update cadd to v1.3

arq5x · Mar 17, 2017 · f4d53e4 · f4d53e4
1 parent a9ecdab
commit f4d53e4
Show file tree

Hide file tree

Showing 3 changed files with 6 additions and 5 deletions.
diff --git a/docs/content/history.rst b/docs/content/history.rst
@@ -22,6 +22,7 @@ Release History
 #. Add new `gemini load` flag `--skip-pls` which can give size reductions for the database and speed Improvements
    for querying and loading. If you never use `gt_phred_ll_homalt/het/homref` then you can load with this flag.
 #. Add new `gt_alt_freqs` column which is `gt_alt_dephts / (gt_ref_depths + gt_alt_depths)`.
+#. Update CADD to v1.3
 
 0.19.1
 ======

diff --git a/gemini/annotation_provenance/make-cadd.sh b/gemini/annotation_provenance/make-cadd.sh
@@ -17,10 +17,9 @@ Chrom	Pos	Ref	RawScore	PHRED
 1	10002	A	-0.64,-0.65,-0.53	1.17,1.15,1.57
 
 
-#compression
-zcat whole_genome_SNVs.tsv.gz | grep -v "^#" | awk '{printf("%s\t%d\t%s\t%s\t%0.2f\t%0.2f\n",$1,$2,$3,$4,$5,$6)}' \
-| bedtools groupby -g 1,2,3 -c 5,6 -o collapse,collapse | bgzip > whole_genome_SNVs.tsv.compressed.gz
 
-#index
+wget -O - http://krishna.gs.washington.edu/download/CADD/v1.3/whole_genome_SNVs.tsv.gz \
+    | zgrep -v ^# \
+    | awk '{printf("%s\t%d\t%s\t%s\t%0.2f\t%0.2f\n",$1,$2,$3,$4,$5,$6)}' \
+    | bedtools groupby -g 1,2,3 -c 5,6 -o collapse,collapse | bgzip -c > whole_genome_SNVs.tsv.compressed.gz
 tabix -b 2 -e 2 whole_genome_SNVs.tsv.compressed.gz
-
diff --git a/gemini/install-data.py b/gemini/install-data.py
@@ -73,6 +73,7 @@
     "ESP6500SI.all.snps_indels.tidy.v2.vcf.gz": 2,
     'ExAC.r0.3.sites.vep.tidy.vcf.gz': 4,
     'geno2mp.variants.tidy.vcf.gz': 1,
+    "whole_genome_SNVs.tsv.compressed.gz": 2,
     }
 
 def install_annotation_files(anno_root_dir, dl_files=False, extra=None):