diff --git a/01_GitHub/data/SRR1039508_R1.fastq.gz b/01_GitHub/data/SRR1039508_R1.fastq.gz deleted file mode 100644 index 199e1f7..0000000 Binary files a/01_GitHub/data/SRR1039508_R1.fastq.gz and /dev/null differ diff --git a/01_GitHub/data/SRR1039508_R2.fastq.gz b/01_GitHub/data/SRR1039508_R2.fastq.gz deleted file mode 100644 index f9f7bd8..0000000 Binary files a/01_GitHub/data/SRR1039508_R2.fastq.gz and /dev/null differ diff --git a/01_GitHub/scripts/03-annotation.sh b/01_GitHub/scripts/03-annotation.sh index 1d002e2..809b89f 100644 --- a/01_GitHub/scripts/03-annotation.sh +++ b/01_GitHub/scripts/03-annotation.sh @@ -14,25 +14,17 @@ echo "Running annotation against database of glucocorticoid-responsive genes" for FILE in "$READS_DIR"/*.fastq.gz; do - echo "Annotating file: $FILE" - - # GROUP 3 - WRITE HERE THE COMMAND TO RUN DIAMOND BLASTX - # READS ARE GZIPPED AT $READS_DIR - # OUTPUT SHOULD GO TO $RESULTS_DIR, WITH FILENAME FORMAT: sample_matches.tab - # USE $DB AS THE DIAMOND DATABASE, $THREADS FOR THREADS, AND $MAX_TARGET_SEQS FOR MAX TARGET SEQS - # OUTFMT SHOULD BE 6 (TABULAR) - # tips below - + diamond blastx -d "$DB" -q "$FILE" -o "$RESULTS_DIR"/$(basename "$FILE" .fastq.gz)_matches.tab --threads "$THREADS" --max-target-seqs "$MAX_TARGET_SEQS" --outfmt 6 done + + # check if 12 annotation results were generated, and exit code 1 if not if [ $(ls "$RESULTS_DIR"/*_matches.tab | wc -l) -ne $N_FILES ]; then echo "Error: Not all annotation results were generated. Expected $N_FILES, but found $(ls "$RESULTS_DIR"/*_matches.tab | wc -l)." exit 1 fi -# tip: $(basename "$FILE" .fastq.gz) extracts the sample name from the filename by removing the directory path and the .fastq.gz extension - echo "Annotation complete" \ No newline at end of file diff --git a/test_output/SRR1039508_R1_matches.tab b/test_output/SRR1039508_R1_matches.tab new file mode 100644 index 0000000..e69de29 diff --git a/test_output/SRR1039509_R1_matches.tab b/test_output/SRR1039509_R1_matches.tab new file mode 100644 index 0000000..e69de29