def hase_convert(args):
R = Reader('genotype')
R.start(args.genotype[0], vcf=args.vcf)
with Timer() as t:
if R.format == 'PLINK':
G = GenotypePLINK(args.study_name[0], reader=R)
G.split_size = CONVERTER_SPLIT_SIZE
G.plink2hdf5(out=args.out)
elif R.format == 'MINIMAC':
G = GenotypeMINIMAC(args.study_name[0], reader=R)
G.split_size = CONVERTER_SPLIT_SIZE
G.MACH2hdf5(args.out, id=args.id)
elif R.format == 'VCF':
G = GenotypeVCF(args.study_name[0], reader=R)
G.split_size = CONVERTER_SPLIT_SIZE
G.VCF2hdf5(args.out)
else:
raise ValueError(
'Genotype data should be in PLINK/MINIMAC/VCF format and alone in folder'
)
check_converter(args.out, args.study_name[0])
print(('Time to convert all data: {} sec'.format(t.secs)))
return
class Study:
def __init__(self, name):
self.name = name
self.genotype = None
self.phenotype = None
self.derivatives = None
self.covariates = None
self.study_name = None
self.encoded = None
def add_genotype(self, genotype_path, hdf5=True):
self.genotype = Reader('genotype')
self.genotype.start(genotype_path,
hdf5=hdf5,
study_name=self.study_name,
ID=False)
def add_phenotype(self, phenotype_path):
self.phenotype = Reader('phenotype')
self.phenotype.start(phenotype_path)
def add_derivatives(self, derivatives_path):
self.derivatives = Reader('partial')
self.derivatives.start(derivatives_path, study_name=self.study_name)
self.derivatives.folder.load()
def add_covariates(self, covariates_path):
self.covariates = Reader('covariates')
self.covariates.start(covariates_path)
def hase_convert(args):
if (os.path.exists(args.outfolder + '/probes/')) and (
os.path.exists(args.outfolder + '/genotype/')) and (
os.path.exists(args.outfolder + '/individuals/')):
print(
"The folders: probes, genotype and individuals already exist. Data seems already in HASE format. Delete "
"the folders if the files are not converted properly. Continuing with the current files:"
)
return
else:
print('using', args.outfolder)
R = Reader('genotype')
R.start(args.genotype[0], vcf=args.vcf)
with Timer() as t:
if R.format == 'PLINK':
G = GenotypePLINK(args.study_name[0], reader=R)
G.split_size = CONVERTER_SPLIT_SIZE
G.plink2hdf5(out=args.out)
elif R.format == 'MINIMAC':
G = GenotypeMINIMAC(args.study_name[0], reader=R)
G.split_size = CONVERTER_SPLIT_SIZE
G.MACH2hdf5(args.out, id=args.id)
elif R.format == 'VCF':
G = GenotypeVCF(args.study_name[0], reader=R)
G.split_size = CONVERTER_SPLIT_SIZE
G.VCF2hdf5(args.out)
else:
raise ValueError(
'Genotype data should be in PLINK/MINIMAC/VCF format and alone in folder'
)
check_converter(args.out, args.study_name[0])
args.outfolder = args.genotype
print(('Time to convert all data: {} sec'.format(t.secs)))
return
def add_derivatives(self, derivatives_path):
self.derivatives = Reader('partial')
self.derivatives.start(derivatives_path, study_name=self.study_name)
self.derivatives.folder.load()
def add_phenotype(self, phenotype_path):
self.phenotype = Reader('phenotype')
self.phenotype.start(phenotype_path)
def add_genotype(self, genotype_path, hdf5=True):
self.genotype = Reader('genotype')
self.genotype.start(genotype_path,
hdf5=hdf5,
study_name=self.study_name,
ID=False)
def add_covariates(self, covariates_path):
self.covariates = Reader('covariates')
self.covariates.start(covariates_path)
raise ValueError('Node # {} > {} total number of nodes'.format(
args.node[1], args.node[0]))
if not os.path.isdir(args.out):
print("Creating output folder {}".format(args.out))
os.mkdir(args.out)
if args.np:
check_np()
################################### CONVERTING ##############################
if args.mode == 'converting':
# ARG_CHECKER.check(args,mode='converting')
R = Reader('genotype')
R.start(args.genotype[0], vcf=args.vcf)
with Timer() as t:
if R.format == 'PLINK':
G = GenotypePLINK(args.study_name[0], reader=R)
G.split_size = CONVERTER_SPLIT_SIZE
G.plink2hdf5(out=args.out)
elif R.format == 'MINIMAC':
G = GenotypeMINIMAC(args.study_name[0], reader=R)
if args.cluster == 'y':
G.cluster = True
G.split_size = CONVERTER_SPLIT_SIZE
G.MACH2hdf5(args.out, id=args.id)