search

tkzeng / Pangolin

Pangolin is a deep-learning method for predicting splice site strengths.
GNU General Public License v3.0
61 stars 32 forks source link

Update format of annotation according to VCF specification #9

Closed kkchau closed 1 year ago

kkchau commented 1 year ago

VCF INFO fields should be comma-delimited annotations. If Pangolin encounters multiple genes, each annotation should be separated by a comma. Otherwise, we get annotations like

Pangolin=ENSG00000179344.12|-24:0.5|-45:0.0|Warnings:NoAnnotatedSitesToMaskForThisGeneENSG00000241287.1|-24:0.5|-45:0.0|Warnings:NoAnnotatedSitesToMaskForThisGene

With this change:

Pangolin=ENSG00000179344.12|-24:0.5|-45:0.0|Warnings:NoAnnotatedSitesToMaskForThisGene,ENSG00000241287.1|-24:0.5|-45:0.0|Warnings:NoAnnotatedSitesToMaskForThisGene
tkzeng commented 1 year ago

Thanks!