def start(self):
freq_item = self.get_freq_item()
with open(self.infile, 'r') as fr, open(self.suffix + '.filter_freq_pass', 'w') as fw_pass,\
open(self.suffix + '.filter_freq_fail', 'w') as fw_fail:
for line in fr:
freq_status_list = [] #
if line.startswith('Scale'):
fw_pass.write(line)
fw_fail.write(line)
head = line
head_index = utils.get_head_index(head)
continue
linelist = line.strip('').split('\t')
for item in freq_item: # item = gnomAD_SAS_AF
if not linelist[head_index[item.lower()]] == '-' and\
float(linelist[head_index[item.lower()]]) < self.freq:
freq_status_list.append('pass')
else:
freq_status_list.append('fail')
if self.judge_freq_tag(freq_status_list):
fw_pass.write(line)
else:
fw_fail.write(line)
# 清空，列表为可更改对象
freq_status_list.clear()
def start(self):
localcontrol_info = self.get_localcontrol_info()
with open(self.infile, 'r') as fr, open(self.suffix + '_pass', 'w') as fw_pass,\
open(self.suffix + '_fail', 'w') as fw_fail:
for line in fr:
if line.startswith('Scale'):
head = line
fw_pass.write(line)
fw_fail.write(line)
head_index = utils.get_head_index(head)
continue
linelist = line.strip('\n').split('\t')
case_freq = float(linelist[head_index['case_var_freq']])
_chr = linelist[head_index['chromosome']]
pos = linelist[
head_index['start_position']] # 理解为什么选取start作为pos
ref = linelist[head_index['reference_allele']]
alt = linelist[head_index['allele']]
key = '{_chr}_{pos}_{ref}_{alt}'.format(**locals())
if key in localcontrol_info and case_freq > localcontrol_info[
key][0]:
fw_pass.write('NOControl{0};{1}'.format(
localcontrol_info[key][1], line))
elif key in localcontrol_info and case_freq <= localcontrol_info[
key][0]:
fw_fail.write('NOControl{0};{1}'.format(
localcontrol_info[key][1], line))
else:
fw_pass.write(line)
def start(self):
func_list = self.get_save_function_list()
with utils.safe_open(self.infile, 'r') as fr, open(self.suffix + '_pass', 'w') as fw_pass, \
open(self.suffix + '_fail', 'w') as fw_fail:
for line in fr:
if line.startswith('Scale'):
fw_pass.write(line)
fw_fail.write(line)
head = line
head_index = utils.get_head_index(head)
continue
linelist = line.strip('').split('\t')
bgi_func = linelist[head_index['bgi_function']] # nonsense
vep_func = linelist[head_index['consequence']] # 原始vep注释结果
gene = linelist[head_index['hugo_symbol']] # TERT
chgvs = linelist[head_index['hgvsc']] # c.-146C>T
# 针对8个tert启动子，构造特殊key
tert_promter = '{gene}:{chgvs}'.format(**locals())
if bgi_func in func_list and self.save_span(
chgvs, bgi_func,
vep_func) or tert_promter in func_list:
fw_pass.write(line)
else:
fw_fail.write(line)
def start(self):
'''
'''
with open(self.infile, 'r') as fr, open(self.suffix + '_pass', 'w') as fw_pass,\
open(self.suffix + '_fail', 'w') as fw_fail:
for line in fr:
if line.startswith('Scale'):
head = line
fw_pass.write(line)
fw_fail.write('{}\tfilter_reason\n'.format(
line.strip('\n')))
head_index = utils.get_head_index(head)
continue
linelist = line.strip('\n').split('\t')
case_read = linelist[head_index['case_var_readsnum']]
case_read_pos = linelist[
head_index['case_var_positive_readsnum']]
case_read_neg = linelist[
head_index['case_var_negative_readsnum']]
if self.pass_read_threshold(case_read, case_read_pos,
case_read_neg):
fw_pass.write(line)
else:
fw_fail.write('{}\tReadNum\n'.format(line.strip('\n')))
def start(self):
'''全部的最终接口均为start函数
'''
uniport_info, uniport_gene_length = self.get_uniport_info()
with open(self.infile, 'r') as fr, open(self.resullt, 'w') as fw:
for line in fr:
if line.startswith('Scale'):
fw.write(line)
head = line
head_index = utils.get_head_index(head)
continue
linelist = line.strip('\n').split('\t')
gene = linelist[head_index['hugo_symbol']]
phgvs = linelist[head_index['hgvsp_short']]
#获取氨基酸发生突变的位置
if re.search(r'(\d+)', phgvs):
phgvs_pos = re.search(r'(\d+)', phgvs).group(1)
else:
phgvs_pos = '*'
key = '{gene}_{phgvs_pos}'.format(**locals())
linelist[head_index['bgi_uniport_position(s)']] = uniport_gene_length.get(gene, '*')
if uniport_info.get(key):
linelist[head_index['bgi_uniport_position(s)']] = uniport_info[key]['length'] or '*'
linelist[head_index['bgi_uniport_feature_key']] = uniport_info[key]['feature_key'] or '*'
linelist[head_index['bgi_uniport_description']] = uniport_info[key]['description'] or '*'
fw.write('{0}\n'.format('\t'.join(linelist)))
def start(self):
final_exon_info = self.get_final_exon_info()
func_relation_info = self.get_func_relation_info()
with open(self.infile, 'r') as fr, open(self.result, 'w') as fw:
for line in fr:
if line.startswith('Scale'):
head = line
fw.write(line)
head_index = utils.get_head_index(head)
continue
linelist = line.strip('\n').split('\t')
gene = linelist[head_index['hugo_symbol']]
tran = linelist[head_index['transcript_id']]
exon = linelist[head_index['exon']]
key = '{tran}_{exon}'.format(**locals())
# 更新Funcregion 字段
linelist[head_index['funcregion']] = func_relation_info.get(
key, 'Nan')
# 更新最后一个exon的写法
linelist[head_index['exon']] = self.final_exon(
final_exon_info, tran, exon)
fw.write('{}\n'.format('\t'.join(linelist)))
def start(self):
driver_info = self.get_driver_info()
special_driver_info = self.get_special_driver_info()
with open(self.infile, 'r') as fr, open(self.result, 'w') as fw:
for line in fr:
if line.startswith('Scale'): #GG
head = line
fw.write(line)
head_index = utils.get_head_index(head)
continue
linelist = line.strip('\n').split('\t')
gene = linelist[head_index['hugo_symbol']]
chgvs = linelist[head_index['hgvsc']]
phgvs = linelist[head_index['hgvsp_short']]
func = linelist[head_index['bgi_function']]
exon = linelist[head_index['exon']]
case_freq = linelist[head_index['case_var_freq']]
# 利用bgicg结果进行测试
# gene = linelist[head_index['#gene']] # gene
# chgvs = linelist[head_index['chgvs']] # cHGVS
# phgvs = linelist[head_index['phgvs']] # pHGVS
# func = linelist[head_index['function']] # Function
# exon = linelist[head_index['exin_id']] # ExIn_ID
# case_freq = linelist[head_index['case_var_freq']]
kw = {
'gene': gene,
'chgvs': chgvs,
'phgvs': phgvs,
'func': func,
'exon': exon,
'driver_info': driver_info,
'special_driver_info': special_driver_info
}
# 进行TMB字段判断
if float(case_freq) < self.tmb_freq:
linelist[head_index['tmb_type']] = 'noTMB' #
elif func == 'span' and re.search(r'-EX1$', exon):
linelist[head_index['tmb_type']] = 'noTMB'
elif self.is_driver_gene(**kw):
linelist[head_index['tmb_type']] = 'Driver'
else:
linelist[head_index['tmb_type']] = 'TMB'
fw.write('{}\n'.format('\t'.join(linelist)))
def start(self):
func_info = self.get_gene_func_info()
chgvs_info, phgvs_info = self.get_gene_pos_info()
exon_info = self.get_gene_exon_info()
with open(self.infile, 'r') as fr, open(self.result, 'w') as fw:
for line in fr:
if line.startswith('Scale'):
head = line
fw.write(line)
head_index = utils.get_head_index(line)
continue
linelist = line.strip('\n').split('\t')
gene = linelist[head_index['hugo_symbol']]
chgvs = linelist[head_index['hgvsc']]
phgvs = linelist[head_index['hgvsp_short']]
func = linelist[head_index['bgi_function']]
exon = linelist[head_index['exon']]
key_func = '{gene}_{func}'.format(**locals())
key_chgvs = '{gene}_{chgvs}'.format(**locals())
key_phgvs = '{gene}_{phgvs}'.format(**locals())
# print(key_func)
#修改Target_gene字段信息
tmp = ''
if func_info.get(key_func):
for key, value in func_info[key_func].items():
tmp += '{key}:{value};'.format(**locals())
elif phgvs_info.get(key_phgvs):
for key, value in phgvs_info[key_phgvs].items():
tmp += '{key}:{value};'.format(**locals())
elif chgvs_info.get(key_chgvs):
for key, value in chgvs_info[key_chgvs].items():
tmp += '{key}:{value};'.format(**locals())
elif exon_info.get(gene) and exon.startswith('EX'):
tmp = exon_info[gene]
# tmp = tmp.replace(';;', ';')
if tmp:
linelist[head_index['target_gene']] = 'YES({tmp})'.format(
**locals()).replace(';;', ';')
else:
linelist[head_index['target_gene']] = 'NO'
fw.write('{}\n'.format('\t'.join(map(str, linelist))))
def get_tran_relation(self):
'''
input:
self.transcript: gene transcript
output:
list: [gene=trans, gene=trans]
'''
tran_relation = []
with utils.safe_open(self.transript_database, 'r') as fr:
for line in fr:
if line.startswith('#'):
head_index = utils.get_head_index(line)
continue
linelist = line.strip('').split('\t')
gene = linelist[head_index['#gene']]
tran = linelist[head_index['transcript']]
tran_relation.append('{gene}={tran}'.format(**locals()))
return tran_relation
def start(self):
maploc_info = self.get_maploc_info()
with open(self.infile, 'r') as fr, open(self.result, 'w') as fw:
for line in fr:
if line.startswith('Scale'):
fw.write(line)
head = line
head_index = utils.get_head_index(head)
continue
linelist = line.strip('\n').split('\t')
_chr = linelist[head_index['chromosome']]
start = int(linelist[head_index['start_position']])
end = int(linelist[head_index['end_position']])
map_location = self.get_variant_maploc(_chr, start, end,
maploc_info)
linelist[head_index['maploc']] = map_location
# print(linelist)
fw.write('{}\n'.format('\t'.join(linelist)))
def start(self):
with open(self.infile, 'r') as fr, open(self.suffix + '_pass', 'w') as fw_pass,\
open(self.suffix + '_fail', 'w') as fw_fail:
for line in fr:
if line.startswith('Scale'):
fw_pass.write(line)
fw_fail.write('{}\tfilter_reason\n'.format(
line.strip('\n')))
head = line
head_index = utils.get_head_index(head)
continue
linelist = line.strip('\n').split('\t')
tmb_tag = linelist[head_index['tmb_type']]
func = linelist[head_index['bgi_function']]
if func == 'coding-synon' and tmb_tag == 'noTMB':
fw_fail.write('{}\tsynonymy\n'.format('\t'.join(linelist)))
else:
fw_pass.write(line)
def get_tran_relation(self, **args):
'''
input:
self.transcript: gene transcript
output:
list: [trans1, trans2]
'''
tran_relation = []
with utils.safe_open(args['transcript_data'], 'r') as fr:
for line in fr:
line = line.strip('\n')
if line.startswith('#'):
head_index = utils.get_head_index(line)
continue
linelist = line.strip('\n').split('\t')
# gene = linelist[head_index['#gene']]
tran = linelist[head_index['transcript']]
tran_relation.append('{tran}'.format(**locals()))
return tran_relation
def start(self, **args):
with open(args['infile'], 'r') as fr, open(args['result'], 'w') as fw:
for line in fr:
if line.startswith('Scale'):
fw.write(line)
head = line
head_index = utils.get_head_index(head)
continue
linelist = line.strip('\n').split('\t')
func = linelist[head_index['bgi_function']]
tran = linelist[head_index['transcript_id']]
start = linelist[head_index['start_position']]
end = linelist[head_index['end_position']]
phgvs = linelist[head_index['hgvsp_short']]
chgvs = linelist[head_index['hgvsc']]
flank = linelist[head_index['flank']]
strand = linelist[head_index['strand']]
gene = linelist[head_index['hugo_symbol']]
exon_id = linelist[head_index['exon']]
end_exon_tag = EndExonCheck(args, tran, start, end,
func).start()
gene_extend_tag = GeneExtendCheck(args, tran, func,
phgvs).start()
splice_affect_tag = SpliceAffectCheck(args, func, chgvs, flank,
strand).start()
newfun_tag = NewFunction(func, gene, exon_id, end_exon_tag,
gene_extend_tag,
splice_affect_tag).start()
linelist[head_index['bgi_end_exon_check']] = end_exon_tag
linelist[head_index['bgi_gene_extend_check']] = gene_extend_tag
linelist[
head_index['bgi_splice_affect_check']] = splice_affect_tag
linelist[head_index['bgi_newfunction']] = newfun_tag
# print(linelist)
fw.write('{}\n'.format('\t'.join(linelist)))
def start(self):
database_info = self.get_database_info()
with open(self.infile, 'r') as fr, open(self.suffix + '_pass', 'w') as fw_pass, \
open(self.suffix + '_fail', 'w') as fw_fail:
for line in fr:
if line.startswith('Scale'):
fw_pass.write(line)
fw_fail.write('{}\tfail_reason\n'.format(line.strip('\n')))
head = line
head_index = utils.get_head_index(head)
continue
linelist = line.strip('\n').split('\t')
_chr = linelist[head_index['chromosome']]
pos = linelist[head_index['start_position']]
ref = linelist[head_index['reference_allele']]
alt = linelist[head_index['allele']]
key = '{_chr}_{pos}_{ref}_{alt}'.format(**locals())
if key in database_info:
fw_fail.write('{}\t{}\n'.format(line.strip('\n'), database_info[key]))
else:
fw_pass.write(line)
def start(self):
# print('>>>cosmic分析中')
cosmic_info = self.get_cosmic_info()
with open(self.infile, 'r') as fr, open(self.result, 'w') as fw:
for line in fr:
if line.startswith('Scale'):
head = line
fw.write(line)
head_index = utils.get_head_index(head)
continue
linelist = line.strip('\n').split('\t')
gene = linelist[head_index['hugo_symbol']]
_chr = linelist[head_index['chromosome']]
pos = linelist[head_index['start_position']] #清楚为什么使用start!!
ref = linelist[head_index['reference_allele']]
alt = linelist[head_index['allele']]
chgvs = linelist[head_index['hgvsc']]
key1 = '{gene}_{_chr}_{pos}_{ref}_{alt}'.format(**locals())
key2 = '{gene}_{chgvs}'.format(**locals())
cosmic_tmp = ''
tmp1 = cosmic_info.get(key1, '')
tmp2 = cosmic_info.get(key2, '')
if tmp1 == tmp2 and tmp1:
cosmic_linelist = tmp1.split('\t')
if cosmic_linelist[11] == '-':
cosmic_tmp = 'the mutation {0} has been exclude from the website.:{1}'.\
format(cosmic_linelist[1], cosmic_linelist[10])
else:
cosmic_tmp = '{0}:{1};{2}'.format(
cosmic_linelist[1], cosmic_linelist[10],
cosmic_linelist[11])
elif tmp1 and not tmp2:
cosmic_linelist = tmp1.split('\t')
if cosmic_linelist[11] == '-':
cosmic_tmp = 'the mutation {0} has beed excluded from \
the website and cosmic gene or chgvs diff {1}_{2}:{3}'.format(
cosmic_linelist[1], cosmic_linelist[0],
cosmic_linelist[2], cosmic_linelist[10])
else:
cosmic_tmp = 'Cosmic gene or cHGVS diff {0}_{1}: {2}:{3};{4}'.format(
cosmic_linelist[0], # gene
cosmic_linelist[2], # hgvs
cosmic_linelist[1], # cosm
cosmic_linelist[10], # 1
cosmic_linelist[11]) # large
elif tmp2 and not tmp1:
cosmic_linelist = tmp2.split('\t')
if cosmic_linelist[11] == '-':
cosmic_tmp = 'The mutation {0} has beed exclude from the website and \
cosmic pos or alt diff {1}:{2} {3}/{4}: {5}'.format(
cosmic_linelist[1],
cosmic_linelist[4], # chr
cosmic_linelist[5],
cosmic_linelist[6],
cosmic_linelist[7],
cosmic_linelist[10])
else:
cosmic_tmp = 'Cosmic Pos or alt diff {0}:{1} {2}/{3}:{4}:{5};{6}'.format(
cosmic_linelist[4], # chr
cosmic_linelist[5],
cosmic_linelist[6],
cosmic_linelist[7],
cosmic_linelist[1],
cosmic_linelist[10],
cosmic_linelist[11])
else:
cosmic_tmp = '*'
# 更细cosmic字段
linelist[head_index['cosmic']] = cosmic_tmp
fw.write('{0}\n'.format('\t'.join(linelist)))
def start(self, **args):
'''
程序运行主函数
'''
other_info = {} # 用于更新其他字段
if args['vcf']:
vcf_info = get_vcf_info.HandleVcf(args['vcf'], args['vcftype']).start()
tran_relation = self.get_tran_relation(**args)
with open(args['vep_annotation'], 'r') as fr, open(args['result'], 'w') as fw:
fw.write('{}\n'.format('\t'.join(headers.HEAD().update_head().keys())))
for line in fr:
if line.startswith('##'):
continue
elif line.startswith('#Uploaded_variation'):
head = line
head_index = utils.get_head_index(head)
continue
linelist = line.strip('').split('\t')
gene = linelist[head_index['symbol']] # TERT
transcript = linelist[head_index['feature']] # NM_198253.3
#提取基因指定的转录本注释信息
if not '{transcript}'.format(**locals()) in tran_relation:
continue
#获取需要的信息
row = headers.HEAD()
## 可以直接提取的信息
upload_variation = linelist[head_index['#Uploaded_variation'.lower()]] # chr5_1295229_-/A
location = linelist[head_index['location']] # chr5:1295187-1295188
vep_function = linelist[head_index['consequence']] # missense_variant
strand = linelist[head_index['strand']] # -1
strand = '+' if strand == '1' else '-'
protein = linelist[head_index['ensp']] # NP_937983.2
sift = linelist[head_index['sift']] # tolerated(0.05)
polyphen = linelist[head_index['polyphen']]
exon_info = linelist[head_index['exon']] # 2/19 or -
intro_info = linelist[head_index['intron']]
chgvs = linelist[head_index['hgvsc']] # NM_198253.3:c.77C>T
phgvs = linelist[head_index['hgvsp']] # NP_937983.2:p.Thr26Met
tert = linelist[head_index['tert']] # 只有tert的启动子区域有
clinvar = linelist[head_index['clinvar_clnsig']]
rs = linelist[head_index['existing_variation']]
bl_muttype = linelist[head_index['variant_class']]
af = linelist[head_index['af']]
afr_af = linelist[head_index['afr_af']]
amr_af = linelist[head_index['amr_af']]
eas_af = linelist[head_index['eas_af']]
eur_af = linelist[head_index['eur_af']]
sas_af = linelist[head_index['sas_af']]
aa_af = linelist[head_index['aa_af']]
ea_af = linelist[head_index['eas_af']]
gnomad_af = linelist[head_index['gnomad_af']]
gnomad_afr_af = linelist[head_index['gnomad_afr_af']]
gnomad_amr_af = linelist[head_index['gnomad_amr_af']]
gnomad_asj_af = linelist[head_index['gnomad_asj_af']]
gnomad_eas_af = linelist[head_index['gnomad_eas_af']]
gnomad_fin_af = linelist[head_index['gnomad_fin_af']]
gnomad_nfe_af = linelist[head_index['gnomad_nfe_af']]
gnomad_oth_af = linelist[head_index['gnomad_oth_af']]
gnomad_sas_af = linelist[head_index['gnomad_sas_af']]
# 需要进行处理获取的信息
hgvsc = utils.simplify_hgvsc(gene, chgvs, tert)
hgvsp = utils.simplify_hgvsp(phgvs) # p.Lys872_Thr874delinsAsnTer
hgvsp_short = utils.get_oneletter_hgvsp(hgvsp) # p.K872_T874delinsN*
exon_id = utils.get_exon_id(exon_info, intro_info)
_chr, start, end = utils.get_chr_start_end_from_location(location)
ref, alt = utils.get_ref_alt_from_upload_variation(upload_variation)
muttype = utils.get_muttype(ref, alt)
genotype = utils.get_genotype(ref, alt, strand)
flank = utils.get_flank_according_upload_variation(upload_variation, args['hg19'])
vep_simple_function = TransverFunction(**args).simplify_function(vep_function, tert, gene)
vep2bgicg_function = TransverFunction(**args).vep2bgi(vep_simple_function, hgvsc, hgvsp, ref, alt, exon_id)
## 存在特殊情况,span,跨越整个内含子,但是phgvs还存在注释信息,这种是错误的
## 针对这种情况，需要对span类型的phgvs赋空值
if vep2bgicg_function == 'span' and (not hgvsp == '-'):
hgvsp = '-'
hgvsp_short = '-'
# 更新row
row.gene = gene
row.chgvs = hgvsc
row.phgvs = hgvsp
row.phgvs_shoft = hgvsp_short
row.exon_id = exon_id
# row.tert = tert
row.vep_function = vep_function
row.vep_simple_function = vep_simple_function
row.vep2bgicg_function = vep2bgicg_function
row.sift = sift
row.polyphen2 = polyphen
row.chr = _chr
row.start = start
row.end = end
row.ref = ref
row.alt = alt
row.muttype = muttype
row.genotype = genotype
row.transcript = transcript
row.protein = protein
row.strand = strand
row.flank = flank
row.rs = rs
row.bl_muttype = bl_muttype
row.clinvar = clinvar
row.af = af
row.afr_af = afr_af
row.amr_af = amr_af
row.eas_af = eas_af
row.eur_af = eur_af
row.sas_af = sas_af
row.aa_af = aa_af
row.ea_af = ea_af
row.gnomad_af = gnomad_af
row.gnomad_afr_af = gnomad_afr_af
row.gnomad_amr_af = gnomad_amr_af
row.gnomad_asj_af = gnomad_asj_af
row.gnomad_eas_af = gnomad_eas_af
row.gnomad_fin_af = gnomad_fin_af
row.gnomad_nfe_af = gnomad_nfe_af
row.gnomad_oth_af = gnomad_oth_af
row.gnomad_sas_af = gnomad_sas_af
if args['vcf']:
freq_tag = vcf_info[upload_variation]
other_info.update(freq_tag)
info = row.update_head(**other_info)
fw.write('\t'.join(map(str, info.values())) + '\n')
def start(self):
'''
程序运行主函数
'''
if self.vcf:
vcf_info = get_vcf_info.HandleVcf(self.vcf, self.vcftype).start()
with open(self.vep, 'r') as fr, open('test', 'w') as fw:
for line in fr:
if line.startswith('##'):
continue
elif line.startswith('#Uploaded_variation'):
head = line
head_index = utils.get_head_index(head)
continue
linelist = line.strip('').split('\t')
#获取需要的信息
row = headers.HEAD()
## 可以直接提取的信息
upload_variation = linelist[head_index['#Uploaded_variation'.lower()]] # chr5_1295229_-/A
location = linelist[head_index['location']] # chr5:1295187-1295188
transcript = linelist[head_index['feature']] # NM_198253.3
function = linelist[head_index['consequence']] # missense_variant
strand = linelist[head_index['strand']] # -1
gene = linelist[head_index['symbol']] # TERT
protein = linelist[head_index['ensp']] # NP_937983.2
sift = linelist[head_index['sift']] # tolerated(0.05)
polyphen = linelist[head_index['polyphen']]
exon_id = linelist[head_index['exon']] # 2/19 or -
chgvs = linelist[head_index['hgvsc']] # NM_198253.3:c.77C>T
phgvs = linelist[head_index['hgvsp']] # NP_937983.2:p.Thr26Met
tert = linelist[head_index['tert']] # 只有tert的启动子区域有
clinvar = linelist[head_index['clinvar_clnsig']]
rs = linelist[head_index['existing_variation']]
# 需要进行处理获取的信息
hgvsc = utils.simplify_hgvsc(chgvs)
hgvsp2 = utils.simplify_hgvsp(phgvs)
hgvsp = utils.get_oneletter_hgvsp(hgvsp2)
exon_id = utils.get_exon_id(exon_id)
_chr, start, end = utils.get_chr_start_end_from_location(location)
ref, alt = utils.get_ref_alt_from_upload_variation(upload_variation)
muttype = utils.get_muttype(ref, alt)
genotype = utils.get_genotype(ref, alt, strand)
flank = utils.get_flank_according_upload_variation(upload_variation, self.hg19)
bl_muttype = utils.get_bl_muttype()
# 更新row
row.gene = gene
row.chgvs = hgvsc
row.phgvs = hgvsp
row.phgvs2 = hgvsp2
row.exon_id = exon_id
row.vep_function = function
row.sift = sift
row.polyphen2 = polyphen
row.chr = _chr
row.start = start
row.end = end
row.ref = ref
row.alt = alt
row.muttype = muttype
row.genotype = genotype
row.transcript = transcript
row.protein = protein
row.strand = strand
row.flank = flank
row.rs = rs
row.bl_muttype = bl_muttype
row.clinvar = clinvar
if self.vcf:
freq_tag = vcf_info[upload_variation]
# print(freq_tag)
info = row.update_head(**freq_tag)
fw.write('\t'.join(info.keys()) + '\n')
fw.write('\t'.join(map(str, info.values())) + '\n')