Merge pull request #106 from nf-cmgg/dev

Release v2.0.2 PR

.github/workflows/ci.yml

@@ -30,8 +30,7 @@ jobs:
     strategy:
       matrix:
         NXF_VER:
-          - "24.04.2"
-          - "latest-everything"
+          - "24.04.4"
         tags:
           - "modules/local/panelcoverage"
           - "subworkflows/local/bam_qc"

CHANGELOG.md

@@ -3,6 +3,16 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## dev
+
+## v2.0.2
+
+- Drop unsed params
+- Set aligner to `star` for RNA-seq
+- Finetune resources
+- Fix some bugs for different input tags
+- Update modules
+
 ## v2.0.1
 
 - Fix syntax according to new rules

assets/multiqc_config.yml

@@ -1,5 +1,5 @@
 report_comment: >
-  This report has been generated by the <a href="https://github.com/nf-cmgg/preprocessing/releases/tag/2.0.1" target="_blank">nf-cmgg/preprocessing</a>
+  This report has been generated by the <a href="https://github.com/nf-cmgg/preprocessing/releases/tag/2.0.2" target="_blank">nf-cmgg/preprocessing</a>
   analysis pipeline.
 report_section_order:
   "nf-cmgg-preprocessing-methods-description":
@@ -23,6 +23,17 @@ mosdepth_config:
     - "HLA*"
     - "chrM"
     - "chrEBV"
+samtools_coverage:
+  include_contigs:
+    - "chr*"
+  exclude_contigs:
+    - "*_alt"
+    - "*_decoy"
+    - "*_random"
+    - "chrUn*"
+    - "HLA*"
+    - "chrM"
+    - "chrEBV"
 extra_fn_clean_exts:
   - ".cram"
   - ".coverage"

assets/schema_input.json

@@ -23,8 +23,7 @@
                 "meta": ["organism"],
                 "type": "string",
                 "description": "Sample organism. Currently supported organisms include Homo sapiens, Mus musculus and Danio rerio",
-                "pattern": "^[a-zA-Z0-9_\\s]+$",
-                "enum": ["Homo sapiens", "Mus musculus", "Danio rerio"]
+                "pattern": "^[a-zA-Z0-9_\\s]+$"
             },
             "genome": {
                 "meta": ["genome"],

assets/schema_sampleinfo.json

@@ -42,16 +42,7 @@
                 "meta": ["organism"],
                 "type": "string",
                 "description": "Sample organism",
-                "pattern": "^[a-zA-Z0-9_\\s]+$",
-                "enum": [
-                    "Homo sapiens",
-                    "Mus musculus",
-                    "Danio rerio",
-                    "SarsCov",
-                    "Mus Musculus",
-                    "Homo Sapiens",
-                    "Danio Rerio"
-                ]
+                "pattern": "^[a-zA-Z0-9_\\s]+$"
             },
             "genome": {
                 "meta": ["genome"],
@@ -89,6 +80,12 @@
                 "description": "Region of interest BED file for coverage analysis",
                 "pattern": "^[a-zA-Z0-9_]+.bed$",
                 "default": null
+            },
+            "aligner": {
+                "meta": ["aligner"],
+                "type": "string",
+                "description": "Aligner to use to align sample to the reference genome",
+                "enum": ["bowtie2", "bwamem", "bwamem2", "dragmap", "snap", "star"]
             }
         }
     },

conf/base.config

@@ -30,17 +30,17 @@ process {
         time   = { 4.h   * task.attempt }
     }
     withLabel:process_medium {
-        cpus   = { 9     * task.attempt }
-        memory = { 72.GB * task.attempt }
+        cpus   = { 8     * task.attempt }
+        memory = { 64.GB * task.attempt }
         time   = { 8.h   * task.attempt }
     }
     withLabel:process_high {
-        cpus   = { 18     * task.attempt }
-        memory = { 144.GB * task.attempt }
+        cpus   = { 16     * task.attempt }
+        memory = { 128.GB * task.attempt }
         time   = { 16.h   * task.attempt }
     }
     withLabel:process_long {
-        time   = { 20.h  * task.attempt }
+        time   = { 72.h  * task.attempt }
     }
     withLabel:process_high_memory {
         memory = { 200.GB * task.attempt }

conf/igenomes.config

@@ -27,6 +27,7 @@ params {
 
             // ROI's
             roi_copgt   = "${params.igenomes_base}/Hsapiens/GRCh38/regions/CMGG_coPGT-M_analyses_ROI_v1.bed"
+            roi_wes     = "${params.igenomes_base}/Hsapiens/GRCh38/regions/CMGG_WES_analysis_ROI_v5.bed"
         }
         "GRCm39" {
             // Genome reference

conf/modules.config

@@ -20,8 +20,6 @@ process {
 
     // BCL convert
     withName: BCLCONVERT {
-        cpus   = 18
-        memory = 144.GB
         ext.args = {[
             meta.lane ? "--bcl-only-lane ${meta.lane}" : "",
             "--force",
@@ -80,6 +78,7 @@ process {
             params.trim_tail    > 0 ? "--trim_tail1  ${params.trim_tail}" : "",
             params.adapter_R1       ? "--adapter_sequence ${params.adapter_R1}" : "",
             params.adapter_R2       ? "--adapter_sequence_r2 ${params.adapter_R2}" : "",
+            "--compression 1"
         ].join(" ").trim()}
         publishDir = [
             [
@@ -93,8 +92,7 @@ process {
     // FASTQ_TO_UCRAM
     //// Samtools Import
     withName: ".*FASTQ_TO_UCRAM:SAMTOOLS_IMPORT" {
-        cpus = 9
-        memory = { 36.GB * task.attempt }
+        label = "process_medium"
         // WARNING: Do NOT escape the RG tag tabs when adding a readgroup
         ext.args = {[
             meta.readgroup ? "--rg-line \"@RG\t" + meta.readgroup.findResults{ it.value?.trim() ? "$it.key:$it.value" : null }.join("\t") + "\"" : "",
@@ -104,11 +102,6 @@ process {
         publishDir = [ enabled: false ]
     }
 
-    withName: ".*FASTQ_TO_UCRAM:SAMTOOLS_CAT" {
-        cpus = 9
-        memory = { 36.GB * task.attempt }
-    }
-
     // FASTQ_TO_CRAM
     // Readgroup
     // Example:
@@ -204,7 +197,8 @@ process {
             "--chimSegmentMin 20",
             // alignment will be output only if it has no more mismatches than this value.
             "--outFilterMismatchNmax 4",
-            meta.readgroup ? "--outSAMattrRGline " + meta.readgroup.findResults{ it.value?.trim() ? "$it.key:$it.value" : null }.join(" ") + "\"" : ""
+            // set the readgroup info, if available. Flag arg MUST start with 'ID' tag
+            meta.readgroup ? "--outSAMattrRGline \"ID:${meta.readgroup.ID}" + meta.readgroup.findResults{ it.value?.trim() && it.key != "ID" ? "$it.key:$it.value" : null }.join(" ") + "\"" : ""
         ].join(" ").trim()}
     }
 
@@ -273,6 +267,7 @@ process {
 
     //// Samtools convert
     withName: ".*FASTQ_TO_CRAM:SAMTOOLS_CONVERT" {
+        label = "process_medium"
         ext.args = {[
             "-C",
             "--output-fmt cram",
@@ -292,6 +287,7 @@ process {
     //// Mosdepth
     withName: ".*COVERAGE:MOSDEPTH" {
         cpus = 4
+        memory = { 4.GB * task.attempt }
         // filter reads with flag 1804
         //     read unmapped (0x4)
         //     mate unmapped (0x8)*

conf/profiles/WES.config

@@ -1,6 +1,6 @@
 params {
-    genome                  = "GRCh38"
     aligner                 = "snap"
     run_coverage            = true
     disable_picard_metrics  = false
+    roi                     = "${params.igenomes_base}/Hsapiens/GRCh38/regions/CMGG_WES_analysis_ROI_v5.bed"
 }

conf/profiles/WGS.config

@@ -1,5 +1,4 @@
 params {
-    genome                  = "GRCh38"
     aligner                 = "snap"
     run_coverage            = true
     disable_picard_metrics  = false

conf/profiles/copgt.config

@@ -1,5 +1,4 @@
 params {
-    genome                  = "GRCh38"
     aligner                 = "snap"
     run_coverage            = true
     disable_picard_metrics  = true

conf/profiles/sWGS.config

@@ -1,5 +1,4 @@
 params {
-    genome                  = "hg38-noalt"
     aligner                 = "bowtie2"
     run_coverage            = false
     disable_picard_metrics  = true