Initial commit: digital-patients pipeline (clean, no large files)

Large reference/model files excluded from repo - to be staged to S3 or baked into Docker images.

app_filter/vep.ini

@@ -0,0 +1,32 @@
+cache 1
+dir_cache  /data
+assembly 'GRCh38'
+offline 1
+force_overwrite 1
+custom file=/opt/vep/.vep/Cosmic_GenomeScreensMutant_v103_GRCh38.vcf.gz,short_name=COSMIC,format=vcf,type=exact,fields=LEGACY_ID%CNT
+
+# Functional impact predictions
+sift b # CALCULATE 1 - score
+polyphen b # THESE TWO CAN BE AVERAGED
+
+plugin REVEL,/opt/vep/.vep/REVEL/new_tabbed_revel_grch38.tsv.gz
+# TODO: CALCUALTE THEIR L2 NORM
+# plugin CADD,/opt/vep/.vep/CADD/GRCh38/whole_genome_SNVs.tsv.gz,/opt/vep/.vep/CADD/GRCh38/InDels.tsv.gz
+
+
+# Clinical significance
+check_existing
+clinvar
+
+# Allele frequencies
+af
+af_1kg
+af_gnomade
+af_gnomadg
+max_af
+
+# Additional useful flags
+numbers
+hgvs
+symbol
+canonical