def __init__(self, *filenames, **kwargs): #data_format=None,printer=None):
"""Create a |BigBedGenomeHash|
Parameters
----------
filenames : str or list of str
Filename or list of filenames of `Tabix`_-compressed files
data_format : str
Format of tabix-compressed file(s). Choices are:
`'GTF2'`,`'GFF3'`,`'BED'`,`'PSL'` (Default: `GTF2`)
"""
from pysam import Tabixfile
if len(filenames) == 1 and isinstance(filenames[0], list):
filenames = filenames[0]
self.filenames = list(multiopen(filenames))
self.printer = kwargs.get("printer", NullWriter())
data_format = kwargs.get("data_format", "GTF2")
try:
self._reader_class = TabixGenomeHash._READERS[data_format]
except ValueError:
msg = "Supported file formats for TabixGenomeHash are: %s" % ", ".join(
sorted(TabixGenomeHash._READERS.keys()))
self.printer.write(msg)
raise ValueError(msg)
self.tabix_readers = [Tabixfile(X) for X in self.filenames]
def __iter__(self):
from pysam import Tabixfile, asTuple
f = Tabixfile(self.filename, mode='r')
try:
# header row
if self.header is not None:
yield self.header
else:
# assume last header line has fields
h = list(f.header)
if len(h) > 0:
header_line = text_type(h[-1], encoding='ascii')
yield tuple(header_line.split('\t'))
# data rows
for row in f.fetch(reference=self.reference,
start=self.start,
end=self.stop,
region=self.region,
parser=asTuple()):
yield tuple(row)
except:
raise
finally:
f.close()
def __init__(self, task_queue, results_queue, family, args):
multiprocessing.Process.__init__(self)
self.task_queue = task_queue
self.family = family
self.results_queue = results_queue
self.verbosity = args.verbose
self.phased = args.phased
self.cadd_file = args.cadd_file[0]
self.chr_prefix = args.chr_prefix
if self.cadd_file:
self.cadd_file = Tabixfile(self.cadd_file, parser=asTuple())
def __init__(self, chromosome, position, annotation_table_file):
annotation_table = Tabixfile(annotation_table_file)
self.line = annotation_table.fetch(reference=chromosome,
start=position - 1,
end=position).next()
self.chromosome, \
self.position, \
self.reference_base, \
self.genic, \
self.exonic, \
self.intronic, \
self.intergenic, \
self.utr5, \
self.utr3, \
self.fold0, \
self.fold4, \
self.fold2, \
self.fold3, \
self.CDS, \
self.mRNA, \
self.rRNA, \
self.tRNA, \
self.feature_names, \
self.feature_types, \
self.feature_ID, \
self.cds_position, \
self.strand, \
self.frame, \
self.codon, \
self.aa, \
self.degen, \
self.FPKM, \
self.rho, \
self.FAIRE, \
self.recombination, \
self.mutability, \
self.quebec_alleles = self.line.split('\t')
self.position = int(self.position)
annotation_table.close()
def __iter__(self):
try:
from pysam import Tabixfile, asTuple
except ImportError as e:
raise UnsatisfiedDependency(e, dep_message)
f = Tabixfile(self.filename, mode='r')
try:
# header row
if self.header is not None:
yield self.header
else:
# assume last header line has fields
h = list(f.header)
if len(h) > 0:
yield tuple(h[-1].split('\t'))
# data rows
for row in f.fetch(reference=self.reference, start=self.start, end=self.end, region=self.region, parser=asTuple()):
yield tuple(row)
except:
raise
finally:
f.close()
genofins = []
for line in genofinfile:
genofins.append(line.strip().split()[1])
genofinfile.close()
genoinds = [genofins.index(x) + 6 for x in officialfindivs]
y = {}
currbimbam = open(currfiles + '.bimbam','w')
#t0 = time.time()
for snp in masterdic.keys():
#for snp in masterdic.keys()[0:1000]:
chrm = masterdic[snp][0]
if chrm == 'chrm':
continue
tabixer = Tabixfile('/mnt/lustre/home/cusanovich/500HT/Imputed1415/ByChr/hutt.all.imputed.' + chrm + '.txt.gz')
tempgenos = [x.split('\t') for x in tabixer.fetch(chrm,int(masterdic[snp][1])-1,int(masterdic[snp][2]))][0]
genos = [tempgenos[x] for x in range(0,6) + genoinds]
tabixer.close()
y[snp] = [genos[3], 'A', 'G'] + genos[6:]
print >> currbimbam, ", ".join(y)
#t1 = time.time()
#print t1-t0
currbimbam.close()
#genomat = matrix_reader(genodir + 'hutt.imputed.dhssnps.bimbam',sep=",")
print "Running GEMMA..."
gemmer = (hmdir + 'Programs/gemma0.94 -g ' + currfiles + '.bimbam -p ' + currfiles + '.pheno -k ' + currfiles + '.square.txt -c ' + currfiles + '.covariates -lmm 4 -maf 0.05 -o curr_' + pheno)
t0 = time.time()
ifier(gemmer)
