From f48091e6d769e7e0ea0b8fc8edfca99d653221e6 Mon Sep 17 00:00:00 2001 From: pamelaxu213 Date: Thu, 18 Jul 2024 15:52:17 -0400 Subject: [PATCH] add greenDB annotation --- cre.gemini2txt.vcf2db.sh | 3 +++ cre.vcf2db.R | 3 ++- 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/cre.gemini2txt.vcf2db.sh b/cre.gemini2txt.vcf2db.sh index 15a7414..43e0f84 100755 --- a/cre.gemini2txt.vcf2db.sh +++ b/cre.gemini2txt.vcf2db.sh @@ -50,6 +50,9 @@ then ctcf_binding_site as CTCF_binding_site, enh_cellline_tissue as ENH_cellline_tissue, tf_binding_sites as TF_binding_sites, + GreenDB_variant_type as GreenDB_variant_type, + GreenDB_closest_gene as GreenDB_closest_gene, + GreenDB_controlled_gene as GreenDB_controlled_gene, c4r_wgs_counts as C4R_WGS_counts, c4r_wgs_samples as C4R_WGS_samples" noncoding_scores="ncER as ncER_score, ReMM as ReMM_score, LinSight_Score as LINSIGHT_score" diff --git a/cre.vcf2db.R b/cre.vcf2db.R index 9d59d44..37d99ff 100644 --- a/cre.vcf2db.R +++ b/cre.vcf2db.R @@ -434,7 +434,8 @@ select_and_write2 <- function(variants, samples, prefix, type) { print(colnames(variants)) if (type == 'wgs' || type == 'denovo'){ - noncoding_cols <- c("DNaseI_hypersensitive_site", "CTCF_binding_site", "ENH_cellline_tissue", "TF_binding_sites") + noncoding_cols <- c("DNaseI_hypersensitive_site", "CTCF_binding_site", "ENH_cellline_tissue", "TF_binding_sites", + "GreenDB_variant_type", "GreenDB_closest_gene", "GreenDB_controlled_gene") noncoding_scores <- c("ncER_score", "ReMM_score", "LINSIGHT_score") wgs_counts <- c("C4R_WGS_counts", "C4R_WGS_samples") variants$C4R_WGS_counts[variants$C4R_WGS_counts == "None"] <- 0