c3e1d16778b3af004003425907b23ae7cdb94844
lrnassar
  Tue Jun 18 10:33:15 2024 -0700
Removing carrots from name, feedback from Anna.

diff --git src/hg/makeDb/scripts/enigma/BRCAsplicing.py src/hg/makeDb/scripts/enigma/BRCAsplicing.py
index e0fcf02..3ef06d5 100644
--- src/hg/makeDb/scripts/enigma/BRCAsplicing.py
+++ src/hg/makeDb/scripts/enigma/BRCAsplicing.py
@@ -12,30 +12,37 @@
     return(bashStdoutt)
 
 rawFilePath = "/hive/data/inside/enigmaTracksData/Anna_CSpec_BRCA12ACMG-Rules-Specifications_V1.1Table-4_2023-11-22.txt"
 
 def assignRGBcolor(lineToCheck):
     if "DEL" in lineToCheck[4]:
         itemRgb = '180,53,53' #Red
     elif "DUP" in lineToCheck[4]:
         itemRgb = '117,136,214' #Blue
     elif "RNA" in lineToCheck[5]:
         itemRgb = '146,64,190' #Black
     else:
         itemRgb = '0,0,0'
     return(itemRgb)
 
+def checkExtraCarrotInPosition(position):
+    if position[len(position)-1] == ">":
+        correctPosition = position[0:len(position)-1]
+    else:
+        correctPosition = position
+    return(correctPosition)
+
 rawFile = open(rawFilePath,'r')
 outputBedFile = open("/hive/data/inside/enigmaTracksData/outputBedFile.bed",'w', encoding='latin-1')
 for line in rawFile:
     line = line.rstrip("\n").split("\t")
     if line[0].startswith("Gene") or line[0]== "":
         continue
     elif line == "":
         continue
     else:
 #         print(line)
         itemRgb = assignRGBcolor(line)
         NMacc = line[1]
 
         if line[0] == "BRCA1":
             strand = "-"
@@ -89,35 +96,36 @@
 
             queryPosition = bash("curl https://hgwdev.gi.ucsc.edu/cgi-bin/hgSearch?search="+NMacc+"%3Ac"+pos)
             for resultsLine in queryPosition.split("\n"):
                 if resultsLine.startswith("<script"):
                     position = int(resultsLine.split("position=")[1].split("-")[0].split(":")[1])+5
             if strand == "-":
                 position = int(position)-int(adjustment)
             elif strand == "+":
                 position = int(position)+int(adjustment)
             chromStart = str(position-1)
             chromEnd = str(position)
 
         varType = line[4].replace('"','')
         ACMGcode = line[5].replace('"','')
         observation = line[6].replace("?","delta").replace('"','')
+        correctedPosition = checkExtraCarrotInPosition(line[3])
         _mouseOver = "<b>Transcript:</b> "+line[1]+"<br><b>Exon:</b> "+line[2]+\
-        "<br><b>Position:</b> "+line[3]+"<br><b>Var Type:</b> "+varType+\
+        "<br><b>Position:</b> "+correctedPosition+"<br><b>Var Type:</b> "+varType+\
         "<br><b>ACMG Code: </b>"+ACMGcode
 
-        outputBedFile.write(chrom+"\t"+chromStart+"\t"+chromEnd+"\t"+line[3]+"\t0\t"+\
+        outputBedFile.write(chrom+"\t"+chromStart+"\t"+chromEnd+"\t"+correctedPosition+"\t0\t"+\
                            strand+"\t"+chromStart+"\t"+chromEnd+"\t"+itemRgb+"\t"+\
                            "\t".join(line[:4])+"\t"+varType+"\t"+\
                             ACMGcode+"\t"+observation+\
                             "\t"+line[7]+"\t"+_mouseOver+"\n")
 
 rawFile.close()
 outputBedFile.close()
 
 bash("bedSort /hive/data/inside/enigmaTracksData/outputBedFile.bed \
 /hive/data/inside/enigmaTracksData/outputBedFile.bed")
 
 startOfAsFile="""table BRCAsplicing
 "BRCA1 and BRCA2 variant codes according to PVS1 decision trees (ENIGMA specifications version 1.1.0)"
    (
    string chrom;       "Reference sequence chromosome or scaffold"