Merge pull request #10 from TRON-Bioinformatics/one-sample-input

add support to providing an individual sample through CLI params

Author: priesgo

Makefile

@@ -22,3 +22,4 @@ test:
 	bash tests/test_06.sh
 	bash tests/test_08.sh
 	bash tests/test_09.sh
+	bash tests/test_10.sh

README.md

@@ -53,6 +53,9 @@ Input:
     * reference: path to the FASTA genome reference (indexes expected *.fai, *.dict)
     
 Optional input:
+    * input_name: sample name (alternative to --input_files)
+    * input_tumor_bam: comma separated list of tumor BAMs (alternative to --input_files)
+    * input_normal_bam: comma separated list of normal BAMs (alternative to --input_files)
     * gnomad: path to the gnomad VCF or other germline resource (recommended). If not provided the contamination will 
     not be estimated and the filter of common germline variants will be disabled
     * intervals: path to a BED file containing the regions to analyse

main.nf

@@ -11,6 +11,9 @@ include { FUNCOTATOR } from './modules/06_annotate'
 
 params.help= false
 params.input_files = false
+params.input_name = false
+params.input_tumor_bam = false
+params.input_normal_bam = false
 params.reference = false
 params.gnomad = false
 params.output = 'output'
@@ -36,6 +39,10 @@ if (params.input_files) {
     .splitCsv(header: ['name', 'tumor_bam', 'normal_bam'], sep: "\t")
     .map{ row-> tuple(row.name, row.tumor_bam, row.normal_bam) }
     .set { input_files }
+} else if (params.input_name && params.input_tumor_bam && params.input_normal_bam) {
+   Channel
+    .fromList([tuple(params.input_name, params.input_tumor_bam, params.input_normal_bam)])
+    .set { input_files }
 } else {
   exit 1, "Input file not specified!"
 }

nextflow.config

@@ -37,7 +37,7 @@ env {
 // Capture exit codes from upstream processes when piping
 process.shell = ['/bin/bash', '-euo', 'pipefail']
 
-VERSION = '1.7.0'
+VERSION = '1.8.0'
 DOI = 'https://zenodo.org/badge/latestdoi/355860788'
 
 manifest {
@@ -68,6 +68,9 @@ Input:
     * reference: path to the FASTA genome reference (indexes expected *.fai, *.dict)
 
 Optional input:
+    * input_name: sample name (alternative to --input_files)
+    * input_tumor_bam: comma separated list of tumor BAMs (alternative to --input_files)
+    * input_normal_bam: comma separated list of normal BAMs (alternative to --input_files)
     * gnomad: path to the gnomad VCF or other germline resource (recommended). If not provided the contamination will
     not be estimated and the filter of common germline variants will be disabled
     * intervals: path to a BED file containing the regions to analyse

tests/test_10.sh

@@ -0,0 +1,12 @@
+#!/bin/bash
+
+
+source bin/assert.sh
+output=output/test10
+
+nextflow main.nf -profile test,conda --output $output \
+--input_name sample_name \
+--input_tumor_bam `pwd`/test_data/SRR8244887.preprocessed.downsampled.bam \
+--input_normal_bam `pwd`/test_data/SRR8244836.preprocessed.downsampled.bam
+
+test -s $output/sample_name/sample_name.mutect2.vcf || { echo "Missing output VCF file!"; exit 1; }