def main():
parser = argparse.ArgumentParser(description='')
parser.add_argument('--nodes')
parser.add_argument('--partition')
parser.add_argument('--resolution',type=int)
parser.add_argument('--re',action='store_true')
parser.add_argument('--subset_chromosomes',default='NA')
args = parser.parse_args()
nodes_modified_file=args.partition+'.tmp'
subp.check_output(['bash','-c','zcat -f '+args.nodes+' | sort -k1,1 -k2,2n | gzip > '+nodes_modified_file+'.sorted'])
nodes_modified=open(nodes_modified_file,'w')
for line in gzip.open(nodes_modified_file+'.sorted','r'):
items=line.strip().split('\t')
chromo,start,end,name=items[0],items[1],items[2],items[3]
if args.subset_chromosomes!='NA':
if chromo not in args.subset_chromosomes.split(','):
continue
nodes_modified.write(re.sub('chr','',chromo)+'\t'+start+'\t'+end+'\t'+name+'\n')
nodes_modified.close()
if args.re:
#restriction fragments
myfends=hifive.Fend(args.partition, mode='w')
myfends.load_fends(nodes_modified_file, format='bed')
else:
#uniform bins
myfends=hifive.Fend(args.partition, mode='w',binned=int(args.resolution))
myfends.load_bins(nodes_modified_file, format='bed')
myfends.save()
os.remove(nodes_modified_file)
os.remove(nodes_modified_file+'.sorted')
#!/usr/bin/env python2.7
"""
Example:
$ python hifive_processing.py alignments.raw name
"""
import hifive
import sys
rawAlign, name = sys.argv[1], sys.argv[
2] # Name will be the prefix of output files
## Load in the restriction enzyme digested fend coordinates
fend = hifive.Fend('%s_fend.hdf5' % (name), mode='w')
fend.load_fends('../ce10nm2.bed',
genome_name='ce10',
re_name='DpnII',
format='bed')
fend.save()
## Load in the read data
data = hifive.HiCData('%s_data.hdf5' % (name), mode='w')
data.load_data_from_bam('%s_fend.hdf5' % (name), rawAlign, maxinsert=500)
data.save()
## Create a HiC object
hic = hifive.HiC('%s_hic.hdf5' % (name), 'w')
hic.load_data('%s_data.hdf5' % (name))
hic.save()
import hifive
import sys
import os
bam1 = sys.argv[1]
bam2 = sys.argv[2]
RE_bed = sys.argv[3]
outdir = sys.argv[4]
#RE_bed='/resources/HindIII_hg19_liftover.bed'
if not os.path.exists(outdir):
os.mkdir(outdir)
# Creating a Fend object
fend = hifive.Fend(outdir + '/fend_object.hdf5', mode='w')
fend.load_fends(RE_bed, re_name='RE', format='bed')
fend.save()
# Creating a HiCData object
data = hifive.HiCData(outdir + '/HiC_data_object.hdf5', mode='w')
data.load_data_from_bam(outdir + '/fend_object.hdf5', [bam1, bam2],
maxinsert=500)
data.save()
# Creating a HiC Project object
hic = hifive.HiC(outdir + '/HiC_project_object.hdf5', 'w')
hic.load_data(outdir + '/HiC_data_object.hdf5')
hic.save()
# Filtering HiC fends
def run_hifive(self, parameters):
fend_file = parameters['fend_file']
bam_file_1 = parameters['bam_file_1']
bam_file_2 = parameters['bam_file_2']
model = parameters['model']
restriction_enzymes = map(
str, parameters['restriction_enzyme'].strip('[]').split(','))
if len(restriction_enzymes) == 1:
restriction_enzyme = restriction_enzymes[0]
else:
restriction_enzyme = ','.join(restriction_enzymes)
if model == 'Yaffe-Tanay':
# Creating a Fend object
fend = hifive.Fend('fend_object.hdf5', mode='w')
fend.load_fends(fend_file,
re_name=restriction_enzyme,
format='bed')
fend.save()
# Creating a HiCData object
data = hifive.HiCData('HiC_data_object.hdf5', mode='w')
data.load_data_from_bam('fend_object.hdf5',
[bam_file_1, bam_file_2],
maxinsert=500,
skip_duplicate_filtering=False)
data.save()
# Creating a HiC Project object
hic = hifive.HiC('HiC_project_object.hdf5', 'w')
hic.load_data('HiC_data_object.hdf5')
hic.save()
# Filtering HiC fends
hic = hifive.HiC('HiC_project_object.hdf5')
hic.filter_fends(mininteractions=1, mindistance=0, maxdistance=0)
hic.save()
# Finding HiC distance function
hic = hifive.HiC('HiC_project_object.hdf5')
hic.find_distance_parameters(numbins=90, minsize=200, maxsize=0)
hic.save()
# Learning correction parameters using the binning algorithm
hic = hifive.HiC('HiC_project_object.hdf5')
hic.find_binning_fend_corrections(
max_iterations=1000,
mindistance=500000,
maxdistance=0,
num_bins=[20, 20, 20, 20],
model=['len', 'distance', 'gc', 'mappability'],
parameters=['even', 'even', 'even', 'even'],
usereads='cis',
learning_threshold=1.0)
hic.save('HiC_norm_binning.hdf5')
elif model == 'Hi-Corrector':
# Creating a Fend object
fend = hifive.Fend('fend_object.hdf5', mode='w')
fend.load_fends(fend_file,
re_name=restriction_enzyme,
format='bed')
fend.save()
# Creating a HiCData object
data = hifive.HiCData('HiC_data_object.hdf5', mode='w')
data.load_data_from_bam('fend_object.hdf5',
[bam_file_1, bam_file_2],
maxinsert=500,
skip_duplicate_filtering=False)
data.save()
# Creating a HiC Project object
hic = hifive.HiC('HiC_project_object.hdf5', 'w')
hic.load_data('HiC_data_object.hdf5')
hic.save()
def run_hifive(self, parameters):
fend_file = parameters['fend_file']
bam_file_1 = parameters['bam_file_1']
bam_file_2 = parameters['bam_file_2']
model = parameters['model']
add_gc = bool(parameters['add_gc'])
add_mappability = bool(parameters['add_mappability'])
restriction_enzymes = map(
str, parameters['restriction_enzyme'].strip('[]').split(','))
if len(restriction_enzymes) == 1:
restriction_enzyme = restriction_enzymes[0]
else:
restriction_enzyme = ','.join(restriction_enzymes)
# Run for both models
if not os.path.isfile('HiC_project_object.hdf5'):
fend = hifive.Fend('fend_object.hdf5', mode='w')
fend.load_fends(fend_file,
re_name=restriction_enzyme,
format='bed')
fend.save()
# Creating a HiCData object
data = hifive.HiCData('HiC_data_object.hdf5', mode='w')
data.load_data_from_bam('fend_object.hdf5',
[bam_file_1, bam_file_2],
maxinsert=500,
skip_duplicate_filtering=False)
data.save()
# Creating a HiC Project object
hic = hifive.HiC('HiC_project_object.hdf5', 'w')
hic.load_data('HiC_data_object.hdf5')
hic.save()
if model == 'Yaffe-Tanay':
if not os.path.isfile('HiC_norm_binning.hdf5'):
# Filtering HiC fends
hic = hifive.HiC('HiC_project_object.hdf5')
hic.filter_fends(mininteractions=1,
mindistance=0,
maxdistance=0)
# Finding HiC distance function
hic.find_distance_parameters(numbins=90,
minsize=200,
maxsize=0)
hic.save('HiC_project_object_with_distance_parameters.hdf5')
# Learning correction parameters using the binning algorithm
my_model = ['len', 'distance']
if add_gc == True:
my_model.append('gc')
if add_mappability == True:
my_model.append('mappability')
my_num_bins = [20] * len(my_model)
my_parameters = ['even'] * len(my_model)
hic.find_binning_fend_corrections(max_iterations=1000,
mindistance=500000,
maxdistance=0,
num_bins=my_num_bins,
model=my_model,
parameters=my_parameters,
usereads='cis',
learning_threshold=1.0)
hic.save('HiC_norm_binning.hdf5')