Add CADD annotation (#266)

* Add CADD annotation * remove cadd patch * Update subworkflows/local/snv_annotation/main.nf Co-authored-by: Anders Jemt <[email protected]> * Update subworkflows/local/annotate_cadd/main.nf Co-authored-by: Anders Jemt <[email protected]> --------- Co-authored-by: Anders Jemt <[email protected]>
genomic-medicine-sweden · Aug 9, 2024 · 687743e · 687743e
1 parent 1b1c8aa
commit 687743e
Show file tree

Hide file tree

Showing 38 changed files with 1,604 additions and 50 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -16,6 +16,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#252](https://github.com/genomic-medicine-sweden/nallo/pull/252) - Added a new `SCATTER_GENOME` subworkflow
 - [#255](https://github.com/genomic-medicine-sweden/nallo/pull/255) - Added a new `RANK_VARIANTS` subworkflow to rank SNVs using genmod
 - [#261](https://github.com/genomic-medicine-sweden/nallo/pull/261) - Added a `--skip_rank_variants` parameter to skip the rank_variants subworkflow
+- [#266](https://github.com/genomic-medicine-sweden/nallo/pull/266) - Added CADD to dynamically calculate indel CADD-scores
 - [#270](https://github.com/genomic-medicine-sweden/nallo/pull/270) - Added SNV phasing stats to MultiQC
 - [#271](https://github.com/genomic-medicine-sweden/nallo/pull/271) - Added a `--skip_aligned_read_qc` parameter to skip the qc aligned reads subworkflow
 
@@ -74,6 +75,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 | `--skip_repeat_wf` | `--skip_repeat_annotation` |
 |                    | `--skip_rank_variants`     |
 |                    | `--skip_aligned_read_qc`   |
+|                    | `--cadd_resources`         |
+|                    | `--cadd_prescored`         |
 
 > [!NOTE]
 > Parameter has been updated if both old and new parameter information is present.
@@ -86,6 +89,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 | ----------- | ----------- | ----------- |
 | deepvariant | 1.5.0       | 1.6.1       |
 | htslib      | 1.19.1      | 1.20        |
+| cadd        |             | 1.6.post1   |
+| gawk        |             | 5.3.0       |
 
 ## v0.2.0 - [2024-06-26]
 

diff --git a/assets/cadd_to_vcf_header_-1.0-.txt b/assets/cadd_to_vcf_header_-1.0-.txt
@@ -0,0 +1 @@
+##INFO=<ID=CADD,Number=1,Type=Float,Description="PHRED-like scaled CADD score.">
diff --git a/conf/modules/annotate_cadd.config b/conf/modules/annotate_cadd.config
@@ -0,0 +1,66 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    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
+----------------------------------------------------------------------------------------
+*/
+
+//
+// CADD annotation
+//
+
+process {
+
+    withName: '.*:ANNOTATE_CADD:.*' {
+        publishDir = [
+            enabled: false
+        ]
+    }
+
+    withName: '.*:ANNOTATE_CADD:BCFTOOLS_VIEW' {
+        ext.args   = [
+            '--output-type z',
+            '--types indels,other'
+        ].join(' ')
+        ext.prefix = { "${vcf.simpleName}_indels" }
+    }
+
+    withName: '.*:ANNOTATE_CADD:CADD' {
+        ext.prefix = { "${vcf.simpleName}_cadd" }
+    }
+
+    withName: '.*:ANNOTATE_CADD:TABIX_CADD' {
+        ext.args = { "--force --sequence 1 --begin 2 --end 2" }
+    }
+
+    withName: '.*:ANNOTATE_CADD:ANNOTATE_INDELS' {
+        ext.args   = [
+            '--columns Chrom,Pos,Ref,Alt,-,CADD',
+            '--output-type z',
+            '--write-index=tbi'
+        ].join(' ')
+        ext.prefix = { "${input.simpleName}_ann" }
+    }
+
+    withName: '.*:ANNOTATE_CADD:REFERENCE_TO_CADD_CHRNAMES' {
+        ext.args2 = '\'{original=$1; sub("chr","",$1); print original, $1}\''
+        ext.prefix = "reference_to_cadd"
+        ext.suffix = "txt"
+    }
+
+    withName: '.*:ANNOTATE_CADD:CADD_TO_REFERENCE_CHRNAMES' {
+        ext.args2 = '\'{original=$1; sub("chr","",$1); print $1, original}\''
+        ext.prefix = "cadd_to_reference"
+        ext.suffix = "txt"
+    }
+
+    withName: '.*:ANNOTATE_CADD:RENAME_CHRNAMES' {
+        ext.args = '--output-type z'
+    }
+}
diff --git a/conf/modules/snv_annotation.config b/conf/modules/snv_annotation.config
@@ -28,6 +28,14 @@ process {
         ext.prefix = { "${meta.id}_echtvar_anno" }
     }
 
+    withName: 'BCFTOOLS_FILLTAGS_ANNO' {
+        ext.prefix = { "${meta.id}_filltags_anno" }
+        ext.args = [
+            '--output-type z',
+            '--write-index=tbi'
+        ].join(' ')
+    }
+
     withName: '.*:SNV_ANNOTATION:ENSEMBLVEP_VEP' {
         ext.prefix = { "${meta.id}_vep" }
         ext.args = { [

diff --git a/docs/usage.md b/docs/usage.md
@@ -114,15 +114,17 @@ Some workflows require additional files:
 - If running without `--skip_repeat_annotation`, download a json variant catalog, (e.g. [variant_catalog_grch38.json](https://github.com/Clinical-Genomics/stranger/raw/main/stranger/resources/variant_catalog_grch38.json)) matching your reference genome to supply with `--variant_catalog`.
 
 - If running without `--skip_snv_annotation`, download [VEP cache](https://ftp.ensembl.org/pub/release-110/variation/vep/homo_sapiens_vep_110_GRCh38.tar.gz) to supply with `--vep_cache` and prepare a samplesheet with annotation databases ([`echtvar encode`](https://github.com/brentp/echtvar)) to supply with `--snp_db`:
-  - If your samplesheet contains at least one affected sample (phenotype = 2), `--reduced_penetrance` (Used by GENMOD while modeling the variants. Contains a list of loci that show [reduced penetrance](https://medlineplus.gov/genetics/understanding/inheritance/penetranceexpressivity/) in people. Sample file [here](https://github.com/nf-core/test-datasets/blob/raredisease/reference/reduced_penetrance.tsv)), `--score_config_snv` (Used by GENMOD for ranking the variants. Sample file [here](https://github.com/nf-core/test-datasets/blob/raredisease/reference/rank_model_snv.ini)) and `--variant_consequences_snv` (File containing list of SO terms listed in the order of severity from most severe to lease severe for annotating genomic and mitochondrial SNVs. Sample file [here](https://github.com/nf-core/test-datasets/blob/raredisease/reference/variant_consequences_v2.txt). You can learn more about these terms [here](https://grch37.ensembl.org/info/genome/variation/prediction/predicted_data.html)) is also required.
-    `snp_dbs.csv`
 
 ```
 sample,file
 gnomad,/path/to/gnomad.v3.1.2.echtvar.popmax.v2.zip
 cadd,/path/to/cadd.v1.6.hg38.zip
 ```
 
+- If your samplesheet contains at least one affected sample (phenotype = 2), `--reduced_penetrance` (Used by GENMOD while modeling the variants. Contains a list of loci that show [reduced penetrance](https://medlineplus.gov/genetics/understanding/inheritance/penetranceexpressivity/) in people. Sample file [here](https://github.com/nf-core/test-datasets/blob/raredisease/reference/reduced_penetrance.tsv)), `--score_config_snv` (Used by GENMOD for ranking the variants. Sample file [here](https://github.com/nf-core/test-datasets/blob/raredisease/reference/rank_model_snv.ini)) and `--variant_consequences_snv` (File containing list of SO terms listed in the order of severity from most severe to lease severe for annotating genomic and mitochondrial SNVs. Sample file [here](https://github.com/nf-core/test-datasets/blob/raredisease/reference/variant_consequences_v2.txt). You can learn more about these terms [here](https://grch37.ensembl.org/info/genome/variation/prediction/predicted_data.html)) is also required.
+
+- Optionally, if running without `--skip_snv_annotation`, supply a path to a folder containing cadd annotations with `--cadd_resources` and prescored indels with `--cadd_prescored`. Equivalent of the data/annotations/ and data/prescored/ folders described [here](https://github.com/kircherlab/CADD-scripts/#manual-installation), and it is used to calculate CADD scores for small indels.
+
 - If running without `--skip_cnv_calling`, expected CN regions for your reference genome can be downloaded from [HiFiCNV GitHub](https://github.com/PacificBiosciences/HiFiCNV/tree/main/data) to supply with `--hificnv_xy`, `--hificnv_xx` (expected_cn) and `--hificnv_exclude` (excluded_regions).
 
 - If you want to include extra samples for mili-sample calling of SVs - prepare a samplesheet with .snf files from Sniffles to supply with `--extra_snfs`:

diff --git a/modules.json b/modules.json
@@ -5,6 +5,12 @@
         "https://github.com/nf-core/modules.git": {
             "modules": {
                 "nf-core": {
+                    "bcftools/annotate": {
+                        "branch": "master",
+                        "git_sha": "c1a7fa1c038061b344f2a41be71942061ec40d2e",
+                        "installed_by": ["modules"],
+                        "patch": "modules/nf-core/bcftools/annotate/bcftools-annotate.diff"
+                    },
                     "bcftools/concat": {
                         "branch": "master",
                         "git_sha": "33ef773a7ea36e88323902f63662aa53c9b88988",
@@ -62,6 +68,12 @@
                         "git_sha": "571a5feac4c9ce0a8df0bc15b94230e7f3e8db47",
                         "installed_by": ["modules"]
                     },
+                    "cadd": {
+                        "branch": "master",
+                        "git_sha": "cf3ed075695639b0a0924eb0901146df1996dc08",
+                        "installed_by": ["modules"],
+                        "patch": "modules/nf-core/cadd/cadd.diff"
+                    },
                     "cat/fastq": {
                         "branch": "master",
                         "git_sha": "4fc983ad0b30e6e32696fa7d980c76c7bfe1c03e",
@@ -89,6 +101,11 @@
                         "installed_by": ["modules"],
                         "patch": "modules/nf-core/fastqc/fastqc.diff"
                     },
+                    "gawk": {
+                        "branch": "master",
+                        "git_sha": "cf3ed075695639b0a0924eb0901146df1996dc08",
+                        "installed_by": ["modules"]
+                    },
                     "genmod/annotate": {
                         "branch": "master",
                         "git_sha": "1aba459a6f3528bee806403ae47bea304de26603",

diff --git a/modules/local/bcftools/filltags/main.nf b/modules/local/bcftools/filltags/main.nf
@@ -12,6 +12,8 @@ process BCFTOOLS_FILLTAGS {
 
     output:
     tuple val(meta), path("*.{vcf,vcf.gz,bcf,bcf.gz}"), emit: vcf
+    tuple val(meta), path("*.csi")                    , emit: csi, optional: true
+    tuple val(meta), path("*.tbi")                    , emit: tbi, optional: true
     path "versions.yml"                               , emit: versions
 
     when:

diff --git a/modules/nf-core/bcftools/annotate/bcftools-annotate.diff b/modules/nf-core/bcftools/annotate/bcftools-annotate.diff
diff --git a/modules/nf-core/bcftools/annotate/environment.yml b/modules/nf-core/bcftools/annotate/environment.yml
diff --git a/modules/nf-core/bcftools/annotate/main.nf b/modules/nf-core/bcftools/annotate/main.nf
diff --git a/modules/nf-core/bcftools/annotate/meta.yml b/modules/nf-core/bcftools/annotate/meta.yml
diff --git a/modules/nf-core/bcftools/annotate/tests/bcf.config b/modules/nf-core/bcftools/annotate/tests/bcf.config
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		##INFO=<ID=CADD,Number=1,Type=Float,Description="PHRED-like scaled CADD score.">