Merge branch 'develop' into feature/make_cff

mskcc · Aug 2, 2023 · 5bfb0d3 · 5bfb0d3
2 parents 452bba0 + b53bb98
commit 5bfb0d3
Show file tree

Hide file tree

Showing 19 changed files with 351 additions and 53 deletions.
diff --git a/.github/workflows/pytest-workflow.yml b/.github/workflows/pytest-workflow.yml
@@ -11,6 +11,7 @@ concurrency:
 jobs:
   test:
     runs-on: ubuntu-20.04
+    timeout-minutes: 45
 
     name: ${{ matrix.tags }} ${{ matrix.profile }}
     strategy:

diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml
@@ -2,3 +2,6 @@ show_analysis_paths: False
 extra_fn_clean_trim:
   - "htseq.count"
 export_plots: true
+
+use_filename_as_sample_name:
+  - kallisto
diff --git a/bin/check_samplesheet.py b/bin/check_samplesheet.py
@@ -167,7 +167,8 @@ def sniff_format(handle):
     sniffer = csv.Sniffer()
     if not sniffer.has_header(peek):
         logger.critical("The given sample sheet does not appear to contain a header.")
-        sys.exit(1)
+        ## Commenting out this line because it sometimes fails when it shouldn't, and there is a downstream check for header names that is essentially redundant.
+        #sys.exit(1)
     dialect = sniffer.sniff(peek)
     return dialect
 

diff --git a/conf/igenomes.config b/conf/igenomes.config
@@ -14,6 +14,7 @@ params {
             fasta          = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Sequence/WholeGenomeFasta/human_g1k_v37_decoy.fasta"
             gtf            = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/Genes/genes.gtf"
             refflat        = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/Genes/refFlat.txt.gz"
+            cdna           = "https://ftp.ensembl.org/pub/release-75/fasta/homo_sapiens/cdna/Homo_sapiens.GRCh37.75.cdna.all.fa.gz"
             starfusion_url = "https://data.broadinstitute.org/Trinity/CTAT_RESOURCE_LIB/__genome_libs_StarFv1.10/GRCh37_gencode_v19_CTAT_lib_Mar012021.plug-n-play.tar.gz"
             arriba_blacklist       = "/usr/local/var/lib/arriba/blacklist_hg19_hs37d5_GRCh37_v2.3.0.tsv.gz"
             arriba_known_fusions   = "/usr/local/var/lib/arriba/known_fusions_hg19_hs37d5_GRCh37_v2.3.0.tsv.gz"
@@ -44,6 +45,7 @@ params {
             arriba_blacklist       = "/usr/local/var/lib/arriba/blacklist_hg38_GRCh38_v2.3.0.tsv.gz"
             arriba_known_fusions   = "/usr/local/var/lib/arriba/known_fusions_hg38_GRCh38_v2.3.0.tsv.gz"
             arriba_protein_domains = "/usr/local/var/lib/arriba/protein_domains_hg38_GRCh38_v2.3.0.gff3"
+            cdna           = "https://ftp.ensembl.org/pub/release-86/fasta/homo_sapiens/cdna/Homo_sapiens.GRCh38.cdna.all.fa.gz"
         }
         'smallGRCh37' {
             fasta          = "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/genome.fasta"
@@ -56,6 +58,8 @@ params {
             genebed = "/juno/work/ccs/pintoa1/references/meta_fusion_bed_generation/v75_gene.bed"
             info = "/juno/work/ccs/pintoa1/fusion_report/metafusion/MetaFusion/gene_info_20230714.txt"
             block = "/juno/work/ccs/pintoa1/fusion_report/metafusion/MetaFusion/reference_files/blocklist_breakpoints.bedpe"
+            cdna           = "https://ftp.ensembl.org/pub/release-75/fasta/homo_sapiens/cdna/Homo_sapiens.GRCh37.75.cdna.all.fa.gz"
+
         }
 /*
         'hg38' {

diff --git a/conf/modules.config b/conf/modules.config
@@ -152,6 +152,10 @@ process {
         storeDir = { "${params.reference_base}/${params.genome}/star_index" }
     }
 
+    withName: KALLISTO_INDEX {
+        storeDir = { "${params.reference_base}/${params.genome}/kallisto" }
+    }
+
     withName: STARFUSION_DOWNLOAD {
         storeDir = { "${params.reference_base}/${params.genome}/starfusion" }
     }
@@ -329,13 +333,53 @@ process {
 
     withName: PICARD_COLLECTRNASEQMETRICS {
         ext.args = { "--STRAND_SPECIFICITY ${meta.single_end || meta.strand == "forward" ? "FIRST_READ_TRANSCRIPTION_STRAND" : meta.strand == "reverse" ? "SECOND_READ_TRANSCRIPTION_STRAND" : "NONE" }" }
+        publishDir = [
+            path: { "${params.outdir}/${meta ? "analysis/" + meta.sample + "/" : "" }${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}/${task.process.tokenize(':')[-2].tokenize('_')[1].toLowerCase()}" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
+    withName: PICARD_COLLECTHSMETRICS {
+        publishDir = [
+            path: { "${params.outdir}/${meta ? "analysis/" + meta.sample + "/" : "" }${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}/${task.process.tokenize(':')[-2].tokenize('_')[1].toLowerCase()}" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
+    withName: 'RSEQC_.*' {
+        publishDir = [
+            path: { "${params.outdir}/${meta ? "analysis/" + meta.sample + "/" : "" }${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}/${task.process.tokenize(':')[-3].tokenize('_')[1].toLowerCase()}" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
     }
 
     withName: HTSEQ_COUNT {
         ext.args = { "-s ${meta.single_end || meta.strand == "forward" ? "yes" : meta.strand == "reverse" ? "reverse" : "no" } -r pos" }
         time     = { check_max( 20.h * task.attempt, 'time' ) }
     }
 
+    withName: KALLISTO_QUANT {
+        ext.prefix = { "$meta.sample" }
+        ext.args = {
+            [
+                "--bias",
+                "-b 100",
+                meta.strand == "forward" ?
+                    "--fr-stranded" :
+                    (
+                        meta.strand == "reverse" ?
+                        "--rf-stranded" :
+                        ""
+                    )
+            ].join(" ")
+        }
+        ext.fragment_len = params.kallisto_fragment_len
+        ext.sd = params.kallisto_fragment_sd
+    }
+
     withName: ARRIBA {
         ext.args = {
             [

diff --git a/main.nf b/main.nf
@@ -20,6 +20,7 @@ params.gtf            = WorkflowMain.getGenomeAttribute(params, 'gtf')
 params.starfusion_url = WorkflowMain.getGenomeAttribute(params, 'starfusion_url')
 params.refflat        = WorkflowMain.getGenomeAttribute(params, 'refflat')
 params.baits          = WorkflowMain.getGenomeAttribute(params, 'baits')
+params.cdna           = WorkflowMain.getGenomeAttribute(params, 'cdna')
 params.arriba_blacklist       = WorkflowMain.getGenomeAttribute(params, 'arriba_blacklist')
 params.arriba_known_fusions   = WorkflowMain.getGenomeAttribute(params, 'arriba_known_fusions')
 params.arriba_protein_domains = WorkflowMain.getGenomeAttribute(params, 'arriba_protein_domains')

diff --git a/modules.json b/modules.json
@@ -45,6 +45,16 @@
                         "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
                         "installed_by": ["modules"]
                     },
+                    "kallisto/index": {
+                        "branch": "master",
+                        "git_sha": "911696ea0b62df80e900ef244d7867d177971f73",
+                        "installed_by": ["modules"]
+                    },
+                    "kallisto/quant": {
+                        "branch": "master",
+                        "git_sha": "911696ea0b62df80e900ef244d7867d177971f73",
+                        "installed_by": ["modules"]
+                    },
                     "multiqc": {
                         "branch": "master",
                         "git_sha": "ee80d14721e76e2e079103b8dcd5d57129e584ba",

diff --git a/modules/local/htseq/count/main.nf b/modules/local/htseq/count/main.nf
@@ -1,6 +1,6 @@
 process HTSEQ_COUNT {
     tag "$meta.id"
-    label 'process_medium'
+    label 'process_low'
 
     conda "bioconda::htseq=2.0.2"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?

diff --git a/modules/local/starfusion/detect/main.nf b/modules/local/starfusion/detect/main.nf
@@ -1,6 +1,6 @@
 process STARFUSION {
     tag "$meta.id"
-    label 'process_high'
+    label 'process_low'
 
     conda "bioconda::dfam=3.3 bioconda::hmmer=3.3.2 bioconda::star-fusion=1.10.0 bioconda::trinity=date.2011_11_2 bioconda::samtools=1.9 bioconda::star=2.7.8a"
     container "docker.io/trinityctat/starfusion:1.10.1"

diff --git a/modules/nf-core/kallisto/index/main.nf b/modules/nf-core/kallisto/index/main.nf
diff --git a/modules/nf-core/kallisto/index/meta.yml b/modules/nf-core/kallisto/index/meta.yml
diff --git a/modules/nf-core/kallisto/quant/main.nf b/modules/nf-core/kallisto/quant/main.nf
diff --git a/modules/nf-core/kallisto/quant/meta.yml b/modules/nf-core/kallisto/quant/meta.yml
diff --git a/nextflow.config b/nextflow.config
@@ -29,7 +29,6 @@ params {
     save_align_intermeds       = false
 
     // Fusion
-    dedup_umi_for_fusions      = false
     run_oncokb_fusionannotator = false
     cosmic_usr                 = null
     fusion_report_cutoff       = 1
@@ -40,6 +39,11 @@ params {
     // rseqc_modules can include ['bam_stat','inner_distance','infer_experiment','junction_annotation','junction_saturation','read_distribution','read_duplication','tin']
     rseqc_modules              = ['bam_stat','inner_distance','infer_experiment','junction_annotation','junction_saturation','read_distribution','read_duplication']
 
+    // Quantification
+    dedup_umi_for_kallisto     = true
+    kallisto_fragment_len      = 500
+    kallisto_fragment_sd       = 150
+
     // MultiQC options
     multiqc_config             = null
     multiqc_title              = null