Merge branch 'dev' into dev

Author: jfy133

CHANGELOG.md

@@ -3,13 +3,15 @@
 The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html).
 
-## [2.3.1] - 2021-14                                                         
+## [2.3.1] - 2021-01-14                                                         
 
 ### `Added`
 
 ### `Fixed`
 
-- Fixed issue with Docker container not being pullable by Nextflow
+- [#654](https://github.com/nf-core/eager/issues/654) - Fixed some values in JSON schema (used in launch GUI) not passing validation checks during run
+- [#655](https://github.com/nf-core/eager/issues/655) - Updated read groups for all mappers to allow proper GATK validation
+- Fixed issue with Docker container not being pullable by Nextflow due to version-number inconsistencies
 
 ### `Dependencies`
 

README.md

@@ -160,6 +160,7 @@ Those who have provided conceptual guidance, suggestions, bug reports etc.
 
 * Arielle Munters
 * [Hester van Schalkwyk](https://github.com/hesterjvs)
+* [Ido Bar](https://github.com/IdoBar)
 * [Irina Velsko](https://github.com/ivelsko)
 * [Katerine Eaton](https://github.com/ktmeaton)
 * [Luc Venturini](https://github.com/lucventurini)

main.nf

@@ -1494,14 +1494,14 @@ process bwa {
     """
     bwa aln -t ${task.cpus} $fasta ${r1} -n ${params.bwaalnn} -l ${params.bwaalnl} -k ${params.bwaalnk} -f ${libraryid}.r1.sai
     bwa aln -t ${task.cpus} $fasta ${r2} -n ${params.bwaalnn} -l ${params.bwaalnl} -k ${params.bwaalnk} -f ${libraryid}.r2.sai
-    bwa sampe -r "@RG\\tID:ILLUMINA-${libraryid}\\tSM:${libraryid}\\tPL:illumina" $fasta ${libraryid}.r1.sai ${libraryid}.r2.sai ${r1} ${r2} | samtools sort -@ ${task.cpus} -O bam - > ${libraryid}_"${seqtype}".mapped.bam
+    bwa sampe -r "@RG\\tID:ILLUMINA-${libraryid}\\tSM:${libraryid}\\tPL:illumina\\tPU:ILLUMINA-${libraryid}-${seqtype}" $fasta ${libraryid}.r1.sai ${libraryid}.r2.sai ${r1} ${r2} | samtools sort -@ ${task.cpus} -O bam - > ${libraryid}_"${seqtype}".mapped.bam
     samtools index "${libraryid}"_"${seqtype}".mapped.bam ${size}
     """
     } else {
     //PE collapsed, or SE data 
     """
     bwa aln -t ${task.cpus} ${fasta} ${r1} -n ${params.bwaalnn} -l ${params.bwaalnl} -k ${params.bwaalnk} -f ${libraryid}.sai
-    bwa samse -r "@RG\\tID:ILLUMINA-${libraryid}\\tSM:${libraryid}\\tPL:illumina" $fasta ${libraryid}.sai $r1 | samtools sort -@ ${task.cpus} -O bam - > "${libraryid}"_"${seqtype}".mapped.bam
+    bwa samse -r "@RG\\tID:ILLUMINA-${libraryid}\\tSM:${libraryid}\\tPL:illumina\\tPU:ILLUMINA-${libraryid}-${seqtype}" $fasta ${libraryid}.sai $r1 | samtools sort -@ ${task.cpus} -O bam - > "${libraryid}"_"${seqtype}".mapped.bam
     samtools index "${libraryid}"_"${seqtype}".mapped.bam ${size}
     """
     }
@@ -1531,12 +1531,12 @@ process bwamem {
 
     if (!params.single_end && params.skip_collapse){
     """
-    bwa mem -t ${task.cpus} $fasta $r1 $r2 -R "@RG\\tID:ILLUMINA-${libraryid}\\tSM:${libraryid}\\tPL:illumina" | samtools sort -@ ${task.cpus} -O bam - > "${libraryid}"_"${seqtype}".mapped.bam
+    bwa mem -t ${task.cpus} $fasta $r1 $r2 -R "@RG\\tID:ILLUMINA-${libraryid}\\tSM:${libraryid}\\tPL:illumina\\tPU:ILLUMINA-${libraryid}-${seqtype}" | samtools sort -@ ${task.cpus} -O bam - > "${libraryid}"_"${seqtype}".mapped.bam
     samtools index ${size} -@ ${task.cpus} "${libraryid}".mapped.bam
     """
     } else {
     """
-    bwa mem -t ${task.cpus} $fasta $r1 -R "@RG\\tID:ILLUMINA-${libraryid}\\tSM:${libraryid}\\tPL:illumina" | samtools sort -@ ${task.cpus} -O bam - > "${libraryid}"_"${seqtype}".mapped.bam
+    bwa mem -t ${task.cpus} $fasta $r1 -R "@RG\\tID:ILLUMINA-${libraryid}\\tSM:${libraryid}\\tPL:illumina\\tPU:ILLUMINA-${libraryid}-${seqtype}" | samtools sort -@ ${task.cpus} -O bam - > "${libraryid}"_"${seqtype}".mapped.bam
     samtools index -@ ${task.cpus} "${libraryid}"_"${seqtype}".mapped.bam ${size} 
     """
     }
@@ -1600,15 +1600,15 @@ process circularmapper{
     """
     bwa aln -t ${task.cpus} $elongated_root $r1 -n ${params.bwaalnn} -l ${params.bwaalnl} -k ${params.bwaalnk} -f ${libraryid}.r1.sai
     bwa aln -t ${task.cpus} $elongated_root $r2 -n ${params.bwaalnn} -l ${params.bwaalnl} -k ${params.bwaalnk} -f ${libraryid}.r2.sai
-    bwa sampe -r "@RG\\tID:ILLUMINA-${libraryid}\\tSM:${libraryid}\\tPL:illumina" $elongated_root ${libraryid}.r1.sai ${libraryid}.r2.sai $r1 $r2 > tmp.out
+    bwa sampe -r "@RG\\tID:ILLUMINA-${libraryid}\\tSM:${libraryid}\\tPL:illumina\\tPU:ILLUMINA-${libraryid}-${seqtype}" $elongated_root ${libraryid}.r1.sai ${libraryid}.r2.sai $r1 $r2 > tmp.out
     realignsamfile -e ${params.circularextension} -i tmp.out -r $fasta $filter 
     samtools sort -@ ${task.cpus} -O bam tmp_realigned.bam > ${libraryid}_"${seqtype}".mapped.bam
     samtools index "${libraryid}"_"${seqtype}".mapped.bam ${size} 
     """
     } else {
     """ 
     bwa aln -t ${task.cpus} $elongated_root $r1 -n ${params.bwaalnn} -l ${params.bwaalnl} -k ${params.bwaalnk} -f ${libraryid}.sai
-    bwa samse -r "@RG\\tID:ILLUMINA-${libraryid}\\tSM:${libraryid}\\tPL:illumina" $elongated_root ${libraryid}.sai $r1 > tmp.out
+    bwa samse -r "@RG\\tID:ILLUMINA-${libraryid}\\tSM:${libraryid}\\tPL:illumina\\tPU:ILLUMINA-${libraryid}-${seqtype}" $elongated_root ${libraryid}.sai $r1 > tmp.out
     realignsamfile -e ${params.circularextension} -i tmp.out -r $fasta $filter 
     samtools sort -@ ${task.cpus} -O bam tmp_realigned.bam > "${libraryid}"_"${seqtype}".mapped.bam
     samtools index "${libraryid}"_"${seqtype}".mapped.bam ${size}
@@ -1677,13 +1677,13 @@ process bowtie2 {
     //PE data without merging, PE data without any AR applied
     if ( seqtype == 'PE' && ( params.skip_collapse || params.skip_adapterremoval ) ){
     """
-    bowtie2 -x ${fasta} -1 ${r1} -2 ${r2} -p ${task.cpus} ${sensitivity} ${bt2n} ${bt2l} ${trim5} ${trim3} 2> "${libraryid}"_bt2.log | samtools sort -@ ${task.cpus} -O bam > "${libraryid}"_"${seqtype}".mapped.bam
+    bowtie2 -x ${fasta} -1 ${r1} -2 ${r2} -p ${task.cpus} ${sensitivity} ${bt2n} ${bt2l} ${trim5} ${trim3} --rg-id ILLUMINA-${libraryid} --rg SM:${libraryid} --rg PL:illumina --rg PU:ILLUMINA-${libraryid}-${seqtype} 2> "${libraryid}"_bt2.log | samtools sort -@ ${task.cpus} -O bam > "${libraryid}"_"${seqtype}".mapped.bam
     samtools index "${libraryid}"_"${seqtype}".mapped.bam ${size}
     """
     } else {
     //PE collapsed, or SE data 
     """
-    bowtie2 -x ${fasta} -U ${r1} -p ${task.cpus} ${sensitivity} ${bt2n} ${bt2l} ${trim5} ${trim3} 2> "${libraryid}"_bt2.log | samtools sort -@ ${task.cpus} -O bam > "${libraryid}"_"${seqtype}".mapped.bam
+    bowtie2 -x ${fasta} -U ${r1} -p ${task.cpus} ${sensitivity} ${bt2n} ${bt2l} ${trim5} ${trim3} --rg-id ILLUMINA-${libraryid} --rg SM:${libraryid} --rg PL:illumina --rg PU:ILLUMINA-${libraryid}-${seqtype} 2> "${libraryid}"_bt2.log | samtools sort -@ ${task.cpus} -O bam > "${libraryid}"_"${seqtype}".mapped.bam
     samtools index "${libraryid}"_"${seqtype}".mapped.bam ${size}
     """
     }

nextflow_schema.json

@@ -587,29 +587,33 @@
                 "bt2n": {
                     "type": "integer",
                     "description": "Specify the -N parameter for bowtie2 (mismatches in seed). This will override defaults from alignmode/sensitivity.",
-                    "default": "0",
+                    "default": 0,
                     "fa_icon": "fas fa-sort-numeric-down",
-                    "help_text": "The number of mismatches allowed in the seed during seed-and-extend procedure of Bowtie2. This will override any values set with `--bt2_sensitivity`. Can either be 0 or 1. Default: 0 (i.e. use`--bt2_sensitivity` defaults).\n\n> Modifies Bowtie2 parameters: `-N`"
+                    "help_text": "The number of mismatches allowed in the seed during seed-and-extend procedure of Bowtie2. This will override any values set with `--bt2_sensitivity`. Can either be 0 or 1. Default: 0 (i.e. use`--bt2_sensitivity` defaults).\n\n> Modifies Bowtie2 parameters: `-N`",
+                    "enum": [
+                        0,
+                        1
+                    ]
                 },
                 "bt2l": {
                     "type": "integer",
+                    "default": 0,
                     "description": "Specify the -L parameter for bowtie2 (length of seed substrings). This will override defaults from alignmode/sensitivity.",
                     "fa_icon": "fas fa-ruler-horizontal",
-                    "default": "0",
                     "help_text": "The length of the seed sub-string to use during seeding. This will override any values set with `--bt2_sensitivity`. Default: 0 (i.e. use`--bt2_sensitivity` defaults: [20 for local and 22 for end-to-end](http://bowtie-bio.sourceforge.net/bowtie2/manual.shtml#command-line).\n\n> Modifies Bowtie2 parameters: `-L`"
                 },
                 "bt2_trim5": {
                     "type": "integer",
+                    "default": 0,
                     "description": "Specify number of bases to trim off from 5' (left) end of read before alignment.",
                     "fa_icon": "fas fa-cut",
-                    "default": "0",
                     "help_text": "Number of bases to trim at the 5' (left) end of read prior alignment. Maybe useful when left-over sequencing artefacts of in-line barcodes present Default: 0\n\n> Modifies Bowtie2 parameters: `-bt2_trim5`"
                 },
                 "bt2_trim3": {
                     "type": "integer",
+                    "default": 0,
                     "description": "Specify number of bases to trim off from 3' (right) end of read before alignment.",
                     "fa_icon": "fas fa-cut",
-                    "default": "0",
                     "help_text": "Number of bases to trim at the 3' (right) end of read prior alignment. Maybe useful when left-over sequencing artefacts of in-line barcodes present Default: 0.\n\n> Modifies Bowtie2 parameters: `-bt2_trim3`"
                 }
             },
@@ -658,15 +662,15 @@
                 "bam_mapping_quality_threshold": {
                     "type": "integer",
                     "description": "Minimum mapping quality for reads filter.",
-                    "default": "0",
+                    "default": 0,
                     "fa_icon": "fas fa-greater-than-equal",
                     "help_text": "Specify a mapping quality threshold for mapped reads to be kept for downstream analysis. By default keeps all reads and is therefore set to `0` (basically doesn't filter anything).\n\n> Modifies samtools view parameter: `-q`"
                 },
                 "bam_filter_minreadlength": {
                     "type": "integer",
+                    "default": 0,
                     "fa_icon": "fas fa-ruler-horizontal",
                     "description": "Specify minimum read length to be kept after mapping.",
-                    "default": "0",
                     "help_text": "Specify minimum length of mapped reads. This filtering will apply at the same time as mapping quality filtering.\n\nIf used _instead_ of minimum length read filtering at AdapterRemoval, this can be useful to get more realistic endogenous DNA percentages, when most of your reads are very short (e.g. in single-stranded libraries) and would otherwise be discarded by AdapterRemoval (thus making an artificially small denominator for a typical endogenous DNA calculation). Note in this context you should not perform mapping quality filtering nor discarding of unmapped reads to ensure a correct denominator of all reads, for the endogenous DNA calculation.\n\n> Modifies filter_bam_fragment_length.py parameter: `-l`"
                 },
                 "bam_unmapped_type": {
@@ -851,28 +855,28 @@
                 },
                 "bamutils_clip_half_udg_left": {
                     "type": "integer",
-                    "default": "1",
+                    "default": 1,
                     "fa_icon": "fas fa-ruler-combined",
                     "description": "Specify the number of bases to clip off reads from 'left' end of read for half-UDG libraries.",
                     "help_text": "Default set to `1` and clips off one base of the left or right side of reads from libraries whose UDG treatment is set to `half`. Note that reverse reads will automatically be clipped off at the reverse side with this (automatically reverses left and right for the reverse read).\n\n> Modifies bamUtil's trimBam parameter: `-L -R`"
                 },
                 "bamutils_clip_half_udg_right": {
                     "type": "integer",
-                    "default": "1",
+                    "default": 1,
                     "fa_icon": "fas fa-ruler",
                     "description": "Specify the number of bases to clip off reads from 'right' end of read for half-UDG libraries.",
                     "help_text": "Default set to `1` and clips off one base of the left or right side of reads from libraries whose UDG treatment is set to `half`. Note that reverse reads will automatically be clipped off at the reverse side with this (automatically reverses left and right for the reverse read).\n\n> Modifies bamUtil's trimBam parameter: `-L -R`"
                 },
                 "bamutils_clip_none_udg_left": {
                     "type": "integer",
-                    "default": "1",
+                    "default": 1,
                     "fa_icon": "fas fa-ruler-combined",
                     "description": "Specify the number of bases to clip off reads from 'left' end of read for non-UDG libraries.",
                     "help_text": "Default set to `1` and clips off one base of the left or right side of reads from libraries whose UDG treatment is set to `none`. Note that reverse reads will automatically be clipped off at the reverse side with this (automatically reverses left and right for the reverse read).\n\n> Modifies bamUtil's trimBam parameter: `-L -R`"
                 },
                 "bamutils_clip_none_udg_right": {
                     "type": "integer",
-                    "default": "1",
+                    "default": 1,
                     "fa_icon": "fas fa-ruler",
                     "description": "Specify the number of bases to clip off reads from 'right' end of read for non-UDG libraries.",
                     "help_text": "Default set to `1` and clips off one base of the left or right side of reads from libraries whose UDG treatment is set to `none`. Note that reverse reads will automatically be clipped off at the reverse side with this (automatically reverses left and right for the reverse read).\n\n> Modifies bamUtil's trimBam parameter: `-L -R`"
@@ -1023,9 +1027,9 @@
                 },
                 "freebayes_g": {
                     "type": "integer",
+                    "default": 0,
                     "description": "Specify to skip over regions of high depth by discarding alignments overlapping positions where total read depth is greater than specified in --freebayes_C.",
                     "fa_icon": "fab fa-think-peaks",
-                    "default": "0",
                     "help_text": "Specify to skip over regions of high depth by discarding alignments overlapping positions where total read depth is greater than specified C. Not set by default.\n\n> Modifies freebayes parameter: `-g`"
                 },
                 "freebayes_p": {