GenesisAM/calcPVT.py at main · MataLabCCF/GenesisAM · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
import argparse
import numpy as np
#import effectsize
import rpy2.robjects as ro
from rpy2.robjects.packages import importr


def calcPVT(VCFFile, begin, end, outFolder, ancList):
    dictEffectiveSize = {}
    coda = importr("coda")

    for POP in ancList:
        for chrom in range(begin, end+1):
            dictLA = {}
            VCF = VCFFile.replace("#", POP).replace("*", f"{chrom}")
            fileIn = open(VCF)

            header = True
            for line in fileIn:
                if header:
                    if line.startswith("#CHROM"):
                        headerInfo = line.strip().split()
                        header = False
                else:
                    split = line.strip().split()

                    for i in range(9, len(split)):
                        sampleID = headerInfo[i]

                        A1, A2 = split[i].split("|")
                        dosage = int(A1) + int(A2)

                        if sampleID not in dictLA:
                            dictLA[sampleID] = [dosage]
                        else:
                            dictLA[sampleID].append(dosage)

            for sampleID in dictLA:
                if sampleID not in dictEffectiveSize:
                    dictEffectiveSize[sampleID] = {}
                x = ro.FloatVector(dictLA[sampleID])
                ess = coda.effectiveSize(x)
                dictEffectiveSize[sampleID][chrom] = ess[0]

        ESS = open(f"{outFolder}/ESS_{POP}_PerSampleAndChrom.txt", "w")
        ESS.write(f"ID")
        for chrom in range(begin, end + 1):
            ESS.write(f"\tchrom{chrom}")
        ESS.write("\n")

        listESS = []
        for sampleID in dictEffectiveSize:
            sum = 0
            ESS.write(f"{sampleID}")
            for chrom in dictEffectiveSize[sampleID]:
                ESS.write(f"\t{dictEffectiveSize[sampleID][chrom]}")
                sum = sum + dictEffectiveSize[sampleID][chrom]
            ESS.write(f"\n")
            listESS.append(sum)
        ESS.close()
        print(f"Mean number of tests ({POP}): {np.mean(listESS)}")
        print(f"PVT (BonFerroni) ({POP}): {0.05/np.mean(listESS)}")

if __name__ == '__main__':
    parser = argparse.ArgumentParser(description='Calcule p-value threshold using R')

    requiredGeneral = parser.add_argument_group("Required arguments for all steps")
    requiredGeneral.add_argument('-v', '--vcf', help='VCF generated by  GENESIS_AM.py with ancestry ID replaced by # and chrom replaced by *'
                                                     'Example: Phase2_All_#_chrom*.vcf',required=True)
    requiredGeneral.add_argument('-O', '--outputFolder', help='Name of output folder', required=True)
    requiredGeneral.add_argument('-b', '--begin', help='First chromosome (default = 1)', default=1, type=int)
    requiredGeneral.add_argument('-e', '--end', help='Last chromosome  (default = 22)', default=22, type=int)
    requiredGeneral.add_argument('-a', '--anc', help='List of ancestry', required= True, nargs = "+")

    args = parser.parse_args()
    calcPVT(args.vcf, args.begin, args.end, args.outputFolder, args.anc)