diff --git a/README.md b/README.md index d6107a2..50d937d 100644 --- a/README.md +++ b/README.md @@ -106,7 +106,7 @@ Modify the conf/references.config file to specify your genome files ## Reference Genomes Pre-built reference genomes with methylation spike-in controls + CpG Island Annotation files: - **T2T CHM13**: [T2T_chm13v2.0+ meth_controls](https://neb-em-seq-sra.s3.us-east-1.amazonaws.com/T2T_chm13v2.0%2Bmeth_controls.fa.gz) [CpG Islands](https://neb-em-seq-sra.s3.us-east-1.amazonaws.com/human_t2t_cpg_islands.gtf) -- **GRCh38**: [GRCh39 + meth controls](https://neb-em-seq-sra.s3.us-east-1.amazonaws.com/grch38_core%2Bmeth_controls.fa.gz) [CpG Islands](https://neb-em-seq-sra.s3.us-east-1.amazonaws.com/human_grch38_cpg_islands.gtf) +- **GRCh38**: [GRCh38 + meth controls](https://neb-em-seq-sra.s3.us-east-1.amazonaws.com/grch38_core%2Bmeth_controls.fa.gz) [CpG Islands](https://neb-em-seq-sra.s3.us-east-1.amazonaws.com/human_grch38_cpg_islands.gtf) - **GRCm39**: [GRCm39 + meth_controls](https://neb-em-seq-sra.s3.us-east-1.amazonaws.com/grcm39%2Bmeth_controls.fa.gz) [CpG Islands](https://neb-em-seq-sra.s3.us-east-1.amazonaws.com/grcm39_cpg_islands.gtf) - Create your own reference by appending the [control sequences](assets/methylation_controls.fa) to your preferred genome fasta (e.g. `cat genome.fa methylation_controls.fa > genome+methylation_controls.fa`) | Sequence | Methylation State | Purpose | diff --git a/main.nf b/main.nf index 0b15f53..6b65c16 100644 --- a/main.nf +++ b/main.nf @@ -1,3 +1,4 @@ +// Nextflow v24 or older only: uncomment the line below (see README's Upgrade section) // nextflow.preview.topic = true include { registerEmailNotifications } from './lib/notifications.nf' diff --git a/modules/tasmanian.nf b/modules/tasmanian.nf index 9441c36..d0e8ec5 100644 --- a/modules/tasmanian.nf +++ b/modules/tasmanian.nf @@ -2,7 +2,7 @@ process tasmanian { label 'medium_cpu' tag { library } publishDir "${params.outputDir}/stats/tasmanian" - conda "bioconda::samtools=1.22 bioconda::tasmanian-mismatch=1.0.9" + conda "bioconda::tasmanian-mismatch=2.0.5" errorStrategy { task.attempt <= 1 ? 'retry' : 'terminate' } maxRetries 1 @@ -15,14 +15,18 @@ process tasmanian { output: tuple val(library), path("${library}.tasmanian.csv"), emit: for_agg - tuple val("${task.process}"), val('samtools'), eval('samtools --version | head -n 1 | sed \'s/^samtools //\''), topic: versions - tuple val("${task.process}"), val('tasmanian'), val('*should be* 1.0.9'), topic: versions + tuple val("${task.process}"), val('tasmanian-mismatch'), val('2.0.5'), topic: versions script: """ set +e set +o pipefail - samtools view -q 30 -F 3840 ${bam} | head -n 2000000 | run_tasmanian -r ${genome_fa} > ${library}.tasmanian.csv + tasmanian-mismatch ${bam} ${genome_fa} \ + --position-mode read \ + --min-base-quality 20 \ + --min-map-quality 30 \ + -F 3840 \ + -o ${library}.tasmanian.csv """ }