feat: Add cadd for indels

CHANGELOG.md

@@ -24,6 +24,7 @@ Initial release of Clinical-Genomics/oncorefiner, created with the [nf-core](htt
 - [#60](https://github.com/Clinical-Genomics/oncorefiner/pull/60) Added `GENERATE_CYTOSURE_FILES` subworkflow and necessary nf-core modules `TIDDIT_COV` and `VCF2CYTOSURE`.
 - [#70](https://github.com/Clinical-Genomics/oncorefiner/pull/70) Added `SAMTOOLS/VIEW` for bam to cram conversion in the `main.nf`.
 - [#66](https://github.com/Clinical-Genomics/oncorefiner/pull/66) Added `PROCESS_SNVS` subworkflow.
+- [#59](https://github.com/Clinical-Genomics/oncorefiner/pull/59) Added `ANNOTATE_CADD` subworkflow with following test (stub only), for CADD scoring of InDels, used in `PROCESS_SNVS`.
 
 ### `Changed`
 

CITATIONS.md

@@ -12,6 +12,12 @@
 
 ## Pipeline tools
 
+- [CADD<sup>1</sup>](https://genomemedicine.biomedcentral.com/articles/10.1186/s13073-021-00835-9)<sup>,</sup> [<sup>2</sup>](https://academic.oup.com/nar/article/47/D1/D886/5146191)
+
+  > Rentzsch P, Schubach M, Shendure J, Kircher M. CADD-Splice—improving genome-wide variant effect prediction using deep learning-derived splice scores. Genome Med. 2021;13(1):31. doi:10.1186/s13073-021-00835-9
+
+  > Rentzsch P, Witten D, Cooper GM, Shendure J, Kircher M. CADD: predicting the deleteriousness of variants throughout the human genome. Nucleic Acids Research. 2019;47(D1):D886-D894. doi:10.1093/nar/gky1016
+
 - [`bcftools`](https://github.com/samtools/bcftools)
 
   > Danecek P, Bonfield JK, Liddle J, Marshall J, Ohan V, Pollard MO, Whitwham A, Keane T, McCarthy SA, Davies RM, Li H. Twelve years of SAMtools and BCFtools. Gigascience. 2021 Jan 29;10(2):giab008. doi: 10.1093/gigascience/giab008. PubMed PMID: 33590861; PubMed Central PMCID: PMC7931819.

assets/cadd_to_vcf_header.txt

@@ -0,0 +1 @@
+##INFO=<ID=CADD,Number=1,Type=Float,Description="PHRED-like scaled CADD score.">

conf/subworkflows/annotate_cadd.config

@@ -0,0 +1,65 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Config file for defining DSL2 per module options and publishing paths
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Available keys to override module options:
+        ext.args            = Additional arguments appended to command in module.
+        ext.args2           = Second set of arguments appended to command in module (multi-tool modules).
+        ext.args3           = Third set of arguments appended to command in module (multi-tool modules).
+        ext.prefix          = File name prefix for output files.
+        ext.when            = Conditional clause
+----------------------------------------------------------------------------------------
+*/
+
+//
+// Annotate with CADD
+//
+
+
+process {
+
+    withName: '.*:ANNOTATE_CADD:.*' {
+        publishDir = [
+            enabled: false
+        ]
+    }
+
+    withName: '.*:ANNOTATE_CADD:BCFTOOLS_RENAME_CHR_CADD' {
+        ext.args   = { "--output-type z" }
+        ext.prefix = { "${input.simpleName}_indels" }
+    }
+
+    withName: '.*:ANNOTATE_CADD:BCFTOOLS_VIEW' {
+        ext.args   = { "--output-type z --types indels,other" }
+        ext.prefix = { "${vcf.simpleName}_indels" }
+    }
+
+    withName: '.*:ANNOTATE_CADD:CADD' {
+        ext.args   = { "-g ${params.genome}" }
+        ext.prefix = { "${vcf.simpleName}_cadd" }
+    }
+
+    withName: '.*:ANNOTATE_CADD:TABIX_CADD' {
+        ext.args = { "--force --sequence 1 --begin 2 --end 2" }
+    }
+
+    withName: '.*:ANNOTATE_CADD:GAWK_CADD_TO_REF_CHRNAMES' {
+        ext.args2 = '\'{original=$1; sub("chr","",$1); print $1, original}\''
+        ext.prefix = "cadd_to_reference"
+        ext.suffix = "txt"
+    }
+
+    withName: '.*:ANNOTATE_CADD:GAWK_REF_TO_CADD_CHRNAMES' {
+        ext.args2 = '\'{original=$1; sub("chr","",$1); print original, $1}\''
+        ext.prefix = "reference_to_cadd"
+        ext.suffix = "txt"
+    }
+
+    withName: '.*:ANNOTATE_CADD:BCFTOOLS_ANNOTATE_INDELS' {
+        ext.args   = { "--columns Chrom,Pos,Ref,Alt,-,CADD --output-type z --write-index=tbi" }
+        ext.prefix = { "${input.simpleName}_ann" }
+        publishDir = [
+            path: { "${params.outdir}/annotations" },
+            mode: params.publish_dir_mode ]
+    }
+}

conf/test.config

@@ -51,4 +51,5 @@ params {
 
     svdb_query_dbs      = params.pipelines_testdata_base_path + 'reference/svdb_querydb_files.csv'
 
+    // TODO make/insert mock input for CADD
 }

docs/parameters.md

@@ -29,6 +29,8 @@ Reference genome related files and options required for the workflow.
 | `genome` | Name of the genome reference. (accepted: `GRCh38`\|`GRCh37`) <details><summary>Help</summary><small>Use this parameter to specify the ID for the reference genome used. This is then used to annotate the SV and SNV files e.g. `--genome GRCh38`.</small></details>| `string` | GRCh38 |  |  |
 | `fasta` | Path to FASTA genome file. <details><summary>Help</summary><small>If you don't have a BWA index available this will be generated for you automatically. Combine with `--save_reference` to save BWA index for future runs.</small></details>| `string` |  |  |  |
 | `fai` | Path to FASTA genome index file. <details><summary>Help</summary><small>If none provided, will be generated automatically from the FASTA reference</small></details>| `string` |  |  |  |
+| `cadd_prescored_indels` | Path to a directory containing prescored indels for CADD. <details><summary>Help</summary><small>This folder contains the compressed files and indexes that would otherwise be in data/prescored folder as described in https://github.com/kircherlab/CADD-scripts/#manual-installation.</small></details>| `string` |  |  |  |
+| `cadd_resources` | Path to the directory containing cadd annotations. <details><summary>Help</summary><small>This folder contains the uncompressed files that would otherwise be in data/annotation folder as described in https://github.com/kircherlab/CADD-scripts/#manual-installation.</small></details>| `string` |  |  |  |
 | `species` | Species of the reference genome. E.g. `--species homo_sapiens`. (accepted: `homo_sapiens`) | `string` | homo_sapiens |  |  |
 
 ## Annotation options

main.nf

@@ -35,6 +35,8 @@ workflow CLINICALGENOMICS_ONCOREFINER {
     val_bai_normal              // string:  [optional]  path to BAI file for the normal sample
     val_bam_tumor               // string:  [optional]  path to BAM file for the tumor sample
     val_bai_tumor               // string:  [optional]  path to BAI file for the tumor sample
+    val_cadd_prescored_indels   // string:  [optional]  path to CADD prescored indels file
+    val_cadd_resources          // string:  [optional]  path to CADD resources directory
     val_genome                  // string:  [optional]  genome assembly (e.g. "GRCh38")
     val_genome_fasta            // string:  [optional]  path to genome fasta file
     val_genome_fai              // string:  [optional]  path to genome fasta index file
@@ -64,15 +66,15 @@ workflow CLINICALGENOMICS_ONCOREFINER {
     //
 
     // Input channels
-    ch_snv_vcf              = channel.fromPath(val_snv_vcf).map { vcf -> [[id:vcf.simpleName], vcf] }.collect()
-    ch_snv_vcf_tbi          = channel.fromPath(val_snv_vcf + '.tbi', checkIfExists: true).map { vcf -> [[id:vcf.simpleName], vcf] }.collect()
-    ch_sv_vcf               = channel.fromPath(val_sv_vcf).map { vcf -> [[id:vcf.simpleName], vcf] }.collect()
-    ch_sv_vcf_tbi           = channel.fromPath(val_sv_vcf + '.tbi', checkIfExists: true).map { vcf -> [[id:vcf.simpleName], vcf] }.collect()
-    ch_vep_extra_files      = channel.empty()
-    ch_svdb_dbs             = channel.empty()
+    ch_snv_vcf         = channel.fromPath(val_snv_vcf).map { vcf -> [[id:vcf.simpleName], vcf] }.collect()
+    ch_snv_vcf_tbi     = channel.fromPath(val_snv_vcf + '.tbi', checkIfExists: true).map { vcf -> [[id:vcf.simpleName], vcf] }.collect()
+    ch_sv_vcf          = channel.fromPath(val_sv_vcf).map { vcf -> [[id:vcf.simpleName], vcf] }.collect()
+    ch_sv_vcf_tbi      = channel.fromPath(val_sv_vcf + '.tbi', checkIfExists: true).map { vcf -> [[id:vcf.simpleName], vcf] }.collect()
+    ch_vep_extra_files = channel.empty()
+    ch_svdb_dbs        = channel.empty()
 
     // Alignment files
-    ch_bam_bai_normal = channel.empty()
+    ch_bam_bai_normal  = channel.empty()
 
     if (val_bam_normal && val_bai_normal) {
         ch_bam_bai_normal = channel.fromPath(val_bam_normal)
@@ -89,9 +91,17 @@ workflow CLINICALGENOMICS_ONCOREFINER {
     }
 
     // Reference files
-    ch_genome_fasta         = channel.fromPath(val_genome_fasta).map { it -> [[id:it.simpleName], it] }.collect()
-    ch_genome_fai           = channel.fromPath(val_genome_fai).map { it -> [[id:it.simpleName], it] }.collect()
-    ch_genome_fasta_fai     = ch_genome_fasta.join(ch_genome_fai, failOnMismatch: true, failOnDuplicate: true)
+    ch_genome_fasta          = channel.fromPath(val_genome_fasta).map { it -> [[id:it.simpleName], it] }.collect()
+    ch_genome_fai            = channel.fromPath(val_genome_fai).map { it -> [[id:it.simpleName], it] }.collect()
+    ch_genome_fasta_fai      = ch_genome_fasta.join(ch_genome_fai, failOnMismatch: true, failOnDuplicate: true)
+
+    // CADD input files
+    ch_cadd_header           = channel.fromPath("$projectDir/assets/cadd_to_vcf_header.txt", checkIfExists: true).collect()
+    ch_cadd_resources        = val_cadd_resources        ? channel.fromPath(val_cadd_resources).map { it -> [[id:'cadd_resources'], it] }.collect()
+                                                         : channel.value([])
+
+    ch_cadd_prescored_indels = val_cadd_prescored_indels ? channel.fromPath(val_cadd_prescored_indels).map { it -> [[id:'cadd_prescored_indels'], it] }.collect()
+                                                         : channel.value([])
 
     // Input for VEP
     ch_vep_extra_files_unsplit  = val_vep_plugin_files ? channel.fromPath(val_vep_plugin_files).collect() : channel.value([])
@@ -129,7 +139,11 @@ workflow CLINICALGENOMICS_ONCOREFINER {
         samplesheet,
         ch_bam_bai_normal,
         ch_bam_bai_tumor,
+        ch_cadd_header,
+        ch_cadd_prescored_indels,
+        ch_cadd_resources,
         ch_genome_fasta,
+        ch_genome_fai,
         ch_snv_vcf,
         ch_snv_vcf_tbi,
         ch_sv_dbs,
@@ -141,6 +155,7 @@ workflow CLINICALGENOMICS_ONCOREFINER {
         ch_vcfanno_toml,
         PREPARE_REFERENCES.out.vep_resources,
         ch_vep_extra_files,
+        val_cadd_resources,
         val_genome,
         val_species,
         val_vep_cache_version
@@ -194,6 +209,8 @@ workflow {
         params.bai_normal,
         params.bam_tumor,
         params.bai_tumor,
+        params.cadd_prescored_indels,
+        params.cadd_resources,
         params.genome,
         params.fasta,
         params.fai,

modules.json

@@ -25,11 +25,21 @@
                         "git_sha": "6383d8fe58f9498eecd5aa303e71a4a932d1e9f6",
                         "installed_by": ["modules"]
                     },
+                    "cadd": {
+                        "branch": "master",
+                        "git_sha": "64ab14a6905e5c9d649f61e2757a1e600dbdb8e0",
+                        "installed_by": ["modules"]
+                    },
                     "ensemblvep/vep": {
                         "branch": "master",
                         "git_sha": "34505e1fc5e9f4fd641210ca440acff6bd33b842",
                         "installed_by": ["modules"]
                     },
+                    "gawk": {
+                        "branch": "master",
+                        "git_sha": "c0da8f3a26835d663873001382a708f75766fec6",
+                        "installed_by": ["modules"]
+                    },
                     "multiqc": {
                         "branch": "master",
                         "git_sha": "2c73cc8fa92cf48de3da0b643fdf357a8a290b36",