# print lines[:400]
lines = lines.split('\n')
for line in lines:
# print line
line = line.strip().split('\t')
snp_id = line[0]
allele = line[1]
assert len(allele) == 1
annotation_dict[snp_id] = allele
# print len(annotation_dict.keys())
# READING PLINK input
if options.verbose:
sys.stderr.write("Reading SNP input...\n")
if options.bfile:
IN = input.plink(options.bfile, type='b', phenoFile=options.phenoFile, normGenotype=options.normalizeGenotype)
elif options.tfile:
IN = input.plink(options.tfile, type='t', phenoFile=options.phenoFile, normGenotype=options.normalizeGenotype)
#elif options.pfile: IN = input.plink(options.pfile,type='p', phenoFile=options.phenoFile,normGenotype=options.normalizeGenotype)
elif options.emmaFile:
IN = input.plink(options.emmaFile, type='emma', phenoFile=options.phenoFile, normGenotype=options.normalizeGenotype)
if not os.path.isfile(options.phenoFile or IN.fbase + '.phenos') and not os.path.isfile(options.emmaPheno):
raise Exception(
"No .pheno file exist for %s. Please provide a phenotype file using the --phenofile or --emmaPHENO argument." % (
options.phenoFile or IN.fbase + '.phenos'))
# Read the emma phenotype file if provided.
# Format should be rows are phenotypes and columns are individuals.
if options.emmaPheno:
f = open(options.emmaPheno, 'r')
sys.exit()
outFile = args[0]
import sys
import os
import numpy as np
from scipy import linalg
from pylmm.lmm import calculateKinship
from pylmm import input
if not options.tfile and not options.bfile and not options.emmaFile:
parser.error("You must provide at least one PLINK input file base (--tfile or --bfile) or an emma formatted file (--emmaSNP).")
if options.verbose: sys.stderr.write("Reading PLINK input...\n")
if options.bfile: IN = input.plink(options.bfile,type='b')
elif options.tfile: IN = input.plink(options.tfile,type='t')
#elif options.pfile: IN = input.plink(options.pfile,type='p')
elif options.emmaFile:
if not options.numSNPs: parser.error("You must provide the number of SNPs when specifying an emma formatted file.")
IN = input.plink(options.emmaFile,type='emma')
else: parser.error("You must provide at least one PLINK input file base (--tfile or --bfile) or an emma formatted file (--emmaSNP).")
n = len(IN.indivs)
m = options.computeSize
W = np.ones((n,m)) * np.nan
IN.getSNPIterator()
# Annoying hack to get around the fact that it is expensive to determine the number of SNPs in an emma file
if options.emmaFile: IN.numSNPs = options.numSNPs
i = 0
#if not options.pfile and not options.tfile and not options.bfile:
parser.error(
"You must provide at least one PLINK input file base (--tfile or --bfile) or an EMMA formatted file (--emmaSNP)."
)
if not options.kfile:
parser.error("Please provide a pre-computed kinship file")
numThreads = None
if options.numThreads:
numThreads = int(options.numThreads)
# READING PLINK input
if options.verbose: sys.stderr.write("Reading SNP input...\n")
if options.bfile:
IN = input.plink(options.bfile,
type='b',
phenoFile=options.phenoFile,
normGenotype=options.normalizeGenotype)
elif options.tfile:
IN = input.plink(options.tfile,
type='t',
phenoFile=options.phenoFile,
normGenotype=options.normalizeGenotype)
#elif options.pfile: IN = input.plink(options.pfile,type='p', phenoFile=options.phenoFile,normGenotype=options.normalizeGenotype)
elif options.emmaFile:
IN = input.plink(options.emmaFile,
type='emma',
phenoFile=options.phenoFile,
normGenotype=options.normalizeGenotype)
else:
parser.error("You must provide at least one PLINK input file base")
print "\tldFlag = %s" % ldFlagStr
print "\tldThresh = %f" % ldThresh
import os
import numpy as np
from scipy import linalg
from pylmm.lmm import calculateKinship
from pylmm import input
if not options.tfile and not options.bfile and not options.emmaFile:
parser.error(
"You must provide at least one PLINK input file base (--tfile or --bfile) or an emma formatted file (--emmaSNP)."
)
if options.verbose: sys.stderr.write("Reading PLINK input...\n")
if options.bfile: IN = input.plink(options.bfile, type='b')
elif options.tfile:
IN = input.plink(options.tfile, type='t')
#elif options.pfile: IN = input.plink(options.pfile,type='p')
elif options.emmaFile:
if not options.numSNPs:
parser.error(
"You must provide the number of SNPs when specifying an emma formatted file."
)
IN = input.plink(options.emmaFile, type='emma')
else:
parser.error(
"You must provide at least one PLINK input file base (--tfile or --bfile) or an emma formatted file (--emmaSNP)."
)
n = len(IN.indivs)
if len(args) != 1:
parser.print_help()
sys.exit()
outFile = args[0]
if not options.tfile and not options.bfile and not options.emmaFile:
#if not options.pfile and not options.tfile and not options.bfile:
parser.error("You must provide at least one PLINK input file base (--tfile or --bfile) or an EMMA formatted file (--emmaSNP).")
if not options.kfile:
parser.error("Please provide a pre-computed kinship file")
# READING PLINK input
if options.verbose: sys.stderr.write("Reading SNP input...\n")
if options.bfile: IN = input.plink(options.bfile,type='b', phenoFile=options.phenoFile,normGenotype=options.normalizeGenotype,impute=options.impute)
elif options.tfile: IN = input.plink(options.tfile,type='t', phenoFile=options.phenoFile,normGenotype=options.normalizeGenotype,impute=options.impute)
#elif options.pfile: IN = input.plink(options.pfile,type='p', phenoFile=options.phenoFile,normGenotype=options.normalizeGenotype)
elif options.emmaFile: IN = input.plink(options.emmaFile,type='emma', phenoFile=options.phenoFile,normGenotype=options.normalizeGenotype,impute=options.impute)
else: parser.error("You must provide at least one PLINK input file base")
if not os.path.isfile(options.phenoFile or IN.fbase + '.phenos') and not os.path.isfile(options.emmaPheno):
parser.error("No .pheno file exist for %s. Please provide a phenotype file using the --phenofile or --emmaPHENO argument." % (options.phenoFile or IN.fbase + '.phenos'))
# Read the emma phenotype file if provided.
# Format should be rows are phenotypes and columns are individuals.
if options.emmaPheno:
f = open(options.emmaPheno,'r')
P = []
for line in f:
v = line.strip().split()
import multiprocessing as mp # Multiprocessing is part of the Python stdlib
import Queue
if not options.tfile and not options.bfile and not options.emmaFile:
parser.error(
"You must provide at least one PLINK input file base (--tfile or --bfile) or an emma formatted file (--emmaSNP)."
)
numThreads = None
if options.numThreads:
numThreads = int(options.numThreads)
if options.verbose:
sys.stderr.write("Reading PLINK input...\n")
if options.bfile:
IN = input.plink(options.bfile, type="b")
elif options.tfile:
IN = input.plink(options.tfile, type="t")
# elif options.pfile: IN = input.plink(options.pfile,type='p')
elif options.emmaFile:
if not options.numSNPs:
parser.error("You must provide the number of SNPs when specifying an emma formatted file.")
IN = input.plink(options.emmaFile, type="emma")
else:
parser.error(
"You must provide at least one PLINK input file base (--tfile or --bfile) or an emma formatted file (--emmaSNP)."
)
def compute_W(job):
"""
from pylmm import input
from numpy.linalg import pinv, inv
if len(args) != 1:
parser.print_help()
sys.exit()
outFile = args[0]
if not options.tfile and not options.bfile and not options.emmaFIle:
parser.error(
"You mustprovide at least one PLINK input file base (--tfile or --bfile) or an emma formatted file (--emmaSNP).")
if options.verbose: sys.stderr.write("Reading PLINK input...\n")
if options.bfile:
IN = input.plink(options.bfile, type='b', impute=True)
elif options.tfile:
IN = input.plink(options.tfile, type='t', impute=True)
elif options.emmaFile:
if not options.numSNPs: parser.error("You must provide the number of SNPs when specifying an emma formatted file.")
IN = input.plink(options.emmaFile, type='emma', impute=True)
else:
parser.error(
"You must provide at least one PLINK input file base (--tfile or --bfile) or an emma formatted file (--emaSNP).")
if options.emmaFile: IN.numSNPs = options.numSNPs
if options.evaluate: Answer = input.plink(options.answer, type='t', impute=True)
if options.evaluate: MeanInpute = input.plink(options.tfile, type='t', impute=False)
IN.getSNPIterator()
if options.evaluate:
Answer.getSNPIterator()
from pylmm import input
from numpy.linalg import pinv, inv
if len(args) != 1:
parser.print_help()
sys.exit()
outFile = args[0]
if not options.tfile and not options.bfile and not options.emmaFIle:
parser.error(
"You mustprovide at least one PLINK input file base (--tfile or --bfile) or an emma formatted file (--emmaSNP).")
if options.verbose: sys.stderr.write("Reading PLINK input...\n")
if options.bfile:
IN = input.plink(options.bfile, type='b', impute=True)
elif options.tfile:
IN = input.plink(options.tfile, type='t', impute=True)
elif options.emmaFile:
if not options.numSNPs: parser.error("You must provide the number of SNPs when specifying an emma formatted file.")
IN = input.plink(options.emmaFile, type='emma', impute=True)
else:
parser.error(
"You must provide at least one PLINK input file base (--tfile or --bfile) or an emma formatted file (--emaSNP).")
if options.emmaFile: IN.numSNPs = options.numSNPs
if options.evaluate: Answer = input.plink(options.answer, type='t', impute=True)
if options.evaluate: MeanInpute = input.plink(options.tfile, type='t', impute=False)
IN.getSNPIterator()
if options.evaluate:
Answer.getSNPIterator()
