Add bam/cram support

CHANGELOG.md

@@ -8,6 +8,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Added
 
 - [#116](https://github.com/nf-core/rnavar/pull/116) - Added `unzip` from nf-core modules for working with unzipped fasta and gtf files
+- [#157](https://github.com/nf-core/rnavar/pull/157) - Added support for `bam` and `cram` input files
 
 ### Changed
 

assets/schema_input.json

@@ -32,8 +32,40 @@
                 "errorMessage": "Strandedness must be provided and be one of 'forward', 'reverse' or 'unstranded'",
                 "enum": ["forward", "reverse", "unstranded"],
                 "meta": ["strandedness"]
+            },
+            "bam": {
+                "type": "string",
+                "format": "file-path",
+                "exists": true,
+                "pattern": "^\\S+\\.bam$",
+                "errorMessage": "BAM file should end with `.bam`, should not contains spaces and should exist."
+            },
+            "bai": {
+                "type": "string",
+                "format": "file-path",
+                "exists": true,
+                "pattern": "^\\S+\\.bai$",
+                "errorMessage": "BAI file should end with `.bai`, should not contains spaces and should exist."
+            },
+            "cram": {
+                "type": "string",
+                "format": "file-path",
+                "exists": true,
+                "pattern": "^\\S+\\.cram$",
+                "errorMessage": "CRAM file should end with `.cram`, should not contains spaces and should exist."
+            },
+            "crai": {
+                "type": "string",
+                "format": "file-path",
+                "exists": true,
+                "pattern": "^\\S+\\.crai$",
+                "errorMessage": "CRAI file should end with `.crai`, should not contains spaces and should exist."
             }
         },
-        "required": ["sample", "fastq_1", "strandedness"]
+        "oneOf": [
+            { "required": ["sample", "fastq_1", "strandedness"] },
+            { "required": ["sample", "bam"] },
+            { "required": ["sample", "cram"] }
+        ]
     }
 }

conf/modules.config

@@ -220,6 +220,7 @@ process {
 
     withName: '.*:SPLITNCIGAR:GATK4_SPLITNCIGARREADS' {
         ext.args    =  '--create-output-bam-index false'
+        ext.prefix  = { "${meta.id}.splitncigarreads" }
     }
 
     withName: '.*:SPLITNCIGAR:SAMTOOLS_INDEX' {

docs/usage.md

@@ -111,8 +111,17 @@ TREATMENT_REP3,AEG588A6_S6_L004_R1_001.fastq.gz,,reverse
 | `sample`       | Custom sample name. This entry will be identical for multiple sequencing libraries/runs from the same sample. Spaces in sample names are automatically converted to underscores (`_`). |
 | `fastq_1`      | Full path to FastQ file for Illumina short reads 1. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz".                                                             |
 | `fastq_2`      | Full path to FastQ file for Illumina short reads 2. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz".                                                             |
+| `bam`          | Full path to BAM file created with STAR and duplicate marked. File has to have the extension ".bam".                                                                                   |
+| `bai`          | Full path to index file of the BAM file. File has to have the extension ".bai".                                                                                                        |
+| `cram`         | Full path to CRAM file created with STAR and duplicate marked. File has to have the extension ".cram".                                                                                 |
+| `crai`         | Full path to index file of the CRAM file. File has to have the extension ".crai".                                                                                                      |
 | `strandedness` | Sample strand-specificity. Must be one of `unstranded`, `forward` or `reverse`.                                                                                                        |
 
+:::note
+Only one file type per sample is allowed. Supplying FASTQ files and a BAM/CRAM file for the same sample will cause an error in the pipeline.
+The pipeline also has no support for multiple BAM/CRAM file per sample.
+:::
+
 An [example samplesheet](../assets/samplesheet.csv) has been provided with the pipeline.
 
 ## PIPELINE PARAMETERS AND DESCRIPTION

main.nf

@@ -112,7 +112,7 @@ workflow NFCORE_RNAVAR {
     ch_gtf              = PREPARE_GENOME.out.gtf
     ch_dict             = params.dict           ? Channel.fromPath(params.dict).map{ it -> [ [id:'dict'], it ] }.collect()
                                                 : PREPARE_GENOME.out.dict
-    ch_fasta_fai        = params.fasta_fai      ? Channel.fromPath(params.fasta_fai)
+    ch_fasta_fai        = params.fasta_fai      ? Channel.fromPath(params.fasta_fai).map{ it -> [ [id:'fasta_fai'], it ] }.collect()
                                                 : PREPARE_GENOME.out.fasta_fai
     ch_exon_bed         = params.exon_bed       ? Channel.fromPath(params.exon_bed).map{ it -> [ [id:'exon_bed'], it ] }.collect()
                                                 : PREPARE_GENOME.out.exon_bed

modules.json

@@ -135,6 +135,11 @@
                         "git_sha": "1943aa60f7490c3d6740e8872e6e69122ccc8087",
                         "installed_by": ["bam_markduplicates_picard"]
                     },
+                    "samtools/convert": {
+                        "branch": "master",
+                        "git_sha": "b13f07be4c508d6ff6312d354d09f2493243e208",
+                        "installed_by": ["modules"]
+                    },
                     "samtools/faidx": {
                         "branch": "master",
                         "git_sha": "f153f1f10e1083c49935565844cccb7453021682",