def genomeAnalysis(datadir, label, gname, method):
"""this method should be made independent of web app paths etc"""
path = os.path.join(datadir, '%s/%s/%s' % (label, gname, method))
#path='test'
gfile = os.path.join(genomespath, '%s.gb' % gname)
g = sequtils.genbank2Dataframe(gfile, cds=True)
b = getAllBinders(path, method=method, n=5)
P = base.getPredictor(method)
res = b.groupby('name').agg({
P.scorekey: [np.mean, np.size, np.max]
}).sort()
res.columns = res.columns.get_level_values(1)
res = res.merge(g[['locus_tag', 'length', 'gene', 'product', 'order']],
left_index=True,
right_on='locus_tag')
res['perc'] = res['size'] / res.length * 100
res = res.sort('perc', ascending=False)
top = b.groupby('peptide').agg({
P.scorekey: np.mean,
'allele': np.max,
'name': lambda x: x
}).reset_index()
top = top.sort(P.scorekey, ascending=P.rankascending)
cl = findClusters(b, method, dist=9, minsize=3)
if cl is not None:
gc = cl.groupby('name').agg({'density': np.max})
res = res.merge(gc, left_on='locus_tag', right_index=True)
#print res[:10]
return res
def testrun(gname):
method = 'tepitope' #'iedbmhc1'#'netmhciipan'
path = 'test'
gfile = os.path.join(genomespath, '%s.gb' % gname)
df = sequtils.genbank2Dataframe(gfile, cds=True)
#names = list(df.locus_tag[:1])
names = ['VP24']
alleles1 = [
"HLA-A*02:02", "HLA-A*11:01", "HLA-A*32:07", "HLA-B*15:17",
"HLA-B*51:01", "HLA-C*04:01", "HLA-E*01:03"
]
alleles2 = [
"HLA-DRB1*0101", "HLA-DRB1*0305", "HLA-DRB1*0812", "HLA-DRB1*1196",
"HLA-DRB1*1346", "HLA-DRB1*1455", "HLA-DRB1*1457", "HLA-DRB1*1612",
"HLA-DRB4*0107", "HLA-DRB5*0203"
]
P = base.getPredictor(method)
P.iedbmethod = 'IEDB_recommended' #'netmhcpan'
P.predictProteins(df,
length=11,
alleles=alleles2,
names=names,
save=True,
path=path)
f = os.path.join('test', names[0] + '.mpk')
df = pd.read_msgpack(f)
P.data = df
#b = P.getBinders(data=df)
#print b[:20]
base.getScoreDistributions(method, path)
return
def genomeAnalysis(datadir,label,gname,method):
"""this method should be made independent of web app paths etc"""
path = os.path.join(datadir, '%s/%s/%s' %(label,gname,method))
#path='test'
gfile = os.path.join(genomespath,'%s.gb' %gname)
g = sequtils.genbank2Dataframe(gfile, cds=True)
b = getAllBinders(path, method=method, n=5)
P = base.getPredictor(method)
res = b.groupby('name').agg({P.scorekey:[np.mean,np.size,np.max]}).sort()
res.columns = res.columns.get_level_values(1)
res = res.merge(g[['locus_tag','length','gene','product','order']],
left_index=True,right_on='locus_tag')
res['perc'] = res['size']/res.length*100
res = res.sort('perc',ascending=False)
top = b.groupby('peptide').agg({P.scorekey:np.mean,'allele':np.max,
'name': lambda x: x}).reset_index()
top = top.sort(P.scorekey,ascending=P.rankascending)
cl = findClusters(b, method, dist=9, minsize=3)
if cl is not None:
gc = cl.groupby('name').agg({'density':np.max})
res = res.merge(gc,left_on='locus_tag',right_index=True)
#print res[:10]
return res
def testLoad(self):
"""Test re-loading predictions"""
infile = os.path.join(self.testdir, 'ZEBOVgp1.mpk')
pred = pd.read_msgpack(infile)
P = base.getPredictor('iedbmhc1')
P.data = pred
return
def testBcell(self):
"""IEDB BCell test"""
df = self.df
names = ['VP24']
P = base.getPredictor('bcell')
P.iedbmethod='Chou-Fasman'
P.predictProteins(df, names=names, save=True, path=self.testdir)
return
def testFasta(self):
"""Test fasta predictions"""
fastafile = 'testing/zaire-ebolavirus.faa'
df = sequtils.fasta2Dataframe(fastafile)
alleles = ["HLA-DRB1*0101"]
P = base.getPredictor('tepitope')
P.predictProteins(df, length=11, alleles=alleles,
save=True, path=self.testdir)
return
def testBcell(gname):
path = 'test'
gfile = os.path.join(genomespath, '%s.gb' % gname)
df = sequtils.genbank2Dataframe(gfile, cds=True)
names = ['VP24']
P = base.getPredictor('bcell')
P.iedbmethod = 'Chou-Fasman'
P.predictProteins(df, names=names, save=True, path=path)
print P.data
return
def testBcell(gname):
path='test'
gfile = os.path.join(genomespath,'%s.gb' %gname)
df = sequtils.genbank2Dataframe(gfile, cds=True)
names=['VP24']
P = base.getPredictor('bcell')
P.iedbmethod='Chou-Fasman'
P.predictProteins(df,names=names,save=True,path=path)
print P.data
return
def testTepitope(self):
"""Tepitope test"""
df = self.df
P = base.getPredictor('tepitope')
alleles = ["HLA-DRB1*0101", "HLA-DRB1*0305"]
print P
P.predictProteins(df, length=11, alleles=alleles,
save=True, path=self.testdir)
P.getBinders(data=P.data)
return
def testIEDB(self):
"""IEDB MHCI test"""
df = self.df
P = base.getPredictor('iedbmhc1')
print P
alleles = ["HLA-A*02:02", "HLA-A*11:01",
"HLA-B*15:17", "HLA-B*51:01",
"HLA-C*04:01", "HLA-E*01:03"]
P.predictProteins(df, length=11, alleles=alleles,
save=True, path=self.testdir)
return
def testnetMHCIIpan(self):
"""netMHCIIpan test"""
#requires netmHCIIpan is installed
df = self.df
P = base.getPredictor('netmhciipan')
alleles = ["HLA-DRB1*0101"]
names = ['ZEBOVgp1']
print P
P.predictProteins(df, length=11, alleles=alleles, names=names,
save=True, path=self.testdir)
P.getBinders(data=P.data)
return
def getPredictions(path, tag, method='tepitope', q=0.96):
"""Get predictions from file system"""
q = round(q, 2)
#preds = OrderedDict()
cutoffs = {}
filename = os.path.join(path, tag + '.mpk')
if not os.path.exists(filename):
return
df = pd.read_msgpack(filename)
pred = base.getPredictor(name=method, data=df)
cutoffs = pred.allelecutoffs = getCutoffs(path, method, q)
pred = pred
return pred
def getPredictions(path,tag,method='tepitope',q=0.96):
"""Get predictions from file system"""
q=round(q,2)
#preds = OrderedDict()
cutoffs = {}
filename = os.path.join(path, tag+'.mpk')
if not os.path.exists(filename):
return
df = pd.read_msgpack(filename)
pred = base.getPredictor(name=method, data=df)
cutoffs = pred.allelecutoffs = getCutoffs(path, method, q)
pred = pred
return pred
def testrun(gname):
method = 'tepitope'#'iedbmhc1'#'netmhciipan'
path='test'
gfile = os.path.join(genomespath,'%s.gb' %gname)
df = sequtils.genbank2Dataframe(gfile, cds=True)
#names = list(df.locus_tag[:1])
names=['VP24']
alleles1 = ["HLA-A*02:02", "HLA-A*11:01", "HLA-A*32:07", "HLA-B*15:17", "HLA-B*51:01",
"HLA-C*04:01", "HLA-E*01:03"]
alleles2 = ["HLA-DRB1*0101", "HLA-DRB1*0305", "HLA-DRB1*0812", "HLA-DRB1*1196", "HLA-DRB1*1346",
"HLA-DRB1*1455", "HLA-DRB1*1457", "HLA-DRB1*1612", "HLA-DRB4*0107", "HLA-DRB5*0203"]
P = base.getPredictor(method)
P.iedbmethod='IEDB_recommended' #'netmhcpan'
P.predictProteins(df,length=11,alleles=alleles2,names=names,
save=True,path=path)
f = os.path.join('test', names[0]+'.mpk')
df = pd.read_msgpack(f)
P.data=df
#b = P.getBinders(data=df)
#print b[:20]
base.getScoreDistributions(method, path)
return
def getAllBinders(path, method='tepitope', n=3, cutoff=0.95, promiscuous=True):
"""Get all promiscuous binders from a set of proteins in path"""
print 'getting binders..'
binders = []
m = method
if m == 'bcell': return #not applicable
l = 9
P = base.getPredictor(m)
files = glob.glob(os.path.join(path, '*.mpk'))
#get allele specific cutoffs
P.allelecutoffs = getCutoffs(path, method, cutoff, overwrite=True)
for f in files:
df = pd.read_msgpack(f)
if promiscuous == True:
b = P.getPromiscuousBinders(data=df, n=n)
else:
b = P.getBinders(data=df)
#print b[:5]
binders.append(b)
result = pd.concat(binders)
result['start'] = result.pos
result['end'] = result.pos + result.peptide.str.len()
return result
def getAllBinders(path, method='tepitope', n=3, cutoff=0.95, promiscuous=True):
"""Get all promiscuous binders from a set of proteins in path"""
print 'getting binders..'
binders = []
m=method
if m=='bcell': return #not applicable
l=9
P = base.getPredictor(m)
files = glob.glob(os.path.join(path, '*.mpk'))
#get allele specific cutoffs
P.allelecutoffs = getCutoffs(path, method, cutoff, overwrite=True)
for f in files:
df = pd.read_msgpack(f)
if promiscuous== True:
b = P.getPromiscuousBinders(data=df,n=n)
else:
b = P.getBinders(data=df)
#print b[:5]
binders.append(b)
result = pd.concat(binders)
result['start'] = result.pos
result['end'] = result.pos+result.peptide.str.len()
return result