loadHumanTFs.py

motifName2entrezId = {}
entrezId2motifName = {}
# humanTFs_All.csv with columns separated by commas - Motif Name,Gene Symbol,Entrez ID
with open('id_conversion/humanTFs_All.csv','r') as inFile:
    header = inFile.readline().strip().split(',') # Capture header, get rid of white space ".strip()", and split by commas ".split(',')"
    while 1:
        inLine = inFile.readline()
        #Breaks out of the while loop when we hit the end of the file
        if not inLine:
            break
        # Build ID conversion dictionary
        splitUp = inLine.strip().split(',') # Get rid of white space ".strip()", and split by commas ".split(',')"
        # Motif name to entrez ID is mostly one to one mapping
        motifName2entrezId[splitUp[0]] = splitUp[2]
        # Entrez Id to motif name is a one to many mapping, so need to have a list under the dictionary key
        if not splitUp[2] in entrezId2motifName:
            entrezId2motifName[splitUp[2]] = []
        entrezId2motifName[splitUp[2]].append(splitUp[0])

print('motifName2entrezId = '+str(len(motifName2entrezId)))

print('entrezId2motifName = '+str(len(entrezId2motifName)))