Skip to content
Snippets Groups Projects
Normal view Permalink
generate_DEC_IGV_solo_scripts.py 45.1 KiB
Newer Older
not populated not populated's avatar
Singleton prioritization scripts
not populated not populated committed
1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 
##.#        if new_key not in G2P_DICT:
##.#            G2P_DICT[new_key] = 0
##.#        else:
##.#            # print "ERROR: duplicate G2P variant new_key = %s" % (new_key)
##.#            # raise SystemExit
##.#            # this will happen if a gene is e.g. hemizygous,x-linked dominant - there will be two separate lines in the output for each req
##.#            pass
#
##.#        # and record the required data (CHILD_TRANS,CHILD_GENE,CHILD_GT) in G2P_DATA
##.#        if new_key not in G2P_DATA:
##.#            G2P_DATA[new_key] = (CHILD_TRANS,CHILD_GENE,CHILD_GT)
##.#        else:
##.#            # print "ERROR: duplicate G2P variant new_key = %s" % (new_key)
##.#            # raise SystemExit
##.#            # this will happen if a gene is e.g. hemizygous,x-linked dominant - there will be two separate lines in the output for each req
##.#            pass


    NUM_UNIQ_G2P_VARS = len(G2P_DICT)
    print "Found %s unique G2P variants in CHILD (%s) after considering MONOALLELIC, BIALLELIC and X-LINKED genes" % (NUM_UNIQ_G2P_VARS,CHILD_ID)
    sys.stdout.flush()

    print ""
    print ""

















def read_ped(in_file):

    global CHILD_ID
    global CHILD_SEX
    global DEC_CHILD_SEX

    CHILD_ID = 0
    CHILD_SEX = 0

    # no need to do PED checks, did them for singletons at trio_setup.sh
    in_han = open(in_file,'r')
    for line in in_han:
        data = [x.strip() for x in line.strip().split('\t')]
        CHILD_ID = data[1]
        CHILD_SEX = int(data[4])
        if CHILD_SEX == 1:          # boy
            DEC_CHILD_SEX = '46XY'
        elif CHILD_SEX == 2:        # girl
            DEC_CHILD_SEX = '46XX'
        else:
            print "ERROR: proband sex unknown"
            print line
            raise SystemExit




def read_map_file(in_file):
    in_han = open(in_file,'r')
    for line in in_han:
        data = [x.strip() for x in line.strip().split('\t')]
        dec_id = data[0]
        int_id = data[1]
        if dec_id not in MAP_DICT:
            MAP_DICT[dec_id] = int_id
        else:
            print "ERROR: duplicate DECIPHER/family ID = %s" % (dec_id)
            raise SystemExit
    in_han.close()




def read_trans_map(in_file):
    in_han = open(in_file,'r')
    for line in in_han:
        data = [x.strip() for x in line.strip().split('\t')]
        old_trans_id = data[0]
        new_trans_id = data[1]
        if old_trans_id not in TRANS_DICT:
            TRANS_DICT[old_trans_id] = new_trans_id
        else:
            print "ERROR: duplicate old transcript ID = %s" % (old_trans_id)
            raise SystemExit
    in_han.close()






if __name__ == '__main__':
    if len(sys.argv) == 11:
        go(sys.argv[1],sys.argv[2],sys.argv[3],sys.argv[4],sys.argv[5],sys.argv[6],sys.argv[7],sys.argv[8],sys.argv[9],sys.argv[10])
    else:
        print "Suggested use: time python /home/u035/u035/shared/scripts/NHS_WES_generate_DEC_IGV.py \
        dec_map_file,trans_map_file,ped_file,in_g2p_file,fam_igv_dir,vcf_dir,plate_id,fam_id,dec_dir,fam_bam_dir"
        raise SystemExit
Show full blame