def parse_result(self):
"""
Align fasta formated sequence to hmm profile.
@return: alignment and matching hmm positions with gaps
@rtype: str, str
"""
## check that the outfut file is there and seems valid
if not os.path.exists(self.f_out):
raise HmmerError,\
'Hmmeralign result file %s does not exist.'%self.f_out
if T.fileLength(self.f_out) < 1:
raise HmmerError,\
'Hmmeralign result file %s seems incomplete.'%self.f_out
## read result
hmm = open(self.f_out, 'r')
out = hmm.read()
hmm.close()
## extract search sequence
fastaSeq = re.findall(self.fastaID + '[ ]+[-a-yA-Y]+', out)
fastaSeq = string.join([string.split(i)[1] for i in fastaSeq], '')
## extract hmm sequence
hmmSeq = re.findall('#=[A-Z]{2}\s[A-Z]{2}\s+[.x]+', out)
hmmSeq = string.join(
[string.strip(string.split(i)[2]) for i in hmmSeq], '')
return fastaSeq, hmmSeq
def parse_result( self ):
"""
Align fasta formated sequence to hmm profile.
@return: alignment and matching hmm positions with gaps
@rtype: str, str
"""
## check that the outfut file is there and seems valid
if not os.path.exists( self.f_out ):
raise HmmerError,\
'Hmmeralign result file %s does not exist.'%self.f_out
if T.fileLength( self.f_out ) < 1:
raise HmmerError,\
'Hmmeralign result file %s seems incomplete.'%self.f_out
## read result
hmm = open( self.f_out, 'r')
out = hmm.read()
hmm.close()
## extract search sequence
fastaSeq = re.findall( self.fastaID + '[ ]+[-a-yA-Y]+', out )
fastaSeq = string.join([ string.split(i)[1] for i in fastaSeq ], '')
## extract hmm sequence
hmmSeq = re.findall( '#=[A-Z]{2}\s[A-Z]{2}\s+[.x]+', out )
hmmSeq = string.join([ string.strip( string.split(i)[2] ) for i in hmmSeq ], '')
return fastaSeq, hmmSeq
def clusterFasta( self, fastaIn=None, simCut=1.75, lenCut=0.9, ncpu=1 ):
"""
Cluster sequences. The input fasta titles must be the IDs.
fastaClust( fastaIn [, simCut, lenCut, ncpu] )
@param fastaIn: name of input fasta file
@type fastaIn: str
@param simCut: similarity threshold (score < 3 or %identity)
(default: 1.75)
@type simCut: double
@param lenCut: length threshold (default: 0.9)
@type lenCut: double
@param ncpu: number of CPUs
@type ncpu: int
@raise BlastError: if fastaIn is empty
"""
fastaIn = fastaIn or self.outFolder + self.F_FASTA_ALL
if T.fileLength( fastaIn ) < 1:
raise IOError( "File %s empty. Nothing to cluster"%fastaIn )
if self.verbose:
self.log.add( "\nClustering sequences:\n%s"%('-'*20) )
cmd = settings.blastclust_bin + ' -i %s -S %f -L %f -a %i' %\
(fastaIn, simCut, lenCut, ncpu)
if self.verbose:
self.log.add("- Command: %s"%cmd)
## bugfix: at all cost prevent blastclust from using shared temp folder
tmp = os.environ.get( 'TMPDIR', None )
if tmp:
del os.environ['TMPDIR']
err, o = commands.getstatusoutput( cmd )
if err:
raise BlastError( "blastclust failed. Error code: " + str(err) )
if tmp:
os.environ['TMPDIR'] = tmp
## blastclust might write errors to file, if so the errors
## occur before the dateline
lines = [ l.split() for l in o.split('\n') ]
dateline = [ l[-1] for l in lines ].index('queries')
self.clusters = lines[dateline+1:]
self.reportClustering( raw=o )
self.bestOfCluster = [ self.selectFasta( ids )
for ids in self.clusters ]
def clusterFasta(self, fastaIn=None, simCut=1.75, lenCut=0.9, ncpu=1):
"""
Cluster sequences. The input fasta titles must be the IDs.
fastaClust( fastaIn [, simCut, lenCut, ncpu] )
@param fastaIn: name of input fasta file
@type fastaIn: str
@param simCut: similarity threshold (score < 3 or %identity)
(default: 1.75)
@type simCut: double
@param lenCut: length threshold (default: 0.9)
@type lenCut: double
@param ncpu: number of CPUs
@type ncpu: int
@raise BlastError: if fastaIn is empty
"""
fastaIn = fastaIn or self.outFolder + self.F_FASTA_ALL
if T.fileLength(fastaIn) < 1:
raise IOError("File %s empty. Nothing to cluster" % fastaIn)
if self.verbose:
self.log.add("\nClustering sequences:\n%s" % ('-' * 20))
cmd = settings.blastclust_bin + ' -i %s -S %f -L %f -a %i' %\
(fastaIn, simCut, lenCut, ncpu)
if self.verbose:
self.log.add("- Command: %s" % cmd)
## bugfix: at all cost prevent blastclust from using shared temp folder
tmp = os.environ.get('TMPDIR', None)
if tmp:
del os.environ['TMPDIR']
err, o = commands.getstatusoutput(cmd)
if err:
raise BlastError("blastclust failed. Error code: " + str(err))
if tmp:
os.environ['TMPDIR'] = tmp
## blastclust might write errors to file, if so the errors
## occur before the dateline
lines = [l.split() for l in o.split('\n')]
dateline = [l[-1] for l in lines].index('queries')
self.clusters = lines[dateline + 1:]
self.reportClustering(raw=o)
self.bestOfCluster = [self.selectFasta(ids) for ids in self.clusters]
def parse_result( self ):
"""
Parse the output from hmmpfam.
@return: dictionary witn profile names as keys and a list of
lists containing information about the range where the
profile matches the sequence
@rtype: dict, [list]
"""
matches = {}
hits = []
## check that the outfut file is there and seems valid
if not os.path.exists( self.f_out ):
raise HmmerError,\
'Hmmersearch result file %s does not exist.'%self.f_out
if T.fileLength( self.f_out ) < 10:
raise HmmerError,\
'Hmmersearch result file %s seems incomplete.'%self.f_out
try:
out = open( self.f_out, 'r' )
while 1:
l = out.readline()
## get names and descriptions of matching profiles
if re.match('^-{8}\s{7,8}-{11}.+-{3}$', l):
m = string.split( out.readline() )
while len(m) != 0:
matches[m[0]] = m[1:]
m = string.split( out .readline() )
## get hits, scores and alignment positions
if re.match('^-{8}\s{7,8}-{7}\s-{5}\s-{5}.+-{7}$', l):
h = string.split( out.readline() )
while len(h) != 0:
hits += [ h ]
h = string.split( out.readline() )
break
except:
raise HmmerError,\
'ERROR parsing hmmpfam search result: %s'%self.f_out
out.close()
return matches, hits
def __init__( self, hmmFile, fastaFile, fastaID, **kw ):
"""
@param hmmFile: path to hmm file (profile)
@type hmmFile: str
@param fastaFile: path to fasta search sequence
@type fastaFile: str
@param fastaID: fasta id of search sequence
@type fastaID: str
"""
self.fastaID = fastaID
self.hmmFile = hmmFile
self.fastaFile = fastaFile
assert T.fileLength( self.hmmFile ) > 10, \
'input HMM file missing or empty'
Executor.__init__( self, 'hmmalign',
args=' -q %s %s'%(hmmFile, fastaFile), **kw )
def parse_result(self):
"""
Parse the output from hmmpfam.
@return: dictionary with profile names as keys and a list of
lists containing information about the range where the
profile matches the sequence
@rtype: dict, [list]
"""
matches = {}
hits = []
## check that the outfut file is there and seems valid
if not os.path.exists(self.f_out):
raise HmmerError,\
'Hmmersearch result file %s does not exist.'%self.f_out
if T.fileLength(self.f_out) < 10:
raise HmmerError,\
'Hmmersearch result file %s seems incomplete.'%self.f_out
try:
lines = open(self.f_out, 'r').readlines()
while lines:
l = lines.pop(0)
## get names and descriptions of matching profiles
if re.match('^-{8}\s{7,8}-{11}.+-{3}$', l):
m = string.split(lines.pop(0))
while len(m) != 0:
matches[m[0]] = m[1:]
m = string.split(lines.pop(0))
## get hits, scores and alignment positions
if re.match('^-{8}\s{7,8}-{7}\s-{5}\s-{5}.+-{7}$', l):
h = string.split(lines.pop(0))
while len(h) != 0:
hits += [h]
h = string.split(lines.pop(0))
break
except Exception, why:
raise HmmerError,\
'ERROR parsing hmmpfam search result: %s'%self.f_out +\
'\n%r' % why
def __init__(self, hmmFile, fastaFile, fastaID, **kw):
"""
@param hmmFile: path to hmm file (profile)
@type hmmFile: str
@param fastaFile: path to fasta search sequence
@type fastaFile: str
@param fastaID: fasta id of search sequence
@type fastaID: str
"""
self.fastaID = fastaID
self.hmmFile = hmmFile
self.fastaFile = fastaFile
assert T.fileLength( self.hmmFile ) > 10, \
'input HMM file missing or empty'
Executor.__init__(self,
'hmmalign',
args=' -q %s %s' % (hmmFile, fastaFile),
**kw)
def parse_result(self):
"""
Extract some information about the profile as well as the
match state emmission scores. Keys of the returned dictionary::
'AA', 'name', 'NrSeq', 'emmScore', 'accession',
'maxAllScale', 'seqNr', 'profLength', 'ent', 'absSum'
@return: dictionary with warious information about the profile
@rtype: dict
"""
## check that the outfut file is there and seems valid
if not os.path.exists(self.f_out):
raise HmmerError,\
'Hmmerfetch result file %s does not exist.'%self.f_out
if T.fileLength(self.f_out) < 10:
raise HmmerError,\
'Hmmerfetch result file %s seems incomplete.'%self.f_out
profileDic = {}
## read result
hmm = open(self.f_out, 'r')
out = hmm.read()
hmm.close()
## collect some data about the hmm profile
profileDic['name'] = self.hmmName
profileDic['profLength'] = \
int( string.split(re.findall('LENG\s+[0-9]+', out)[0])[1] )
profileDic['accession'] = \
string.split(re.findall('ACC\s+PF[0-9]+', out)[0])[1]
profileDic['NrSeq'] = \
int( string.split(re.findall('NSEQ\s+[0-9]+', out)[0])[1] )
profileDic['AA'] = \
string.split(re.findall('HMM[ ]+' + '[A-Y][ ]+'*20, out)[0] )[1:]
## collect null emmission scores
pattern = 'NULE[ ]+' + '[-0-9]+[ ]+' * 20
nullEmm = [
float(j) for j in string.split(re.findall(pattern, out)[0])[1:]
]
## get emmision scores
prob = []
for i in range(1, profileDic['profLength'] + 1):
pattern = "[ ]+%i" % i + "[ ]+[-0-9]+" * 20
e = [float(j) for j in string.split(re.findall(pattern, out)[0])]
prob += [e]
profileDic['seqNr'] = N.transpose(N.take(prob, (0, ), 1))
profileDic['emmScore'] = N.array(prob)[:, 1:]
## calculate emission probablitities
emmProb, nullProb = self.hmmEmm2Prob(nullEmm, profileDic['emmScore'])
ent = [
N.resize(self.entropy(e, nullProb), (1, 20))[0] for e in emmProb
]
profileDic['ent'] = N.array(ent)
###### TEST #####
proba = N.array(prob)[:, 1:]
## # test set all to max score
## p = proba
## p1 = []
## for i in range( len(p) ):
## p1 += [ N.resize( p[i][N.argmax( N.array( p[i] ) )] , N.shape( p[i] ) ) ]
## profileDic['maxAll'] = p1
# test set all to N.sum( abs( probabilities ) )
p = proba
p2 = []
for i in range(len(p)):
p2 += [N.resize(N.sum(N.absolute(p[i])), N.shape(p[i]))]
profileDic['absSum'] = p2
# set all to normalized max score
p = proba
p4 = []
for i in range(len(p)):
p_scale = (p[i] - N.average(p[i])) / math.SD(p[i])
p4 += [
N.resize(p_scale[N.argmax(N.array(p_scale))], N.shape(p[i]))
]
profileDic['maxAllScale'] = p4
return profileDic
def parse_result( self ):
"""
Extract some information about the profile as well as the
match state emmission scores. Keys of the returned dictionary::
'AA', 'name', 'NrSeq', 'emmScore', 'accession',
'maxAllScale', 'seqNr', 'profLength', 'ent', 'absSum'
@return: dictionary with warious information about the profile
@rtype: dict
"""
## check that the outfut file is there and seems valid
if not os.path.exists( self.f_out ):
raise HmmerError,\
'Hmmerfetch result file %s does not exist.'%self.f_out
if T.fileLength( self.f_out ) < 10:
raise HmmerError,\
'Hmmerfetch result file %s seems incomplete.'%self.f_out
profileDic = {}
## read result
hmm = open( self.f_out, 'r')
out = hmm.read()
hmm.close()
## collect some data about the hmm profile
profileDic['name'] = self.hmmName
profileDic['profLength'] = \
int( string.split(re.findall('LENG\s+[0-9]+', out)[0])[1] )
profileDic['accession'] = \
string.split(re.findall('ACC\s+PF[0-9]+', out)[0])[1]
profileDic['NrSeq'] = \
int( string.split(re.findall('NSEQ\s+[0-9]+', out)[0])[1] )
profileDic['AA'] = \
string.split(re.findall('HMM[ ]+' + '[A-Y][ ]+'*20, out)[0] )[1:]
## collect null emmission scores
pattern = 'NULE[ ]+' + '[-0-9]+[ ]+'*20
nullEmm = [ float(j) for j in string.split(re.findall(pattern, out)[0])[1:] ]
## get emmision scores
prob=[]
for i in range(1, profileDic['profLength']+1):
pattern = "[ ]+%i"%i + "[ ]+[-0-9]+"*20
e = [ float(j) for j in string.split(re.findall(pattern, out)[0]) ]
prob += [ e ]
profileDic['seqNr'] = N.transpose( N.take( prob, (0,),1 ) )
profileDic['emmScore'] = N.array(prob)[:,1:]
## calculate emission probablitities
emmProb, nullProb = self.hmmEmm2Prob( nullEmm, profileDic['emmScore'])
ent = [ N.resize( self.entropy(e, nullProb), (1,20) )[0] for e in emmProb ]
profileDic['ent'] = N.array(ent)
###### TEST #####
proba = N.array(prob)[:,1:]
## # test set all to max score
## p = proba
## p1 = []
## for i in range( len(p) ):
## p1 += [ N.resize( p[i][N.argmax( N.array( p[i] ) )] , N.shape( p[i] ) ) ]
## profileDic['maxAll'] = p1
# test set all to N.sum( abs( probabilities ) )
p = proba
p2 = []
for i in range( len(p) ) :
p2 += [ N.resize( N.sum( N.absolute( p[i] )), N.shape( p[i] ) ) ]
profileDic['absSum'] = p2
# set all to normalized max score
p = proba
p4 = []
for i in range( len(p) ) :
p_scale = (p[i] - N.average(p[i]) )/ math.SD(p[i])
p4 += [ N.resize( p_scale[N.argmax( N.array(p_scale) )] ,
N.shape( p[i] ) ) ]
profileDic['maxAllScale'] = p4
return profileDic