def ubiquitin(filepath,fts):
table = functions.connectMongoDB('uniprot','ubiquitinTable')
# Open a file
ac_flag = 0
out_ac = []
out_position = []
out_data = dict()
special = 0
specials = ['Glycyllysineisopeptide(Lys-Gly)','Peptide(Met-Gly)(interchainwithG-Cter','Glycylserineester(Ser-Gly)','Glycylcysteinethioester(Cys-Gly)']
with open(filepath) as fp:
for line in fp:
collapsed = ' '.join(line.split())
data = collapsed.split(";")
parsed_1 = data[0].split(" ")
if parsed_1[0] == "AC" and ac_flag == 0:
ac_flag = 1
out_ac.append(parsed_1[1])
if len(data) > 2:
for x in range(1, len(data)-1):
out_ac.append(data[x])
out_data = {'ac':out_ac}
##[go,interpro,pfam,prosite,smart,supfam]
elif parsed_1[0] == "FT":
if len(parsed_1) > 4 and special == 0:
ft = ''
for i in range(4,len(parsed_1)):
ft = ft + parsed_1[i]
ft = re.sub('[.]', '', ft)
out_position = functions.remove_duplicates([parsed_1[2],parsed_1[3]])
if ft in specials:
special = 1
continue
if ft in fts:
fts.setdefault(ft, []).append(out_position)
out_position = []
elif special == 1:
for i in range(1,len(parsed_1)):
ft = ft + parsed_1[i]
ft = re.sub('[.]', '', ft)
if ft in fts:
fts.setdefault(ft, []).append(out_position)
out_position = []
special = 0
elif parsed_1[0] == '//':
fts = dict( [(k,list(itertools.chain.from_iterable(v))) for k,v in fts.items() if len(v)>0]) #delete empty FTs from dictionary ##list(itertools.chain.from_iterable(v)) format
out_data = functions.merge_two_dicts(out_data,fts)
#print(out_data)
table.save(out_data)
fts = {'Glycyllysineisopeptide(Lys-Gly)(interchainwithG-Cterinubiquitin)':[],'Glycylserineester(Ser-Gly)(interchainwithG-Cterinubiquitin)':[],
'Peptide(Met-Gly)(interchainwithG-Cterinubiquitin)':[],'Glycylcysteinethioester(Cys-Gly)(interchainwithG-Cterinubiquitin)':[]}
##rewind
out_ac = []
ac_flag = 0
out_position = []
fp.close()
def tableGeneration(filepath, fts):
table = functions.connectMongoDB('uniprot', 'table')
# Open a file
id_flag = 0
ac_flag = 0
out_ac = []
out_position = []
out_data = dict()
special = 0
sequence = ''
with open(filepath) as fp:
for line in fp:
collapsed = ' '.join(line.split())
data = collapsed.split(";")
parsed_1 = data[0].split(" ")
if parsed_1[0] == "ID" and id_flag == 0:
id_flag = 1
out_id = parsed_1[1]
elif parsed_1[0] == "AC" and ac_flag == 0:
ac_flag = 1
out_ac.append(parsed_1[1])
if len(data) > 2:
for x in range(1, len(data) - 1):
out_ac.append(data[x])
out_data = {'_id': out_id, 'ac': out_ac}
##[go,interpro,pfam,prosite,smart,supfam]
elif parsed_1[0] == "FT":
if len(parsed_1) > 4 and special == 0:
ft = ''
for i in range(4, len(parsed_1)):
ft = ft + parsed_1[i]
ft = re.sub('[.]', '', ft)
out_position = functions.remove_duplicates(
[parsed_1[2], parsed_1[3]])
if ft == 'Glycyllysineisopeptide(Lys-Gly)':
special = 1
continue
if ft in fts:
fts.setdefault(ft, []).append(out_position)
out_position = []
elif special == 1:
for i in range(1, len(parsed_1)):
ft = ft + parsed_1[i]
ft = re.sub('[.]', '', ft)
if ft in fts:
fts.setdefault(ft, []).append(out_position)
out_position = []
special = 0
##
## parse_1[0] is usually RT,DR,FT,or SQ etc... only squence part has length greater than 2
elif len(parsed_1[0]) > 2:
sequence += collapsed
elif parsed_1[0] == '//':
fts = dict(
[(k, list(itertools.chain.from_iterable(v)))
for k, v in fts.items() if len(v) > 0]
) #delete empty FTs from dictionary ##list(itertools.chain.from_iterable(v)) format
out_data = functions.merge_two_dicts(out_data, fts)
sequence = ''.join(sequence.split())
out_data['sequence'] = sequence
#print(out_data)
table.save(out_data)
fts = {
'Phosphoserine': [],
'Phosphothreonine': [],
'Phosphotyrosine': [],
'N6-acetyllysine': [],
'Omega-N-methylarginine': [],
'N6-methyllysine': [],
'N6,N6-dimethyllysine': [],
'N6,N6,N6-trimethyllysine': [],
'N-linked(GlcNAc)asparagine': [],
'S-palmitoylcysteine': [],
'Pyrrolidonecarboxylicacid': [],
'Glycyllysineisopeptide(Lys-Gly)(interchainwithG-CterinSUMO)':
[],
'Glycyllysineisopeptide(Lys-Gly)(interchainwithG-Cterinubiquitin)':
[]
}
##rewind
out_ac = []
id_flag = 0
ac_flag = 0
out_position = []
sequence = ''
fp.close()
def tableGeneration(filepath, ptms):
table = functions.connectMongoDB('uniprot', 'table')
table.drop()
out_id = ""
out_ac = []
out_position = []
out_data = dict()
sequence = ""
temp_ptm = ""
prev_fp_pos = 0
check = []
fp = open(filepath)
line = fp.readline()
while line:
collapsed = ' '.join(line.split())
data = collapsed.split(";")
info = data[0].split(" ")
tag = info[0]
#print(info[0]+" info1 "+info[1]+"\n")
if tag == "ID":
out_id = info[1]
elif tag == "AC":
out_ac.append(info[1])
if len(data) > 2:
for x in range(1, len(data) - 1):
out_ac.append(data[x].lstrip())
elif tag == "OC":
check.append(info[1].lstrip())
if len(data) > 2:
for x in range(1, len(data) - 1):
check.append(data[x].lstrip())
out_data = {"_id": out_id, "ac": out_ac, "species": check}
elif tag == "FT":
temp_ptm = ""
out_position = functions.remove_duplicates([info[2], info[3]])
temp_ptm = " ".join(info[4:])
#if "Q9TT90" in out_ac:
# print("################temp_ptm is 1 "+temp_ptm+"\n")
prev_fp_pos = fp.tell()
line = ' '.join(fp.readline().split())
info = line.split(" ")
while info[0] == "FT":
if len(info) > 3 and is_number(info[2]) and is_number(info[3]):
#if "Q9TT90" in out_ac:
# print("###########temp_ptm is 2 "+temp_ptm+"\n")
temp_ptm = re.sub('(\.*)\)', ')', temp_ptm)
for doc in ptms:
#if "Q9TT90" in out_ac and doc == 'Glycyllysineisopeptide(Lys-Gly)(interchainwithG-CterinSUMO)':
# print(doc+" vs "+re.sub('[\.|\;].*','',temp_ptm)+"\n")
if doc == re.sub('[\.|\;].*', '', temp_ptm):
#if "Q9TT90" in out_ac:
# print("yes\n")
ptms.setdefault(doc, []).append(out_position)
temp_ptm = ""
out_position = functions.remove_duplicates(
[info[2], info[3]])
temp_ptm = " ".join(info[4:])
else:
temp_ptm = temp_ptm + " ".join(info[1:])
#if "Q9TT90" in out_ac:
# print("#################temp_ptm is 3 "+temp_ptm+"\n")
#for i in range(1,len(info)):
# temp_ptm += info[i].rstrip()
#print(temp_ptm+"\n")
prev_fp_pos = fp.tell()
line = ' '.join(fp.readline().split())
info = line.split(" ")
temp_ptm = re.sub('(\.*)\)', ')', temp_ptm)
for doc in ptms:
#if "Q9TT90" in out_ac and doc == 'Glycyllysineisopeptide(Lys-Gly)(interchainwithG-CterinSUMO)':
# print(doc+" vs "+re.sub('[\.|\;].*','',temp_ptm)+"\n")
if doc == re.sub('[\.|\;].*', '', temp_ptm):
#if "Q9TT90" in out_ac:
# print("yes\n")
ptms.setdefault(doc, []).append(out_position)
ptms = dict([(k, list(itertools.chain.from_iterable(v)))
for k, v in ptms.items() if len(v) > 0])
fp.seek(prev_fp_pos)
elif tag == "SQ":
sequence = seq_read(fp)
out_data = functions.merge_two_dicts(out_data, ptms)
out_data['sequence'] = sequence
table.save(out_data)
##rewind
ptms = {
'Phosphoserine': [],
'Phosphothreonine': [],
'Phosphotyrosine': [],
'N6-acetyllysine': [],
'Omega-N-methylarginine': [],
'Dimethylated arginine': [],
'Symmetric dimethylarginine': [],
'Asymmetric dimethylarginine': [],
'N6-methyllysine': [],
'N6,N6-dimethyllysine': [],
'N6,N6,N6-trimethyllysine': [],
'N-linked (GlcNAc) asparagine': [],
'S-palmitoyl cysteine': [],
'Pyrrolidone carboxylic acid': [],
'Glycyl lysine isopeptide (Lys-Gly)(interchain with G-Cter in SUMO)':
[],
'Glycyl lysine isopeptide (Lys-Gly)(interchain with G-Cter in ubiquitin)':
[]
}
out_data.clear()
out_ac = []
out_position = []
sequence = ""
check = []
line = fp.readline()
fp.close()
with open(Dic_File, 'a') as f:
f.write(stock_info['公司名称：'] + "\n")
f.write(stock_info['公司简称：'] + "\n")
for n in stock_info['证券简称更名历史：']:
f.write(n + '\n')
if 'A' in n or 'B' in n or 'G' in n or 'N' in n:
f.write(
n.replace('A', '').replace('B', '').replace(
'G', '').replace('N', '') + '\n')
stock_info['证券简称更名历史：'] = ' '.join(stock_info['证券简称更名历史：'])
stock_info_csv.append(stock_info)
i += 1
print("%s/%s" % (i, len(Stock_Codes)), stock_info)
time.sleep(10 + random.random() * 10)
## 重新读入文件，删除重复
remove_duplicates(Dic_File)
## 写入csv文件
csv_exist = os.path.exists(Csv_File)
with open(Csv_File, 'a') as f:
header = ['code', '公司名称：', '公司简称：', '证券简称更名历史：']
f_csv = csv.DictWriter(f, header)
if not csv_exist:
f_csv.writeheader()
f_csv.writerows(stock_info_csv)
remove_duplicates(Csv_File, csv=True)
else:
from functions import getdic
getdic("stock_name.txt")
print("Complete 1/2. See ./sub_dics/stock_name.txt")
getdic("indus_name.txt")
print("Complete 2/2. See ./sub_dics/indus_name.txt")
return
if __name__ == "__main__":
## 获取命令行参数
Need_Craw = False
args = sys.argv[1:]
for arg in args:
if arg == "-update":
Need_Craw = True
else:
print("无效的参数：" + arg)
sys.exit(1)
if Need_Craw:
## 从网络爬取
get_glossary()
## 写入文件
remove_duplicates(Dic_File)
## 写入csv文件
csv_exist = os.path.exists(Csv_File)
with open(Csv_File, 'a') as f:
header = ['iterm', 'link', 'father', 'tag']
f_csv = csv.DictWriter(f, header)
if not csv_exist:
f_csv.writeheader()
f_csv.writerows(glossary)
else:
from functions import getdic
getdic("glossary.txt")
print("Complete. See ./sub_dics/glossary.txt")