def testconservation(label, gname):
"""Conservation analysis"""
tag = 'VP24'
pd.set_option('max_colwidth', 800)
gfile = os.path.join(genomespath, '%s.gb' % gname)
g = sequtils.genbank2Dataframe(gfile, cds=True)
res = g[g['locus_tag'] == tag]
seq = res.translation.head(1).squeeze()
print seq
#alnrows = getOrthologs(seq)
#alnrows.to_csv('blast_%s.csv' %tag)
alnrows = pd.read_csv('blast_%s.csv' % tag, index_col=0)
alnrows.drop_duplicates(subset=['accession'], inplace=True)
alnrows = alnrows[alnrows['perc_ident'] >= 60]
seqs = [
SeqRecord(Seq(a.sequence), a.accession) for i, a in alnrows.iterrows()
]
print seqs[:2]
sequtils.distanceTree(seqs=seqs) #,ref=seqs[0])
#sequtils.ETETree(seqs, ref, metric)
#df = sequtils.getFastaProteins("blast_found.faa",idindex=3)
'''method='tepitope'
P = base.getPredictor(method)
P.predictSequences(df,seqkey='sequence')
b = P.getBinders()'''
return
def setUp(self):
genbankfile = 'testing/zaire-ebolavirus.gb'
self.df = sequtils.genbank2Dataframe(genbankfile, cds=True)
self.testdir = 'testing'
if not os.path.exists(self.testdir):
os.mkdir(self.testdir)
return
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 testconservation(label,gname):
"""Conservation analysis"""
tag='VP24'
pd.set_option('max_colwidth', 800)
gfile = os.path.join(genomespath,'%s.gb' %gname)
g = sequtils.genbank2Dataframe(gfile, cds=True)
res = g[g['locus_tag']==tag]
seq = res.translation.head(1).squeeze()
print seq
#alnrows = getOrthologs(seq)
#alnrows.to_csv('blast_%s.csv' %tag)
alnrows = pd.read_csv('blast_%s.csv' %tag,index_col=0)
alnrows.drop_duplicates(subset=['accession'], inplace=True)
alnrows = alnrows[alnrows['perc_ident']>=60]
seqs=[SeqRecord(Seq(a.sequence),a.accession) for i,a in alnrows.iterrows()]
print seqs[:2]
sequtils.distanceTree(seqs=seqs)#,ref=seqs[0])
#sequtils.ETETree(seqs, ref, metric)
#df = sequtils.getFastaProteins("blast_found.faa",idindex=3)
'''method='tepitope'
P = base.getPredictor(method)
P.predictSequences(df,seqkey='sequence')
b = P.getBinders()'''
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 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 testFeatures():
"""test feature handling"""
fname = os.path.join(datadir, 'MTB-H37Rv.gb')
df = sequtils.genbank2Dataframe(fname, cds=True)
df = df.set_index('locus_tag')
keys = df.index
name = 'Rv0011c'
row = df.ix[name]
seq = row.translation
prod = row['product']
rec = SeqRecord(Seq(seq), id=name, description=prod)
fastafmt = rec.format("fasta")
print fastafmt
print row.to_dict()
ind = keys.get_loc(name)
previous = keys[ind - 1]
if ind < len(keys) - 1:
next = keys[ind + 1]
else:
next = None
return
def testFeatures():
"""test feature handling"""
fname = os.path.join(datadir,'MTB-H37Rv.gb')
df = sequtils.genbank2Dataframe(fname, cds=True)
df = df.set_index('locus_tag')
keys = df.index
name='Rv0011c'
row = df.ix[name]
seq = row.translation
prod = row['product']
rec = SeqRecord(Seq(seq),id=name,description=prod)
fastafmt = rec.format("fasta")
print fastafmt
print row.to_dict()
ind = keys.get_loc(name)
previous = keys[ind-1]
if ind<len(keys)-1:
next = keys[ind+1]
else:
next=None
return
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