diff --git a/CHANGELOG.md b/CHANGELOG.md
index fa72bd6..298c9a8 100644
--- a/CHANGELOG.md
+++ b/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`
diff --git a/CITATIONS.md b/CITATIONS.md
index d75c30f..801daaf 100644
--- a/CITATIONS.md
+++ b/CITATIONS.md
@@ -12,6 +12,12 @@
## Pipeline tools
+- [CADD1](https://genomemedicine.biomedcentral.com/articles/10.1186/s13073-021-00835-9), [2](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.
diff --git a/assets/cadd_to_vcf_header.txt b/assets/cadd_to_vcf_header.txt
new file mode 100644
index 0000000..8deee48
--- /dev/null
+++ b/assets/cadd_to_vcf_header.txt
@@ -0,0 +1 @@
+##INFO=
diff --git a/conf/subworkflows/annotate_cadd.config b/conf/subworkflows/annotate_cadd.config
new file mode 100644
index 0000000..301f91c
--- /dev/null
+++ b/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 ]
+ }
+}
diff --git a/conf/test.config b/conf/test.config
index 7eed828..5bf10a6 100644
--- a/conf/test.config
+++ b/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
}
diff --git a/docs/parameters.md b/docs/parameters.md
index ed78e4c..3931d97 100644
--- a/docs/parameters.md
+++ b/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`) Help
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`.Help
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.Help
If none provided, will be generated automatically from the FASTA referenceHelp
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.Help
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.