feat: adding pHaplo, pTriplo, sHet as seen in DECIPHER (#56)

Author: holtgrewe

Snakefile

@@ -86,12 +86,16 @@ rule all:
         #
         # genes
         f"work/download/genes/clingen/{DV.clingen_gene}/clingen.csv",
+        f"work/download/genes/rcnv/2022/Collins_rCNV_2022.dosage_sensitivity_scores.tsv.gz",
+        f"work/download/genes/shet/2019/Collins_rCNV_2022.dosage_sensitivity_scores.tsv.gz",
         f"work/genes/dbnsfp/{DV.dbnsfp}/genes.tsv.gz",
         f"work/genes/ensembl/{DV.ensembl}/ensembl_xlink.tsv",
         f"work/genes/enst_ensg/grch37/{DV.ensembl_37}/enst_ensg.tsv",
         f"work/genes/entrez/{DV.today}/gene_info.jsonl",
         f"work/genes/gnomad/{DV.gnomad_constraints}/gnomad_constraints.tsv",
         f"work/genes/hgnc/{DV.today}/hgnc_info.jsonl",
+        "work/genes/rcnv/2022/rcnv_collins_2022.tsv",
+        "work/genes/shet/2019/shet_weghorn_2019.tsv",
         # reference-specific annotations
         # -- background/population sequence variants and annotations thereof
         # ---- GRCh37
@@ -324,6 +328,8 @@ include: "rules/work/genes/gnomad.smk"
 include: "rules/work/genes/hgnc.smk"
 include: "rules/work/genes/mehari_data_tx.smk"
 include: "rules/work/genes/ncbi.smk"
+include: "rules/work/genes/rcnv.smk"
+include: "rules/work/genes/shet.smk"
 # Reference sequence--related rules.
 include: "rules/work/reference/human.smk"
 # Features (position and not variant specific).

bundled-data/weghorn_2019/Weghorn_2019_Supplementary_Table_1.txt.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3e976fa85bcce488ed726bf8c6362d4b6f63be044e1691fdd643ad702a7d4f0
+size 366098

download_urls.yml

@@ -1,3 +1,5 @@
+- url: https://zenodo.org/record/6347673/files/Collins_rCNV_2022.dosage_sensitivity_scores.tsv.gz
+
 - comment: The curation activity summary report is built in real-time.
   url: https://search.clinicalgenome.org/kb/reports/curation-activity-summary-report
 

excerpt-data/31137c2c77bc0cea/Collins_rCNV_2022.dosage_sensitivity_scores.tsv.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e60e4cdf8a5b95fc4740ff447e50cc48798f4d553bf339a605e0a02300091b96
+size 2095

excerpt-data/31137c2c77bc0cea/url.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52a5e225efe130a6f89bf8eeb16aa0f76dd7b4ef31d900fe056cd25e452b191b
+size 91

rules/output/annonars/genes.smk

@@ -9,6 +9,8 @@ rule output_annonars_genes:  # -- build annonars genes RocksDB file
         dbnsfp="work/genes/dbnsfp/{v_dbnsfp}/genes.tsv.gz",
         hgnc="work/genes/hgnc/{date}/hgnc_info.jsonl",
         ncbi="work/genes/entrez/{date}/gene_info.jsonl",
+        rcnv="work/genes/rcnv/2022/rcnv_collins_2022.tsv",
+        shet="work/genes/shet/2019/shet_weghorn_2019.tsv",
     output:
         rocksdb_identity=(
             "output/full/annonars/genes-{v_acmg_sf}+{v_gnomad_constraints}+{v_dbnsfp}+{date}+{v_annonars}/"
@@ -38,7 +40,9 @@ rule output_annonars_genes:  # -- build annonars genes RocksDB file
             --path-in-gnomad-constraints {input.gnomad_constraints} \
             --path-in-dbnsfp {input.dbnsfp} \
             --path-in-hgnc {input.hgnc} \
-            --path-in-ncbi {input.ncbi}
+            --path-in-ncbi {input.ncbi} \
+            --path-in-rcnv {input.rcnv} \
+            --path-in-shet {input.shet}
 
         varfish-db-downloader tpl \
             --template rules/output/annonars/genes.spec.yaml \

rules/work/genes/rcnv.smk

@@ -0,0 +1,37 @@
+## Rules related to Collins (2022) gene annotation.
+
+
+rule genes_rcnv_download:  # -- download pHaplo/pTriplo scores
+    output:
+        tsv="work/download/genes/rcnv/2022/Collins_rCNV_2022.dosage_sensitivity_scores.tsv.gz",
+        tsv_md5="work/download/genes/rcnv/2022/Collins_rCNV_2022.dosage_sensitivity_scores.tsv.gz.md5",
+    shell:
+        r"""
+        wget --no-check-certificate \
+            -O {output.tsv} \
+            https://zenodo.org/record/6347673/files/Collins_rCNV_2022.dosage_sensitivity_scores.tsv.gz
+
+        md5sum {output.tsv} > {output.tsv_md5}
+        """
+
+
+rule genes_rcnv_postproces:  # -- postprocess file for HGNC gene IDs
+    input:
+        tsv="work/download/genes/rcnv/2022/Collins_rCNV_2022.dosage_sensitivity_scores.tsv.gz",
+        xlink=f"output/full/mehari/genes-xlink-{DV.today}/genes-xlink.tsv",
+    output:
+        tsv="work/genes/rcnv/2022/rcnv_collins_2022.tsv",
+        tsv_md5="work/genes/rcnv/2022/rcnv_collins_2022.tsv.md5",
+    shell:
+        """
+        qsv join -d '\t' \
+            '#gene' <(zcat {input.tsv}) \
+            gene_symbol {input.xlink} \
+        | qsv select 'hgnc_id,pHaplo,pTriplo' \
+        | qsv rename 'hgnc_id,p_haplo,p_triplo' \
+        | qsv sort \
+        | tr ',' '\t' \
+        > {output.tsv}
+
+        md5sum {output.tsv} > {output.tsv}.md5
+        """

rules/work/genes/shet.smk

@@ -0,0 +1,22 @@
+## Rules related to Weghorn (2019) gene annotation.
+
+
+rule genes_shet:  # -- postprocess file for HGNC gene IDs
+    input:
+        tsv="bundled-data/weghorn_2019/Weghorn_2019_Supplementary_Table_1.txt.gz",
+        xlink=f"output/full/mehari/genes-xlink-{DV.today}/genes-xlink.tsv",
+    output:
+        tsv="work/genes/shet/2019/shet_weghorn_2019.tsv",
+    shell:
+        """
+        qsv join -d '\t' \
+            'Gene' <(zcat {input.tsv}) \
+            gene_symbol {input.xlink} \
+        | qsv select 'hgnc_id,low_det' \
+        | qsv rename 'hgnc_id,s_het' \
+        | qsv sort \
+        | tr ',' '\t' \
+        > {output.tsv}
+
+        md5sum {output.tsv} > {output.tsv}.md5
+        """