def write_head(self):
with open(self.__outvcf, 'w') as fi:
##header
fi.write("{}".format(Read.Readvcf(self.__invcf).header))
#samples行
samples = Read.Readvcf(self.__invcf).samples.split('|')
newsamples = []
for group_name in self.__grp_dict:
for i in self.__grp_dict[group_name]['index']:
newsamples.append(samples[i])
fi.write(
"#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\t{}\n".
format("\t".join(newsamples)))
def main(self):
if not self.__invcf:
print('Use --help for command line help')
return
try:
os.makedirs(args.work_dir)
except:
pass
#print ('%s exists' %(args.work_dir))
self.get_group()
self.write_head()
low_dp, high_dp = self.__depth.split(',')
vcfinfo = Read.Readvcf(self.__invcf).extract
#pool = mp.Pool(1) #启动多线程池
for each in vcfinfo:
self.run_filter(each, self.__grp_dict, low_dp, high_dp)
#pool.apply_async(self.run_filter, args=(each, self.__grp_dict, low_dp, high_dp))#函数写入到多线程池
"""
print('Waiting for all subprocesses done...')
pool.close()
pool.join()
print('All subprocesses done.')
pool.terminate()
"""
print("低/高深度标记次数: {}".format(self.__total_dp_num))
print("Homogeneous标记次数: {}".format(self.__total_homogeneous_num))
def __init__(self, invcf, grp_dict, grp_name="", samples_lst=[]):
self.invcf = invcf
self.all_samples_lst = Read.Readvcf(self.invcf).samples.split('|')
self.grp_dict = grp_dict
if grp_name:
self.grp_name = grp_name
else:
self.grp_name = 'All'
if len(samples_lst) > 1:
self.samples_lst = samples_lst
else:
self.samples_lst = self.all_samples_lst
self.handle_grp()