def getUNIPid(line):
seqid = list()
seqid.append(line[11:line[0].find(']') - 1])
pairs = uniprot.batch_uniprot_id_mapping_pairs('P_REFSEQ_AC', 'ACC', seqid)
reviewedpair = ""
revStat = 0
#Cette partie du code sert a determiner qu'elle des uniprotID sont reviewed
#et va conserver le premier de la liste
for y in pairs:
uniCode = y[1]
req = urllib2.Request(
'http://www.uniprot.org/uniprot/?query={}&sort=score&columns=reviewed&format=tab'
.format(uniCode))
web = urllib2.urlopen(req)
for i in web:
if i.find("Status") == -1:
if i.find("unreviewed") == -1:
if revStat == 0:
reviewedpair = y[1]
revStat = 1
break
elif reviewedpair == "":
reviewedpair = y[1]
return [GetGoAnnotation(reviewedpair)]
def map_to_refseq(seqids):
uniprot_mapping = uniprot.sequentially_convert_to_uniprot_id(seqids, "func.cache.json")
uniprot_ids = uniprot_mapping.values()
pairs = uniprot.batch_uniprot_id_mapping_pairs("ACC", "P_REFSEQ_AC", uniprot_ids)
mapping = {}
for seqid in seqids:
if seqid in uniprot_mapping:
uniprot_id = uniprot_mapping[seqid]
for pair in pairs:
if uniprot_id == pair[0]:
mapping[seqid] = pair[1]
os.remove("func.cache.json")
return mapping
def map_to_refseq(seqids):
uniprot_mapping = uniprot.sequentially_convert_to_uniprot_id(
seqids, 'func.cache.json')
uniprot_ids = uniprot_mapping.values()
pairs = uniprot.batch_uniprot_id_mapping_pairs(
'ACC', 'P_REFSEQ_AC', uniprot_ids)
mapping = {}
for seqid in seqids:
if seqid in uniprot_mapping:
uniprot_id = uniprot_mapping[seqid]
for pair in pairs:
if uniprot_id == pair[0]:
mapping[seqid] = pair[1]
os.remove('func.cache.json')
return mapping
def getUNIPid(line):
seqid = list()
seqid.append(line[11:line[0].find(']')-1])
pairs = uniprot.batch_uniprot_id_mapping_pairs('P_REFSEQ_AC','ACC',seqid)
reviewedpair = ""
revStat= 0
#Cette partie du code sert a determiner qu'elle des uniprotID sont reviewed
#et va conserver le premier de la liste
for y in pairs:
uniCode = y[1]
req = urllib2.Request('http://www.uniprot.org/uniprot/?query={}&sort=score&columns=reviewed&format=tab'.format(uniCode))
web = urllib2.urlopen(req)
for i in web:
if i.find("Status") == -1:
if i.find("unreviewed") == -1:
if revStat == 0 :
reviewedpair = y[1]
revStat = 1
break
elif reviewedpair == "" :
reviewedpair = y[1]
return[GetGoAnnotation(reviewedpair)]
import os
import uniprot
import pprint
import sys
# Clean up caches
os.system('rm cache*')
# Example 1 - reading a fasta file
seqids, fastas = uniprot.read_fasta('example.fasta')
pprint.pprint(seqids, indent=2)
# Example 2 - map identifiers for RefSeq to Uniprot
seqids = "NP_000508.1 NP_001018081.3".split()
pairs = uniprot.batch_uniprot_id_mapping_pairs('P_REFSEQ_AC', 'ACC', seqids)
pprint.pprint(pairs, indent=2)
# Example 2 - get UniProt metadata
uniprot_seqids = [j for i, j in pairs]
uniprot_data = uniprot.batch_uniprot_metadata(uniprot_seqids, 'cache')
pprint.pprint(uniprot_data, indent=2)
# Example 3 - parse for isoforms in metadata
text = open('cache/metadata.0.txt').read()
uniprot_data = uniprot.parse_isoforms(text)
pprint.pprint(uniprot_data)
# Example 4 - chaining commands to map seqids
seqids = "EFG_MYCA1 YP_885981.1 ENSG00000196176 Q91ZU6-8".split()
uniprot_data = uniprot.get_metadata_with_some_seqid_conversions(
seqids, 'cache2')
# Example 1 - reading a fasta file
seqids, fastas = uniprot.read_fasta("example.fasta")
pprint.pprint(seqids, indent=2)
# Example 2 - batch read identifier mappings with
# prespecified identifier types
seqids = """
NP_000508.1 NP_001018081.3
""".split()
pairs = uniprot.batch_uniprot_id_mapping_pairs("P_REFSEQ_AC", "ACC", seqids)
pprint.pprint(pairs, indent=2)
# Example 3 - sequential identifier mapping to UniProt
# identifiers using robust but slow method
seqids = """
EFG_MYCA1 YP_885981.1 CpC231_1796
""".split()
mapping = uniprot.sequentially_convert_to_uniprot_id(seqids, "cache.json")
uniprot_seqids = mapping.values()
import os
import uniprot
import pprint
import sys
# Clean up caches
os.system('rm cache*')
# Example 1 - reading a fasta file
seqids, fastas = uniprot.read_fasta('example.fasta')
pprint.pprint(seqids, indent=2)
# Example 2 - map identifiers for RefSeq to Uniprot
seqids = "NP_000508.1 NP_001018081.3".split()
pairs = uniprot.batch_uniprot_id_mapping_pairs(
'P_REFSEQ_AC', 'ACC', seqids)
pprint.pprint(pairs, indent=2)
# Example 2 - get UniProt metadata
uniprot_seqids = [j for i,j in pairs]
uniprot_data = uniprot.batch_uniprot_metadata(
uniprot_seqids, 'cache')
pprint.pprint(uniprot_data, indent=2)
# Example 3 - parse for isoforms in metadata
text = open('cache/metadata.0.txt').read()
uniprot_data = uniprot.parse_isoforms(text)
pprint.pprint(uniprot_data)
# Example 4 - chaining commands to map seqids
seqids = "EFG_MYCA1 YP_885981.1 ENSG00000196176 Q91ZU6-8".split()
