diff --git a/Snakefile b/Snakefile index e088368..c99453f 100644 --- a/Snakefile +++ b/Snakefile @@ -88,6 +88,7 @@ rule all: 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/orphapacket/{DV.orphapacket}/orphapacket.tar.gz", + "work/download/genes/alphamissense/1/AlphaMissense_gene_hg38.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", @@ -323,6 +324,7 @@ rule all: # Misc rules. include: "rules/work/misc/hpo.smk" # Gene-related rules. +include: "rules/work/genes/alphamissense.smk" include: "rules/work/genes/dbnsfp.smk" include: "rules/work/genes/clingen.smk" include: "rules/work/genes/ensembl.smk" @@ -344,6 +346,7 @@ include: "rules/work/annos/features/refseq.smk" include: "rules/work/annos/features/tads.smk" include: "rules/work/annos/features/ucsc.smk" # Sequence variants and annotations. +include: "rules/work/annos/seqvars/alphamissense.smk" include: "rules/work/annos/seqvars/cadd.smk" include: "rules/work/annos/seqvars/dbnsfp.smk" include: "rules/work/annos/seqvars/dbscsnv.smk" diff --git a/environment.yml b/environment.yml index 058ad0a..f44f1af 100644 --- a/environment.yml +++ b/environment.yml @@ -1,4 +1,3 @@ -name: varfish-db-downloader channels: - bioconda - conda-forge diff --git a/excerpt-data/31296ac84aa243ce/AlphaMissense_hg19.tsv.gz b/excerpt-data/31296ac84aa243ce/AlphaMissense_hg19.tsv.gz new file mode 100644 index 0000000..9a29994 --- /dev/null +++ b/excerpt-data/31296ac84aa243ce/AlphaMissense_hg19.tsv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59e4ae2448406ca7d201aa2bb7508bea90bf154a1c39a59ed7df9e60aeab5799 +size 1126 diff --git a/excerpt-data/31296ac84aa243ce/url.txt b/excerpt-data/31296ac84aa243ce/url.txt new file mode 100644 index 0000000..6d11716 --- /dev/null +++ b/excerpt-data/31296ac84aa243ce/url.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b304f0ef4fecce99a54b68348ff334923254fd23d27261bf356222b81997beb7 +size 74 diff --git a/excerpt-data/521f5677c9d5d6b3/AlphaMissense_gene_hg38.tsv.gz b/excerpt-data/521f5677c9d5d6b3/AlphaMissense_gene_hg38.tsv.gz new file mode 100644 index 0000000..5bb7a81 --- /dev/null +++ b/excerpt-data/521f5677c9d5d6b3/AlphaMissense_gene_hg38.tsv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f962ac005fbee1508151625464b952876ced8d21231627942159d944b2b1bd39 +size 1569 diff --git a/excerpt-data/521f5677c9d5d6b3/url.txt b/excerpt-data/521f5677c9d5d6b3/url.txt new file mode 100644 index 0000000..7574e01 --- /dev/null +++ b/excerpt-data/521f5677c9d5d6b3/url.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ee9e2f439cea6047377e83f67124fdca50c925bc64a588fc03af4991a608bbf +size 79 diff --git a/excerpt-data/c47fb6a5c19a1ec2/AlphaMissense_hg38.tsv.gz b/excerpt-data/c47fb6a5c19a1ec2/AlphaMissense_hg38.tsv.gz new file mode 100644 index 0000000..9cd6015 --- /dev/null +++ b/excerpt-data/c47fb6a5c19a1ec2/AlphaMissense_hg38.tsv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c97ac023f6607dbd402e33dfea71118301b5d965dc758f7760dec4e3a9f40ccf +size 1141 diff --git a/excerpt-data/c47fb6a5c19a1ec2/url.txt b/excerpt-data/c47fb6a5c19a1ec2/url.txt new file mode 100644 index 0000000..2d98465 --- /dev/null +++ b/excerpt-data/c47fb6a5c19a1ec2/url.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fdab28332daf40f4567d25b03de660c6db2fe073ed156f7c58c332d78c12367 +size 74 diff --git a/rules/work/annos/seqvars/alphamissense.smk b/rules/work/annos/seqvars/alphamissense.smk new file mode 100644 index 0000000..fca5d2f --- /dev/null +++ b/rules/work/annos/seqvars/alphamissense.smk @@ -0,0 +1,15 @@ +## Rules related to the AlphaMissense scores + + +rule annos_alphamissense_download: # -- download AlphaMissense data + output: + tsv="work/download/annos/alphamissense/1/{genome}/AlphaMissense_{genome}.tsv.gz", + tsv_md5="work/download/annos/alphamissense/1/{genome}/AlphaMissense_{genome}.tsv.gz.md5", + shell: + r""" + wget --no-check-certificate \ + -O {output.tsv} \ + https://storage.googleapis.com/dm_alphamissense/AlphaMissense_{wildcards.genome}.tsv.gz + + md5sum {output.tsv} >{output.tsv_md5} + """ diff --git a/rules/work/genes/alphamissense.smk b/rules/work/genes/alphamissense.smk new file mode 100644 index 0000000..b8a1a50 --- /dev/null +++ b/rules/work/genes/alphamissense.smk @@ -0,0 +1,15 @@ +## Rules related to AlphaMissense per-gene scores + + +rule genes_alphamissense_download: # -- download AlphaMissense per-gene scores + output: + tsv="work/download/genes/alphamissense/1/AlphaMissense_gene_hg38.tsv.gz", + tsv_md5="work/download/genes/alphamissense/1/AlphaMissense_gene_hg38.tsv.gz.md5", + shell: + r""" + wget --no-check-certificate \ + -O {output.tsv} \ + https://storage.googleapis.com/dm_alphamissense/AlphaMissense_gene_hg38.tsv.gz + + md5sum {output.tsv} > {output.tsv_md5} + """