def __init__(self,verbose=True):
"""
Constructor
"""
## setup db
self.session, self.engine = db_connect(verbose=verbose)
self.conn = self.engine.connect()
## global variables
self.verbose = verbose
self.dpi = 400
self.labelOffset = 0.05
self.fontSize = 8
self.legendFontSize = 8
self.increment = 0.03
self.fontName = 'serif'
self.termAlpha = 0.95
self.geneAlpha = 0.4
self.nodeSizeGene = 300
self.nodeSizeTerm = 300
self.colors = ['#000000','#FFCC33','#3333DD',"#002200",'y','b','orange',"#CC55FF","#990033",'#FF6600',"#CCCCCC","#660033",
'#FFCC00','#FFFFAA','#6622AA','#33FF77','#998800','#0000FF',"#995599","#00AA00","#777777","#FF0033",'#990066',
'#FA58AC','#8A0808','#D8D8D8',"#CC2277",'#336666','#996633',"#FFCCCC","#CC0011","#FFBB33","#DDDDDD","#991188",
"#FF9966","#009999","#FF0099","#996633","#990000","#660000","#9900BB","#330033","#FF5544","#9966CC",
"#330066","#99FF99","#FF99FF","#333333","#CC3333","#CC9900","#99DD22","#3322BB","#663399","#002255",
"#003333","#66CCFF","#CCFFFF","#AA11BB","#000011","#FFCCFF","#00EE33","#337722","#CCBBFF","#FF3300",
"#009999","#110000","#AAAAFF","#990000","#880022","#BBBBBB","#00EE88","#66AA22","#99FFEE","#660022",
"#FFFF33","#00CCFF","#990066","#006600","#00CCFF",'#AAAAAA',"#33FF00","#0066FF","#FF9900","#FFCC00"]
self.cmap = plt.cm.Blues
self.lineEnd = 53
self.linesMax = 32
def setUp(self):
"""
connect to the database
"""
self.session, self.engine = db_connect(upass=UPASS)
self.conn = self.engine.connect()
self.testID = '5476'
def __init__(self):
"""
Constructor
"""
self.session,self.engine = db_connect()
self.conn = self.engine.connect()
self.hits = None
def setUp(self):
"""
connect to the database
"""
self.session, self.engine = db_connect(upass=UPASS)
self.conn = self.engine.connect()
self.testID = '5476'
def __init__(self):
"""
Constructor
"""
self.session, self.engine = db_connect()
self.conn = self.engine.connect()
self.hits = None
def __init__(self,taxaInput,delimiter="\t",upass=''):
"""
The input is a path to a tab delimited file
or simply a python list
The delimiter can also be specified
The first column is the ncbi taxa id
All additional columns are optional and user specified
"""
self.taxaList = []
self.session,self.engine = db_connect(upass=upass)
if type(taxaInput) == type([]):
for taxon in taxaInput:
if re.search("\D",taxon):
raise Exception("Bad taxa in taxaList (%s)"%(taxon))
continue
self.taxaList.append(taxon)
else:
self.taxaList = list(set(self.read_file(taxaInput)))
print("There are %s unique taxa in the list"%(len(self.taxaList)))
def __init__(self,taxaList,verbose=False,upass='',idType='ncbi',useIea=True,\
aspect='biological_process'):
"""
Constructor
taxaList a list of NCBI taxa ids
"""
## error checking
idType = idType.lower()
if idType not in ['uniprot','ncbi']:
raise Exception("Invalid idType argument in fetch annotations use 'uniprot' or 'ncbi'")
## start a database session
self.session,self.engine = db_connect(verbose=verbose,upass=upass)
## global variables
self.taxaList = taxaList
self.idType = idType
self.useIea = useIea
self.aspect = aspect
def __init__(self, taxaInput, delimiter="\t", upass=''):
"""
The input is a path to a tab delimited file
or simply a python list
The delimiter can also be specified
The first column is the ncbi taxa id
All additional columns are optional and user specified
"""
self.taxaList = []
self.session, self.engine = db_connect(upass=upass)
if type(taxaInput) == type([]):
for taxon in taxaInput:
if re.search("\D", taxon):
raise Exception("Bad taxa in taxaList (%s)" % (taxon))
continue
self.taxaList.append(taxon)
else:
self.taxaList = list(set(self.read_file(taxaInput)))
print("There are %s unique taxa in the list" % (len(self.taxaList)))
def __init__(self, verbose=True):
"""
Constructor
"""
## setup db
self.session, self.engine = db_connect(verbose=verbose)
self.conn = self.engine.connect()
## global variables
self.verbose = verbose
self.dpi = 400
self.labelOffset = 0.05
self.fontSize = 8
self.legendFontSize = 8
self.increment = 0.03
self.fontName = 'serif'
self.termAlpha = 0.95
self.geneAlpha = 0.4
self.nodeSizeGene = 300
self.nodeSizeTerm = 300
self.colors = [
'#000000', '#FFCC33', '#3333DD', "#002200", 'y', 'b', 'orange',
"#CC55FF", "#990033", '#FF6600', "#CCCCCC", "#660033", '#FFCC00',
'#FFFFAA', '#6622AA', '#33FF77', '#998800', '#0000FF', "#995599",
"#00AA00", "#777777", "#FF0033", '#990066', '#FA58AC', '#8A0808',
'#D8D8D8', "#CC2277", '#336666', '#996633', "#FFCCCC", "#CC0011",
"#FFBB33", "#DDDDDD", "#991188", "#FF9966", "#009999", "#FF0099",
"#996633", "#990000", "#660000", "#9900BB", "#330033", "#FF5544",
"#9966CC", "#330066", "#99FF99", "#FF99FF", "#333333", "#CC3333",
"#CC9900", "#99DD22", "#3322BB", "#663399", "#002255", "#003333",
"#66CCFF", "#CCFFFF", "#AA11BB", "#000011", "#FFCCFF", "#00EE33",
"#337722", "#CCBBFF", "#FF3300", "#009999", "#110000", "#AAAAFF",
"#990000", "#880022", "#BBBBBB", "#00EE88", "#66AA22", "#99FFEE",
"#660022", "#FFFF33", "#00CCFF", "#990066", "#006600", "#00CCFF",
'#AAAAAA', "#33FF00", "#0066FF", "#FF9900", "#FFCC00"
]
self.cmap = plt.cm.Blues
self.lineEnd = 53
self.linesMax = 32
def __init__(self,taxaList,verbose=False,upass='',idType='ncbi',useIea=True,\
aspect='biological_process'):
"""
Constructor
taxaList a list of NCBI taxa ids
"""
## error checking
idType = idType.lower()
if idType not in ['uniprot', 'ncbi']:
raise Exception(
"Invalid idType argument in fetch annotations use 'uniprot' or 'ncbi'"
)
## start a database session
self.session, self.engine = db_connect(verbose=verbose, upass=upass)
## global variables
self.taxaList = taxaList
self.idType = idType
self.useIea = useIea
self.aspect = aspect
def enrichment_hypergeo(
termList, entityList, species, useIea=True, asGenes=True, aspect="biological_process", verbose=True
):
"""
termList -- are the terms to be tested
species -- an ncbi taxa id
entityList -- gene or uniprot ids
What is the probability of finding a given number of terms if we randomly select N out of M objects?
M -- genes with at least one annotation
N -- number of draws or size of gene list
k -- the number of genes annotated by a given term (total type I objects)
x -- number of times we observe a term in the gene list (draws)
in R the cdf can be obtained with
phyper(x,k,M-k,N)
hypergeom.pmf(x, M, k, N)
Returns a dict where term id is the key and hypergeo pvalue is the value
"""
## connect to db and get annotations for the species
session, engine = db_connect()
geneAnnots, uniprotAnnots = fetch_taxa_annotations([species], engine, useIea=useIea, verbose=verbose, aspect=aspect)
if asGenes == True:
entity2go = geneAnnots
else:
entity2go = uniprotAnnots
go2entity = {}
for entity, go in entity2go.iteritems():
for term in go:
if not go2entity.has_key(term):
go2entity[term] = set([])
go2entity[term].update([entity])
for go, entity in go2entity.iteritems():
go2entity[go] = list(entity)
print ("total go terms - %s" % (len(go2entity.keys())))
print ("total entities - %s" % (len(entity2go.keys())))
## set variables
M = len(entity2go.keys())
N = len(entityList)
results = {}
for testTerm in termList:
## find
k = len(go2entity[testTerm])
x = 0
for entity in entityList:
if entity in entity2go and testTerm in entity2go[entity]:
x += 1
## get a p-value
if 0 in [x, M, N, k]:
pvalue = np.nan
else:
cdf = hypergeom.cdf(x, M, k, N, loc=0)
if cdf > 0:
pvalue = 2 * (1 - hypergeom.cdf(x, M, k, N))
else:
pvalue = 2 * hypergeom.cdf(x, M, k, N)
results[testTerm] = pvalue
return results
#!/usr/bin/env python
"""
probe the taxa in the list for annotation coverage
and summary information
"""
import sys, getopt, os
from htsint import TaxaSummary
from htsint.database import db_connect
self.session, self.engine = db_connect()
## get how many genes code for proteins
codingQuery = self.session.query(Uniprot).filter_by(taxa_id=taxaQuery.id).all()
codingGenes = list(set([u.gene_id for u in uniprotQuery]))
remove_empty(codingGenes)
## get number of genes/proteins with at least one annotation
annotatedGenes = list(set([a.gene_id for a in annotations]))
annotatedProts = list(set([a.uniprot_id for a in annotations]))
remove_empty(annotatedGenes)
remove_empty(annotatedProts)
apQuery = [
self.session.query(Uniprot).filter_by(id=uid).first()
for uid in annotatedProts
]
#apQuery = self.session.query(Uniprot).filter(Uniprot.id.in_(annotatedProts)).all()
def enrichment_hypergeo(termList,
entityList,
species,
useIea=True,
asGenes=True,
aspect='biological_process',
verbose=True):
'''
termList -- are the terms to be tested
species -- an ncbi taxa id
entityList -- gene or uniprot ids
What is the probability of finding a given number of terms if we randomly select N out of M objects?
M -- genes with at least one annotation
N -- number of draws or size of gene list
k -- the number of genes annotated by a given term (total type I objects)
x -- number of times we observe a term in the gene list (draws)
in R the cdf can be obtained with
phyper(x,k,M-k,N)
hypergeom.pmf(x, M, k, N)
Returns a dict where term id is the key and hypergeo pvalue is the value
'''
## connect to db and get annotations for the species
session, engine = db_connect()
geneAnnots, uniprotAnnots = fetch_taxa_annotations([species],
engine,
useIea=useIea,
verbose=verbose,
aspect=aspect)
if asGenes == True:
entity2go = geneAnnots
else:
entity2go = uniprotAnnots
go2entity = {}
for entity, go in entity2go.items():
for term in go:
if term not in go2entity:
go2entity[term] = set([])
go2entity[term].update([entity])
for go, entity in go2entity.items():
go2entity[go] = list(entity)
print('total go terms - %s' % (len(go2entity.keys())))
print('total entities - %s' % (len(entity2go.keys())))
## set variables
M = len(entity2go.keys())
N = len(entityList)
results = {}
for testTerm in termList:
## find
k = len(go2entity[testTerm])
x = 0
for entity in entityList:
if entity in entity2go and testTerm in entity2go[entity]:
x += 1
## get a p-value
if 0 in [x, M, N, k]:
pvalue = np.nan
else:
cdf = hypergeom.cdf(x, M, k, N, loc=0)
if cdf > 0:
pvalue = 2 * (1 - hypergeom.cdf(x, M, k, N))
else:
pvalue = 2 * hypergeom.cdf(x, M, k, N)
results[testTerm] = pvalue
return results
def get_blast_map(resultsFilePath,
evalue=0.00001,
taxaList=None,
asGenes=False,
append=False):
"""
load assembly blast results into dictionary
if taxaList is provided then only genes from given taxa will be included in map
if asGene == True the results are provided with keys to genes not isoforms
"""
if not os.path.exists(resultsFilePath):
raise Exception("cannot find results file path %s" % resultsFilePath)
if taxaList != None:
## prepare database connections
session, engine = db_connect()
conn = engine.connect()
s = select([Taxon.id, Taxon.ncbi_id,
Taxon.name]).where(Taxon.ncbi_id.in_(taxaList))
_taxaQueries = conn.execute(s)
taxaQueries = _taxaQueries.fetchall()
totalQueries = set([])
filteredQueries = set([])
filteredHits = set([])
selectedTaxa = [str(tquery['id']) for tquery in taxaQueries]
taxa2name = dict([(str(tquery['id']), str(tquery['ncbi_id']))
for tquery in taxaQueries])
## create a gene2taxa dictionary
#gene2taxa,gene2desc = {},{}
#for tquery in taxaQueries:
# s = select([Gene.taxa_id,Gene.ncbi_id,Gene.description],Gene.taxa_id==tquery['id'])
# _geneQueries = conn.execute(s)
# geneQueries = _geneQueries.fetchall()
# gene2taxa.update(dict([(str(r['ncbi_id']),str(r['taxa_id'])) for r in geneQueries]))
# gene2desc.update(dict([(str(r['ncbi_id']),str(r['description'])) for r in geneQueries]))
results = {}
fid = open(resultsFilePath, 'rU')
reader = csv.reader(fid)
header = reader.next()
print(header)
## loop through file and save best
uniqueQueries = set([])
totalQueries = 0
unfilteredQueries = 0
for linja in reader:
if len(linja) == 4:
queryId = linja[0]
hitId = linja[1]
hitNcbiId = linja[2]
_evalue = float(linja[3])
else:
queryId = linja[0]
queryNcbi = linja[1]
hitId = linja[2]
hitNcbiId = linja[3]
_evalue = linja[4]
if asGenes == True:
queryId = re.sub("_i\d+", "", queryId)
# filtering
totalQueries += 1
if '-' in linja:
continue
if _evalue > evalue:
continue
if taxaList and gene2taxa.has_key(str(hitNcbiId)) == False:
continue
unfilteredQueries += 1
uniqueQueries.update([queryId])
## use the best evalue
if not results.has_key(queryId):
if append:
results[queryId] = [(hitNcbiId, _evalue)]
else:
results[queryId] = (hitNcbiId, _evalue)
if _evalue < results[queryId][1]:
if append:
results[queryId].append((hitNcbiId, _evalue))
else:
results[queryId] = (hitNcbiId, _evalue)
uniqueQueries = list(uniqueQueries)
fid.close()
print("total queries: %s" % totalQueries)
print("unfiltered queries: %s" % unfilteredQueries)
print("unique: %s" % len(uniqueQueries))
return results
def create_blast_map(refTaxon,
taxaList,
resultsFilePath,
evalue=0.00001,
verbose=False):
"""
read a summarized reference blast results file and create a map
results are gene centric
example results file looks like this
query(refseq),query(geneId),hit(uniprotEntry),hit(geneEntry),e-value
NP_001016845.1,549599,AQP3_HUMAN,360,1.24637e-170
NP_001016845.1,549599,AQP9_HUMAN,366,7.57313e-92
NP_001016845.1,549599,AQP10_HUMAN,89872,2.87154e-85
NP_001016845.1,549599,AQP7_HUMAN,364,8.01308e-84
NP_001016845.1,549599,AQP5_HUMAN,362,4.267e-15
"""
## error check
if not os.path.exists(resultsFilePath):
raise Exception("cannot find results file path %s" % resultsFilePath)
if refTaxon not in taxaList:
raise Exception("refTaxon must be in taxaList")
## prepare database connections
session, engine = db_connect()
conn = engine.connect()
## read through the file to map the genes to taxa ids
s = select([Taxon.id, Taxon.ncbi_id,
Taxon.name]).where(Taxon.ncbi_id.in_(taxaList))
_taxaQueries = conn.execute(s)
taxaQueries = _taxaQueries.fetchall()
totalQueries = set([])
filteredQueries = set([])
filteredHits = set([])
selectedTaxa = [str(tquery['id']) for tquery in taxaQueries]
taxa2name = dict([(str(tquery['id']), str(tquery['ncbi_id']))
for tquery in taxaQueries])
## create a gene2taxa dictionary
gene2taxa = {}
for tquery in taxaQueries:
s = select([Gene.taxa_id, Gene.ncbi_id], Gene.taxa_id == tquery['id'])
_geneQueries = conn.execute(s)
gene2taxa.update(
dict([(str(r['ncbi_id']), str(r['taxa_id']))
for r in _geneQueries.fetchall()]))
## creats a dictionary results['geneId]['taxaId'] = bestHitMappedTaxa
results = {}
fid = open(resultsFilePath, 'rU')
reader = csv.reader(fid)
header = reader.next()
## loop through file and save best
for linja in reader:
_evalue = float(linja[4])
totalQueries.update([linja[1]])
## filter by species and evalue
if not gene2taxa.has_key(linja[3]) or _evalue > evalue:
continue
if linja[1] == '-' or linja[3] == '-':
continue
## filter self matches
if taxa2name[gene2taxa[linja[3]]] == refTaxon:
continue
if taxa2name[gene2taxa[linja[1]]] != refTaxon:
raise Exception("Invalid query or invalid refTaxon %s != %s" %
(taxa2name[gene2taxa[linja[1]]], refTaxon))
taxId = taxa2name[gene2taxa[linja[3]]]
filteredQueries.update([linja[1]])
filteredHits.update([linja[3]])
if not results.has_key(taxId):
results[taxId] = {}
## use the best evalue
if not results[taxId].has_key(linja[1]):
results[taxId][linja[1]] = (linja[3], _evalue)
if _evalue < results[taxId][linja[1]][1]:
results[taxId][linja[1]] = (linja[3], _evalue)
fid.close()
## returns a simplified form of the results as two mappers
mapper1, mapper2 = {}, {}
test1 = set([])
for taxId in results.iterkeys():
for queryGene, hit in results[taxId].iteritems():
if not mapper1.has_key(hit[0]):
mapper1[hit[0]] = []
mapper1[hit[0]].append(queryGene)
if not mapper2.has_key(queryGene):
mapper2[queryGene] = []
mapper2[queryGene].append(hit[0])
#debug = set([])
#for key, item in mapper.iteritems():
# debug.update(item)
#for tquery in taxaQueries:
# taxId = str(tquery['ncbi_id'])
# for key,item in results[taxId].iteritems():
# debug.update([key])
# mapper[item[0]] = key
#debug = list(debug)
#print 'debug', len(debug),missing
#print results.keys(),len(results['8364'].keys()), len(results['8355'].keys()), len(list(set(results['8364'].keys() + results['8355'].keys())))
print('BLAST: total queries: %s' % (len(list(totalQueries))))
print('BLAST: filtered queries (evalue=%s)(taxa=%s): %s' %
(evalue, str(taxaList), len(list(filteredQueries))))
print('BLAST: filtered hits: %s' % (len(list(filteredHits))))
return mapper1, mapper2
import time,sys
from htsint.database import db_connect,Gene,GoAnnotation,GoTerm
from htsint.database import fetch_annotations,gene_mapper
## variables
session,engine = db_connect()
geneList = ['30970']#,'30971','30972','30973','30975']
expEvidCodes = ["EXP","IDA","IPI","IMP","IGI","IEP"]
compEvidCodes = ["ISS","ISO","ISA","ISM","IGC","RCA"]
statEvidCodes = ["TAS","NAS","IC"]
nonCuratedEvidCodes = ["IEA"]
acceptedCodes = expEvidCodes + statEvidCodes
annotations = {}
aspect = 'biological_process'
timeStart = time.time()
geneQueries = session.query(Gene).filter(Gene.ncbi_id.in_(geneList)).all()
print("...extraction time 1: %s"%time.strftime('%H:%M:%S',time.gmtime(time.time()-timeStart)))
#timeStart = time.time()
#geneIdMap = gene_mapper(session,ncbiIdList=geneList)
#print("...extraction time 1: %s"%time.strftime('%H:%M:%S',time.gmtime(time.time()-timeStart)))
## get all results
timeStart = time.time()
for geneQuery in geneQueries:
annotations[geneQuery.ncbi_id] = set([])
print geneQuery.ncbi_id
annotations[geneQuery.ncbi_id].update(session.query(GoAnnotation).filter_by(gene_id=geneQuery.id).all())
print("...extraction q1: %s"%time.strftime('%H:%M:%S',time.gmtime(time.time()-timeStart)))
def create_blast_map(refTaxon,taxaList,resultsFilePath,evalue=0.00001,verbose=False):
"""
read a summarized reference blast results file and create a map
results are gene centric
example results file looks like this
query(refseq),query(geneId),hit(uniprotEntry),hit(geneEntry),e-value
NP_001016845.1,549599,AQP3_HUMAN,360,1.24637e-170
NP_001016845.1,549599,AQP9_HUMAN,366,7.57313e-92
NP_001016845.1,549599,AQP10_HUMAN,89872,2.87154e-85
NP_001016845.1,549599,AQP7_HUMAN,364,8.01308e-84
NP_001016845.1,549599,AQP5_HUMAN,362,4.267e-15
"""
## error check
if not os.path.exists(resultsFilePath):
raise Exception("cannot find results file path %s"%resultsFilePath)
if refTaxon not in taxaList:
raise Exception("refTaxon must be in taxaList")
## prepare database connections
session,engine = db_connect()
conn = engine.connect()
## read through the file to map the genes to taxa ids
s = select([Taxon.id,Taxon.ncbi_id,Taxon.name]).where(Taxon.ncbi_id.in_(taxaList))
_taxaQueries = conn.execute(s)
taxaQueries = _taxaQueries.fetchall()
totalQueries = set([])
filteredQueries = set([])
filteredHits = set([])
selectedTaxa = [str(tquery['id']) for tquery in taxaQueries]
taxa2name = dict([(str(tquery['id']),str(tquery['ncbi_id'])) for tquery in taxaQueries])
## create a gene2taxa dictionary
gene2taxa = {}
for tquery in taxaQueries:
s = select([Gene.taxa_id,Gene.ncbi_id],Gene.taxa_id==tquery['id'])
_geneQueries = conn.execute(s)
gene2taxa.update(dict([(str(r['ncbi_id']),str(r['taxa_id'])) for r in _geneQueries.fetchall()]))
## creats a dictionary results['geneId]['taxaId'] = bestHitMappedTaxa
results = {}
fid = open(resultsFilePath,'rU')
reader = csv.reader(fid)
header = reader.next()
## loop through file and save best
for linja in reader:
_evalue = float(linja[4])
totalQueries.update([linja[1]])
## filter by species and evalue
if not gene2taxa.has_key(linja[3]) or _evalue > evalue:
continue
if linja[1] == '-' or linja[3] == '-':
continue
## filter self matches
if taxa2name[gene2taxa[linja[3]]] == refTaxon:
continue
if taxa2name[gene2taxa[linja[1]]] != refTaxon:
raise Exception("Invalid query or invalid refTaxon %s != %s"%(taxa2name[gene2taxa[linja[1]]],refTaxon))
taxId = taxa2name[gene2taxa[linja[3]]]
filteredQueries.update([linja[1]])
filteredHits.update([linja[3]])
if not results.has_key(taxId):
results[taxId] = {}
## use the best evalue
if not results[taxId].has_key(linja[1]):
results[taxId][linja[1]] = (linja[3],_evalue)
if _evalue < results[taxId][linja[1]][1]:
results[taxId][linja[1]] = (linja[3],_evalue)
fid.close()
## returns a simplified form of the results as two mappers
mapper1,mapper2 = {},{}
test1 = set([])
for taxId in results.iterkeys():
for queryGene,hit in results[taxId].iteritems():
if not mapper1.has_key(hit[0]):
mapper1[hit[0]] = []
mapper1[hit[0]].append(queryGene)
if not mapper2.has_key(queryGene):
mapper2[queryGene] = []
mapper2[queryGene].append(hit[0])
#debug = set([])
#for key, item in mapper.iteritems():
# debug.update(item)
#for tquery in taxaQueries:
# taxId = str(tquery['ncbi_id'])
# for key,item in results[taxId].iteritems():
# debug.update([key])
# mapper[item[0]] = key
#debug = list(debug)
#print 'debug', len(debug),missing
#print results.keys(),len(results['8364'].keys()), len(results['8355'].keys()), len(list(set(results['8364'].keys() + results['8355'].keys())))
print('BLAST: total queries: %s'%(len(list(totalQueries))))
print('BLAST: filtered queries (evalue=%s)(taxa=%s): %s'%(evalue,str(taxaList),len(list(filteredQueries))))
print('BLAST: filtered hits: %s'%(len(list(filteredHits))))
return mapper1,mapper2
#!/usr/bin/python
import time
from sqlalchemy.sql import select
from htsint.database import db_connect, Taxon, Gene, Uniprot, Refseq
from htsint.database import uniprot_mapper
session, engine = db_connect()
conn = engine.connect()
uniprotEntries = [
"KCNQ4_MOUSE", "CSMT1_XENTR", "CSMT1_MOUSE", "MILK2_MOUSE", "MILK2_RAT",
"MILK1_RAT", "MILK1_MOUSE", "MICA3_MOUSE", "MCA3A_DANRE", "MCA3B_DANRE",
"MICA1_DANRE", "MCA2B_DANRE", "MICLK_MOUSE", "MICLK_RAT", "MILK2_RAT",
"MILK2_MOUSE", "MILK1_RAT", "MILK1_MOUSE", "MICA3_MOUSE", "MICA2_RAT",
"MCA3A_DANRE", "MICA2_MOUSE", "EHBP1_MOUSE", "EH1L1_MOUSE", "SPTB2_MOUSE",
"MCA2B_DANRE", "SPTN2_RAT", "MICA2_XENTR", "SPTCB_DROME", "ACTN_DROME",
"SPTB1_MOUSE", "ACTN2_MOUSE", "ACTN3_MOUSE", "ACTN2_CHICK", "ACTN1_RAT",
"ACTN1_CHICK", "ACTN1_MOUSE", "CYTSA_CHICK", "MCA3B_DANRE", "CYTSA_CANFA",
"CYTSA_DANRE", "CYTSA_MOUSE", "AIN1_SCHPO", "MICA1_DANRE", "CYTSA_RAT",
"SYNE2_MOUSE", "ACTN4_CHICK", "ACTN4_MOUSE", "ACTN4_RAT", "CYTSA_XENTR",
"CYTSB_MOUSE", "SMTL2_MOUSE", "SMTN_MOUSE", "DYST_MOUSE", "PLEC_RAT",
"PLEC_MOUSE", "DMD_CHICK", "DMD_CANFA", "DMD_MOUSE", "MICA1_RAT",
"SMTL1_MOUSE", "MICA1_MOUSE", "MACF1_MOUSE", "MACF1_RAT", "DMD_CAEEL",
"MILK2_MOUSE", "MILK2_RAT", "MILK1_RAT", "MILK1_MOUSE", "ACTN4_CHICK"
"ACTN4_RAT", "ACTN4_MOUSE", "ACTN1_CHICK", "ACTN_DROME", "ACTN1_RAT"
"ACTN1_MOUSE", "ACTN3_MOUSE", "SPTCB_DROME", "ACTN2_MOUSE", "ACTN2_CHICK"
]
## using select method
timeStart = time.time()
def get_blast_map(resultsFilePath,evalue=0.00001,taxaList=None,asGenes=False,append=False):
"""
load assembly blast results into dictionary
if taxaList is provided then only genes from given taxa will be included in map
if asGene == True the results are provided with keys to genes not isoforms
"""
if not os.path.exists(resultsFilePath):
raise Exception("cannot find results file path %s"%resultsFilePath)
if taxaList != None:
## prepare database connections
session,engine = db_connect()
conn = engine.connect()
s = select([Taxon.id,Taxon.ncbi_id,Taxon.name]).where(Taxon.ncbi_id.in_(taxaList))
_taxaQueries = conn.execute(s)
taxaQueries = _taxaQueries.fetchall()
totalQueries = set([])
filteredQueries = set([])
filteredHits = set([])
selectedTaxa = [str(tquery['id']) for tquery in taxaQueries]
taxa2name = dict([(str(tquery['id']),str(tquery['ncbi_id'])) for tquery in taxaQueries])
## create a gene2taxa dictionary
#gene2taxa,gene2desc = {},{}
#for tquery in taxaQueries:
# s = select([Gene.taxa_id,Gene.ncbi_id,Gene.description],Gene.taxa_id==tquery['id'])
# _geneQueries = conn.execute(s)
# geneQueries = _geneQueries.fetchall()
# gene2taxa.update(dict([(str(r['ncbi_id']),str(r['taxa_id'])) for r in geneQueries]))
# gene2desc.update(dict([(str(r['ncbi_id']),str(r['description'])) for r in geneQueries]))
results = {}
fid = open(resultsFilePath,'rU')
reader = csv.reader(fid)
header = reader.next()
print header
## loop through file and save best
uniqueQueries = set([])
totalQueries = 0
unfilteredQueries = 0
for linja in reader:
if len(linja) == 4:
queryId = linja[0]
hitId = linja[1]
hitNcbiId = linja[2]
_evalue = float(linja[3])
else:
queryId = linja[0]
queryNcbi = linja[1]
hitId = linja[2]
hitNcbiId = linja[3]
_evalue = linja[4]
if asGenes == True:
queryId = re.sub("_i\d+","",queryId)
# filtering
totalQueries += 1
if '-' in linja:
continue
if _evalue > evalue:
continue
if taxaList and gene2taxa.has_key(str(hitNcbiId)) == False:
continue
unfilteredQueries += 1
uniqueQueries.update([queryId])
## use the best evalue
if not results.has_key(queryId):
if append:
results[queryId] = [(hitNcbiId,_evalue)]
else:
results[queryId] = (hitNcbiId,_evalue)
if _evalue < results[queryId][1]:
if append:
results[queryId].append((hitNcbiId,_evalue))
else:
results[queryId] = (hitNcbiId,_evalue)
uniqueQueries = list(uniqueQueries)
print("total queries: %s"%totalQueries)
print("unfiltered queries: %s"%unfilteredQueries)
print("unique: %s"%len(uniqueQueries))
return results