Merge pull request #935 from nf-core/patch-mapdamage

Fix mapdamage and add parameter

Author: jfy133

CHANGELOG.md

@@ -7,6 +7,8 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 
 ### `Added`
 
+- [#933](https://github.com/nf-core/eager/issues/933) Added support for customising --seq-length in mapDamage rescaling (♥ to @ashildv for requesting)
+
 ### `Fixed`
 
 - Changed endors.py license from GPL to MIT (♥ to @aidaanva for fixing)
@@ -15,6 +17,7 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 - Fixed edge case of DamageProfiler occasionally requiring FASTA index (♥ to @asmaa-a-abdelwahab for reporting)
 - [#834](https://github.com/nf-core/eager/issues/834) Increased significance values in general stats table for Qualimap mean/median coverages (♥ to @neija2611 for reporting)
 - Fixed parameter documentation for `--snpcapture_bed` regarding on-target SNP stats to state these stats currently not displayed in MultiQC only in the Qualimap results (♥ to @meganemichel and @TCLamnidis for reporting)
+- [#934](https://github.com/nf-core/eager/issues/934) Fixed broken parameter setting in mapDamage2 rescale length (♥ to @ashildv for reporting)
 
 ### `Dependencies`
 

Dockerfile

@@ -7,7 +7,7 @@ COPY environment.yml /
 RUN conda env create --quiet -f /environment.yml && conda clean -a
 
 # Add conda installation dir to PATH (instead of doing 'conda activate')
-ENV PATH /opt/conda/envs/nf-core-eager-2.4.5dev/bin:$PATH
+ENV PATH /opt/conda/envs/nf-core-eager-2.4.6dev/bin:$PATH
 
 # Dump the details of the installed packages to a file for posterity
-RUN conda env export --name nf-core-eager-2.4.5dev > nf-core-eager-2.4.5dev.yml
+RUN conda env export --name nf-core-eager-2.4.6dev > nf-core-eager-2.4.6dev.yml

environment.yml

@@ -1,6 +1,6 @@
 # You can use this file to create a conda environment for this pipeline:
 #   conda env create -f environment.yml
-name: nf-core-eager-2.4.5dev
+name: nf-core-eager-2.4.6dev
 channels:
   - conda-forge
   - bioconda
@@ -50,4 +50,4 @@ dependencies:
   - bioconda::eigenstratdatabasetools=1.0.2
   - bioconda::mapdamage2=2.2.1
   - bioconda::bbmap=38.92
-  - bioconda::bcftools=1.12
+  - bioconda::bcftools=1.12

main.nf

@@ -2129,8 +2129,10 @@ process mapdamage_rescaling {
     def base = "${bam.baseName}"
     def singlestranded = strandedness == "single" ? '--single-stranded' : ''
     def size = params.large_ref ? '-c' : ''
+    def rescale_length_3p = params.rescale_length_3p != 0 ? "--rescale-length-3p=${params.rescale_length_3p}" : ""
+    def rescale_length_5p = params.rescale_length_5p != 0 ? "--rescale-length-5p=${params.rescale_length_5p}" : ""
     """
-    mapDamage -i ${bam} -r ${fasta} --rescale --rescale-out ${base}_rescaled.bam --rescale-length-5p ${params.rescale_length_5p} --rescale-length-3p=${params.rescale_length_3p} ${singlestranded}
+    mapDamage -i ${bam} -r ${fasta} --rescale --rescale-out="${base}_rescaled.bam" --seq-length=${params.rescale_seqlength} ${rescale_length_5p} ${rescale_length_3p} ${singlestranded}
     samtools index ${base}_rescaled.bam ${size}
     """
 

nextflow.config

@@ -135,8 +135,9 @@ params {
 
   // mapDamage
   run_mapdamage_rescaling = false
-  rescale_length_5p = 12
-  rescale_length_3p = 12
+  rescale_length_5p = 0
+  rescale_length_3p = 0
+  rescale_seqlength = 12
 
   //Bedtools settings
   run_bedtools_coverage = false 
@@ -414,7 +415,7 @@ manifest {
   description = 'A fully reproducible and state-of-the-art ancient DNA analysis pipeline'
   mainScript = 'main.nf'
   nextflowVersion = '>=20.07.1'
-  version = '2.4.5dev'
+  version = '2.4.6dev'
 }
 
 // Function to ensure that resource requirements don't go beyond

nextflow_schema.json

@@ -877,20 +877,27 @@
           "description": "Turn on damage rescaling of BAM files using mapDamage2 to probabilistically remove damage.",
           "help_text": "Turns on mapDamage2's BAM rescaling functionality. This probablistically replaces Ts back to Cs depending on the likelihood this reference-mismatch was originally caused by damage. If the library is specified to be single stranded, this will automatically use the `--single-stranded` mode.\n\nThis functionality does not have any MultiQC output.\n\n:warning: rescaled libraries will not be merged with non-scaled libraries of the same sample for downstream genotyping, as the model may be different for each library. If you wish to merge these, please do this manually and re-run nf-core/eager using the merged BAMs as input. \n\n> Modifies the `--rescale` parameter of mapDamage2"
         },
-        "rescale_length_5p": {
+        "rescale_seqlength": {
           "type": "integer",
           "default": 12,
-          "fa_icon": "fas fa-balance-scale-right",
-          "description": "Length of read for mapDamage2 to rescale from 5p end.",
-          "help_text": "Specify the length from the end of the read that mapDamage should rescale.\n\n> Modifies the `--rescale-length-5p` parameter of mapDamage2."
+          "fa_icon": "fas fa-ruler-horizontal",
+          "description": "Length of read sequence to use from each side for rescaling. Can be overridden by --rescale_length_*p.",
+          "help_text": "Specify the length from the end of the read that mapDamage should rescale at both ends.\n\n> Modifies the `--seq-length` parameter of mapDamage2."
+        },
+        "rescale_length_5p": {
+            "type": "integer",
+            "default": 0,
+            "fa_icon": "fas fa-balance-scale-right",
+            "description": "Length of read for mapDamage2 to rescale from 5p end.  Only used if not 0 otherwise --rescale_seqlength used.",
+            "help_text": "Specify the length from the end of the read that mapDamage should rescale. Overrides `--rescale_seqlength`.\n\n> Modifies the `--rescale-length-5p` parameter of mapDamage2."
         },
         "rescale_length_3p": {
-          "type": "integer",
-          "default": 12,
-          "fa_icon": "fas fa-balance-scale-left",
-          "description": "Length of read for mapDamage2 to rescale from 3p end.",
-          "help_text": "Specify the length from the end of the read that mapDamage should rescale.\n\n> Modifies the `--rescale-length-3p` parameter of mapDamage2."
-        }
+            "type": "integer",
+            "default": 0,
+            "fa_icon": "fas fa-balance-scale-left",
+            "description": "Length of read for mapDamage2 to rescale from 3p end. Only used if not 0 otherwise --rescale_seqlength used..",
+            "help_text": "Specify the length from the end of the read that mapDamage should rescale.\n\n> Modifies the `--rescale-length-3p` parameter of mapDamage2."
+            }
       },
       "fa_icon": "fas fa-chart-line",
       "help_text": "More documentation can be seen in the follow links for:\n\n- [DamageProfiler](https://github.com/Integrative-Transcriptomics/DamageProfiler)\n- [PMDTools documentation](https://github.com/pontussk/PMDtools)\n\nIf using TSV input, DamageProfiler is performed per library, i.e. after lane\nmerging. PMDtools and  BAM Trimming is run after library merging of same-named\nlibrary BAMs that have the same type of UDG treatment. BAM Trimming is only\nperformed on non-UDG and half-UDG treated data.\n"