Finish deeptools modules (#442)

* Adding bigWig and deeptools computeMatrix files to config

* Adding meta.yml for deeptools modules

* Add test for deeptools modules

* Fixing and reordering tags

* Fixing conda test that worked in local...

* Apply suggestions from code review

* Changing bigwig file pattern to include bigwig extension

* Saving after last change is a good practice

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

software/deeptools/computematrix/meta.yml

@@ -0,0 +1,58 @@
+name: deeptools_computematrix
+description: calculates scores per genome regions for other deeptools plotting utilities
+keywords:
+  - genome
+  - regions
+  - scores
+  - matrix
+tools:
+  - deeptools:
+      description: A set of user-friendly tools for normalization and visualization of deep-sequencing data
+      homepage:
+      documentation: https://deeptools.readthedocs.io/en/develop/index.html
+      tool_dev_url: https://github.com/deeptools/deepTools
+      doi: "10.1093/nar/gku365"
+      licence: ['GPL v3']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - bigwig:
+      type: file
+      description: bigwig file containing genomic scores
+      pattern: "*.{bw,bigwig}"
+  - bed:
+      type: file
+      description: bed file containing genomic regions
+      pattern: "*.{bed}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - matrix:
+      type: file
+      description: |
+        gzipped matrix file needed by the plotHeatmap and plotProfile
+        deeptools utilities
+      pattern: "*.{computeMatrix.mat.gz}"
+  - table:
+      type: file
+      description: |
+        tabular file containing the scores of the generated matrix
+      pattern: "*.{computeMatrix.vals.mat.tab}"
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.{version.txt}"
+
+authors:
+  - "@jeremy1805"
+  - "@emiller88"
+  - "@drpatelh"
+  - "@joseespinosa"

software/deeptools/plotfingerprint/meta.yml

@@ -0,0 +1,61 @@
+name: deeptools_plotfingerprint
+description: plots cumulative reads coverages by BAM file
+keywords:
+  - plot
+  - fingerprint
+  - cumulative coverage
+  - bam
+tools:
+  - deeptools:
+      description: A set of user-friendly tools for normalization and visualization of deep-sequencing data
+      homepage:
+      documentation: https://deeptools.readthedocs.io/en/develop/index.html
+      tool_dev_url: https://github.com/deeptools/deepTools
+      doi: "10.1093/nar/gku365"
+      licence: ['GPL v3']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - bam:
+      type: file
+      description: One or more BAM files
+      pattern: "*.{bam}"
+  - bais:
+      type: file
+      description: Corresponding BAM file indexes
+      pattern: "*.bam.bai"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - pdf:
+      type: file
+      description: |
+        Output figure containing resulting plot
+      pattern: "*.{plotFingerprint.pdf}"
+  - matrix:
+      type: file
+      description: |
+        Output file summarizing the read counts per bin
+      pattern: "*.{plotFingerprint.raw.txt}"
+  - metrics:
+      type: file
+      description: |
+        file containing BAM file quality metrics
+      pattern: "*.{qcmetrics.txt}"
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.{version.txt}"
+
+authors:
+  - "@emiller88"
+  - "@drpatelh"
+  - "@joseespinosa"

software/deeptools/plotheatmap/meta.yml

@@ -0,0 +1,55 @@
+name: deeptools_plotheatmap
+description: plots values produced by deeptools_computematrix as a heatmap
+keywords:
+  - plot
+  - heatmap
+  - scores
+  - matrix
+tools:
+  - deeptools:
+      description: A set of user-friendly tools for normalization and visualization of deep-sequencing data
+      homepage:
+      documentation: https://deeptools.readthedocs.io/en/develop/index.html
+      tool_dev_url: https://github.com/deeptools/deepTools
+      doi: "10.1093/nar/gku365"
+      licence: ['GPL v3']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - matrix:
+      type: file
+      description: |
+        gzipped matrix file produced by deeptools_
+        computematrix deeptools utility
+      pattern: "*.{mat.gz}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - pdf:
+      type: file
+      description: |
+        Output figure containing resulting plot
+      pattern: "*.{plotHeatmap.pdf}"
+  - matrix:
+      type: file
+      description: |
+        File containing the matrix of values
+        used to generate the heatmap
+      pattern: "*.{plotHeatmap.mat.tab}"
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.{version.txt}"
+
+authors:
+  - "@emiller88"
+  - "@drpatelh"
+  - "@joseespinosa"

software/deeptools/plotprofile/meta.yml

@@ -0,0 +1,55 @@
+name: deeptools_plotprofile
+description: plots values produced by deeptools_computematrix as a profile plot
+keywords:
+  - plot
+  - profile
+  - scores
+  - matrix
+tools:
+  - deeptools:
+      description: A set of user-friendly tools for normalization and visualization of deep-sequencing data
+      homepage:
+      documentation: https://deeptools.readthedocs.io/en/develop/index.html
+      tool_dev_url: https://github.com/deeptools/deepTools
+      doi: "10.1093/nar/gku365"
+      licence: ['GPL v3']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - matrix:
+      type: file
+      description: |
+        gzipped matrix file produced by deeptools_
+        computematrix deeptools utility
+      pattern: "*.{mat.gz}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - pdf:
+      type: file
+      description: |
+        Output figure containing resulting plot
+      pattern: "*.{plotProfile.pdf}"
+  - matrix:
+      type: file
+      description: |
+        File containing the matrix of values
+        used to generate the profile
+      pattern: "*.{plotProfile.mat.tab}"
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.{version.txt}"
+
+authors:
+  - "@emiller88"
+  - "@drpatelh"
+  - "@joseespinosa"

tests/config/pytest_software.yml

@@ -166,6 +166,22 @@ cutadapt:
   - software/cutadapt/**
   - tests/software/cutadapt/**
 
+deeptools/computematrix:
+  - software/deeptools/computematrix/**
+  - tests/software/deeptools/computematrix/**
+
+deeptools/plotfingerprint:
+  - software/deeptools/plotfingerprint/**
+  - tests/software/deeptools/plotfingerprint/**
+
+deeptools/plotheatmap:
+  - software/deeptools/plotheatmap/**
+  - tests/software/deeptools/plotheatmap/**
+
+deeptools/plotprofile:
+  - software/deeptools/plotprofile/**
+  - tests/software/deeptools/plotprofile/**
+
 dsh/filterbed:
   - software/dsh/filterbed/**
   - tests/software/dsh/filterbed/**

tests/config/test_data.config

@@ -47,10 +47,13 @@ params {
                 test_methylated_2_fastq_gz                = "${test_data_dir}/genomics/sarscov2/illumina/fastq/test_methylated_2.fastq.gz"
 
                 test_bedgraph                             = "${test_data_dir}/genomics/sarscov2/illumina/bedgraph/test.bedgraph"
+                test_bigwig                               = "${test_data_dir}/genomics/sarscov2/illumina/bigwig/test.bigwig"
                 test_wig_gz                               = "${test_data_dir}/genomics/sarscov2/illumina/wig/test.wig.gz"
 
                 test_baserecalibrator_table               = "${test_data_dir}/genomics/sarscov2/illumina/gatk/test.baserecalibrator.table"
 
+                test_computematrix_mat_gz                 = "${test_data_dir}/genomics/sarscov2/illumina/deeptools/test.computeMatrix.mat.gz"
+
                 test_vcf                                  = "${test_data_dir}/genomics/sarscov2/illumina/vcf/test.vcf"
                 test_vcf_gz                               = "${test_data_dir}/genomics/sarscov2/illumina/vcf/test.vcf.gz"
                 test_vcf_gz_tbi                           = "${test_data_dir}/genomics/sarscov2/illumina/vcf/test.vcf.gz.tbi"

tests/software/deeptools/computematrix/main.nf

@@ -0,0 +1,16 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { DEEPTOOLS_COMPUTEMATRIX } from '../../../../software/deeptools/computematrix/main.nf' addParams( options: ['args' : 'scale-regions -b 1000'] )
+
+workflow test_deeptools_computematrix {
+
+    input = [ [ id:'test' ], // meta map
+              file(params.test_data['sarscov2']['illumina']['test_bigwig'], checkIfExists: true)
+            ]
+
+    bed = file(params.test_data['sarscov2']['genome']['test_bed'], checkIfExists: true)
+
+    DEEPTOOLS_COMPUTEMATRIX ( input, bed )
+}

tests/software/deeptools/computematrix/test.yml

@@ -0,0 +1,9 @@
+- name: deeptools computematrix
+  command: nextflow run tests/software/deeptools/computematrix -entry test_deeptools_computematrix -c tests/config/nextflow.config
+  tags:
+    - deeptools
+    - deeptools/computematrix
+  files:
+    - path: output/deeptools/test.computeMatrix.mat.gz
+    - path: output/deeptools/test.computeMatrix.vals.mat.tab
+      md5sum: 19e22051cc44edb7db3e0f8345330d90

tests/software/deeptools/plotfingerprint/main.nf

@@ -0,0 +1,17 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+params.fragment_size = 1000
+
+include { DEEPTOOLS_PLOTFINGERPRINT } from '../../../../software/deeptools/plotfingerprint/main.nf' addParams( options: [:] )
+
+workflow test_deeptools_plotfingerprint {
+
+    input = [ [ id:'test' ], // meta map
+              file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+              file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true)
+            ]
+
+    DEEPTOOLS_PLOTFINGERPRINT ( input )
+}

tests/software/deeptools/plotfingerprint/test.yml

@@ -0,0 +1,13 @@
+- name: deeptools plotfingerprint
+  command: nextflow run tests/software/deeptools/plotfingerprint -entry test_deeptools_plotfingerprint -c tests/config/nextflow.config
+  tags:
+    - deeptools
+    - deeptools/plotfingerprint
+  files:
+    - path: output/deeptools/test.plotFingerprint.pdf
+    - path: output/deeptools/test.plotFingerprint.qcmetrics.txt
+      contains:
+      - "AUC"
+      - "0.24184576629880325"
+    - path: output/deeptools/test.plotFingerprint.raw.txt
+      md5sum: e2a9ff341a315f49e7c8387a3323bdfb

tests/software/deeptools/plotheatmap/main.nf

@@ -0,0 +1,14 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { DEEPTOOLS_PLOTHEATMAP } from '../../../../software/deeptools/plotheatmap/main.nf' addParams( options: [:] )
+
+workflow test_deeptools_plotheatmap {
+
+    input = [ [ id:'test' ], // meta map
+              file(params.test_data['sarscov2']['illumina']['test_computematrix_mat_gz'], checkIfExists: true)
+            ]
+
+    DEEPTOOLS_PLOTHEATMAP ( input )
+}

tests/software/deeptools/plotheatmap/test.yml

@@ -0,0 +1,9 @@
+- name: deeptools plotheatmap
+  command: nextflow run tests/software/deeptools/plotheatmap -entry test_deeptools_plotheatmap -c tests/config/nextflow.config
+  tags:
+    - deeptools
+    - deeptools/plotheatmap
+  files:
+    - path: output/deeptools/test.plotHeatmap.mat.tab
+    - path: output/deeptools/test.plotHeatmap.pdf
+

tests/software/deeptools/plotprofile/main.nf

@@ -0,0 +1,14 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { DEEPTOOLS_PLOTPROFILE } from '../../../../software/deeptools/plotprofile/main.nf' addParams( options: [:] )
+
+workflow test_deeptools_plotprofile {
+
+    input = [ [ id:'test' ], // meta map
+              file(params.test_data['sarscov2']['illumina']['test_computematrix_mat_gz'], checkIfExists: true)
+            ]
+
+    DEEPTOOLS_PLOTPROFILE ( input )
+}

tests/software/deeptools/plotprofile/test.yml

@@ -0,0 +1,9 @@
+- name: deeptools plotprofile
+  command: nextflow run tests/software/deeptools/plotprofile -entry test_deeptools_plotprofile -c tests/config/nextflow.config
+  tags:
+    - deeptools
+    - deeptools/plotprofile
+  files:
+    - path: output/deeptools/test.plotProfile.pdf
+    - path: output/deeptools/test.plotProfile.tab
+      md5sum: d561cb659a292cef973ea631c7d440cb