def save(aclist, dbnam, fnotSave=None):
# aclist = ['P06685', 'P06686']
# dbnam = 'seqtmppi_test1'
do_all = DataOperation('uniprot', 'seqtmppi_positive')
do_new = DataOperation('uniprot', dbnam)
notsaveCount = 0
notsaveList = []
for ac in aclist:
protein = queryProtein(ac, do_all)
if protein == None:
print('not save protein %s' % ac)
continue
# projection = {'_id': True, 'sequence.@length': True, 'sequence.#text': True, 'keyword.@id': True,
# 'comment.subcellularLocation.location': True}
# protein_ens = ensomblePortein(queryProtein(ac, do_all,projection=projection))
# protein_ens['accession'] = ac
# protein['ensomble'] = protein_ens
result = do_new.UpSertOne({'accession': ac}, protein)
if result.matched_count != 0:
print('not save %s' % ac)
notsaveCount = notsaveCount + 1
notsaveList.append(ac)
print('not save %d' % (notsaveCount))
if fnotSave:
saveList(notsaveList, fnotSave)
return notsaveList
def pairToproteinList(fin,fout=''):
"""
# Gets a list of non-repeating proteins from the protein pair
:param fin:
:param fout:
:return:
"""
proteinlist = []
with open(fin,'r') as fi:
line = fi.readline()
while(line):
pair = line.split('\t')
a = pair[0]
b = pair[1][:-1]
if a not in proteinlist:
proteinlist.append(a)
# fo.write(a+'\n')
# fo.flush()
if b not in proteinlist:
proteinlist.append(b)
# fo.write(b+'\n')
# fo.flush()
line = fi.readline()
if fout:saveList(proteinlist,fout)
print('pairToproteinList end')
return proteinlist
def generateSomeSpeciesLists(ftmp, fnontmp, species='MYCPN'):
do = DataOperation('uniprot', 'uniprot_sprot')
projection = {'_id': False, 'accession': True}
docs = do.QueryObj({
"keyword.@id": 'KW-0812',
'_id': {
'$regex': species
}
},
projection=projection)
tmplist = [
x['accession'][0]
if isinstance(x['accession'], list) else x['accession'] for x in docs
]
docs = do.QueryObj(
{
"keyword.@id": {
'$ne': 'KW-0812'
},
'keyword': {
'$exists': True
},
'_id': {
'$regex': 'HUMAN'
}
},
projection=projection)
nontmplist = [
x['accession'][0]
if isinstance(x['accession'], list) else x['accession'] for x in docs
]
print('query %d tmp and %d nontmp' % (len(tmplist), len(nontmplist)))
saveList(tmplist, ftmp)
saveList(nontmplist, fnontmp)
return tmplist, nontmplist
def queryPathway_Gene(foutPathway_Gene,
fpathway=None,
fpathwayInfo=None,
hsa='hsa'):
'''
:param foutPathway_Gene:
0 hsa00010 pathway id
1 3101 gene id
2 HK3 gene symbol
3 [K00844] KO id
4 [2.7.1.1] EC number
:param fpathway:
:param fpathwayInfo:
:param hsa:
:return:
'''
if os.access(fpathway, os.F_OK):
repair_pathways = readIDlist(fpathway)
else:
repair_pathways = queryAllPathway(fpathway=fpathway,
fpathwayInfo=fpathwayInfo,
hsa=hsa)
for idx, pathway in enumerate(repair_pathways):
geneID_geneName_KO_EC = []
print(idx, end='.')
if idx < 65: continue
for gene_id, gene_symbol, KO, EC in extractGeneFromPathway(pathway):
geneID_geneName_KO_EC.append(
(pathway, gene_id, gene_symbol, KO, EC))
saveList(geneID_geneName_KO_EC, foutPathway_Gene, file_mode='a')
def queryKid_pathway(fTmpKEGGCount, outListFile):
df = pd.read_table(fTmpKEGGCount, header=None)
# kid_pathway = []
for id, item in df.iterrows():
# kid_pathway.extend(queryPathwayByKid(item[0]))
print(id, 'query for ', item[0], item[1])
result = queryPathwayByKid(item[0])
if result == []: continue
saveList(result, outListFile, file_mode='a')
def queryAllPathway(fpathway=None, fpathwayInfo=None, hsa='hsa'):
human_pathways = REST.kegg_list("pathway", hsa).read()
repair_pathways = []
repair_pathways_info = []
for line in human_pathways.rstrip().split("\n"):
entry, description = line.split("\t")
entry = entry.split(':')[1]
repair_pathways.append(entry)
repair_pathways_info.append((entry, description))
if fpathway: saveList(repair_pathways, fpathway)
if fpathwayInfo: saveList(repair_pathways_info, fpathwayInfo)
return repair_pathways
def findKeyProtein(fin, fout, keyword):
# keyword = 'KW-0297'
tmplist = readIDlist(fin)
GPCRlist = []
do = DataOperation('uniprot', 'uniprot_sprot')
projection = {'_id': True}
for ac in tmplist:
dic = {'accession': ac, "keyword.@id": keyword}
result = do.QueryObj(dic, projection=projection)
for r in result:
GPCRlist.append(ac)
print(r)
saveList(GPCRlist, fout)
def getALlGprotein(fout):
# {$or:[
# {"protein.recommendedName.fullName":{$regex:/G protein +/}},
# {"protein.recommendedName.fullName":{$regex:/G protein-coupled receptor +/}},
# {"protein.alternativeName.fullName":{$regex:/G protein +/}},
# {"protein.alternativeName.fullName":{$regex:/G protein-coupled receptor +/}}
# ]}
GPCRlist = []
do = DataOperation('uniprot', 'uniprot_sprot')
projection = {
'_id': True,
'protein.recommendedName.fullName': True,
'protein.alternativeName.fullName': True
}
count = 0
dic = {
# 'accession': ac,
'$or': [{
"protein.recommendedName.fullName": {
'$regex': 'G protein '
}
}, {
"protein.recommendedName.fullName": {
'$regex': 'Guanine nucleotide-binding protein'
}
}, {
"protein.alternativeName.fullName": {
'$regex': 'G protein '
}
}, {
"protein.alternativeName.fullName": {
'$regex': 'Guanine nucleotide-binding protein'
}
}]
}
result = do.QueryObj(dic, projection=projection)
for r in result:
count = count + 1
GPCRlist.append(((r['_id'], [
x for x in handleSubcelluarLeaf(
r['protein'],
keys=['alternativeName', 'recommendedName', 'fullName'])
])))
print(((r['_id'], [
x for x in handleSubcelluarLeaf(
r['protein'],
keys=['alternativeName', 'recommendedName', 'fullName'])
])))
saveList(GPCRlist, fout)
def getallProtein(fout):
'''
dao
:param AC:
:param do:
:return:
'''
do = DataOperation('DrugKB', 'protein')
projection = {'_id': True, 'accession': True}
# one accession mapping several protein sequence
docs = do.GetALL(projection=projection, limit=0)
proteinlist = [
x['accession'][0]
if isinstance(x['accession'], list) else x['accession'] for x in docs
]
saveList(proteinlist, fout)
def findGProtein(fin, fout):
# {"protein.recommendedName.fullName":{$regex:/Guanine nucleotide-binding protein*/}}
# keyword = 'KW-0297'
tmplist = readIDlist(fin)
GPCRlist = []
do = DataOperation('uniprot', 'uniprot_sprot')
projection = {'_id': True}
count = 0
for ac in tmplist:
dic = {
'accession':
ac,
'$or': [{
"protein.recommendedName.fullName": {
'$regex': 'G protein '
}
}, {
"protein.recommendedName.fullName": {
'$regex': 'Guanine nucleotide-binding protein'
}
}, {
"protein.alternativeName.fullName": {
'$regex': 'G protein '
}
}, {
"protein.alternativeName.fullName": {
'$regex': 'Guanine nucleotide-binding protein'
}
}]
}
result = do.QueryObj(dic, projection=projection)
for r in result:
count = count + 1
GPCRlist.append(ac)
print(count, r)
saveList(GPCRlist, fout)
def generateCriterLists(ftmp, fnontmp):
do = DataOperation('uniprot', 'uniprot_sprot')
projection = {'_id': False, 'accession': True}
docs = do.QueryObj(
{
"keyword.@id": 'KW-0812',
'comment.subcellularLocation.location.#text': {
'$exists': True
}
},
projection=projection)
tmplist = [
x['accession'][0]
if isinstance(x['accession'], list) else x['accession'] for x in docs
]
docs = do.QueryObj(
{
"keyword.@id": {
'$ne': 'KW-0812'
},
'keyword': {
'$exists': True
},
'comment.subcellularLocation.location.#text': {
'$exists': True
}
},
projection=projection)
nontmplist = [
x['accession'][0]
if isinstance(x['accession'], list) else x['accession'] for x in docs
]
print('query %d tmp and %d nontmp' % (len(tmplist), len(nontmplist)))
saveList(tmplist, ftmp)
saveList(nontmplist, fnontmp)
return tmplist, nontmplist
def writeProtins(fout):
proteins = []
for protein in getallProtein():
proteins.extend(protein)
saveList(getallProtein(),fout)