def get_gene():
table = util.get_modified_data()
gene_list = []
id_list = []
current_date = util.get_current_date()
pattern = re.compile('[A-Za-z0-9]*-*[A-Za-z0-9]*,\s*\{[0-9]*\.?[0-9]*\}')
for i in range(table.nrows): # 循环逐行打印
if i == 0:
continue
else:
list = util.get_list_by_enter(table.row_values(i)[3]) # 获取基因数据
for item in list: # 对每一行数据进行处理
if item == '\n' or item == '':
continue
m = pattern.match(item)
if m != None:
temp = m.group()
gene_list.append(temp.split(',')[0])
id_list.append(
temp.split(',')[1][temp.split(',')[1].find('{') +
1:temp.split(',')[1].find('}')])
wb = xlwt.Workbook()
sheet1 = wb.add_sheet('gene')
sheet1.write(0, 0, 'id')
sheet1.write(0, 1, 'geneName')
sheet1.write(0, 2, 'geneNumber')
for i in range(len(gene_list)):
sheet1.write(i + 1, 0, i + 1)
sheet1.write(i + 1, 1, gene_list[i])
sheet1.write(i + 1, 2, id_list[i])
wb.save("../final_data/gene.xls")
def get_hpo():
current_date = util.get_current_date()
table = util.get_file_data('../final_data/system.xls')
src = []
dst = []
for i in range(table.nrows):
if i == 0:
continue
else:
src.append(table.row_values(i)[8])
for item in src:
if item=="":
continue
item = item[item.index(":") + 1:]
list = util.get_list_by_colon(item)
for l in list:
if l == "":
continue
else:
try:
dst.index(l)
except:
dst.append(l)
wb = xlwt.Workbook()
sheet1 = wb.add_sheet('sheet1')
sheet1.write(0, 0, 'hid')
sheet1.write(0, 1, 'hpo')
for i in range(len(dst)):
# print(result[i][j])
try:
sheet1.write(i + 1, 0, i + 1)
sheet1.write(i + 1, 1, dst[i])
except:
print(i, dst[i])
wb.save("../final_data/HPO.xls")
print("end")
def get_all():
# 获取需要的数据
type_dict = util.get_type_list()
raw_data = util.get_modified_data()
current_date = util.get_current_date()
phenomenon_src = []
phenomenon_dst = []
type_dst = []
system_dst = []
for i in range(raw_data.nrows):
if i == 0:
continue
else:
phenomenon_src.append(raw_data.row_values(i)[4])
for p in phenomenon_src:
list = util.get_list_by_enter(p)
for l in list:
if l == ";snomedct:;;;;" or l == "":
continue
first_colon = l.index(':')
first_semicolon = l.index(';')
type = l[0:first_colon] # 获取疾病部位
phenomenon = l[0:first_semicolon] # 获取疾病描述
system = l[first_semicolon + 1:] # 获取各个系统的所有信息
# 此处假设对相同部位相同表型，只有一种描述
try:
phenomenon_dst.index(phenomenon)
except:
type_dst.append(type)
phenomenon_dst.append(phenomenon)
system_dst.append(system)
wb = xlwt.Workbook()
sheet1 = wb.add_sheet('sheet1')
sheet1.write(0, 0, 'pid')
sheet1.write(0, 1, 'phenomenon')
sheet1.write(0, 2, 'type')
sheet1.write(0, 3, 'system')
sheet1.write(0, 4, 'snomedct')
sheet1.write(0, 5, 'UMLS')
sheet1.write(0, 6, 'ICD10CM')
sheet1.write(0, 7, 'ICD9Cm')
sheet1.write(0, 8, 'HPO')
for i in range(len(phenomenon_dst)):
try:
sheet1.write(i + 1, 0, i + 1)
sheet1.write(i + 1, 1, phenomenon_dst[i])
sheet1.write(i + 1, 2, type_dict.index(type_dst[i]) + 1)
sheet1.write(i + 1, 3, system_dst[i])
list = util.get_list_by_semicolon(system_dst[i])
sheet1.write(i + 1, 4, list[0])
sheet1.write(i + 1, 5, list[1])
sheet1.write(i + 1, 6, list[2])
sheet1.write(i + 1, 7, list[3])
sheet1.write(i + 1, 8, list[4])
except:
print(i, phenomenon_dst[i], ":", type_dst[i])
wb.save("../final_data/system.xls")
print("end")
def prehandler():
current_date = util.get_current_date()
phenomenon_src = []
phenomenon_dst = []
mimnumber_src = []
preferred_title_src = []
inheritance_src = []
gene_src = []
# 获取原表数据
raw_data = util.get_raw_data()
for i in range(raw_data.nrows):
if i == 0:
continue
else:
phenomenon_src.append(raw_data.row_values(i)[4])
mimnumber_src.append(raw_data.row_values(i)[0])
preferred_title_src.append(raw_data.row_values(i)[1])
inheritance_src.append(raw_data.row_values(i)[2])
gene_src.append(raw_data.row_values(i)[3])
# 获取部位列表
type_dict = util.get_type_list()
# 处理表型，在每个表型前增加部位，并将之前多余的信息去除
for p in phenomenon_src:
list = util.get_list_by_enter(p)
if list[-1] == "":
list.pop()
type = ''
temp = ''
for l in list:
if l == ";snomedct:;;;;":
continue
first_colon = l.index(':')
first_semicolon = l.index(';')
if first_colon < first_semicolon:
tmp = l[:first_colon]
try:
type_dict.index(tmp)
except:
l = type + ":" + l
else:
type = tmp
else:
l = type + ":" + l
temp = temp + "\n" + l;
phenomenon_dst.append(temp)
wb = xlwt.Workbook()
sheet1 = wb.add_sheet('sheet1')
sheet1.write(0, 0, 'mimnumber')
sheet1.write(0, 1, 'preferredTitle')
sheet1.write(0, 2, 'inheritance')
sheet1.write(0, 3, 'molecularBasis')
sheet1.write(0, 4, 'clinicalSynopsis')
for i in range(len(phenomenon_dst)):
sheet1.write(i + 1, 0, mimnumber_src[i])
sheet1.write(i + 1, 1, preferred_title_src[i])
sheet1.write(i + 1, 2, inheritance_src[i])
sheet1.write(i + 1, 3, gene_src[i])
sheet1.write(i + 1, 4, phenomenon_dst[i])
wb.save("../final_data/omim_phenotype_modified.xls")
print("modify data end")