def saveGeneDataToDB(gene_file):
current_info_type = ''
compound_info = dict()
for line in gene_file.readlines():
if line.endswith('\n'):
line = line[:-1]
if line.startswith('/'):
continue
infos = line.split(' ')
if not line.startswith(' ') and not line.startswith('/'):
current_info_type = infos[0]
infos = infos[1:]
if current_info_type == 'ENTRY':
for info_item in infos:
if info_item != '':
compound_info['ENTRY'] = info_item
break
if current_info_type == 'NTSEQ':
for info_item in infos:
if info_item != '':
compound_info['NTSEQLEN'] = int(info_item)
break
if current_info_type == 'ORGANISM':
orStr = line.replace('ORGANISM ', '')
orList = orStr.split(' ')
compound_info['ORGANISM_SHORT'] = orList[0]
compound_info['ORGANISM'] = orList[1]
for info_item in infos:
if info_item.endswith('\n'):
info_item = info_item[:-1]
if current_info_type == 'ENTRY' or current_info_type == 'ORGANISM':
continue
if line.startswith('NTSEQ'):
continue
try:
compound_info[current_info_type] += info_item
except:
compound_info[current_info_type] = info_item
try:
names = compound_info['NAME'].split(';')
compound_info['NAME'] = names[0]
compound_info['NICKNAME'] = ''
for i in range(1, len(names)):
compound_info['NICKNAME'] += names[i] + '_'
new_gene = gene(gene_id=compound_info['ENTRY'])
new_gene.name = compound_info['NAME']
new_gene.nicknames = compound_info['NICKNAME']
new_gene.definition = compound_info['DEFINITION']
new_gene.organism_short = compound_info['ORGANISM_SHORT']
new_gene.organism = compound_info['ORGANISM']
new_gene.position = compound_info['POSITION']
new_gene.ntseq_length = compound_info['NTSEQLEN']
new_gene.ntseq = compound_info['NTSEQ']
try:
new_gene.save()
except:
traceback.print_exc()
print '%s can not be saved' % compound_info['NAME']
except:
traceback.print_exc()
def get_or_create_gene(self, gid):
"""
find gene in database, if found, return gene, or search in ncbi
@param gid: gene id
@type gid: str
@return gene object
@rtype: gene
"""
#get in database
try:
gene_obj = gene.objects.get(gene_id=gid)
return gene_obj
except:
#get from ncbi
baseUrl = 'http://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=nuccore&rettype=fasta&id='
req = urllib2.Request(baseUrl + gid)
response = urllib2.urlopen(req)
resStr = response.read()
gene_dict = parse_fasta_str(resStr)
for gn in gene_dict.keys():
gid = gn.split('|')[1]
#get detail information
new_gene_obj = gene(gene_id=gid)
detail_info = self.retrive_gene_detain(gid)
if detail_info == None:
continue
new_gene_obj.name = detail_info['name']
new_gene_obj.definition = detail_info['definition']
new_gene_obj.organism = detail_info['organism']
new_gene_obj.ntseq = gene_dict[gn]
new_gene_obj.ntseq_length = len(gene_dict[gn])
try:
new_gene_obj.save()
return new_gene_obj
except:
pass
return None
