def _iterate_vcf(self, vcf_ittr, distin_dict, reg):
"""
"""
pick_mode = distin_dict['pick_mode']
# 辞書のキーが0。名前の文字列を示している。
gr_list = [distin_dict[0], distin_dict[1]]
log.info("gr_list {}.".format(gr_list))
# At first, we check difference of genotype between two sample
# that described at the beginning of each group
top_smpl_list = [
glv.conf.g_members_dict[gr_list[0]][0],
glv.conf.g_members_dict[gr_list[1]][0]
]
log.info("top_smpl_list {}.".format(top_smpl_list))
# ================================================================
start = time.time()
# write out to file
out_txt_file = distin_dict['variant']['out_path']
utl.save_to_tmpfile(out_txt_file)
# ここがparallele化できるか
# f.writeの最後のflash必要か。
with open(out_txt_file, mode='a') as f:
# write header
f.write("{}\n".format(distin_dict['variant']['hdr_text']))
# access to vcf using iterater
for record in vcf_ittr:
# 1. Skip same GT between top two sample
if self._skip_same_GT_between_top2sample(
record, top_smpl_list) > 0:
continue
# 2. Check GT in your own group
if self._skip_different_GT_in_own_group(
record, top_smpl_list, gr_list) > 0:
continue
# 3. Select different allele combination among 2x2 allele
asel = AlleleSelect()
asel.select_diff_allele(record, top_smpl_list, gr_list)
# skip if pick_mode is different
# if utl.is_my_pick_mode(
# asel.var_type, distin_dict['pick_mode']) != True:
# continue
# 4. Save variant information as text file
for var_type, line in zip(asel.var_types, asel.lines):
if utl.is_my_pick_mode(var_type,
distin_dict['pick_mode']) == True:
f.write("{}\n".format(line))
log.info("variant {} {}".format(utl.elapsed_time(time.time(), start),
distin_dict['variant']['base_nam']))
def _iterate_vcf(self, vcf_ittr, distin_dict, proc_cnt):
"""
"""
# basic informations
gr_list = [distin_dict[0], distin_dict[1]]
reg = distin_dict['region']
reg_dict = glv.conf.regions_dict[reg]
pick_mode = distin_dict['pick_mode']
indel_size = distin_dict['indel_size']
min_indel_len, max_indel_len = \
[int(i) for i in indel_size.split('-')]
# At first, we check difference of genotype between two sample
# that described at the beginning of each group
top_smpl_list = [
glv.conf.group_members_dict[gr_list[0]][0],
glv.conf.group_members_dict[gr_list[1]][0]
]
# logging current target
utl.print_distin_info("variant", distin_dict, proc_cnt)
start = time.time()
# File name to export variant
out_txt_file = distin_dict['variant']['out_path']
utl.save_to_tmpfile(out_txt_file)
#------------------------------------------------------
# To add an allele_int column for all sample
# Members of the specified group come first
# gr0:s1 g0:s2 g0:s3 g1:s4 g1:s5 g1:s6 s7 s8 s9 s10
sample_nickname_ordered_list, \
sample_fullname_ordered_list = \
utl.get_ordered_sample_list(gr_list)
sample_added_header = "{}\t{}".format(
distin_dict['variant']['hdr_text'],
"\t".join(sample_nickname_ordered_list))
# Can I parallelize here?
with open(out_txt_file, mode='a') as f:
# write sample added header
f.write("{}\n".format(sample_added_header))
# access to vcf using iterater
for record in vcf_ittr:
# 1. Skip same GT between top two sample
if self._skip_same_GT_between_top2sample(
record, top_smpl_list) > 0:
continue
# 2. Check GT in your own group
if self._skip_different_GT_in_own_group(
record, top_smpl_list, gr_list) > 0:
continue
# 3. Select different allele combination among 2x2 allele
asel = AlleleSelect(min_indel_len, max_indel_len)
asel.select_diff_allele(record, top_smpl_list, gr_list)
# from record, construct allele_int of the member
# who is paying attention
allele_int_line = ""
# 4. Save variant information as text file
for var_type, line in zip(asel.var_types, asel.lines):
if utl.is_my_pick_mode(var_type,
distin_dict['pick_mode']) == True:
# make allele_int line
if allele_int_line == "":
#self._get_ai_line(
allele_int_line = \
self._get_allele_line(
record, sample_fullname_ordered_list)
# add allele line
f.write("{}\t{}\n".format(line, allele_int_line))
log.info("variant {} > {}.txt\n".format(
utl.elapsed_time(time.time(), start),
distin_dict['variant']['base_nam']))