Merge pull request #34 from luslab/feat-mod-umitools

Added Umi-tools module covering the dedup function

tools/umi_tools/Dockerfile

@@ -0,0 +1,8 @@
+FROM nfcore/base:1.7
+LABEL authors="chris.cheshire@crick.ac.uk" \
+      description="Docker image containing all requirements for the nf-core umi_tools module"
+
+# Install conda packages
+COPY environment.yml /
+RUN conda env create -f /environment.yml && conda clean -a
+ENV PATH /opt/conda/envs/nfcore-module-umitools/bin:$PATH

tools/umi_tools/environment.yml

@@ -0,0 +1,10 @@
+# This file creates a conda environment for the umi_tools module
+#   conda env create -f environment.yml
+name: nfcore-module-umitools
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - umi_tools=1.0.1
+  - samtools=1.1.0

tools/umi_tools/main.nf

@@ -0,0 +1,45 @@
+#!/usr/bin/env nextflow
+
+// Specify DSL2
+nextflow.preview.dsl = 2
+
+// Process definition
+process umitools_dedup {
+    publishDir "${params.outdir}/umitools/dedup",
+        mode: "copy", overwrite: true
+
+    container 'luslab/nf-modules-umitools:latest'
+
+    input:
+        tuple val(sample_id), path(bam)
+       
+    output:
+        tuple val(sample_id), path("${sample_id}.dedup.bam"), emit: dedupBam
+        tuple val(sample_id), path("${sample_id}.dedup.bam.bai"), emit: dedupBai
+        path "*.dedup.log", emit: report
+
+    script:
+
+    // Init
+    args = "--log=${sample_id}.dedup.log"
+
+    // Check main args string exists and strip whitespace
+    if(params.umitools_dedup_args) {
+        ext_args = params.umitools_dedup_args
+        args += " " + ext_args.trim()
+    }
+
+    // Contruct CL line
+    dedup_command = "umi_tools dedup ${args} -I ${bam[0]} -S ${sample_id}.dedup.bam --output-stats=${sample_id}"
+
+    // Log
+    if (params.verbose){
+        println ("[MODULE] umi_tools/dedup command: " + dedup_command)
+    }
+
+    //SHELL
+    """
+    ${dedup_command}
+    samtools index ${sample_id}.dedup.bam
+    """
+}

tools/umi_tools/test/main.nf

@@ -0,0 +1,62 @@
+#!/usr/bin/env nextflow
+
+// Define DSL2
+nextflow.preview.dsl=2
+
+// Log
+log.info ("Starting tests for umi_tools dedup...")
+
+/*------------------------------------------------------------------------------------*/
+/* Define params
+--------------------------------------------------------------------------------------*/
+
+params.umitools_dedup_args = '--umi-separator=":"'
+params.verbose = false
+
+/*------------------------------------------------------------------------------------*/
+/* Module inclusions
+--------------------------------------------------------------------------------------*/
+
+include umitools_dedup from '../main.nf'
+
+/*------------------------------------------------------------------------------------*/
+/* Define input channels
+--------------------------------------------------------------------------------------*/
+
+// Define test data
+testData = [
+    ['sample1', "$baseDir/input/sample1.bam", "$baseDir/input/sample1.bai"],
+    ['sample2', "$baseDir/input/sample2.bam", "$baseDir/input/sample2.bai"],
+    ['sample3', "$baseDir/input/sample3.bam", "$baseDir/input/sample3.bai"],
+    ['sample4', "$baseDir/input/sample4.bam", "$baseDir/input/sample4.bai"],
+    ['sample5', "$baseDir/input/sample5.bam", "$baseDir/input/sample5.bai"],
+    ['sample6', "$baseDir/input/sample6.bam", "$baseDir/input/sample6.bai"]
+]
+
+//Define test data input channel
+Channel
+    .from(testData)
+    .map { row -> [ row[0], [file(row[1], checkIfExists: true), file(row[2], checkIfExists: true)]]}
+    .set {ch_bam}
+
+/*------------------------------------------------------------------------------------*/
+/* Run tests
+--------------------------------------------------------------------------------------*/
+
+workflow {
+    // Run dedup
+    umitools_dedup ( ch_bam )
+}
+
+workflow.onComplete {
+    def proc = "$baseDir/verify-checksum.sh $baseDir/../../../results/umitools/dedup/*.bam $baseDir/output/*.bam".execute()
+    def b = new StringBuffer()
+    proc.consumeProcessErrorStream(b)
+
+    log.info proc.text
+
+    errorString = b.toString()
+    if(errorString != '')
+        log.error errorString
+        exit 1
+}

tools/umi_tools/test/nextflow.config

@@ -0,0 +1,2 @@
+params.outdir = './results'
+docker.enabled = true

tools/umi_tools/test/verify-checksum.sh

@@ -0,0 +1,40 @@
+#!/bin/sh
+
+if [ -z "$1" ]
+  then
+    echo "No check pattern argument supplied" >&2
+    exit 1
+fi
+
+if [ -z "$2" ]
+  then
+    echo "No verify pattern argument supplied" >&2
+    exit 1
+fi
+
+checkfiles=$1
+infiles=$2
+#echo $checkfiles
+#echo $infiles
+
+echo '\nCalculating check file hashes...'
+md5sum $checkfiles
+
+echo '\nCalculating input file hashes...'
+md5sum $infiles
+
+echo '\nComparing hash of file of hashes...'
+checkver=$(md5sum $checkfiles | awk '{print $1}' | md5sum | awk '{print $1}')
+echo $checkver
+
+inver=$(md5sum $infiles | awk '{print $1}' | md5sum | awk '{print $1}')
+echo $inver
+
+if [ "$checkver" == "$inver" ]
+then
+  echo "Hashes match"
+  exit 0
+else
+  echo "Hashes do not match" >&2
+  exit 1
+fi

tools/umi_tools/umi_tools.yml

@@ -0,0 +1,46 @@
+name: umi_tools
+version: 1.0
+description: Tools for dealing with Unique Molecular Identifiers (UMIs)/Random Molecular Tags (RMTs) and single cell RNA-Seq cell barcodes. 
+keywords:
+    - UMI
+    - RMT
+    - Barcode
+tools:
+    - umi_tools:
+        description: |
+            Tools for dealing with Unique Molecular Identifiers (UMIs)/Random Molecular Tags (RMTs) and single cell RNA-Seq cell barcodes. 
+        homepage: https://github.com/CGATOxford/UMI-tools
+        documentation: https://umi-tools.readthedocs.io/en/latest/
+processes:
+    - dedup:
+        operation: |
+            Set command args to params.umitools_dedup_args
+            The program will execute with the following pattern:
+                umi_tools dedup --log={SAMPLE_ID}.dedup.log {params.umitools_dedup_args} -I {SAMPLE_ID}.bam -S {SAMPLE_ID}.dedup.bam --output-stats={SAMPLE_ID}
+        description: |
+            Groups PCR duplicates and de-duplicates reads to yield one read per group. 
+            Use this when you want to remove the PCR duplicates prior to any downstream analysis.
+        input:
+            - sample_id:
+                type: string
+                description: Sample identifier
+            - bam:
+                type: file array
+                description: BAM sequence file and associated BAI index file
+        output:
+            - dedupBam:
+                type: tuple
+                description: A tuple of samples id and output bam file
+                pattern: [sample_id, *SAMPLE_ID.dedup.bam]
+            - dedupBam:
+                type: tuple
+                description: A tuple of samples id and output bai file
+                pattern: [sample_id, *SAMPLE_ID.dedup.bam.bai]
+            - report:
+                type: file
+                description: Log file for the umi_tools operation
+                pattern: *SAMPLE_ID.dedup.log
+authors:
+    - @candiceh08
+    - @chris-cheshire
+