 DP 1037 . REL606 490485 1 REL606 666130 -1 background_e_value=3.536e-14 candidate_discordant_count=29 concordant_count=0.0 discordant_count=29 distinct_discordant_count=29 expected_concordant_count=23.2 frequency=1.0000 frequency_lower=0.9019 frequency_upper=1.0000 neg_log10_discordance_p_value=0.1 side_1_annotate_key=gene side_1_concordant_count=0 side_1_discordant_count=29 side_1_gene_name=ybbN/ybbO side_1_gene_position=intergenic (-38/+23) side_1_gene_product=predicted thioredoxin domain-containing protein/short chain dehydrogenase side_1_gene_strand= side_2_redundant=1 side_2_unpaired_count=14509 DP 1038 . REL606 502543 1 REL606 664688 1 background_e_value=3.536e-14 candidate_discordant_count=24 concordant_count=0.0 discordant_count=24 distinct_discordant_count=24 expected_concordant_count=23.2 frequency=1.0000 frequency_lower=0.8827 frequency_upper=1.0000 neg_log10_discordance_p_value=0.3 side_1_annotate_key=gene side_1_concordant_count=0 side_1_discordant_count=24 side_1_gene_name=ybbB side_1_gene_position=coding (850/1095 nt) side_1_gene_product=tRNA 2-selenouridine synthase, selenophosphate-dependent side_1_gene_strand=< side_1_locus_tag=ECB_00453 side_1_unpaired_count=90 side_2_annotate_key=repeat side_2_concordant_count=25 side_2_discordant_count=24 side_2_gene_name=IS150 side_2_gene_position=noncoding (1/1443 nt) side_2_gene_product=repeat region side_2_gene_strand=> side_2_redundant=1 side_2_unpaired_count=13342 @@ -1057,8 +1057,8 @@ DP 1043 . REL606 588495 1 REL606 3048489 1 background_e_value=3.536e-14 candidat DP 1044 . REL606 588495 1 REL606 3550158 1 background_e_value=3.536e-14 candidate_discordant_count=48 concordant_count=NA discordant_count=48 distinct_discordant_count=48 expected_concordant_count=23.2 frequency=NA frequency_lower=NA frequency_upper=NA neg_log10_discordance_p_value=0.0 side_1_annotate_key=repeat side_1_concordant_count=28 side_1_discordant_count=48 side_1_gene_name=IS150 side_1_gene_position=noncoding (1/1977 nt) side_1_gene_product=repeat region side_1_gene_strand=> side_1_redundant=1 side_1_unpaired_count=13791 side_2_annotate_key=repeat side_2_concordant_count=0 side_2_discordant_count=48 side_2_gene_name=rhsB side_2_gene_position=coding (279/4236 nt) side_2_gene_product=rhsB element core protein RshB side_2_gene_strand=> side_2_locus_tag=ECB_03331 side_2_redundant=1 side_2_unpaired_count=498 DP 1045 . REL606 588495 1 REL606 4047675 -1 background_e_value=3.536e-14 candidate_discordant_count=37 concordant_count=0.0 discordant_count=37 distinct_discordant_count=37 expected_concordant_count=23.2 frequency=1.0000 frequency_lower=0.9222 frequency_upper=1.0000 neg_log10_discordance_p_value=0.0 side_1_annotate_key=repeat side_1_concordant_count=28 side_1_discordant_count=37 side_1_gene_name=IS150 side_1_gene_position=noncoding (1/1977 nt) side_1_gene_product=repeat region side_1_gene_strand=> side_1_redundant=1 side_1_unpaired_count=13791 side_2_annotate_key=gene side_2_concordant_count=0 side_2_discordant_count=37 side_2_gene_name=yihR side_2_gene_position=coding (874/927 nt) side_2_gene_product=predicted aldose-1-epimerase side_2_gene_strand=< side_2_locus_tag=ECB_03764 side_2_unpaired_count=84 DP 1046 . REL606 590372 1 REL606 666130 -1 background_e_value=1.951e-02 candidate_discordant_count=5 concordant_count=18.0 discordant_count=5 distinct_discordant_count=5 expected_concordant_count=23.2 frequency=0.2174 frequency_lower=0.0898 frequency_upper=0.4039 neg_log10_discordance_p_value=3.0 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=18 side_1_discordant_count=5 side_1_gene_name=IS150 side_1_gene_position=noncoding (1878/1977 nt) side_1_gene_product=repeat region side_1_gene_strand=> side_1_unpaired_count=1175 side_2_annotate_key=repeat side_2_concordant_count=37 side_2_discordant_count=5 side_2_gene_name=IS150 side_2_gene_position=noncoding (1443/1443 nt) side_2_gene_product=repeat region side_2_gene_strand=> side_2_redundant=1 side_2_unpaired_count=14509 -SC 1047 . REL606 607325 -1 agree_read_count=4 clipped_sequence=GGGGGGGCCCCC consensus_fraction=0.3636 frequency=0.1111 frequency_lower=0.0389 frequency_upper=0.2365 gene_name=fepB/entC gene_position=intergenic (-107/-268) gene_product=iron-enterobactin transporter subunit/isochorismate synthase gene_strand= locus_tag=ECB_00559/ECB_00560 log10_e_value=0.3 read_count=11 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,CLIPPED_TAIL_CONSENSUS total_count=36 -SC 1048 . REL606 629269 -1 agree_read_count=4 clipped_sequence=TACCCCCTCCAA consensus_fraction=0.5714 frequency=0.0976 frequency_lower=0.0340 frequency_upper=0.2095 gene_name=citG gene_position=coding (292/879 nt) gene_product=triphosphoribosyl-dephospho-CoA transferase gene_strand=< locus_tag=ECB_00581 log10_e_value=0.1 read_count=7 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=41 +SC 1047 . REL606 607325 -1 agree_read_count=4 agree_read_count_forward=0 agree_read_count_reverse=4 clipped_sequence=GGGGGGGCCCCC consensus_fraction=0.3636 fisher_strand_p_value=4.21035e-05 frequency=0.1111 frequency_lower=0.0389 frequency_upper=0.2365 gene_name=fepB/entC gene_position=intergenic (-107/-268) gene_product=iron-enterobactin transporter subunit/isochorismate synthase gene_strand= locus_tag=ECB_00559/ECB_00560 log10_e_value=0.3 read_count=11 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,CLIPPED_TAIL_CONSENSUS,FISHER_STRAND spanning_read_count_forward=25 spanning_read_count_reverse=0 total_count=36 +SC 1048 . REL606 629269 -1 agree_read_count=4 agree_read_count_forward=0 agree_read_count_reverse=4 clipped_sequence=TACCCCCTCCAA consensus_fraction=0.5714 fisher_strand_p_value=4.47064e-03 frequency=0.0976 frequency_lower=0.0340 frequency_upper=0.2095 gene_name=citG gene_position=coding (292/879 nt) gene_product=triphosphoribosyl-dephospho-CoA transferase gene_strand=< locus_tag=ECB_00581 log10_e_value=0.1 read_count=7 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND spanning_read_count_forward=27 spanning_read_count_reverse=7 total_count=41 DP 1049 . REL606 651703 1 REL606 666130 -1 background_e_value=3.536e-14 candidate_discordant_count=37 concordant_count=0.0 discordant_count=37 distinct_discordant_count=37 expected_concordant_count=23.2 frequency=1.0000 frequency_lower=0.9222 frequency_upper=1.0000 neg_log10_discordance_p_value=0.0 side_1_annotate_key=gene side_1_concordant_count=0 side_1_discordant_count=37 side_1_gene_name=ybeB/phpB side_1_gene_position=intergenic (-83/+177) side_1_gene_product=hypothetical protein/predicted alpha-ribazole-5'-P phosphatase side_1_gene_strand= side_2_redundant=1 side_2_unpaired_count=14509 DP 1050 . REL606 651704 -1 REL606 664688 1 background_e_value=3.536e-14 candidate_discordant_count=31 concordant_count=0.0 discordant_count=31 distinct_discordant_count=31 expected_concordant_count=23.2 frequency=1.0000 frequency_lower=0.9079 frequency_upper=1.0000 neg_log10_discordance_p_value=0.1 side_1_annotate_key=gene side_1_concordant_count=0 side_1_discordant_count=31 side_1_gene_name=ybeB/phpB side_1_gene_position=intergenic (-84/+176) side_1_gene_product=hypothetical protein/predicted alpha-ribazole-5'-P phosphatase side_1_gene_strand= side_2_redundant=1 side_2_unpaired_count=13342 DP 1051 . REL606 664688 1 REL606 896465 -1 background_e_value=3.536e-14 candidate_discordant_count=17 concordant_count=0.0 discordant_count=17 distinct_discordant_count=17 expected_concordant_count=23.2 frequency=1.0000 frequency_lower=0.8384 frequency_upper=1.0000 neg_log10_discordance_p_value=0.8 side_1_annotate_key=repeat side_1_concordant_count=25 side_1_discordant_count=17 side_1_gene_name=IS150 side_1_gene_position=noncoding (1/1443 nt) side_1_gene_product=repeat region side_1_gene_strand=> side_1_redundant=1 side_1_unpaired_count=13342 side_2_annotate_key=gene side_2_concordant_count=0 side_2_discordant_count=17 side_2_gene_name=ECB_00838 side_2_gene_position=coding (161/432 nt) side_2_gene_product=putative phage tail protein side_2_gene_strand=> side_2_locus_tag=ECB_00838 side_2_unpaired_count=105 @@ -1109,29 +1109,29 @@ DP 1095 . REL606 666130 -1 REL606 4049580 1 background_e_value=3.536e-14 candida DP 1096 . REL606 666130 -1 REL606 4092861 1 background_e_value=3.536e-14 candidate_discordant_count=39 concordant_count=0.0 discordant_count=39 distinct_discordant_count=38 expected_concordant_count=23.2 frequency=1.0000 frequency_lower=0.9242 frequency_upper=1.0000 neg_log10_discordance_p_value=0.0 side_1_annotate_key=repeat side_1_concordant_count=37 side_1_discordant_count=39 side_1_gene_name=IS150 side_1_gene_position=noncoding (1443/1443 nt) side_1_gene_product=repeat region side_1_gene_strand=> side_1_redundant=1 side_1_unpaired_count=14509 side_2_annotate_key=gene side_2_concordant_count=0 side_2_discordant_count=39 side_2_gene_name=yiiT side_2_gene_position=coding (87/429 nt) side_2_gene_product=stress-induced protein side_2_gene_strand=> side_2_locus_tag=ECB_03808 side_2_unpaired_count=133 DP 1097 . REL606 666130 -1 REL606 4415712 -1 background_e_value=3.536e-14 candidate_discordant_count=39 concordant_count=0.0 discordant_count=39 distinct_discordant_count=39 expected_concordant_count=23.2 frequency=1.0000 frequency_lower=0.9261 frequency_upper=1.0000 neg_log10_discordance_p_value=0.0 side_1_annotate_key=repeat side_1_concordant_count=37 side_1_discordant_count=39 side_1_gene_name=IS150 side_1_gene_position=noncoding (1443/1443 nt) side_1_gene_product=repeat region side_1_gene_strand=> side_1_redundant=1 side_1_unpaired_count=14509 side_2_annotate_key=gene side_2_concordant_count=0 side_2_discordant_count=39 side_2_gene_name=cycA side_2_gene_position=coding (850/1413 nt) side_2_gene_product=D-alanine/D-serine/glycine transporter side_2_gene_strand=> side_2_locus_tag=ECB_04080 side_2_unpaired_count=114 DP 1098 . REL606 666130 -1 REL606 4615673 1 background_e_value=3.536e-14 candidate_discordant_count=25 concordant_count=0.0 discordant_count=25 distinct_discordant_count=25 expected_concordant_count=23.2 frequency=1.0000 frequency_lower=0.8871 frequency_upper=1.0000 neg_log10_discordance_p_value=0.2 side_1_annotate_key=repeat side_1_concordant_count=37 side_1_discordant_count=25 side_1_gene_name=IS150 side_1_gene_position=noncoding (1443/1443 nt) side_1_gene_product=repeat region side_1_gene_strand=> side_1_redundant=1 side_1_unpaired_count=14509 side_2_annotate_key=gene side_2_concordant_count=0 side_2_discordant_count=25 side_2_gene_name=nadR side_2_gene_position=coding (145/1233 nt) side_2_gene_product=nicotinamide-nucleotide adenylyltransferase side_2_gene_strand=> side_2_locus_tag=ECB_04266 side_2_unpaired_count=115 -SC 1099 . REL606 687954 1 agree_read_count=8 clipped_sequence=GGGAAAAACCCC consensus_fraction=0.6154 frequency=0.2424 frequency_lower=0.1268 frequency_upper=0.3951 gene_name=nagE gene_position=coding (1916/1947 nt) gene_product=fused N-acetyl glucosamine specific PTS enzyme: IIC, IIB , and IIA components gene_strand=> locus_tag=ECB_00636 log10_e_value=6.1 read_count=13 total_count=33 +SC 1099 . REL606 687954 1 agree_read_count=8 agree_read_count_forward=8 agree_read_count_reverse=0 clipped_sequence=GGGAAAAACCCC consensus_fraction=0.6154 fisher_strand_p_value=2.89566e-06 frequency=0.2424 frequency_lower=0.1268 frequency_upper=0.3951 gene_name=nagE gene_position=coding (1916/1947 nt) gene_product=fused N-acetyl glucosamine specific PTS enzyme: IIC, IIB , and IIA components gene_strand=> locus_tag=ECB_00636 log10_e_value=6.1 read_count=13 reject=FISHER_STRAND spanning_read_count_forward=1 spanning_read_count_reverse=19 total_count=33 PD 1100 . REL606 762192 -1 REL606 762358 1 ambiguous_pair_count=20 candidate_covering_count=36 distinct_pair_count=15 frequency=0.8333 frequency_lower=0.6233 frequency_upper=0.9530 normal_pair_count=3 position_range=29 score=3.8 seed_z_score=7.24 shifted_pair_count=15 side_1_annotate_key=gene side_1_gene_name=lysZ side_1_gene_position=noncoding (40/76 nt) side_1_gene_product=tRNA-Lys side_1_gene_strand=> side_1_locus_tag=ECB_t00020 side_2_annotate_key=gene side_2_gene_name=lysZ/lysQ side_2_gene_position=intergenic (+130/-3) side_2_gene_product=tRNA-Lys/tRNA-Lys side_2_gene_strand=>/> side_2_locus_tag=ECB_t00020/ECB_t00021 size_shift=165 size_shift_lower=142 size_shift_upper=207 total_pair_count=38 DP 1101 . REL606 1111784 -1 REL606 1608003 -1 background_e_value=1.288e-03 candidate_discordant_count=6 concordant_count=10.0 discordant_count=6 distinct_discordant_count=6 expected_concordant_count=23.2 frequency=0.3750 frequency_lower=0.1778 frequency_upper=0.6090 neg_log10_discordance_p_value=2.7 side_1_annotate_key=repeat side_1_concordant_count=19 side_1_discordant_count=6 side_1_gene_name=IS3 side_1_gene_position=noncoding (1/1255 nt) side_1_gene_product=repeat region side_1_gene_strand=< side_1_redundant=1 side_1_unpaired_count=808 side_2_annotate_key=gene side_2_concordant_count=10 side_2_discordant_count=6 side_2_gene_name=IS3 side_2_gene_position=noncoding (84/1255 nt) side_2_gene_product=repeat region side_2_gene_strand=> side_2_unpaired_count=283 -SC 1102 . REL606 1359218 -1 agree_read_count=5 clipped_sequence=GAAAGGGCCCCC consensus_fraction=0.7143 frequency=0.1020 frequency_lower=0.0411 frequency_upper=0.2027 gene_name=ycjK gene_position=coding (59/1419 nt) gene_product=gamma-Glu-putrescine synthase gene_strand=< locus_tag=ECB_01274 log10_e_value=1.0 read_count=7 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=49 -SC 1103 . REL606 1505984 -1 agree_read_count=4 clipped_sequence=AAGCAGAAGACG consensus_fraction=1.0000 frequency=0.0930 frequency_lower=0.0324 frequency_upper=0.2004 gene_name=ECB_01417 gene_position=coding (47/201 nt) gene_product=hypothetical protein gene_strand=> locus_tag=ECB_01417 log10_e_value=0.0 read_count=4 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=43 -SC 1104 . REL606 1716933 -1 agree_read_count=13 clipped_sequence=CCCCCCCCCCCC consensus_fraction=0.8667 frequency=0.3421 frequency_lower=0.2156 frequency_upper=0.4880 gene_name=ydhB gene_position=coding (133/933 nt) gene_product=predicted DNA-binding transcriptional regulator gene_strand=< locus_tag=ECB_01630 log10_e_value=12.5 read_count=15 total_count=38 +SC 1102 . REL606 1359218 -1 agree_read_count=5 agree_read_count_forward=0 agree_read_count_reverse=5 clipped_sequence=GAAAGGGCCCCC consensus_fraction=0.7143 fisher_strand_p_value=1.36902e-05 frequency=0.1020 frequency_lower=0.0411 frequency_upper=0.2027 gene_name=ycjK gene_position=coding (59/1419 nt) gene_product=gamma-Glu-putrescine synthase gene_strand=< locus_tag=ECB_01274 log10_e_value=1.0 read_count=7 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND spanning_read_count_forward=40 spanning_read_count_reverse=2 total_count=49 +SC 1103 . REL606 1505984 -1 agree_read_count=4 agree_read_count_forward=0 agree_read_count_reverse=4 clipped_sequence=AAGCAGAAGACG consensus_fraction=1.0000 fisher_strand_p_value=1.27299e-01 frequency=0.0930 frequency_lower=0.0324 frequency_upper=0.2004 gene_name=ECB_01417 gene_position=coding (47/201 nt) gene_product=hypothetical protein gene_strand=> locus_tag=ECB_01417 log10_e_value=0.0 read_count=4 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF spanning_read_count_forward=18 spanning_read_count_reverse=21 total_count=43 +SC 1104 . REL606 1716933 -1 agree_read_count=13 agree_read_count_forward=0 agree_read_count_reverse=13 clipped_sequence=CCCCCCCCCCCC consensus_fraction=0.8667 fisher_strand_p_value=4.32753e-10 frequency=0.3421 frequency_lower=0.2156 frequency_upper=0.4880 gene_name=ydhB gene_position=coding (133/933 nt) gene_product=predicted DNA-binding transcriptional regulator gene_strand=< locus_tag=ECB_01630 log10_e_value=12.5 read_count=15 reject=FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=23 spanning_read_count_reverse=0 total_count=38 DP 1105 . REL606 2034357 -1 REL606 2053849 1 background_e_value=3.536e-14 candidate_discordant_count=28 concordant_count=0.0 discordant_count=28 distinct_discordant_count=28 expected_concordant_count=23.2 frequency=1.0000 frequency_lower=0.8985 frequency_upper=1.0000 neg_log10_discordance_p_value=0.1 side_1_annotate_key=gene side_1_concordant_count=0 side_1_discordant_count=28 side_1_gene_name=IS1 side_1_gene_position=noncoding (737/768 nt) side_1_gene_product=repeat region side_1_gene_strand=< side_1_unpaired_count=339 side_2_annotate_key=gene side_2_concordant_count=0 side_2_discordant_count=28 side_2_gene_name=wcaJ side_2_gene_position=coding (823/1395 nt) side_2_gene_product=predicted UDP-glucose lipid carrier transferase side_2_gene_strand=< side_2_locus_tag=ECB_01953 side_2_unpaired_count=79 -SC 1106 . REL606 2103888 -1 agree_read_count=6 clipped_sequence=CAGCCAGCCAGC consensus_fraction=1.0000 frequency=0.2069 frequency_lower=0.0942 frequency_upper=0.3680 gene_name=ECB_01992 gene_position=coding (155/216 nt) gene_product=hypothetical protein gene_strand=> locus_tag=ECB_01992 log10_e_value=3.6 read_count=6 reject=FREQUENCY_BELOW_CUTOFF total_count=29 -SC 1107 . REL606 2103918 1 agree_read_count=9 clipped_sequence=CCAGCCAGCCAG consensus_fraction=0.9000 frequency=0.2647 frequency_lower=0.1456 frequency_upper=0.4165 gene_name=ECB_01992 gene_position=coding (185/216 nt) gene_product=hypothetical protein gene_strand=> locus_tag=ECB_01992 log10_e_value=7.4 read_count=10 total_count=34 -SC 1108 . REL606 2540547 -1 agree_read_count=6 clipped_sequence=GGGGGGAAAACC consensus_fraction=0.6000 frequency=0.1429 frequency_lower=0.0641 frequency_upper=0.2626 gene_name=uraA gene_position=coding (434/1290 nt) gene_product=uracil transporter gene_strand=< locus_tag=ECB_02389 log10_e_value=2.7 read_count=10 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=42 -SC 1109 . REL606 2760104 1 agree_read_count=16 clipped_sequence=GGGGGGGGGGGA consensus_fraction=0.7619 frequency=0.2909 frequency_lower=0.1918 frequency_upper=0.4077 gene_name=ygbN gene_position=coding (143/1365 nt) gene_product=predicted transporter gene_strand=> locus_tag=ECB_02590 log10_e_value=13.8 read_count=21 total_count=55 +SC 1106 . REL606 2103888 -1 agree_read_count=6 agree_read_count_forward=3 agree_read_count_reverse=3 clipped_sequence=CAGCCAGCCAGC consensus_fraction=1.0000 fisher_strand_p_value=3.39068e-01 frequency=0.2069 frequency_lower=0.0942 frequency_upper=0.3680 gene_name=ECB_01992 gene_position=coding (155/216 nt) gene_product=hypothetical protein gene_strand=> locus_tag=ECB_01992 log10_e_value=3.6 read_count=6 reject=FREQUENCY_BELOW_CUTOFF spanning_read_count_forward=17 spanning_read_count_reverse=6 total_count=29 +SC 1107 . REL606 2103918 1 agree_read_count=9 agree_read_count_forward=7 agree_read_count_reverse=2 clipped_sequence=CCAGCCAGCCAG consensus_fraction=0.9000 fisher_strand_p_value=1.33583e-01 frequency=0.2647 frequency_lower=0.1456 frequency_upper=0.4165 gene_name=ECB_01992 gene_position=coding (185/216 nt) gene_product=hypothetical protein gene_strand=> locus_tag=ECB_01992 log10_e_value=7.4 read_count=10 spanning_read_count_forward=11 spanning_read_count_reverse=13 total_count=34 +SC 1108 . REL606 2540547 -1 agree_read_count=6 agree_read_count_forward=0 agree_read_count_reverse=6 clipped_sequence=GGGGGGAAAACC consensus_fraction=0.6000 fisher_strand_p_value=1.01424e-05 frequency=0.1429 frequency_lower=0.0641 frequency_upper=0.2626 gene_name=uraA gene_position=coding (434/1290 nt) gene_product=uracil transporter gene_strand=< locus_tag=ECB_02389 log10_e_value=2.7 read_count=10 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND spanning_read_count_forward=30 spanning_read_count_reverse=2 total_count=42 +SC 1109 . REL606 2760104 1 agree_read_count=16 agree_read_count_forward=16 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGGGGA consensus_fraction=0.7619 fisher_strand_p_value=2.03100e-13 frequency=0.2909 frequency_lower=0.1918 frequency_upper=0.4077 gene_name=ygbN gene_position=coding (143/1365 nt) gene_product=predicted transporter gene_strand=> locus_tag=ECB_02590 log10_e_value=13.8 read_count=21 reject=FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=0 spanning_read_count_reverse=34 total_count=55 DP 1110 . REL606 2774435 1 REL606 3766595 1 background_e_value=3.536e-14 candidate_discordant_count=32 concordant_count=0.0 discordant_count=32 distinct_discordant_count=32 expected_concordant_count=23.2 frequency=1.0000 frequency_lower=0.9106 frequency_upper=1.0000 neg_log10_discordance_p_value=0.1 side_1_annotate_key=repeat side_1_concordant_count=34 side_1_discordant_count=32 side_1_gene_name=IS150 side_1_gene_position=noncoding (1443/1443 nt) side_1_gene_product=repeat region side_1_gene_strand=< side_1_redundant=1 side_1_unpaired_count=15426 side_2_annotate_key=gene side_2_concordant_count=0 side_2_discordant_count=32 side_2_gene_name=gltS side_2_gene_position=coding (1113/1206 nt) side_2_gene_product=glutamate transporter side_2_gene_strand=< side_2_locus_tag=ECB_03511 side_2_unpaired_count=98 DP 1111 . REL606 2774435 1 REL606 3981784 -1 background_e_value=3.536e-14 candidate_discordant_count=41 concordant_count=0.0 discordant_count=41 distinct_discordant_count=40 expected_concordant_count=23.2 frequency=1.0000 frequency_lower=0.9278 frequency_upper=1.0000 neg_log10_discordance_p_value=0.0 side_1_annotate_key=repeat side_1_concordant_count=34 side_1_discordant_count=41 side_1_gene_name=IS150 side_1_gene_position=noncoding (1443/1443 nt) side_1_gene_product=repeat region side_1_gene_strand=< side_1_redundant=1 side_1_unpaired_count=15426 side_2_annotate_key=gene side_2_concordant_count=0 side_2_discordant_count=41 side_2_gene_name=ECB_03710 side_2_gene_position=coding (249/1224 nt) side_2_gene_product=putative permease side_2_gene_strand=< side_2_locus_tag=ECB_03710 side_2_unpaired_count=146 DP 1112 . REL606 2775877 -1 REL606 3766597 -1 background_e_value=3.536e-14 candidate_discordant_count=24 concordant_count=0.0 discordant_count=24 distinct_discordant_count=24 expected_concordant_count=23.2 frequency=1.0000 frequency_lower=0.8827 frequency_upper=1.0000 neg_log10_discordance_p_value=0.3 side_1_annotate_key=repeat side_1_concordant_count=23 side_1_discordant_count=24 side_1_gene_name=IS150 side_1_gene_position=noncoding (1/1443 nt) side_1_gene_product=repeat region side_1_gene_strand=< side_1_redundant=1 side_1_unpaired_count=13960 side_2_annotate_key=gene side_2_concordant_count=0 side_2_discordant_count=24 side_2_gene_name=gltS side_2_gene_position=coding (1111/1206 nt) side_2_gene_product=glutamate transporter side_2_gene_strand=< side_2_locus_tag=ECB_03511 side_2_unpaired_count=113 DP 1113 . REL606 2775877 -1 REL606 3981782 1 background_e_value=3.536e-14 candidate_discordant_count=25 concordant_count=0.0 discordant_count=25 distinct_discordant_count=25 expected_concordant_count=23.2 frequency=1.0000 frequency_lower=0.8871 frequency_upper=1.0000 neg_log10_discordance_p_value=0.2 side_1_annotate_key=repeat side_1_concordant_count=23 side_1_discordant_count=25 side_1_gene_name=IS150 side_1_gene_position=noncoding (1/1443 nt) side_1_gene_product=repeat region side_1_gene_strand=< side_1_redundant=1 side_1_unpaired_count=13960 side_2_annotate_key=gene side_2_concordant_count=0 side_2_discordant_count=25 side_2_gene_name=ECB_03710 side_2_gene_position=coding (251/1224 nt) side_2_gene_product=putative permease side_2_gene_strand=< side_2_locus_tag=ECB_03710 side_2_unpaired_count=154 PD 1114 . REL606 2842093 -1 REL606 2842280 1 ambiguous_pair_count=20 candidate_covering_count=32 distinct_pair_count=17 frequency=0.7727 frequency_lower=0.5802 frequency_upper=0.9059 normal_pair_count=5 position_range=14 score=3.2 seed_z_score=6.97 shifted_pair_count=17 side_1_annotate_key=gene side_1_gene_name=metZ/metW side_1_gene_position=intergenic (+11/-23) side_1_gene_product=tRNA-Met/tRNA-Met side_1_gene_strand=>/> side_1_locus_tag=ECB_t00051/ECB_t00052 side_2_annotate_key=gene side_2_gene_name=metV side_2_gene_position=noncoding (55/77 nt) side_2_gene_product=tRNA-Met side_2_gene_strand=> side_2_locus_tag=ECB_t00053 size_shift=186 size_shift_lower=156 size_shift_upper=213 total_pair_count=42 -SC 1115 . REL606 3432765 1 agree_read_count=5 clipped_sequence=CCCCCCCCCCCC consensus_fraction=0.7143 frequency=0.1190 frequency_lower=0.0481 frequency_upper=0.2342 gene_name=yhfR/yhfS gene_position=intergenic (+77/+75) gene_product=predicted DNA-binding transcriptional regulator/putative enzyme; b3376_1 gene_strand=>/< locus_tag=ECB_03225/ECB_03226 log10_e_value=1.4 read_count=7 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=42 -SC 1116 . REL606 3600911 -1 agree_read_count=4 clipped_sequence=CCTTTCTCTTTT consensus_fraction=0.8000 frequency=0.0976 frequency_lower=0.0340 frequency_upper=0.2095 gene_name=yhjB gene_position=coding (476/603 nt) gene_product=predicted DNA-binding response regulator in two-component regulatory system gene_strand=< locus_tag=ECB_03368 log10_e_value=0.1 read_count=5 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=41 -SC 1117 . REL606 3636130 -1 agree_read_count=6 clipped_sequence=CCCCCCCGTCCC consensus_fraction=0.4615 frequency=0.1132 frequency_lower=0.0505 frequency_upper=0.2113 gene_name=dppB gene_position=coding (119/1020 nt) gene_product=dipeptide transporter gene_strand=< locus_tag=ECB_03394 log10_e_value=2.1 read_count=13 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,CLIPPED_TAIL_CONSENSUS total_count=53 -SC 1118 . REL606 3697156 1 agree_read_count=6 clipped_sequence=TGTACTGACCCC consensus_fraction=1.0000 frequency=1.0000 frequency_lower=0.6070 frequency_upper=1.0000 gene_name=rhsA gene_position=coding (280/4134 nt) gene_product=rhsA element core protein RshA gene_strand=> locus_tag=ECB_03448 log10_e_value=9.2 read_count=6 total_count=6 -SC 1119 . REL606 3868898 -1 agree_read_count=5 clipped_sequence=GGGGGGGGGGGA consensus_fraction=0.6250 frequency=0.1282 frequency_lower=0.0519 frequency_upper=0.2509 gene_name=pstB/pstA gene_position=intergenic (-165/+18) gene_product=phosphate transporter subunit/phosphate transporter subunit gene_strand=/< locus_tag=ECB_03225/ECB_03226 log10_e_value=1.4 read_count=7 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=6 spanning_read_count_reverse=29 total_count=42 +SC 1116 . REL606 3600911 -1 agree_read_count=4 agree_read_count_forward=0 agree_read_count_reverse=4 clipped_sequence=CCTTTCTCTTTT consensus_fraction=0.8000 fisher_strand_p_value=3.61090e-03 frequency=0.0976 frequency_lower=0.0340 frequency_upper=0.2095 gene_name=yhjB gene_position=coding (476/603 nt) gene_product=predicted DNA-binding response regulator in two-component regulatory system gene_strand=< locus_tag=ECB_03368 log10_e_value=0.1 read_count=5 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND spanning_read_count_forward=29 spanning_read_count_reverse=7 total_count=41 +SC 1117 . REL606 3636130 -1 agree_read_count=6 agree_read_count_forward=0 agree_read_count_reverse=6 clipped_sequence=CCCCCCCGTCCC consensus_fraction=0.4615 fisher_strand_p_value=3.20600e-04 frequency=0.1132 frequency_lower=0.0505 frequency_upper=0.2113 gene_name=dppB gene_position=coding (119/1020 nt) gene_product=dipeptide transporter gene_strand=< locus_tag=ECB_03394 log10_e_value=2.1 read_count=13 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,CLIPPED_TAIL_CONSENSUS,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=32 spanning_read_count_reverse=8 total_count=53 +SC 1118 . REL606 3697156 1 agree_read_count=6 agree_read_count_forward=4 agree_read_count_reverse=2 clipped_sequence=TGTACTGACCCC consensus_fraction=1.0000 fisher_strand_p_value=6.87406e-01 frequency=1.0000 frequency_lower=0.6070 frequency_upper=1.0000 gene_name=rhsA gene_position=coding (280/4134 nt) gene_product=rhsA element core protein RshA gene_strand=> locus_tag=ECB_03448 log10_e_value=9.2 read_count=6 spanning_read_count_forward=0 spanning_read_count_reverse=0 total_count=6 +SC 1119 . REL606 3868898 -1 agree_read_count=5 agree_read_count_forward=0 agree_read_count_reverse=5 clipped_sequence=GGGGGGGGGGGA consensus_fraction=0.6250 fisher_strand_p_value=1.15865e-02 frequency=0.1282 frequency_lower=0.0519 frequency_upper=0.2509 gene_name=pstB/pstA gene_position=intergenic (-165/+18) gene_product=phosphate transporter subunit/phosphate transporter subunit gene_strand=/< locus_tag=ECB_r00022/ECB_03884 log10_e_value=1.2 read_count=6 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=46 +SC 1121 . REL606 4192979 -1 agree_read_count=5 agree_read_count_forward=0 agree_read_count_reverse=5 clipped_sequence=GGGGGCGGCCCC consensus_fraction=0.8333 fisher_strand_p_value=4.90956e-02 frequency=0.1087 frequency_lower=0.0438 frequency_upper=0.2151 gene_name=rrfE/yjaB gene_position=intergenic (+147/+146) gene_product=5S ribosomal RNA/predicted acetyltransferase gene_strand=>/< locus_tag=ECB_r00022/ECB_03884 log10_e_value=1.2 read_count=6 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND spanning_read_count_forward=22 spanning_read_count_reverse=18 total_count=46 DP 1122 . REL606 4275716 -1 REL606 4333227 1 background_e_value=3.536e-14 candidate_discordant_count=34 concordant_count=0.0 discordant_count=34 distinct_discordant_count=34 expected_concordant_count=23.2 frequency=1.0000 frequency_lower=0.9157 frequency_upper=1.0000 neg_log10_discordance_p_value=0.0 side_1_annotate_key=gene side_1_concordant_count=0 side_1_discordant_count=34 side_1_gene_name=yjcO side_1_gene_position=coding (232/690 nt) side_1_gene_product=hypothetical protein side_1_gene_strand=< side_1_locus_tag=ECB_03950 side_1_unpaired_count=270 side_2_annotate_key=gene side_2_concordant_count=0 side_2_discordant_count=34 side_2_gene_name=lysU side_2_gene_position=coding (211/1518 nt) side_2_gene_product=lysine tRNA synthetase, inducible side_2_gene_strand=< side_2_locus_tag=ECB_04000 side_2_unpaired_count=85 -SC 1123 . REL606 4610078 1 agree_read_count=4 clipped_sequence=TGCCCCCCCCCC consensus_fraction=0.8000 frequency=0.1111 frequency_lower=0.0389 frequency_upper=0.2365 gene_name=deoB/deoD gene_position=intergenic (+18/-62) gene_product=phosphopentomutase/purine nucleoside phosphorylase gene_strand=>/> locus_tag=ECB_04259/ECB_04260 log10_e_value=0.3 read_count=5 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=36 -SC 1124 . REL606 4620002 1 agree_read_count=4 clipped_sequence=GGGGGTTTCTTC consensus_fraction=0.6667 frequency=0.1081 frequency_lower=0.0378 frequency_upper=0.2305 gene_name=slt gene_position=coding (1057/1938 nt) gene_product=lytic murein transglycosylase, soluble gene_strand=> locus_tag=ECB_04268 log10_e_value=0.3 read_count=6 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=37 +SC 1123 . REL606 4610078 1 agree_read_count=4 agree_read_count_forward=4 agree_read_count_reverse=0 clipped_sequence=TGCCCCCCCCCC consensus_fraction=0.8000 fisher_strand_p_value=9.45378e-03 frequency=0.1111 frequency_lower=0.0389 frequency_upper=0.2365 gene_name=deoB/deoD gene_position=intergenic (+18/-62) gene_product=phosphopentomutase/purine nucleoside phosphorylase gene_strand=>/> locus_tag=ECB_04259/ECB_04260 log10_e_value=0.3 read_count=5 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=8 spanning_read_count_reverse=23 total_count=36 +SC 1124 . REL606 4620002 1 agree_read_count=4 agree_read_count_forward=4 agree_read_count_reverse=0 clipped_sequence=GGGGGTTTCTTC consensus_fraction=0.6667 fisher_strand_p_value=1.91176e-02 frequency=0.1081 frequency_lower=0.0378 frequency_upper=0.2305 gene_name=slt gene_position=coding (1057/1938 nt) gene_product=lytic murein transglycosylase, soluble gene_strand=> locus_tag=ECB_04268 log10_e_value=0.3 read_count=6 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND spanning_read_count_forward=10 spanning_read_count_reverse=21 total_count=37 diff --git a/tests/long_ltee_ara_p3_30k_pe150/expected.gd b/tests/long_ltee_ara_p3_30k_pe150/expected.gd index 03b2538f..08172647 100644 --- a/tests/long_ltee_ara_p3_30k_pe150/expected.gd +++ b/tests/long_ltee_ara_p3_30k_pe150/expected.gd @@ -1,6 +1,6 @@ #=GENOME_DIFF 1.0 -#=CREATED 16:49:53 22 Aug 2026 -#=PROGRAM breseq 0.50.0 revision 77916ce0087c +#=CREATED 14:40:54 23 Aug 2026 +#=PROGRAM breseq 0.50.0 revision 68145331ba14 #=COMMAND ./src/breseq/breseq -j 7 -o ./tests/long_ltee_ara_p3_30k_pe150 -r ./tests/long_ltee_ara_p3_30k_pe150/../data/downloads/ltee_REL606/REL606.gbk --predict-copy-number --predict-discordant-pairs --predict-missing-pairs --predict-pair-distance --predict-soft-clipping ./tests/long_ltee_ara_p3_30k_pe150/../data/downloads/ena_SRR2588848/SRR2588848_1.fastq.gz ./tests/long_ltee_ara_p3_30k_pe150/../data/downloads/ena_SRR2588848/SRR2588848_2.fastq.gz #=REFSEQ ./tests/long_ltee_ara_p3_30k_pe150/../data/downloads/ltee_REL606/REL606.gbk #=READSEQ ./tests/long_ltee_ara_p3_30k_pe150/../data/downloads/ena_SRR2588848/SRR2588848_1.fastq.gz @@ -2818,19 +2818,19 @@ DP 2804 . REL606 16728 -1 REL606 2322345 -1 background_e_value=0.000e+00 candida DP 2805 . REL606 16728 -1 REL606 2322345 1 background_e_value=8.698e-07 candidate_discordant_count=8 concordant_count=0.0 discordant_count=6 distinct_discordant_count=6 expected_concordant_count=62.8 frequency=1.0000 frequency_lower=0.6070 frequency_upper=1.0000 neg_log10_discordance_p_value=7.0 reject=CONCORDANT_PAIR_SKEW side_1_annotate_key=repeat side_1_concordant_count=38 side_1_discordant_count=7 side_1_gene_name=IS186 side_1_gene_position=noncoding (1343/1343 nt) side_1_gene_product=repeat region side_1_gene_strand=> side_1_redundant=1 side_1_unpaired_count=1469 side_2_annotate_key=gene side_2_concordant_count=0 side_2_discordant_count=6 side_2_gene_name=menC side_2_gene_position=coding (131/963 nt) side_2_gene_product=O-succinylbenzoate synthase side_2_gene_strand=< side_2_locus_tag=ECB_02188 side_2_unpaired_count=173 DP 2806 . REL606 16728 -1 REL606 2772069 -1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=71.0 discordant_count=2 distinct_discordant_count=2 expected_concordant_count=62.8 frequency=0.0274 frequency_lower=0.0049 frequency_upper=0.0837 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=repeat side_1_concordant_count=38 side_1_discordant_count=3 side_1_redundant=1 side_1_unpaired_count=1469 side_2_annotate_key=gene side_2_concordant_count=71 side_2_discordant_count=2 side_2_unpaired_count=9 DP 2807 . REL606 23291 1 REL606 241554 1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=43.0 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0227 frequency_lower=0.0012 frequency_upper=0.1033 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=repeat side_1_concordant_count=55 side_1_discordant_count=1 side_1_redundant=1 side_1_unpaired_count=1519 side_2_annotate_key=gene side_2_concordant_count=43 side_2_discordant_count=1 side_2_unpaired_count=1432 -SC 2808 . REL606 37539 -1 agree_read_count=5 clipped_sequence=AAAAAATTTTCC consensus_fraction=0.5000 frequency=0.1562 frequency_lower=0.0637 frequency_upper=0.3008 log10_e_value=0.3 no_show=1 read_count=10 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=32 -SC 2809 . REL606 52532 1 agree_read_count=6 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.5455 frequency=0.1579 frequency_lower=0.0711 frequency_upper=0.2880 gene_name=kefC gene_position=coding (569/1863 nt) gene_product=glutathione-regulated potassium-efflux system protein gene_strand=> locus_tag=ECB_00051 log10_e_value=1.1 read_count=11 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=38 +SC 2808 . REL606 37539 -1 agree_read_count=5 agree_read_count_forward=0 agree_read_count_reverse=5 clipped_sequence=AAAAAATTTTCC consensus_fraction=0.5000 fisher_strand_p_value=5.72278e-03 frequency=0.1562 frequency_lower=0.0637 frequency_upper=0.3008 log10_e_value=0.3 no_show=1 read_count=10 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND spanning_read_count_forward=16 spanning_read_count_reverse=6 total_count=32 +SC 2809 . REL606 52532 1 agree_read_count=6 agree_read_count_forward=6 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.5455 fisher_strand_p_value=2.52806e-05 frequency=0.1579 frequency_lower=0.0711 frequency_upper=0.2880 log10_e_value=1.1 no_show=1 read_count=11 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=2 spanning_read_count_reverse=25 total_count=38 DP 2810 . REL606 72677 -1 REL606 80009 -1 background_e_value=8.698e-07 candidate_discordant_count=8 concordant_count=63.5 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0155 frequency_lower=0.0008 frequency_upper=0.0714 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=75 side_1_discordant_count=1 side_1_unpaired_count=19 side_2_annotate_key=gene side_2_concordant_count=52 side_2_discordant_count=1 side_2_unpaired_count=10 -SC 2811 . REL606 77882 1 agree_read_count=6 clipped_sequence=TTTTTTTTTTTT consensus_fraction=0.8571 frequency=0.1538 frequency_lower=0.0692 frequency_upper=0.2812 gene_name=tbpA gene_position=coding (403/984 nt) gene_product=thiamin transporter subunit gene_strand=< locus_tag=ECB_00070 log10_e_value=1.1 read_count=7 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=39 +SC 2811 . REL606 77882 1 agree_read_count=6 agree_read_count_forward=6 agree_read_count_reverse=0 clipped_sequence=TTTTTTTTTTTT consensus_fraction=0.8571 fisher_strand_p_value=1.08778e-03 frequency=0.1538 frequency_lower=0.0692 frequency_upper=0.2812 log10_e_value=1.1 no_show=1 read_count=7 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=8 spanning_read_count_reverse=24 total_count=39 DP 2812 . REL606 85373 -1 REL606 88327 -1 background_e_value=4.424e-05 candidate_discordant_count=7 concordant_count=51.5 discordant_count=2 distinct_discordant_count=2 expected_concordant_count=62.8 frequency=0.0374 frequency_lower=0.0067 frequency_upper=0.1130 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=51 side_1_discordant_count=2 side_1_unpaired_count=18 side_2_annotate_key=gene side_2_concordant_count=52 side_2_discordant_count=2 side_2_unpaired_count=3 DP 2813 . REL606 177239 -1 REL606 182421 -1 background_e_value=4.424e-05 candidate_discordant_count=7 concordant_count=77.0 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0128 frequency_lower=0.0007 frequency_upper=0.0594 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=81 side_1_discordant_count=1 side_1_unpaired_count=17 side_2_annotate_key=gene side_2_concordant_count=73 side_2_discordant_count=1 side_2_unpaired_count=21 -SC 2814 . REL606 204557 1 agree_read_count=7 clipped_sequence=GTGGCGGGGGGG consensus_fraction=0.6364 frequency=0.1522 frequency_lower=0.0737 frequency_upper=0.2669 gene_name=lpxD gene_position=coding (745/1026 nt) gene_product=UDP-3-O-[3-hydroxymyristoyl] glucosamine N-acyltransferase gene_strand=> locus_tag=ECB_00177 log10_e_value=1.8 read_count=11 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=46 -SC 2815 . REL606 216177 1 agree_read_count=8 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.6154 frequency=0.1311 frequency_lower=0.0670 frequency_upper=0.2242 gene_name=tilS gene_position=coding (1005/1299 nt) gene_product=tRNA(Ile)-lysidine synthetase gene_strand=> locus_tag=ECB_00186 log10_e_value=2.0 read_count=13 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=61 +SC 2814 . REL606 204557 1 agree_read_count=7 agree_read_count_forward=7 agree_read_count_reverse=0 clipped_sequence=GTGGCGGGGGGG consensus_fraction=0.6364 fisher_strand_p_value=6.36066e-05 frequency=0.1522 frequency_lower=0.0737 frequency_upper=0.2669 gene_name=lpxD gene_position=coding (745/1026 nt) gene_product=UDP-3-O-[3-hydroxymyristoyl] glucosamine N-acyltransferase gene_strand=> locus_tag=ECB_00177 log10_e_value=1.8 read_count=11 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=6 spanning_read_count_reverse=29 total_count=46 +SC 2815 . REL606 216177 1 agree_read_count=8 agree_read_count_forward=8 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.6154 fisher_strand_p_value=2.11405e-06 frequency=0.1311 frequency_lower=0.0670 frequency_upper=0.2242 gene_name=tilS gene_position=coding (1005/1299 nt) gene_product=tRNA(Ile)-lysidine synthetase gene_strand=> locus_tag=ECB_00186 log10_e_value=2.0 read_count=13 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=6 spanning_read_count_reverse=42 total_count=61 DP 2816 . REL606 226579 1 REL606 3903377 -1 background_e_value=0.000e+00 candidate_discordant_count=36 concordant_count=20.0 discordant_count=36 distinct_discordant_count=36 expected_concordant_count=62.8 frequency=0.6429 frequency_lower=0.5247 frequency_upper=0.7492 neg_log10_discordance_p_value=1.5 side_1_annotate_key=repeat side_1_concordant_count=71 side_1_discordant_count=36 side_1_gene_name=gmhB/rrsH side_1_gene_position=intergenic (+334/-30) side_1_gene_product=hypothetical protein/16S ribosomal RNA side_1_gene_strand=>/> side_1_locus_tag=ECB_00199/ECB_r00001 side_1_redundant=1 side_1_unpaired_count=1500 side_2_annotate_key=gene side_2_concordant_count=20 side_2_discordant_count=36 side_2_gene_name=yieP/rrsC side_2_gene_position=intergenic (-243/-238) side_2_gene_product=predicted transcriptional regulator/16S ribosomal RNA side_2_gene_strand= side_2_locus_tag=ECB_03641/ECB_r00011 side_2_unpaired_count=8 DP 2817 . REL606 229127 -1 REL606 3354723 -1 background_e_value=0.000e+00 candidate_discordant_count=15 concordant_count=NA discordant_count=15 distinct_discordant_count=15 expected_concordant_count=62.8 frequency=NA frequency_lower=NA frequency_upper=NA neg_log10_discordance_p_value=7.0 no_show=1 reject=CONCORDANT_PAIR_SKEW side_1_annotate_key=repeat side_1_concordant_count=7 side_1_discordant_count=15 side_1_redundant=1 side_1_unpaired_count=1783 side_2_annotate_key=repeat side_2_concordant_count=41 side_2_discordant_count=15 side_2_redundant=1 side_2_unpaired_count=2143 DP 2818 . REL606 243686 1 REL606 264492 1 background_e_value=4.424e-05 candidate_discordant_count=7 concordant_count=45.5 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0215 frequency_lower=0.0011 frequency_upper=0.0980 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=51 side_1_discordant_count=1 side_1_unpaired_count=6 side_2_annotate_key=gene side_2_concordant_count=40 side_2_discordant_count=1 side_2_unpaired_count=15 DP 2819 . REL606 307378 1 REL606 325771 1 background_e_value=4.424e-05 candidate_discordant_count=7 concordant_count=67.0 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0147 frequency_lower=0.0008 frequency_upper=0.0679 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=87 side_1_discordant_count=1 side_1_unpaired_count=13 side_2_annotate_key=gene side_2_concordant_count=47 side_2_discordant_count=1 side_2_unpaired_count=25 -SC 2820 . REL606 326928 1 agree_read_count=6 clipped_sequence=GGGGGGGGGGGG consensus_fraction=1.0000 frequency=0.1091 frequency_lower=0.0486 frequency_upper=0.2040 log10_e_value=0.2 no_show=1 read_count=6 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=55 +SC 2820 . REL606 326928 1 agree_read_count=6 agree_read_count_forward=6 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGGGGG consensus_fraction=1.0000 fisher_strand_p_value=6.10907e-03 frequency=0.1091 frequency_lower=0.0486 frequency_upper=0.2040 log10_e_value=0.2 no_show=1 read_count=6 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=19 spanning_read_count_reverse=30 total_count=55 DP 2821 . REL606 369956 1 REL606 378850 1 background_e_value=4.424e-05 candidate_discordant_count=7 concordant_count=64.0 discordant_count=3 distinct_discordant_count=3 expected_concordant_count=62.8 frequency=0.0448 frequency_lower=0.0123 frequency_upper=0.1117 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=61 side_1_discordant_count=3 side_1_unpaired_count=2 side_2_annotate_key=gene side_2_concordant_count=67 side_2_discordant_count=3 side_2_unpaired_count=10 PD 2822 . REL606 376452 -1 REL606 376453 1 ambiguous_pair_count=21 candidate_covering_count=48 distinct_pair_count=19 frequency=0.7037 frequency_lower=0.5286 frequency_upper=0.8432 normal_pair_count=8 position_range=3 reject=PAIR_DISTANCE_SCORE score=0.5 seed_z_score=-6.23 shifted_pair_count=19 side_1_annotate_key=gene side_1_gene_name=ykiA side_1_gene_position=coding (138/282 nt) side_1_gene_product=hypothetical protein side_1_gene_strand=> side_1_locus_tag=ECB_00339 side_2_annotate_key=gene side_2_gene_name=ykiA side_2_gene_position=coding (139/282 nt) side_2_gene_product=hypothetical protein side_2_gene_strand=> side_2_locus_tag=ECB_00339 size_shift=-453 size_shift_lower=-675 size_shift_upper=-264 total_pair_count=48 DP 2823 . REL606 382579 -1 REL606 386429 -1 background_e_value=4.424e-05 candidate_discordant_count=7 concordant_count=73.5 discordant_count=4 distinct_discordant_count=4 expected_concordant_count=62.8 frequency=0.0516 frequency_lower=0.0178 frequency_upper=0.1142 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=80 side_1_discordant_count=4 side_1_unpaired_count=14 side_2_annotate_key=gene side_2_concordant_count=67 side_2_discordant_count=4 side_2_unpaired_count=11 @@ -2845,23 +2845,23 @@ DP 2831 . REL606 555013 -1 REL606 1422045 1 background_e_value=0.000e+00 candida DP 2832 . REL606 556025 -1 REL606 1604692 -1 background_e_value=0.000e+00 candidate_discordant_count=59 concordant_count=0.0 discordant_count=59 distinct_discordant_count=59 expected_concordant_count=62.8 frequency=1.0000 frequency_lower=0.9505 frequency_upper=1.0000 neg_log10_discordance_p_value=0.4 side_1_annotate_key=gene side_1_concordant_count=0 side_1_discordant_count=59 side_1_gene_name=ECB_00513 side_1_gene_position=coding (1310/2346 nt) side_1_gene_product=conserved hypothetical protein side_1_gene_strand=> side_1_locus_tag=ECB_00513 side_1_unpaired_count=79 side_2_annotate_key=gene side_2_concordant_count=0 side_2_discordant_count=59 side_2_gene_name=stfR side_2_gene_position=coding (1191/2379 nt) side_2_gene_product=predicted tail fiber protein side_2_gene_strand=< side_2_locus_tag=ECB_01508 side_2_unpaired_count=4 DP 2833 . REL606 588495 1 REL606 664688 1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=NA discordant_count=4 distinct_discordant_count=4 expected_concordant_count=62.8 frequency=NA frequency_lower=NA frequency_upper=NA neg_log10_discordance_p_value=7.0 no_show=1 reject=CONCORDANT_PAIR_SKEW side_1_annotate_key=repeat side_1_concordant_count=0 side_1_discordant_count=4 side_1_redundant=1 side_1_unpaired_count=2545 side_2_annotate_key=repeat side_2_concordant_count=70 side_2_discordant_count=4 side_2_redundant=1 side_2_unpaired_count=1499 DP 2834 . REL606 629208 1 REL606 635378 1 background_e_value=8.698e-07 candidate_discordant_count=8 concordant_count=85.0 discordant_count=4 distinct_discordant_count=4 expected_concordant_count=62.8 frequency=0.0449 frequency_lower=0.0155 frequency_upper=0.0999 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=90 side_1_discordant_count=4 side_1_unpaired_count=21 side_2_annotate_key=gene side_2_concordant_count=80 side_2_discordant_count=4 side_2_unpaired_count=10 -SC 2835 . REL606 654142 1 agree_read_count=10 clipped_sequence=TCAATGAAGGGC consensus_fraction=1.0000 frequency=0.1370 frequency_lower=0.0762 frequency_upper=0.2213 gene_name=holA gene_position=coding (48/1032 nt) gene_product=DNA polymerase III subunit delta gene_strand=< locus_tag=ECB_00609 log10_e_value=3.3 read_count=10 reject=FREQUENCY_BELOW_CUTOFF total_count=73 -SC 2836 . REL606 654153 -1 agree_read_count=8 clipped_sequence=GCTCAATGAAGG consensus_fraction=1.0000 frequency=0.1111 frequency_lower=0.0565 frequency_upper=0.1916 gene_name=holA gene_position=coding (37/1032 nt) gene_product=DNA polymerase III subunit delta gene_strand=< locus_tag=ECB_00609 log10_e_value=1.4 read_count=8 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=72 +SC 2835 . REL606 654142 1 agree_read_count=10 agree_read_count_forward=1 agree_read_count_reverse=9 clipped_sequence=TCAATGAAGGGC consensus_fraction=1.0000 fisher_strand_p_value=3.98591e-02 frequency=0.1370 frequency_lower=0.0762 frequency_upper=0.2213 gene_name=holA gene_position=coding (48/1032 nt) gene_product=DNA polymerase III subunit delta gene_strand=< locus_tag=ECB_00609 log10_e_value=3.3 read_count=10 reject=FREQUENCY_BELOW_CUTOFF,FISHER_STRAND spanning_read_count_forward=29 spanning_read_count_reverse=34 total_count=73 +SC 2836 . REL606 654153 -1 agree_read_count=8 agree_read_count_forward=8 agree_read_count_reverse=0 clipped_sequence=GCTCAATGAAGG consensus_fraction=1.0000 fisher_strand_p_value=8.64206e-03 frequency=0.1111 frequency_lower=0.0565 frequency_upper=0.1916 log10_e_value=1.4 no_show=1 read_count=8 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND spanning_read_count_forward=33 spanning_read_count_reverse=31 total_count=72 DP 2837 . REL606 664688 1 REL606 1270125 1 background_e_value=0.000e+00 candidate_discordant_count=72 concordant_count=2.0 discordant_count=70 distinct_discordant_count=70 expected_concordant_count=62.8 frequency=0.9722 frequency_lower=0.9151 frequency_upper=0.9950 neg_log10_discordance_p_value=0.2 side_1_annotate_key=repeat side_1_concordant_count=70 side_1_discordant_count=70 side_1_gene_name=IS150 side_1_gene_position=noncoding (1/1443 nt) side_1_gene_product=repeat region side_1_gene_strand=> side_1_redundant=1 side_1_unpaired_count=1499 side_2_annotate_key=gene side_2_concordant_count=2 side_2_discordant_count=70 side_2_gene_name=ldrB/ldrC side_2_gene_position=intergenic (-167/+261) side_2_gene_product=toxic polypeptide, small/toxic polypeptide, small side_2_gene_strand= side_1_redundant=1 side_1_unpaired_count=1501 side_2_annotate_key=gene side_2_concordant_count=2 side_2_discordant_count=55 side_2_gene_name=ldrB/ldrC side_2_gene_position=intergenic (-170/+258) side_2_gene_product=toxic polypeptide, small/toxic polypeptide, small side_2_gene_strand= side_1_redundant=1 side_1_unpaired_count=1501 side_2_annotate_key=gene side_2_concordant_count=0 side_2_discordant_count=80 side_2_gene_name=yieO side_2_gene_position=coding (1258/1428 nt) side_2_gene_product=predicted multidrug or homocysteine efflux system side_2_gene_strand=< side_2_locus_tag=ECB_03640 side_2_unpaired_count=89 DP 2840 . REL606 685543 1 REL606 691711 1 background_e_value=4.424e-05 candidate_discordant_count=7 concordant_count=63.5 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0155 frequency_lower=0.0008 frequency_upper=0.0714 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=74 side_1_discordant_count=1 side_1_unpaired_count=23 side_2_annotate_key=gene side_2_concordant_count=53 side_2_discordant_count=1 side_2_unpaired_count=26 DP 2841 . REL606 712700 -1 REL606 714176 1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=56.0 discordant_count=6 distinct_discordant_count=6 expected_concordant_count=62.8 frequency=0.0968 frequency_lower=0.0430 frequency_upper=0.1821 neg_log10_discordance_p_value=7.0 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=repeat side_1_concordant_count=74 side_1_discordant_count=6 side_1_gene_name=rhsC side_1_gene_position=coding (845/1665 nt) side_1_gene_product=rhsC element core protein RshC side_1_gene_strand=> side_1_locus_tag=ECB_00658 side_1_redundant=1 side_1_unpaired_count=76 side_2_annotate_key=gene side_2_concordant_count=56 side_2_discordant_count=6 side_2_gene_name=ybfO side_2_gene_position=coding (213/1434 nt) side_2_gene_product=conserved protein, rhs-like side_2_gene_strand=> side_2_locus_tag=ECB_00660 side_2_unpaired_count=12 -SC 2842 . REL606 737310 1 agree_read_count=8 clipped_sequence=GGGGGGGGATTT consensus_fraction=1.0000 frequency=0.1212 frequency_lower=0.0618 frequency_upper=0.2081 gene_name=sdhA gene_position=coding (613/1767 nt) gene_product=succinate dehydrogenase flavoprotein subunit gene_strand=> locus_tag=ECB_00683 log10_e_value=1.7 read_count=8 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=66 -SC 2843 . REL606 790860 1 agree_read_count=6 clipped_sequence=GGGGGGAAAGGG consensus_fraction=0.4615 frequency=0.1333 frequency_lower=0.0597 frequency_upper=0.2463 log10_e_value=0.7 no_show=1 read_count=13 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,CLIPPED_TAIL_CONSENSUS total_count=45 +SC 2842 . REL606 737310 1 agree_read_count=8 agree_read_count_forward=8 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGATTT consensus_fraction=1.0000 fisher_strand_p_value=1.37349e-03 frequency=0.1212 frequency_lower=0.0618 frequency_upper=0.2081 gene_name=sdhA gene_position=coding (613/1767 nt) gene_product=succinate dehydrogenase flavoprotein subunit gene_strand=> locus_tag=ECB_00683 log10_e_value=1.7 read_count=8 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=23 spanning_read_count_reverse=35 total_count=66 +SC 2843 . REL606 790860 1 agree_read_count=6 agree_read_count_forward=6 agree_read_count_reverse=0 clipped_sequence=GGGGGGAAAGGG consensus_fraction=0.4615 fisher_strand_p_value=3.62229e-07 frequency=0.1333 frequency_lower=0.0597 frequency_upper=0.2463 log10_e_value=0.7 no_show=1 read_count=13 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,CLIPPED_TAIL_CONSENSUS,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=0 spanning_read_count_reverse=32 total_count=45 DP 2844 . REL606 801763 1 REL606 812326 1 background_e_value=2.349e-10 candidate_discordant_count=10 concordant_count=60.0 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0164 frequency_lower=0.0008 frequency_upper=0.0754 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=52 side_1_discordant_count=1 side_1_unpaired_count=14 side_2_annotate_key=gene side_2_concordant_count=68 side_2_discordant_count=1 side_2_unpaired_count=3 -SC 2845 . REL606 829210 1 agree_read_count=9 clipped_sequence=GGGGGGGGCCCC consensus_fraction=0.6429 frequency=0.1343 frequency_lower=0.0719 frequency_upper=0.2227 gene_name=ybiC gene_position=coding (235/1086 nt) gene_product=predicted dehydrogenase gene_strand=> locus_tag=ECB_00768 log10_e_value=2.7 read_count=14 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=67 +SC 2845 . REL606 829210 1 agree_read_count=9 agree_read_count_forward=9 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGCCCC consensus_fraction=0.6429 fisher_strand_p_value=2.45196e-05 frequency=0.1343 frequency_lower=0.0719 frequency_upper=0.2227 gene_name=ybiC gene_position=coding (235/1086 nt) gene_product=predicted dehydrogenase gene_strand=> locus_tag=ECB_00768 log10_e_value=2.7 read_count=14 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=13 spanning_read_count_reverse=40 total_count=67 DP 2846 . REL606 844436 -1 REL606 847563 -1 background_e_value=4.424e-05 candidate_discordant_count=7 concordant_count=61.0 discordant_count=3 distinct_discordant_count=3 expected_concordant_count=62.8 frequency=0.0469 frequency_lower=0.0129 frequency_upper=0.1167 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=81 side_1_discordant_count=4 side_1_unpaired_count=8 side_2_annotate_key=gene side_2_concordant_count=41 side_2_discordant_count=3 side_2_unpaired_count=7 DP 2847 . REL606 849056 -1 REL606 853294 -1 background_e_value=4.424e-05 candidate_discordant_count=7 concordant_count=66.5 discordant_count=2 distinct_discordant_count=2 expected_concordant_count=62.8 frequency=0.0292 frequency_lower=0.0052 frequency_upper=0.0891 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=73 side_1_discordant_count=2 side_1_unpaired_count=5 side_2_annotate_key=gene side_2_concordant_count=60 side_2_discordant_count=2 side_2_unpaired_count=8 -SC 2848 . REL606 876897 1 agree_read_count=6 clipped_sequence=GGGGGGGGGGCG consensus_fraction=0.3529 frequency=0.1091 frequency_lower=0.0486 frequency_upper=0.2040 log10_e_value=0.2 no_show=1 read_count=17 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,CLIPPED_TAIL_CONSENSUS total_count=55 +SC 2848 . REL606 876897 1 agree_read_count=6 agree_read_count_forward=6 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGGGCG consensus_fraction=0.3529 fisher_strand_p_value=3.96654e-06 frequency=0.1091 frequency_lower=0.0486 frequency_upper=0.2040 log10_e_value=0.2 no_show=1 read_count=17 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,CLIPPED_TAIL_CONSENSUS,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=2 spanning_read_count_reverse=36 total_count=55 DP 2849 . REL606 913740 1 REL606 922371 1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=55.5 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0177 frequency_lower=0.0009 frequency_upper=0.0812 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=41 side_1_discordant_count=1 side_1_unpaired_count=10 side_2_annotate_key=gene side_2_concordant_count=70 side_2_discordant_count=1 side_2_unpaired_count=9 -SC 2850 . REL606 992005 1 agree_read_count=7 clipped_sequence=GGGGGGGGTTCC consensus_fraction=0.6364 frequency=0.1489 frequency_lower=0.0720 frequency_upper=0.2616 gene_name=mukF gene_position=coding (595/1323 nt) gene_product=condesin subunit F gene_strand=> locus_tag=ECB_00926 log10_e_value=1.7 read_count=11 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=47 -SC 2851 . REL606 1011012 -1 agree_read_count=6 clipped_sequence=CGCCCCCCCCCC consensus_fraction=0.4286 frequency=0.1333 frequency_lower=0.0597 frequency_upper=0.2463 log10_e_value=0.7 no_show=1 read_count=14 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,CLIPPED_TAIL_CONSENSUS total_count=45 +SC 2850 . REL606 992005 1 agree_read_count=7 agree_read_count_forward=7 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGTTCC consensus_fraction=0.6364 fisher_strand_p_value=9.87583e-04 frequency=0.1489 frequency_lower=0.0720 frequency_upper=0.2616 gene_name=mukF gene_position=coding (595/1323 nt) gene_product=condesin subunit F gene_strand=> locus_tag=ECB_00926 log10_e_value=1.7 read_count=11 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=11 spanning_read_count_reverse=25 total_count=47 +SC 2851 . REL606 1011012 -1 agree_read_count=6 agree_read_count_forward=0 agree_read_count_reverse=6 clipped_sequence=CGCCCCCCCCCC consensus_fraction=0.4286 fisher_strand_p_value=1.29173e-03 frequency=0.1333 frequency_lower=0.0597 frequency_upper=0.2463 log10_e_value=0.7 no_show=1 read_count=14 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,CLIPPED_TAIL_CONSENSUS,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=23 spanning_read_count_reverse=8 total_count=45 DP 2852 . REL606 1029925 -1 REL606 1042025 -1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=71.0 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0139 frequency_lower=0.0007 frequency_upper=0.0642 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=64 side_1_discordant_count=1 side_1_unpaired_count=15 side_2_annotate_key=gene side_2_concordant_count=78 side_2_discordant_count=1 side_2_unpaired_count=13 DP 2853 . REL606 1068382 1 REL606 1074350 1 background_e_value=8.698e-07 candidate_discordant_count=8 concordant_count=57.5 discordant_count=2 distinct_discordant_count=2 expected_concordant_count=62.8 frequency=0.0336 frequency_lower=0.0060 frequency_upper=0.1021 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=67 side_1_discordant_count=2 side_1_unpaired_count=10 side_2_annotate_key=gene side_2_concordant_count=48 side_2_discordant_count=2 side_2_unpaired_count=2 DP 2854 . REL606 1086456 1 REL606 1096007 1 background_e_value=8.698e-07 candidate_discordant_count=8 concordant_count=59.0 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0167 frequency_lower=0.0009 frequency_upper=0.0766 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=57 side_1_discordant_count=1 side_1_unpaired_count=12 side_2_annotate_key=gene side_2_concordant_count=61 side_2_discordant_count=1 side_2_unpaired_count=38 @@ -2875,21 +2875,21 @@ DP 2861 . REL606 1255825 -1 REL606 1257529 -1 background_e_value=1.970e-03 candi DP 2862 . REL606 1315053 1 REL606 1326854 1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=80.0 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0123 frequency_lower=0.0006 frequency_upper=0.0572 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=76 side_1_discordant_count=1 side_1_unpaired_count=9 side_2_annotate_key=gene side_2_concordant_count=84 side_2_discordant_count=1 side_2_unpaired_count=13 DP 2863 . REL606 1322543 -1 REL606 1325731 -1 background_e_value=1.520e-08 candidate_discordant_count=9 concordant_count=65.5 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0150 frequency_lower=0.0008 frequency_upper=0.0694 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=54 side_1_discordant_count=1 side_1_unpaired_count=6 side_2_annotate_key=gene side_2_concordant_count=77 side_2_discordant_count=1 side_2_unpaired_count=6 DP 2864 . REL606 1365112 -1 REL606 1370532 -1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=77.5 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0127 frequency_lower=0.0007 frequency_upper=0.0590 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=75 side_1_discordant_count=1 side_1_unpaired_count=13 side_2_annotate_key=gene side_2_concordant_count=80 side_2_discordant_count=1 side_2_unpaired_count=2 -SC 2865 . REL606 1367870 1 agree_read_count=8 clipped_sequence=GGGGGGGGGGAA consensus_fraction=0.8000 frequency=0.1739 frequency_lower=0.0896 frequency_upper=0.2920 gene_name=pspD gene_position=coding (110/222 nt) gene_product=peripheral inner membrane phage-shock protein gene_strand=> locus_tag=ECB_01284 log10_e_value=2.9 read_count=10 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=46 -SC 2866 . REL606 1480510 -1 agree_read_count=8 clipped_sequence=AGAAAAAAAAAC consensus_fraction=0.8000 frequency=0.1778 frequency_lower=0.0917 frequency_upper=0.2980 gene_name=ydcR gene_position=coding (398/1407 nt) gene_product=fused predicted DNA-binding transcriptional regulator/predicted amino transferase gene_strand=> locus_tag=ECB_01396 log10_e_value=3.0 read_count=10 reject=FREQUENCY_BELOW_CUTOFF total_count=45 +SC 2865 . REL606 1367870 1 agree_read_count=8 agree_read_count_forward=8 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGGGAA consensus_fraction=0.8000 fisher_strand_p_value=2.53904e-07 frequency=0.1739 frequency_lower=0.0896 frequency_upper=0.2920 gene_name=pspD gene_position=coding (110/222 nt) gene_product=peripheral inner membrane phage-shock protein gene_strand=> locus_tag=ECB_01284 log10_e_value=2.9 read_count=10 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=2 spanning_read_count_reverse=34 total_count=46 +SC 2866 . REL606 1480510 -1 agree_read_count=8 agree_read_count_forward=0 agree_read_count_reverse=8 clipped_sequence=AGAAAAAAAAAC consensus_fraction=0.8000 fisher_strand_p_value=3.41359e-06 frequency=0.1778 frequency_lower=0.0917 frequency_upper=0.2980 gene_name=ydcR gene_position=coding (398/1407 nt) gene_product=fused predicted DNA-binding transcriptional regulator/predicted amino transferase gene_strand=> locus_tag=ECB_01396 log10_e_value=3.0 read_count=10 reject=FREQUENCY_BELOW_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=31 spanning_read_count_reverse=4 total_count=45 DP 2867 . REL606 1488506 -1 REL606 1493876 -1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=66.5 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0148 frequency_lower=0.0008 frequency_upper=0.0684 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=74 side_1_discordant_count=1 side_1_unpaired_count=7 side_2_annotate_key=gene side_2_concordant_count=59 side_2_discordant_count=2 side_2_unpaired_count=8 -SC 2868 . REL606 1516271 -1 agree_read_count=6 clipped_sequence=GGGGGGAAAAAC consensus_fraction=0.6000 frequency=0.1538 frequency_lower=0.0692 frequency_upper=0.2812 log10_e_value=1.1 no_show=1 read_count=10 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=39 +SC 2868 . REL606 1516271 -1 agree_read_count=6 agree_read_count_forward=0 agree_read_count_reverse=6 clipped_sequence=GGGGGGAAAAAC consensus_fraction=0.6000 fisher_strand_p_value=7.39835e-02 frequency=0.1538 frequency_lower=0.0692 frequency_upper=0.2812 log10_e_value=1.1 no_show=1 read_count=10 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF spanning_read_count_forward=12 spanning_read_count_reverse=17 total_count=39 DP 2869 . REL606 1653534 -1 REL606 1664956 -1 background_e_value=4.424e-05 candidate_discordant_count=7 concordant_count=64.5 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0153 frequency_lower=0.0008 frequency_upper=0.0704 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=63 side_1_discordant_count=1 side_1_unpaired_count=8 side_2_annotate_key=gene side_2_concordant_count=66 side_2_discordant_count=1 side_2_unpaired_count=2 DP 2870 . REL606 1668330 -1 REL606 1669271 -1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=70.0 discordant_count=3 distinct_discordant_count=3 expected_concordant_count=62.8 frequency=0.0411 frequency_lower=0.0113 frequency_upper=0.1028 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=68 side_1_discordant_count=4 side_1_unpaired_count=4 side_2_annotate_key=gene side_2_concordant_count=72 side_2_discordant_count=4 side_2_unpaired_count=6 -SC 2871 . REL606 1674823 -1 agree_read_count=6 clipped_sequence=AAAAAACCCCCC consensus_fraction=1.0000 frequency=0.1579 frequency_lower=0.0711 frequency_upper=0.2880 log10_e_value=1.1 no_show=1 read_count=6 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=38 +SC 2871 . REL606 1674823 -1 agree_read_count=6 agree_read_count_forward=0 agree_read_count_reverse=6 clipped_sequence=AAAAAACCCCCC consensus_fraction=1.0000 fisher_strand_p_value=6.21586e-04 frequency=0.1579 frequency_lower=0.0711 frequency_upper=0.2880 log10_e_value=1.1 no_show=1 read_count=6 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND spanning_read_count_forward=25 spanning_read_count_reverse=7 total_count=38 DP 2872 . REL606 1691078 -1 REL606 1698622 -1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=65.5 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0150 frequency_lower=0.0008 frequency_upper=0.0694 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=67 side_1_discordant_count=1 side_1_unpaired_count=15 side_2_annotate_key=gene side_2_concordant_count=64 side_2_discordant_count=1 side_2_unpaired_count=6 -SC 2873 . REL606 1714057 -1 agree_read_count=18 clipped_sequence=ACCCCCCCCCCC consensus_fraction=0.9000 frequency=0.3396 frequency_lower=0.2323 frequency_upper=0.4610 gene_name=ydhP|ydhP gene_position=pseudogene (110/779 nt)|pseudogene (501/1167 nt) gene_product=putative transport protein (MFS family); b1657_1|putative transport protein (MFS family); b1657_1 gene_strand=<|< locus_tag=ECB_01627|ECB_01627 log10_e_value=13.6 read_count=20 snp_type=| total_count=53 -SC 2874 . REL606 1716933 -1 agree_read_count=11 clipped_sequence=CCCCCCCCCCCC consensus_fraction=0.8462 frequency=0.2973 frequency_lower=0.1765 frequency_upper=0.4438 gene_name=ydhB gene_position=coding (133/933 nt) gene_product=predicted DNA-binding transcriptional regulator gene_strand=< locus_tag=ECB_01630 log10_e_value=7.5 read_count=13 total_count=37 +SC 2873 . REL606 1714057 -1 agree_read_count=18 agree_read_count_forward=0 agree_read_count_reverse=18 clipped_sequence=ACCCCCCCCCCC consensus_fraction=0.9000 fisher_strand_p_value=3.58411e-14 frequency=0.3396 frequency_lower=0.2323 frequency_upper=0.4610 gene_name=ydhP|ydhP gene_position=pseudogene (110/779 nt)|pseudogene (501/1167 nt) gene_product=putative transport protein (MFS family); b1657_1|putative transport protein (MFS family); b1657_1 gene_strand=<|< locus_tag=ECB_01627|ECB_01627 log10_e_value=13.6 read_count=20 reject=FISHER_STRAND,LOW_COMPLEXITY_TAIL snp_type=| spanning_read_count_forward=33 spanning_read_count_reverse=0 total_count=53 +SC 2874 . REL606 1716933 -1 agree_read_count=11 agree_read_count_forward=0 agree_read_count_reverse=11 clipped_sequence=CCCCCCCCCCCC consensus_fraction=0.8462 fisher_strand_p_value=2.87614e-08 frequency=0.2973 frequency_lower=0.1765 frequency_upper=0.4438 gene_name=ydhB gene_position=coding (133/933 nt) gene_product=predicted DNA-binding transcriptional regulator gene_strand=< locus_tag=ECB_01630 log10_e_value=7.5 read_count=13 reject=FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=23 spanning_read_count_reverse=1 total_count=37 DP 2875 . REL606 1792554 -1 REL606 1795140 -1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=56.5 discordant_count=5 distinct_discordant_count=4 expected_concordant_count=62.8 frequency=0.0661 frequency_lower=0.0229 frequency_upper=0.1449 neg_log10_discordance_p_value=7.0 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=49 side_1_discordant_count=5 side_1_gene_name=katE side_1_gene_position=coding (1423/2262 nt) side_1_gene_product=hydroperoxidase HPII(III) (catalase) side_1_gene_strand=> side_1_locus_tag=ECB_01701 side_1_unpaired_count=8 side_2_annotate_key=gene side_2_concordant_count=64 side_2_discordant_count=10 side_2_gene_name=celF side_2_gene_position=coding (626/1353 nt) side_2_gene_product=cryptic phospho-beta-glucosidase, NAD(P)-binding side_2_gene_strand=< side_2_locus_tag=ECB_01703 side_2_unpaired_count=24 DP 2876 . REL606 1815044 1 REL606 1814842 1 background_e_value=4.424e-05 candidate_discordant_count=7 concordant_count=78.0 discordant_count=4 distinct_discordant_count=3 expected_concordant_count=62.8 frequency=0.0370 frequency_lower=0.0102 frequency_upper=0.0929 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=93 side_1_discordant_count=6 side_1_unpaired_count=9 side_2_annotate_key=gene side_2_concordant_count=63 side_2_discordant_count=8 side_2_unpaired_count=7 DP 2877 . REL606 1921364 -1 REL606 1924950 -1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=61.0 discordant_count=2 distinct_discordant_count=2 expected_concordant_count=62.8 frequency=0.0317 frequency_lower=0.0057 frequency_upper=0.0966 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=67 side_1_discordant_count=2 side_1_unpaired_count=6 side_2_annotate_key=gene side_2_concordant_count=55 side_2_discordant_count=3 side_2_unpaired_count=6 DP 2878 . REL606 1996129 -1 REL606 1999540 -1 background_e_value=4.424e-05 candidate_discordant_count=7 concordant_count=40.5 discordant_count=8 distinct_discordant_count=8 expected_concordant_count=62.8 frequency=0.1649 frequency_lower=0.0848 frequency_upper=0.2780 neg_log10_discordance_p_value=7.0 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=35 side_1_discordant_count=8 side_1_gene_name=asnW/yeeO side_1_gene_position=intergenic (-27/+74) side_1_gene_product=tRNA-Asn/predicted multidrug efflux system side_1_gene_strand= locus_tag=ECB_01902/ECB_01903 log10_e_value=3.6 read_count=8 total_count=38 +SC 2879 . REL606 2005207 1 agree_read_count=8 agree_read_count_forward=8 agree_read_count_reverse=0 clipped_sequence=GACATAAGCTGT consensus_fraction=1.0000 fisher_strand_p_value=7.65316e-02 frequency=0.2105 frequency_lower=0.1093 frequency_upper=0.3479 gene_name=cobU/yoeA gene_position=intergenic (-1443/-229) gene_product=adenosylcobinamide kinase/adenosylcobinamide-phosphate guanylyltransferase/b1995(b4582); putative hemine receptor gene_strand= locus_tag=ECB_01902/ECB_01903 log10_e_value=3.6 read_count=8 spanning_read_count_forward=19 spanning_read_count_reverse=11 total_count=38 DP 2880 . REL606 2011992 -1 REL606 2015958 -1 background_e_value=8.698e-07 candidate_discordant_count=8 concordant_count=53.5 discordant_count=2 distinct_discordant_count=2 expected_concordant_count=62.8 frequency=0.0360 frequency_lower=0.0064 frequency_upper=0.1091 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=43 side_1_discordant_count=2 side_1_unpaired_count=3 side_2_annotate_key=gene side_2_concordant_count=64 side_2_discordant_count=2 side_2_unpaired_count=14 DP 2881 . REL606 2017080 1 REL606 2017514 1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=72.0 discordant_count=2 distinct_discordant_count=2 expected_concordant_count=62.8 frequency=0.0270 frequency_lower=0.0048 frequency_upper=0.0826 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=70 side_1_discordant_count=4 side_1_unpaired_count=9 side_2_annotate_key=gene side_2_concordant_count=74 side_2_discordant_count=4 side_2_unpaired_count=11 DP 2882 . REL606 2023281 -1 REL606 2023990 -1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=89.0 discordant_count=3 distinct_discordant_count=3 expected_concordant_count=62.8 frequency=0.0326 frequency_lower=0.0089 frequency_upper=0.0821 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=72 side_1_discordant_count=3 side_1_unpaired_count=15 side_2_annotate_key=gene side_2_concordant_count=106 side_2_discordant_count=5 side_2_unpaired_count=23 @@ -2898,51 +2898,51 @@ DP 2884 . REL606 2063177 -1 REL606 2063177 -1 background_e_value=1.970e-03 candi DP 2885 . REL606 2096225 -1 REL606 2098699 -1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=66.0 discordant_count=2 distinct_discordant_count=2 expected_concordant_count=62.8 frequency=0.0294 frequency_lower=0.0053 frequency_upper=0.0897 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=79 side_1_discordant_count=2 side_1_unpaired_count=4 side_2_annotate_key=gene side_2_concordant_count=53 side_2_discordant_count=2 side_2_unpaired_count=4 DP 2886 . REL606 2127094 -1 REL606 2134730 -1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=63.0 discordant_count=2 distinct_discordant_count=2 expected_concordant_count=62.8 frequency=0.0308 frequency_lower=0.0055 frequency_upper=0.0937 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=53 side_1_discordant_count=2 side_1_unpaired_count=10 side_2_annotate_key=gene side_2_concordant_count=73 side_2_discordant_count=2 side_2_unpaired_count=6 DP 2887 . REL606 2154135 -1 REL606 2161495 -1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=64.5 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0153 frequency_lower=0.0008 frequency_upper=0.0704 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=58 side_1_discordant_count=1 side_1_unpaired_count=8 side_2_annotate_key=gene side_2_concordant_count=71 side_2_discordant_count=1 side_2_unpaired_count=12 -SC 2888 . REL606 2161495 1 agree_read_count=7 clipped_sequence=GGAAATGTTTTT consensus_fraction=0.6364 frequency=0.1346 frequency_lower=0.0649 frequency_upper=0.2380 gene_name=yehQ gene_position=coding (1200/2001 nt) gene_product=hypothetical protein gene_strand=> locus_tag=ECB_02051 log10_e_value=1.4 read_count=11 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=52 -SC 2889 . REL606 2170748 1 agree_read_count=6 clipped_sequence=GGGGGGTTGGGG consensus_fraction=0.3529 frequency=0.1224 frequency_lower=0.0547 frequency_upper=0.2274 log10_e_value=0.5 no_show=1 read_count=17 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,CLIPPED_TAIL_CONSENSUS total_count=49 +SC 2888 . REL606 2161495 1 agree_read_count=7 agree_read_count_forward=7 agree_read_count_reverse=0 clipped_sequence=GGAAATGTTTTT consensus_fraction=0.6364 fisher_strand_p_value=6.84349e-04 frequency=0.1346 frequency_lower=0.0649 frequency_upper=0.2380 log10_e_value=1.4 no_show=1 read_count=11 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND spanning_read_count_forward=12 spanning_read_count_reverse=29 total_count=52 +SC 2889 . REL606 2170748 1 agree_read_count=6 agree_read_count_forward=6 agree_read_count_reverse=0 clipped_sequence=GGGGGGTTGGGG consensus_fraction=0.3529 fisher_strand_p_value=3.62229e-07 frequency=0.1224 frequency_lower=0.0547 frequency_upper=0.2274 log10_e_value=0.5 no_show=1 read_count=17 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,CLIPPED_TAIL_CONSENSUS,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=0 spanning_read_count_reverse=32 total_count=49 DP 2890 . REL606 2195802 -1 REL606 2204256 -1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=50.0 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0196 frequency_lower=0.0010 frequency_upper=0.0897 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=57 side_1_discordant_count=1 side_1_unpaired_count=8 side_2_annotate_key=gene side_2_concordant_count=43 side_2_discordant_count=1 side_2_unpaired_count=7 DP 2891 . REL606 2304115 -1 REL606 2307448 -1 background_e_value=1.520e-08 candidate_discordant_count=9 concordant_count=69.5 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0142 frequency_lower=0.0007 frequency_upper=0.0655 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=73 side_1_discordant_count=1 side_1_unpaired_count=5 side_2_annotate_key=gene side_2_concordant_count=66 side_2_discordant_count=1 side_2_unpaired_count=14 -SC 2892 . REL606 2322348 1 agree_read_count=6 clipped_sequence=ATAAGCGCTAAC consensus_fraction=1.0000 frequency=0.5455 frequency_lower=0.2712 frequency_upper=0.8004 gene_name=menC gene_position=coding (128/963 nt) gene_product=O-succinylbenzoate synthase gene_strand=< locus_tag=ECB_02188 log10_e_value=4.8 read_count=6 total_count=11 +SC 2892 . REL606 2322348 1 agree_read_count=6 agree_read_count_forward=4 agree_read_count_reverse=2 clipped_sequence=ATAAGCGCTAAC consensus_fraction=1.0000 fisher_strand_p_value=6.06061e-02 frequency=0.5455 frequency_lower=0.2712 frequency_upper=0.8004 gene_name=menC gene_position=coding (128/963 nt) gene_product=O-succinylbenzoate synthase gene_strand=< locus_tag=ECB_02188 log10_e_value=4.8 read_count=6 spanning_read_count_forward=0 spanning_read_count_reverse=5 total_count=11 DP 2893 . REL606 2389741 -1 REL606 2397908 -1 background_e_value=4.424e-05 candidate_discordant_count=7 concordant_count=40.5 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0241 frequency_lower=0.0012 frequency_upper=0.1093 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=39 side_1_discordant_count=1 side_1_unpaired_count=28 side_2_annotate_key=gene side_2_concordant_count=42 side_2_discordant_count=1 side_2_unpaired_count=5 DP 2894 . REL606 2427204 1 REL606 2435257 1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=58.0 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0169 frequency_lower=0.0009 frequency_upper=0.0779 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=33 side_1_discordant_count=1 side_1_unpaired_count=1 side_2_annotate_key=gene side_2_concordant_count=83 side_2_discordant_count=1 side_2_unpaired_count=8 DP 2895 . REL606 2450988 1 REL606 2453776 1 background_e_value=0.000e+00 candidate_discordant_count=12 concordant_count=65.0 discordant_count=11 distinct_discordant_count=11 expected_concordant_count=62.8 frequency=0.1447 frequency_lower=0.0833 frequency_upper=0.2282 neg_log10_discordance_p_value=7.0 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=66 side_1_discordant_count=11 side_1_gene_name=alaX side_1_gene_position=noncoding (5/76 nt) side_1_gene_product=tRNA-Ala side_1_gene_strand=< side_1_locus_tag=ECB_t00039 side_1_unpaired_count=12 side_2_annotate_key=gene side_2_concordant_count=64 side_2_discordant_count=11 side_2_gene_name=gltX/valU side_2_gene_position=intergenic (-228/-31) side_2_gene_product=glutamyl-tRNA synthetase/tRNA-Val side_2_gene_strand= side_2_locus_tag=ECB_02306/ECB_t00041 side_2_unpaired_count=13 DP 2896 . REL606 2470951 1 REL606 2501707 1 background_e_value=4.424e-05 candidate_discordant_count=7 concordant_count=69.5 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0142 frequency_lower=0.0007 frequency_upper=0.0655 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=59 side_1_discordant_count=1 side_1_unpaired_count=9 side_2_annotate_key=gene side_2_concordant_count=80 side_2_discordant_count=1 side_2_unpaired_count=36 DP 2897 . REL606 2509471 1 REL606 2510666 1 background_e_value=4.424e-05 candidate_discordant_count=7 concordant_count=67.5 discordant_count=3 distinct_discordant_count=3 expected_concordant_count=62.8 frequency=0.0426 frequency_lower=0.0117 frequency_upper=0.1063 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=77 side_1_discordant_count=4 side_1_unpaired_count=7 side_2_annotate_key=gene side_2_concordant_count=58 side_2_discordant_count=4 side_2_unpaired_count=7 DP 2898 . REL606 2520389 -1 REL606 2527826 -1 background_e_value=8.698e-07 candidate_discordant_count=8 concordant_count=68.0 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0145 frequency_lower=0.0007 frequency_upper=0.0669 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=58 side_1_discordant_count=1 side_1_unpaired_count=10 side_2_annotate_key=gene side_2_concordant_count=78 side_2_discordant_count=1 side_2_unpaired_count=10 -SC 2899 . REL606 2563919 1 agree_read_count=9 clipped_sequence=TACTTTATGTAC consensus_fraction=1.0000 frequency=0.1139 frequency_lower=0.0607 frequency_upper=0.1904 gene_name=yfgA/yfgB gene_position=intergenic (-256/+29) gene_product=hypothetical protein/predicted enzyme gene_strand= locus_tag=ECB_02426 log10_e_value=4.2 read_count=12 reject=FREQUENCY_BELOW_CUTOFF total_count=74 +SC 2899 . REL606 2563919 1 agree_read_count=9 agree_read_count_forward=3 agree_read_count_reverse=6 clipped_sequence=TACTTTATGTAC consensus_fraction=1.0000 fisher_strand_p_value=1.62743e-01 frequency=0.1139 frequency_lower=0.0607 frequency_upper=0.1904 gene_name=yfgA/yfgB gene_position=intergenic (-256/+29) gene_product=hypothetical protein/predicted enzyme gene_strand= locus_tag=ECB_02426 log10_e_value=4.2 read_count=12 reject=FREQUENCY_BELOW_CUTOFF,FISHER_STRAND spanning_read_count_forward=11 spanning_read_count_reverse=51 total_count=74 DP 2901 . REL606 2597727 -1 REL606 2617090 -1 background_e_value=4.424e-05 candidate_discordant_count=7 concordant_count=69.5 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0142 frequency_lower=0.0007 frequency_upper=0.0655 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=62 side_1_discordant_count=1 side_1_unpaired_count=20 side_2_annotate_key=gene side_2_concordant_count=77 side_2_discordant_count=1 side_2_unpaired_count=8 DP 2902 . REL606 2634990 1 REL606 2637845 1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=77.5 discordant_count=3 distinct_discordant_count=3 expected_concordant_count=62.8 frequency=0.0373 frequency_lower=0.0102 frequency_upper=0.0935 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=72 side_1_discordant_count=5 side_1_unpaired_count=13 side_2_annotate_key=gene side_2_concordant_count=83 side_2_discordant_count=3 side_2_unpaired_count=6 DP 2903 . REL606 2650295 1 REL606 3355732 -1 background_e_value=0.000e+00 candidate_discordant_count=17 concordant_count=NA discordant_count=18 distinct_discordant_count=18 expected_concordant_count=62.8 frequency=NA frequency_lower=NA frequency_upper=NA neg_log10_discordance_p_value=2.8 side_1_annotate_key=repeat side_1_concordant_count=0 side_1_discordant_count=18 side_1_gene_name=rrlG side_1_gene_position=noncoding (383/2906 nt) side_1_gene_product=23S ribosomal RNA side_1_gene_strand=< side_1_locus_tag=ECB_r00005 side_1_redundant=1 side_1_unpaired_count=2454 side_2_annotate_key=repeat side_2_concordant_count=0 side_2_discordant_count=18 side_2_gene_name=rrsD side_2_gene_position=noncoding (936/1542 nt) side_2_gene_product=16S ribosomal RNA side_2_gene_strand=< side_2_locus_tag=ECB_r00010 side_2_redundant=1 side_2_unpaired_count=1726 DP 2904 . REL606 2650825 -1 REL606 4148395 -1 background_e_value=0.000e+00 candidate_discordant_count=16 concordant_count=65.0 discordant_count=16 distinct_discordant_count=15 expected_concordant_count=62.8 frequency=0.1875 frequency_lower=0.1193 frequency_upper=0.2739 neg_log10_discordance_p_value=7.0 reject=CONCORDANT_PAIR_SKEW side_1_annotate_key=repeat side_1_concordant_count=0 side_1_discordant_count=16 side_1_gene_name=rrlG/gltW side_1_gene_position=intergenic (-148/+37) side_1_gene_product=23S ribosomal RNA/tRNA-Glu side_1_gene_strand=/> side_2_locus_tag=ECB_t00073/ECB_r00018 side_2_unpaired_count=1878 DP 2905 . REL606 2734913 1 REL606 2736958 1 background_e_value=4.424e-05 candidate_discordant_count=7 concordant_count=82.0 discordant_count=2 distinct_discordant_count=2 expected_concordant_count=62.8 frequency=0.0238 frequency_lower=0.0042 frequency_upper=0.0731 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=87 side_1_discordant_count=2 side_1_unpaired_count=45 side_2_annotate_key=gene side_2_concordant_count=77 side_2_discordant_count=2 side_2_unpaired_count=28 -SC 2906 . REL606 2760104 1 agree_read_count=16 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.8889 frequency=0.3019 frequency_lower=0.1994 frequency_upper=0.4217 gene_name=ygbN gene_position=coding (143/1365 nt) gene_product=predicted transporter gene_strand=> locus_tag=ECB_02590 log10_e_value=11.3 read_count=18 total_count=53 +SC 2906 . REL606 2760104 1 agree_read_count=16 agree_read_count_forward=16 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.8889 fisher_strand_p_value=1.39382e-13 frequency=0.3019 frequency_lower=0.1994 frequency_upper=0.4217 gene_name=ygbN gene_position=coding (143/1365 nt) gene_product=predicted transporter gene_strand=> locus_tag=ECB_02590 log10_e_value=11.3 read_count=18 reject=FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=0 spanning_read_count_reverse=35 total_count=53 DP 2907 . REL606 2778768 -1 REL606 2780857 -1 background_e_value=4.424e-05 candidate_discordant_count=7 concordant_count=82.0 discordant_count=2 distinct_discordant_count=2 expected_concordant_count=62.8 frequency=0.0238 frequency_lower=0.0042 frequency_upper=0.0731 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=86 side_1_discordant_count=2 side_1_unpaired_count=6 side_2_annotate_key=gene side_2_concordant_count=78 side_2_discordant_count=6 side_2_unpaired_count=7 -SC 2908 . REL606 2810116 -1 agree_read_count=8 clipped_sequence=CCCCCCACCCCC consensus_fraction=0.6154 frequency=0.1455 frequency_lower=0.0745 frequency_upper=0.2472 gene_name=gudP gene_position=coding (914/1353 nt) gene_product=predicted D-glucarate transporter gene_strand=< locus_tag=ECB_02634 log10_e_value=2.3 read_count=13 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=55 +SC 2908 . REL606 2810116 -1 agree_read_count=8 agree_read_count_forward=0 agree_read_count_reverse=8 clipped_sequence=CCCCCCACCCCC consensus_fraction=0.6154 fisher_strand_p_value=8.15045e-05 frequency=0.1455 frequency_lower=0.0745 frequency_upper=0.2472 gene_name=gudP gene_position=coding (914/1353 nt) gene_product=predicted D-glucarate transporter gene_strand=< locus_tag=ECB_02634 log10_e_value=2.3 read_count=13 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=32 spanning_read_count_reverse=10 total_count=55 DP 2909 . REL606 2810863 1 REL606 2817219 1 background_e_value=8.698e-07 candidate_discordant_count=8 concordant_count=71.5 discordant_count=3 distinct_discordant_count=3 expected_concordant_count=62.8 frequency=0.0403 frequency_lower=0.0111 frequency_upper=0.1008 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=64 side_1_discordant_count=3 side_1_unpaired_count=4 side_2_annotate_key=gene side_2_concordant_count=79 side_2_discordant_count=3 side_2_unpaired_count=11 -SC 2910 . REL606 2815141 1 agree_read_count=7 clipped_sequence=TCTGGCTGGCAG consensus_fraction=1.0000 frequency=0.0854 frequency_lower=0.0408 frequency_upper=0.1544 log10_e_value=0.1 no_show=1 read_count=7 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=82 -SC 2911 . REL606 2876060 1 agree_read_count=6 clipped_sequence=CTGTCTCTTATA consensus_fraction=1.0000 frequency=0.1277 frequency_lower=0.0571 frequency_upper=0.2365 log10_e_value=0.6 no_show=1 read_count=6 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=47 +SC 2910 . REL606 2815141 1 agree_read_count=7 agree_read_count_forward=5 agree_read_count_reverse=2 clipped_sequence=TCTGGCTGGCAG consensus_fraction=1.0000 fisher_strand_p_value=2.34943e-01 frequency=0.0854 frequency_lower=0.0408 frequency_upper=0.1544 log10_e_value=0.1 no_show=1 read_count=7 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF spanning_read_count_forward=32 spanning_read_count_reverse=43 total_count=82 +SC 2911 . REL606 2876060 1 agree_read_count=6 agree_read_count_forward=6 agree_read_count_reverse=0 clipped_sequence=CTGTCTCTTATA consensus_fraction=1.0000 fisher_strand_p_value=7.37402e-02 frequency=0.1277 frequency_lower=0.0571 frequency_upper=0.2365 log10_e_value=0.6 no_show=1 read_count=6 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF spanning_read_count_forward=24 spanning_read_count_reverse=17 total_count=47 DP 2912 . REL606 2999526 1 REL606 3000546 1 background_e_value=8.698e-07 candidate_discordant_count=8 concordant_count=62.5 discordant_count=5 distinct_discordant_count=5 expected_concordant_count=62.8 frequency=0.0741 frequency_lower=0.0296 frequency_upper=0.1495 neg_log10_discordance_p_value=7.0 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=57 side_1_discordant_count=6 side_1_gene_name=yeeP/flu side_1_gene_position=intergenic (+334/-38) side_1_gene_product=b1999; predicted GTP-binding protein/antigen 43 (Ag43) phase-variable biofilm formation autotransporter side_1_gene_strand=>/> side_1_locus_tag=ECB_02799/ECB_02800 side_1_unpaired_count=31 side_2_annotate_key=gene side_2_concordant_count=68 side_2_discordant_count=5 side_2_gene_name=flu side_2_gene_position=coding (983/2847 nt) side_2_gene_product=antigen 43 (Ag43) phase-variable biofilm formation autotransporter side_2_gene_strand=> side_2_locus_tag=ECB_02800 side_2_unpaired_count=7 DP 2913 . REL606 3029521 1 REL606 3032647 1 background_e_value=4.424e-05 candidate_discordant_count=7 concordant_count=55.0 discordant_count=3 distinct_discordant_count=3 expected_concordant_count=62.8 frequency=0.0517 frequency_lower=0.0142 frequency_upper=0.1283 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=34 side_1_discordant_count=3 side_1_unpaired_count=7 side_2_annotate_key=gene side_2_concordant_count=76 side_2_discordant_count=3 side_2_unpaired_count=10 DP 2914 . REL606 3110419 1 REL606 3113588 1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=72.5 discordant_count=2 distinct_discordant_count=2 expected_concordant_count=62.8 frequency=0.0268 frequency_lower=0.0048 frequency_upper=0.0821 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=85 side_1_discordant_count=2 side_1_unpaired_count=5 side_2_annotate_key=gene side_2_concordant_count=60 side_2_discordant_count=3 side_2_unpaired_count=13 DP 2915 . REL606 3146923 1 REL606 3158086 1 background_e_value=4.424e-05 candidate_discordant_count=7 concordant_count=82.0 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0120 frequency_lower=0.0006 frequency_upper=0.0559 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=87 side_1_discordant_count=1 side_1_unpaired_count=6 side_2_annotate_key=gene side_2_concordant_count=77 side_2_discordant_count=1 side_2_unpaired_count=4 DP 2916 . REL606 3177019 1 REL606 3185969 1 background_e_value=8.698e-07 candidate_discordant_count=8 concordant_count=52.0 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0189 frequency_lower=0.0010 frequency_upper=0.0864 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=68 side_1_discordant_count=1 side_1_unpaired_count=8 side_2_annotate_key=gene side_2_concordant_count=36 side_2_discordant_count=1 side_2_unpaired_count=6 DP 2917 . REL606 3183316 -1 REL606 3194008 -1 background_e_value=4.424e-05 candidate_discordant_count=7 concordant_count=78.5 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0126 frequency_lower=0.0006 frequency_upper=0.0583 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=90 side_1_discordant_count=1 side_1_unpaired_count=7 side_2_annotate_key=gene side_2_concordant_count=67 side_2_discordant_count=1 side_2_unpaired_count=15 -SC 2918 . REL606 3188283 1 agree_read_count=7 clipped_sequence=GGGTTGTTTAAT consensus_fraction=1.0000 frequency=0.1429 frequency_lower=0.0690 frequency_upper=0.2516 gene_name=yhaL/yhaM gene_position=intergenic (+43/+91) gene_product=hypothetical protein/hypothetical protein gene_strand=>/< locus_tag=ECB_02976/ECB_02977 log10_e_value=1.6 read_count=7 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=49 -SC 2919 . REL606 3227843 1 agree_read_count=6 clipped_sequence=GGAGGGTTTTTT consensus_fraction=0.2727 frequency=0.1176 frequency_lower=0.0525 frequency_upper=0.2191 log10_e_value=0.4 no_show=1 read_count=22 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,CLIPPED_TAIL_CONSENSUS total_count=51 -SC 2920 . REL606 3241374 -1 agree_read_count=11 clipped_sequence=AACCCCCCCCCC consensus_fraction=0.6111 frequency=0.2292 frequency_lower=0.1342 frequency_upper=0.3507 gene_name=deaD gene_position=coding (1721/1890 nt) gene_product=ATP-dependent RNA helicase gene_strand=< locus_tag=ECB_03029 log10_e_value=6.2 read_count=18 total_count=48 +SC 2918 . REL606 3188283 1 agree_read_count=7 agree_read_count_forward=1 agree_read_count_reverse=6 clipped_sequence=GGGTTGTTTAAT consensus_fraction=1.0000 fisher_strand_p_value=2.38346e-01 frequency=0.1429 frequency_lower=0.0690 frequency_upper=0.2516 log10_e_value=1.6 no_show=1 read_count=7 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF spanning_read_count_forward=17 spanning_read_count_reverse=25 total_count=49 +SC 2919 . REL606 3227843 1 agree_read_count=6 agree_read_count_forward=6 agree_read_count_reverse=0 clipped_sequence=GGAGGGTTTTTT consensus_fraction=0.2727 fisher_strand_p_value=3.08349e-03 frequency=0.1176 frequency_lower=0.0525 frequency_upper=0.2191 log10_e_value=0.4 no_show=1 read_count=22 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,CLIPPED_TAIL_CONSENSUS,FISHER_STRAND spanning_read_count_forward=9 spanning_read_count_reverse=20 total_count=51 +SC 2920 . REL606 3241374 -1 agree_read_count=11 agree_read_count_forward=0 agree_read_count_reverse=11 clipped_sequence=AACCCCCCCCCC consensus_fraction=0.6111 fisher_strand_p_value=3.79812e-09 frequency=0.2292 frequency_lower=0.1342 frequency_upper=0.3507 gene_name=deaD gene_position=coding (1721/1890 nt) gene_product=ATP-dependent RNA helicase gene_strand=< locus_tag=ECB_03029 log10_e_value=6.2 read_count=18 reject=FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=29 spanning_read_count_reverse=1 total_count=48 DP 2921 . REL606 3251621 -1 REL606 3265313 -1 background_e_value=4.424e-05 candidate_discordant_count=7 concordant_count=59.5 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0165 frequency_lower=0.0008 frequency_upper=0.0760 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=68 side_1_discordant_count=1 side_1_unpaired_count=7 side_2_annotate_key=gene side_2_concordant_count=51 side_2_discordant_count=1 side_2_unpaired_count=16 DP 2922 . REL606 3282659 1 REL606 3288559 1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=71.5 discordant_count=3 distinct_discordant_count=3 expected_concordant_count=62.8 frequency=0.0403 frequency_lower=0.0111 frequency_upper=0.1008 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=78 side_1_discordant_count=3 side_1_unpaired_count=14 side_2_annotate_key=gene side_2_concordant_count=65 side_2_discordant_count=3 side_2_unpaired_count=4 -SC 2923 . REL606 3325442 -1 agree_read_count=8 clipped_sequence=TTTTTTTCCCCC consensus_fraction=0.6154 frequency=0.1333 frequency_lower=0.0681 frequency_upper=0.2277 gene_name=rng gene_position=coding (245/1470 nt) gene_product=ribonuclease G gene_strand=< locus_tag=ECB_03106 log10_e_value=2.0 read_count=13 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=60 -SC 2924 . REL606 3374158 -1 agree_read_count=6 clipped_sequence=CCCCCCCCCCCC consensus_fraction=0.5455 frequency=0.1463 frequency_lower=0.0657 frequency_upper=0.2685 log10_e_value=0.9 no_show=1 read_count=11 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=41 +SC 2923 . REL606 3325442 -1 agree_read_count=8 agree_read_count_forward=0 agree_read_count_reverse=8 clipped_sequence=TTTTTTTCCCCC consensus_fraction=0.6154 fisher_strand_p_value=8.88309e-04 frequency=0.1333 frequency_lower=0.0681 frequency_upper=0.2277 gene_name=rng gene_position=coding (245/1470 nt) gene_product=ribonuclease G gene_strand=< locus_tag=ECB_03106 log10_e_value=2.0 read_count=13 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND spanning_read_count_forward=30 spanning_read_count_reverse=17 total_count=60 +SC 2924 . REL606 3374158 -1 agree_read_count=6 agree_read_count_forward=0 agree_read_count_reverse=6 clipped_sequence=CCCCCCCCCCCC consensus_fraction=0.5455 fisher_strand_p_value=5.13402e-07 frequency=0.1463 frequency_lower=0.0657 frequency_upper=0.2685 log10_e_value=0.9 no_show=1 read_count=11 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=30 spanning_read_count_reverse=0 total_count=41 DP 2925 . REL606 3452461 1 REL606 3455327 1 background_e_value=4.424e-05 candidate_discordant_count=7 concordant_count=64.0 discordant_count=2 distinct_discordant_count=2 expected_concordant_count=62.8 frequency=0.0303 frequency_lower=0.0054 frequency_upper=0.0923 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=52 side_1_discordant_count=3 side_1_unpaired_count=12 side_2_annotate_key=gene side_2_concordant_count=76 side_2_discordant_count=2 side_2_unpaired_count=1 -SC 2926 . REL606 3568056 -1 agree_read_count=5 clipped_sequence=AAAAAAAACCCC consensus_fraction=0.3846 frequency=0.1429 frequency_lower=0.0580 frequency_upper=0.2772 log10_e_value=0.1 no_show=1 read_count=13 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,CLIPPED_TAIL_CONSENSUS total_count=35 -SC 2927 . REL606 3571666 1 agree_read_count=6 clipped_sequence=GTTTTTTTTTTT consensus_fraction=0.8571 frequency=0.1053 frequency_lower=0.0468 frequency_upper=0.1972 log10_e_value=0.1 no_show=1 read_count=7 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=57 -SC 2928 . REL606 3595625 1 agree_read_count=6 clipped_sequence=CTTTAAAAAAAC consensus_fraction=1.0000 frequency=0.1053 frequency_lower=0.0468 frequency_upper=0.1972 log10_e_value=0.1 no_show=1 read_count=6 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=57 -SC 2929 . REL606 3595639 -1 agree_read_count=7 clipped_sequence=TTTAAAAAAACA consensus_fraction=1.0000 frequency=0.1186 frequency_lower=0.0570 frequency_upper=0.2113 log10_e_value=1.1 no_show=1 read_count=7 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=59 +SC 2926 . REL606 3568056 -1 agree_read_count=5 agree_read_count_forward=0 agree_read_count_reverse=5 clipped_sequence=AAAAAAAACCCC consensus_fraction=0.3846 fisher_strand_p_value=6.93670e-04 frequency=0.1429 frequency_lower=0.0580 frequency_upper=0.2772 log10_e_value=0.1 no_show=1 read_count=13 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,CLIPPED_TAIL_CONSENSUS,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=19 spanning_read_count_reverse=3 total_count=35 +SC 2927 . REL606 3571666 1 agree_read_count=6 agree_read_count_forward=6 agree_read_count_reverse=0 clipped_sequence=GTTTTTTTTTTT consensus_fraction=0.8571 fisher_strand_p_value=2.32065e-02 frequency=0.1053 frequency_lower=0.0468 frequency_upper=0.1972 log10_e_value=0.1 no_show=1 read_count=7 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=22 spanning_read_count_reverse=28 total_count=57 +SC 2928 . REL606 3595625 1 agree_read_count=6 agree_read_count_forward=0 agree_read_count_reverse=6 clipped_sequence=CTTTAAAAAAAC consensus_fraction=1.0000 fisher_strand_p_value=2.66343e-02 frequency=0.1053 frequency_lower=0.0468 frequency_upper=0.1972 log10_e_value=0.1 no_show=1 read_count=6 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND spanning_read_count_forward=26 spanning_read_count_reverse=25 total_count=57 +SC 2929 . REL606 3595639 -1 agree_read_count=7 agree_read_count_forward=6 agree_read_count_reverse=1 clipped_sequence=TTTAAAAAAACA consensus_fraction=1.0000 fisher_strand_p_value=1.11955e-01 frequency=0.1186 frequency_lower=0.0570 frequency_upper=0.2113 log10_e_value=1.1 no_show=1 read_count=7 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF spanning_read_count_forward=26 spanning_read_count_reverse=26 total_count=59 DP 2930 . REL606 3629394 1 REL606 3630691 -1 background_e_value=0.000e+00 candidate_discordant_count=36 concordant_count=71.0 discordant_count=36 distinct_discordant_count=35 expected_concordant_count=62.8 frequency=0.3302 frequency_lower=0.2547 frequency_upper=0.4130 neg_log10_discordance_p_value=1.5 side_1_annotate_key=gene side_1_concordant_count=80 side_1_discordant_count=36 side_1_gene_name=yhjU/ldrD side_1_gene_position=intergenic (+9/+78) side_1_gene_product=predicted inner membrane protein/toxic polypeptide, small side_1_gene_strand=>/< side_1_locus_tag=ECB_03386/ECB_03387 side_1_unpaired_count=26 side_2_annotate_key=gene side_2_concordant_count=62 side_2_discordant_count=36 side_2_gene_name=ldrD/yhjV side_2_gene_position=intergenic (-146/-330) side_2_gene_product=toxic polypeptide, small/predicted transporter side_2_gene_strand= side_2_locus_tag=ECB_03389/ECB_03390 side_2_unpaired_count=24 PD 2931 . REL606 3630056 -1 REL606 3630493 1 ambiguous_pair_count=22 candidate_covering_count=96 distinct_pair_count=63 frequency=0.8514 frequency_lower=0.7660 frequency_upper=0.9143 normal_pair_count=11 position_range=42 score=23.3 seed_z_score=14.44 shifted_pair_count=63 side_1_annotate_key=gene side_1_gene_name=ldrD side_1_gene_position=coding (7/108 nt) side_1_gene_product=toxic polypeptide, small side_1_gene_strand=< side_1_locus_tag=ECB_03388 side_2_annotate_key=gene side_2_gene_name=ldrD side_2_gene_position=coding (53/108 nt) side_2_gene_product=toxic polypeptide, small side_2_gene_strand=< side_2_locus_tag=ECB_03389 size_shift=436 size_shift_lower=394 size_shift_upper=468 total_pair_count=96 -SC 2932 . REL606 3630081 1 agree_read_count=4 clipped_sequence=CTGTCTCTTATA consensus_fraction=1.0000 frequency=0.2667 frequency_lower=0.0967 frequency_upper=0.5108 log10_e_value=0.3 no_show=1 read_count=4 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=15 +SC 2932 . REL606 3630081 1 agree_read_count=4 agree_read_count_forward=4 agree_read_count_reverse=0 clipped_sequence=CTGTCTCTTATA consensus_fraction=1.0000 fisher_strand_p_value=1.09890e-02 frequency=0.2667 frequency_lower=0.0967 frequency_upper=0.5108 log10_e_value=0.3 no_show=1 read_count=4 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND spanning_read_count_forward=2 spanning_read_count_reverse=9 total_count=15 DP 2933 . REL606 3660120 -1 REL606 3665608 -1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=63.0 discordant_count=3 distinct_discordant_count=2 expected_concordant_count=62.8 frequency=0.0308 frequency_lower=0.0055 frequency_upper=0.0937 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=69 side_1_discordant_count=3 side_1_unpaired_count=7 side_2_annotate_key=gene side_2_concordant_count=57 side_2_discordant_count=3 side_2_unpaired_count=18 DP 2934 . REL606 3700198 -1 REL606 3701969 1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=83.0 discordant_count=6 distinct_discordant_count=6 expected_concordant_count=62.8 frequency=0.0674 frequency_lower=0.0298 frequency_upper=0.1287 neg_log10_discordance_p_value=7.0 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=82 side_1_discordant_count=6 side_1_gene_name=rhsA side_1_gene_position=coding (3322/4134 nt) side_1_gene_product=rhsA element core protein RshA side_1_gene_strand=> side_1_locus_tag=ECB_03448 side_1_unpaired_count=325 side_2_annotate_key=gene side_2_concordant_count=84 side_2_discordant_count=6 side_2_gene_name=yibJ side_2_gene_position=coding (55/945 nt) side_2_gene_product=predicted Rhs-family protein side_2_gene_strand=> side_2_locus_tag=ECB_03450 side_2_unpaired_count=10 DP 2935 . REL606 3741198 1 REL606 4503628 1 background_e_value=0.000e+00 candidate_discordant_count=58 concordant_count=75.0 discordant_count=59 distinct_discordant_count=57 expected_concordant_count=62.8 frequency=0.4318 frequency_lower=0.3588 frequency_upper=0.5071 neg_log10_discordance_p_value=0.5 side_1_annotate_key=repeat side_1_concordant_count=54 side_1_discordant_count=59 side_1_gene_name=IS1 side_1_gene_position=noncoding (768/768 nt) side_1_gene_product=repeat region side_1_gene_strand=< side_1_redundant=1 side_1_unpaired_count=1677 side_2_annotate_key=gene side_2_concordant_count=75 side_2_discordant_count=59 side_2_gene_name=IS1 side_2_gene_position=noncoding (125/768 nt) side_2_gene_product=repeat region side_2_gene_strand=> side_2_unpaired_count=620 @@ -2950,15 +2950,15 @@ DP 2936 . REL606 3741418 -1 REL606 4507747 -1 background_e_value=0.000e+00 candi DP 2937 . REL606 3749772 -1 REL606 3757007 -1 background_e_value=8.698e-07 candidate_discordant_count=8 concordant_count=64.5 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0153 frequency_lower=0.0008 frequency_upper=0.0704 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=61 side_1_discordant_count=1 side_1_unpaired_count=20 side_2_annotate_key=gene side_2_concordant_count=68 side_2_discordant_count=3 side_2_unpaired_count=4 DP 2938 . REL606 3801347 1 REL606 3814445 1 background_e_value=8.698e-07 candidate_discordant_count=8 concordant_count=44.0 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0222 frequency_lower=0.0011 frequency_upper=0.1011 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=30 side_1_discordant_count=1 side_1_unpaired_count=8 side_2_annotate_key=gene side_2_concordant_count=58 side_2_discordant_count=1 side_2_unpaired_count=8 DP 2939 . REL606 3813099 -1 REL606 3815901 -1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=47.0 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0208 frequency_lower=0.0011 frequency_upper=0.0951 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=37 side_1_discordant_count=1 side_1_unpaired_count=5 side_2_annotate_key=gene side_2_concordant_count=57 side_2_discordant_count=1 side_2_unpaired_count=25 -SC 2940 . REL606 3837247 1 agree_read_count=15 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.4839 frequency=0.2239 frequency_lower=0.1434 frequency_upper=0.3236 gene_name=yidA gene_position=coding (67/813 nt) gene_product=predicted hydrolase gene_strand=< locus_tag=ECB_03580 log10_e_value=8.6 read_count=31 reject=CLIPPED_TAIL_CONSENSUS total_count=67 -SC 2941 . REL606 3886728 -1 agree_read_count=8 clipped_sequence=TGGGTGAAAAAC consensus_fraction=0.7273 frequency=0.1778 frequency_lower=0.0917 frequency_upper=0.2980 gene_name=mioC gene_position=coding (89/444 nt) gene_product=flavodoxin gene_strand=< locus_tag=ECB_03626 log10_e_value=3.0 read_count=11 reject=FREQUENCY_BELOW_CUTOFF total_count=45 +SC 2940 . REL606 3837247 1 agree_read_count=15 agree_read_count_forward=15 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.4839 fisher_strand_p_value=5.01776e-12 frequency=0.2239 frequency_lower=0.1434 frequency_upper=0.3236 gene_name=yidA gene_position=coding (67/813 nt) gene_product=predicted hydrolase gene_strand=< locus_tag=ECB_03580 log10_e_value=8.6 read_count=31 reject=CLIPPED_TAIL_CONSENSUS,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=1 spanning_read_count_reverse=35 total_count=67 +SC 2941 . REL606 3886728 -1 agree_read_count=8 agree_read_count_forward=0 agree_read_count_reverse=8 clipped_sequence=TGGGTGAAAAAC consensus_fraction=0.7273 fisher_strand_p_value=6.60195e-03 frequency=0.1778 frequency_lower=0.0917 frequency_upper=0.2980 gene_name=mioC gene_position=coding (89/444 nt) gene_product=flavodoxin gene_strand=< locus_tag=ECB_03626 log10_e_value=3.0 read_count=11 reject=FREQUENCY_BELOW_CUTOFF,FISHER_STRAND spanning_read_count_forward=18 spanning_read_count_reverse=16 total_count=45 DP 2942 . REL606 3903112 -1 REL606 4146173 1 background_e_value=0.000e+00 candidate_discordant_count=16 concordant_count=37.0 discordant_count=13 distinct_discordant_count=13 expected_concordant_count=62.8 frequency=0.2600 frequency_lower=0.1612 frequency_upper=0.3813 neg_log10_discordance_p_value=7.0 reject=CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=18 side_1_discordant_count=13 side_1_gene_name=yieP side_1_gene_position=coding (23/693 nt) side_1_gene_product=predicted transcriptional regulator side_1_gene_strand=< side_1_locus_tag=ECB_03641 side_1_unpaired_count=62 side_2_annotate_key=gene side_2_concordant_count=56 side_2_discordant_count=13 side_2_gene_name=murI/rrsB side_2_gene_position=intergenic (+27/-347) side_2_gene_product=glutamate racemase/16S ribosomal RNA side_2_gene_strand=>/> side_2_locus_tag=ECB_03852/ECB_r00017 side_2_unpaired_count=1884 DP 2943 . REL606 3903382 -1 REL606 4013647 1 background_e_value=0.000e+00 candidate_discordant_count=20 concordant_count=20.0 discordant_count=20 distinct_discordant_count=20 expected_concordant_count=62.8 frequency=0.5000 frequency_lower=0.3611 frequency_upper=0.6389 neg_log10_discordance_p_value=2.6 side_1_annotate_key=gene side_1_concordant_count=20 side_1_discordant_count=20 side_1_gene_name=yieP/rrsC side_1_gene_position=intergenic (-248/-233) side_1_gene_product=predicted transcriptional regulator/16S ribosomal RNA side_1_gene_strand= side_1_locus_tag=ECB_03641/ECB_r00011 side_1_unpaired_count=8 side_2_annotate_key=repeat side_2_concordant_count=67 side_2_discordant_count=20 side_2_gene_name=hemG/rrsA side_2_gene_position=intergenic (+121/-257) side_2_gene_product=protoporphyrin oxidase, flavoprotein/16S ribosomal RNA side_2_gene_strand=>/> side_2_locus_tag=ECB_03741/ECB_r00014 side_2_redundant=1 side_2_unpaired_count=1954 DP 2944 . REL606 3938151 1 REL606 3949921 1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=50.5 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0194 frequency_lower=0.0010 frequency_upper=0.0888 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=44 side_1_discordant_count=1 side_1_unpaired_count=17 side_2_annotate_key=gene side_2_concordant_count=57 side_2_discordant_count=1 side_2_unpaired_count=10 DP 2945 . REL606 3956725 1 REL606 3957398 1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=78.5 discordant_count=3 distinct_discordant_count=3 expected_concordant_count=62.8 frequency=0.0368 frequency_lower=0.0101 frequency_upper=0.0924 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=86 side_1_discordant_count=5 side_1_unpaired_count=25 side_2_annotate_key=gene side_2_concordant_count=71 side_2_discordant_count=5 side_2_unpaired_count=25 DP 2946 . REL606 3969066 1 REL606 3970137 1 background_e_value=4.424e-05 candidate_discordant_count=7 concordant_count=51.0 discordant_count=5 distinct_discordant_count=5 expected_concordant_count=62.8 frequency=0.0893 frequency_lower=0.0358 frequency_upper=0.1786 neg_log10_discordance_p_value=7.0 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=48 side_1_discordant_count=8 side_1_gene_name=yigI side_1_gene_position=coding (67/468 nt) side_1_gene_product=hypothetical protein side_1_gene_strand=< side_1_locus_tag=ECB_03699 side_1_unpaired_count=23 side_2_annotate_key=gene side_2_concordant_count=54 side_2_discordant_count=6 side_2_gene_name=pldA side_2_gene_position=coding (841/870 nt) side_2_gene_product=outer membrane phospholipase A side_2_gene_strand=> side_2_locus_tag=ECB_03700 side_2_unpaired_count=9 DP 2947 . REL606 4041644 1 REL606 4048860 1 background_e_value=1.520e-08 candidate_discordant_count=9 concordant_count=65.0 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0152 frequency_lower=0.0008 frequency_upper=0.0699 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=88 side_1_discordant_count=1 side_1_unpaired_count=6 side_2_annotate_key=gene side_2_concordant_count=42 side_2_discordant_count=1 side_2_unpaired_count=4 -SC 2948 . REL606 4117714 1 agree_read_count=5 clipped_sequence=GGGGTGGGGAAA consensus_fraction=1.0000 frequency=0.1724 frequency_lower=0.0705 frequency_upper=0.3289 log10_e_value=0.5 no_show=1 read_count=5 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF total_count=29 +SC 2948 . REL606 4117714 1 agree_read_count=5 agree_read_count_forward=5 agree_read_count_reverse=0 clipped_sequence=GGGGTGGGGAAA consensus_fraction=1.0000 fisher_strand_p_value=1.76835e-04 frequency=0.1724 frequency_lower=0.0705 frequency_upper=0.3289 log10_e_value=0.5 no_show=1 read_count=5 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,FISHER_STRAND spanning_read_count_forward=2 spanning_read_count_reverse=22 total_count=29 DP 2949 . REL606 4180404 1 REL606 4181031 1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=71.5 discordant_count=4 distinct_discordant_count=3 expected_concordant_count=62.8 frequency=0.0403 frequency_lower=0.0111 frequency_upper=0.1008 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=84 side_1_discordant_count=6 side_1_unpaired_count=5 side_2_annotate_key=gene side_2_concordant_count=59 side_2_discordant_count=6 side_2_unpaired_count=5 DP 2950 . REL606 4206354 1 REL606 4220409 1 background_e_value=1.520e-08 candidate_discordant_count=9 concordant_count=64.0 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0154 frequency_lower=0.0008 frequency_upper=0.0709 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=81 side_1_discordant_count=1 side_1_unpaired_count=11 side_2_annotate_key=gene side_2_concordant_count=47 side_2_discordant_count=1 side_2_unpaired_count=8 DP 2951 . REL606 4222194 1 REL606 4232332 1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=58.0 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0169 frequency_lower=0.0009 frequency_upper=0.0779 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=59 side_1_discordant_count=1 side_1_unpaired_count=9 side_2_annotate_key=gene side_2_concordant_count=57 side_2_discordant_count=1 side_2_unpaired_count=7 @@ -2966,9 +2966,9 @@ DP 2952 . REL606 4262700 1 REL606 4269212 1 background_e_value=1.520e-08 candida DP 2953 . REL606 4266289 -1 REL606 4276507 -1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=63.0 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0156 frequency_lower=0.0008 frequency_upper=0.0720 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=60 side_1_discordant_count=1 side_1_unpaired_count=22 side_2_annotate_key=gene side_2_concordant_count=66 side_2_discordant_count=1 side_2_unpaired_count=63 PD 2954 . REL606 4274838 -1 REL606 4275047 1 ambiguous_pair_count=51 candidate_covering_count=83 distinct_pair_count=22 frequency=0.8800 frequency_lower=0.7183 frequency_upper=0.9665 normal_pair_count=3 position_range=51 score=5.4 seed_z_score=8.68 shifted_pair_count=22 side_1_annotate_key=gene side_1_gene_name=gltP/yjcO side_1_gene_position=intergenic (+111/+420) side_1_gene_product=glutamate/aspartate:proton symporter/hypothetical protein side_1_gene_strand=>/< side_1_locus_tag=ECB_03949/ECB_03950 side_2_annotate_key=gene side_2_gene_name=gltP/yjcO side_2_gene_position=intergenic (+320/+211) side_2_gene_product=glutamate/aspartate:proton symporter/hypothetical protein side_2_gene_strand=>/< side_2_locus_tag=ECB_03949/ECB_03950 size_shift=208 size_shift_lower=175 size_shift_upper=281 total_pair_count=76 DP 2955 . REL606 4414143 1 REL606 4414553 1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=66.5 discordant_count=4 distinct_discordant_count=4 expected_concordant_count=62.8 frequency=0.0567 frequency_lower=0.0196 frequency_upper=0.1251 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=75 side_1_discordant_count=7 side_1_unpaired_count=9 side_2_annotate_key=gene side_2_concordant_count=58 side_2_discordant_count=6 side_2_unpaired_count=10 -SC 2956 . REL606 4437551 1 agree_read_count=14 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.8750 frequency=0.1944 frequency_lower=0.1216 frequency_upper=0.2872 gene_name=yjfF gene_position=coding (719/996 nt) gene_product=predicted sugar transporter subunit: membrane component of ABC superfamily gene_strand=> locus_tag=ECB_04099 log10_e_value=7.2 read_count=16 total_count=72 -SC 2957 . REL606 4455506 1 agree_read_count=6 clipped_sequence=GGGGGGGGGAGG consensus_fraction=0.4000 frequency=0.1714 frequency_lower=0.0774 frequency_upper=0.3106 gene_name=pyrB gene_position=coding (167/936 nt) gene_product=aspartate carbamoyltransferase catalytic subunit gene_strand=< locus_tag=ECB_04113 log10_e_value=1.4 read_count=15 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,CLIPPED_TAIL_CONSENSUS total_count=35 -SC 2958 . REL606 4504257 1 agree_read_count=26 clipped_sequence=CTGTCTCTTATA consensus_fraction=1.0000 frequency=0.1436 frequency_lower=0.1026 frequency_upper=0.1937 gene_name=IS1 gene_position=noncoding (754/768 nt) gene_product=repeat region gene_strand=> log10_e_value=9.5 read_count=26 total_count=181 +SC 2956 . REL606 4437551 1 agree_read_count=14 agree_read_count_forward=14 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGGGGG consensus_fraction=0.8750 fisher_strand_p_value=6.01696e-10 frequency=0.1944 frequency_lower=0.1216 frequency_upper=0.2872 gene_name=yjfF gene_position=coding (719/996 nt) gene_product=predicted sugar transporter subunit: membrane component of ABC superfamily gene_strand=> locus_tag=ECB_04099 log10_e_value=7.2 read_count=16 reject=FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=7 spanning_read_count_reverse=49 total_count=72 +SC 2957 . REL606 4455506 1 agree_read_count=6 agree_read_count_forward=6 agree_read_count_reverse=0 clipped_sequence=GGGGGGGGGAGG consensus_fraction=0.4000 fisher_strand_p_value=4.34348e-06 frequency=0.1714 frequency_lower=0.0774 frequency_upper=0.3106 log10_e_value=1.4 no_show=1 read_count=15 reject=SCORE_CUTOFF,FREQUENCY_BELOW_CUTOFF,CLIPPED_TAIL_CONSENSUS,FISHER_STRAND,LOW_COMPLEXITY_TAIL spanning_read_count_forward=0 spanning_read_count_reverse=20 total_count=35 +SC 2958 . REL606 4504257 1 agree_read_count=26 agree_read_count_forward=26 agree_read_count_reverse=0 clipped_sequence=CTGTCTCTTATA consensus_fraction=1.0000 fisher_strand_p_value=1.09664e-09 frequency=0.1436 frequency_lower=0.1026 frequency_upper=0.1937 gene_name=IS1 gene_position=noncoding (754/768 nt) gene_product=repeat region gene_strand=> log10_e_value=9.5 read_count=26 reject=FISHER_STRAND spanning_read_count_forward=63 spanning_read_count_reverse=92 total_count=181 DP 2959 . REL606 4540407 1 REL606 4547981 1 background_e_value=8.698e-07 candidate_discordant_count=8 concordant_count=58.5 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0168 frequency_lower=0.0009 frequency_upper=0.0773 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=50 side_1_discordant_count=1 side_1_unpaired_count=8 side_2_annotate_key=gene side_2_concordant_count=67 side_2_discordant_count=1 side_2_unpaired_count=16 DP 2960 . REL606 4582964 -1 REL606 4588135 -1 background_e_value=1.970e-03 candidate_discordant_count=6 concordant_count=70.5 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0140 frequency_lower=0.0007 frequency_upper=0.0646 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=61 side_1_discordant_count=1 side_1_unpaired_count=10 side_2_annotate_key=gene side_2_concordant_count=80 side_2_discordant_count=1 side_2_unpaired_count=3 DP 2961 . REL606 4606941 -1 REL606 4614488 -1 background_e_value=8.698e-07 candidate_discordant_count=8 concordant_count=90.0 discordant_count=1 distinct_discordant_count=1 expected_concordant_count=62.8 frequency=0.0110 frequency_lower=0.0006 frequency_upper=0.0511 neg_log10_discordance_p_value=7.0 no_show=1 reject=DISCORDANT_PAIR_FREQUENCY,CONCORDANT_PAIR_SKEW side_1_annotate_key=gene side_1_concordant_count=111 side_1_discordant_count=1 side_1_unpaired_count=17 side_2_annotate_key=gene side_2_concordant_count=69 side_2_discordant_count=1 side_2_unpaired_count=7