382d7a0dacd948be55a2aa8548db7542a5e3335a max Thu Feb 18 06:31:43 2021 -0800 fixing cadd deletions and inserts, refs #18492 diff --git src/hg/makeDb/cadd/caddToBed.py src/hg/makeDb/cadd/caddToBed.py index d902ef4..e8b0171 100644 --- src/hg/makeDb/cadd/caddToBed.py +++ src/hg/makeDb/cadd/caddToBed.py @@ -13,24 +13,28 @@ for line in subprocess.Popen(['zcat', inFname], stdout=subprocess.PIPE, encoding="ascii").stdout: if line.startswith("#"): continue row = line.rstrip("\n").split("\t") chrom, pos, ref, alt, raw, phred = row chrom = "chr"+chrom pos = int(row[1])-1 phred = float(phred) if len(ref) < len(alt): # insertion insLen = len(alt)-1 name = str(insLen) desc = "ins."+alt[1:] ofh = insFh + start = str(pos+1) + end = str(pos+1) else: delLen = len(ref)-1 name = str(delLen) desc = "del."+ref[1:] ofh = delFh + start = str(pos+1) + end = str(pos+1+delLen) - bed = [chrom, str(pos), str(pos+1), name, str(round(phred)), ".", str(pos), str(pos+1), "0", desc, str(phred)] + bed = [chrom, start, end, name, str(round(phred)), ".", start, end, "0", desc, str(phred)] ofh.write("\t".join(bed)) ofh.write("\n")