def testSeqidLabel(self):
seqid = 0.50
label = "FSHB_BOVIN"
labeled = refineMSA(FASTA, label=label)
unique = uniqueSequences(labeled, seqid)
unique[FASTA.getIndex(label)] = True
refined = refineMSA(FASTA, label=label, seqid=seqid)
assert_array_equal(refined._getArray(), labeled._getArray()[unique])
def testSeqid(self):
seqid = 0.50
label = 'FSHB_BOVIN'
unique = uniqueSequences(FASTA, seqid)
refined = refineMSA(FASTA, seqid=seqid)
assert_array_equal(refined._getArray(), FASTA._getArray()[unique])
def testSeqid(self):
seqid = 0.50
label = "FSHB_BOVIN"
unique = uniqueSequences(FASTA, seqid)
refined = refineMSA(FASTA, seqid=seqid)
assert_array_equal(refined._getArray(), FASTA._getArray()[unique])
def testLabel(self):
label = 'FSHB_BOVIN'
index = FASTA.getIndex(label)
refined = refineMSA(FASTA, label=label)._getArray()
expected = FASTA._getArray().take(FASTA_ALPHA[index].nonzero()[0], 1)
assert_array_equal(refined, expected)
def testLabel(self):
label = "FSHB_BOVIN"
index = FASTA.getIndex(label)
refined = refineMSA(FASTA, label=label)._getArray()
expected = FASTA._getArray().take(FASTA_ALPHA[index].nonzero()[0], 1)
assert_array_equal(refined, expected)
def testRowCol(self):
rowocc = 0.9
colocc = 1.0
refined = refineMSA(FASTA, rowocc=rowocc, colocc=colocc)._getArray()
rows = FASTA_ALPHA.sum(1) / 112.0 >= rowocc
expected = FASTA._getArray()[rows]
cols = char.isalpha(expected).sum(0, dtype=float) / expected.shape[0] >= colocc
expected = expected.take(cols.nonzero()[0], 1)
assert_array_equal(refined, expected)
def testRowCol(self):
rowocc = 0.9
colocc = 1.0
refined = refineMSA(FASTA, rowocc=rowocc, colocc=colocc)._getArray()
rows = FASTA_ALPHA.sum(1) / 112. >= rowocc
expected = FASTA._getArray()[rows]
cols = char.isalpha(expected).sum(
0, dtype=float) / expected.shape[0] >= colocc
expected = expected.take(cols.nonzero()[0], 1)
assert_array_equal(refined, expected)
def evol_refine(msa, **kwargs):
from prody import parseMSA, refineMSA, writeMSA, LOGGER
from os.path import splitext
outname = kwargs.get('outname')
if outname is None:
outname, ext = splitext(msa)
if ext.lower() == '.gz':
outname, _ = splitext(msa)
outname += '_refined' + ext
writeMSA(outname, refineMSA(parseMSA(msa), **kwargs), **kwargs)
LOGGER.info('Refined MSA is written in file: ' + outname)
def evol_refine(msa, **kwargs):
import prody
from prody import parseMSA, refineMSA, writeMSA, LOGGER
from os.path import splitext
outname = kwargs.get('outname')
if outname is None:
outname, ext = splitext(msa)
if ext.lower() == '.gz':
outname, _ = splitext(msa)
outname += '_refined' + ext
writeMSA(outname, refineMSA(parseMSA(msa), **kwargs), **kwargs)
LOGGER.info('Refined MSA is written in file: ' + outname)
def evol_refine(msa, **kwargs):
import prody
from prody import parseMSA, refineMSA, writeMSA, LOGGER
from os.path import splitext
outname = kwargs.get("outname")
if outname is None:
outname, ext = splitext(msa)
if ext.lower() == ".gz":
outname, _ = splitext(msa)
outname += "_refined" + ext
writeMSA(outname, refineMSA(parseMSA(msa), **kwargs), **kwargs)
LOGGER.info("Refined MSA is written in file: " + outname)
def testAll(self):
rowocc = 0.9
colocc = 0.9
seqid = 0.98
label = "FSHB_BOVIN"
refined = refineMSA(FASTA, label=label, seqid=seqid, rowocc=rowocc, colocc=colocc)
index = FASTA.getIndex(label)
which = FASTA_ALPHA[index].nonzero()[0]
expected = FASTA._getArray().take(which, 1)
expected = expected[uniqueSequences(expected, seqid)]
expected = expected[calcMSAOccupancy(expected, "row") >= rowocc]
which = (calcMSAOccupancy(expected) >= colocc).nonzero()[0]
expected = expected.take(which, 1)
assert_array_equal(refined._getArray(), expected)
def testAll(self):
rowocc = 0.9
colocc = 0.9
seqid = 0.98
label = 'FSHB_BOVIN'
refined = refineMSA(FASTA, label=label, seqid=seqid,
rowocc=rowocc, colocc=colocc)
index = FASTA.getIndex(label)
which = FASTA_ALPHA[index].nonzero()[0]
expected = FASTA._getArray().take(which, 1)
expected = expected[uniqueSequences(expected, seqid)]
expected = expected[calcMSAOccupancy(expected, 'row') >= rowocc]
which = (calcMSAOccupancy(expected) >= colocc).nonzero()[0]
expected = expected.take(which, 1)
assert_array_equal(refined._getArray(), expected)
def calcEvolProperties(self,
resid='all',
refresh=False,
folder=None,
max_cols=None,
max_seqs=25000,
**kwargs):
''' Computes Evol properties, i.e. Shannon entropy, Mutual
Information and Direct Information, from Pfam Multiple
Sequence Alignments, for a given residue.
'''
assert type(refresh) is bool
# recover Pfam mapping (if not found already)
self._searchPfam(refresh=refresh)
if resid == 'all':
PF_list = self.Pfam.keys()
else:
# get list of Pfam domains containing resid
PF_list = [
k for k in self.Pfam if any([
resid >= int(segment['start'])
and resid <= int(segment['end'])
for segment in self.Pfam[k]['locations']
])
]
if len(PF_list) == 0:
raise RuntimeError(
'No Pfam domain for resid {}.'.format(resid))
if len(PF_list) > 1:
LOGGER.warn('Residue {} is found in multiple '.format(resid) + \
'({}) Pfam domains.'.format(len(PF_list)))
if folder is None:
folder = SETTINGS.get('rhapsody_local_folder', './')
# iterate over Pfam families
for PF in PF_list:
d = self.Pfam[PF]
# skip if properties are pre-computed
if not refresh and d.get('mapping') is not None:
continue
d['mapping'] = None
d['ref_MSA'] = None
d['entropy'] = np.nan
d['MutInfo'] = np.nan
d['DirInfo'] = np.nan
try:
LOGGER.info('Processing {}...'.format(PF))
# fetch & parse MSA
# fname = PF + '_full.sth'
# fullname = os.path.join(folder, fname)
# if not os.path.isfile(fullname):
# f = fetchPfamMSA(PF)
# os.rename(f, fullname)
# msa = parseMSA(fullname, **kwargs)
# fetch & parse MSA without saving downloaded MSA
f = fetchPfamMSA(PF)
msa = parseMSA(f, **kwargs)
os.remove(f)
# slice MSA to match all segments of the Uniprot sequence
sliced_msa, indexes = self._sliceMSA(msa)
# if max_cols is not None and sliced_msa.numResidues() > max_cols:
# raise Exception('Unable to compute DI: MSA has ' +\
# 'too many columns (max: {}).'.format(max_cols))
# get mapping between Uniprot sequence and Pfam domain
d['mapping'] = self._mapUniprot2Pfam(PF, sliced_msa, indexes)
except Exception as e:
LOGGER.warn('{}: {}'.format(PF, e))
d['mapping'] = str(e)
continue
try:
# refine MSA ('seqid' param. is set as in PolyPhen-2)
rowocc = 0.6
while True:
sliced_msa = refineMSA(sliced_msa, rowocc=rowocc)
rowocc += 0.02
if sliced_msa.numSequences() <= max_seqs or rowocc >= 1:
break
ref_msa = refineMSA(sliced_msa, seqid=0.94, **kwargs)
d['ref_MSA'] = ref_msa
# compute evolutionary properties
d['entropy'] = calcShannonEntropy(ref_msa)
d['MutInfo'] = buildMutinfoMatrix(ref_msa)
# d['DirInfo'] = buildDirectInfoMatrix(ref_msa)
except Exception as e:
LOGGER.warn('{}: {}'.format(PF, e))
return {k: self.Pfam[k] for k in PF_list}
def testRowocc(self):
refined = refineMSA(FASTA, rowocc=0.9)._getArray()
expected = FASTA._getArray()[FASTA_ALPHA.sum(1) / 112.0 >= 0.9, :]
assert_array_equal(refined, expected)
def testColocc(self):
refined = refineMSA(FASTA, colocc=0.9)._getArray()
expected = FASTA._getArray()[:, FASTA_ALPHA.sum(0) / NUMSEQ >= 0.9]
assert_array_equal(refined, expected)
def testColocc(self):
refined = refineMSA(FASTA, colocc=0.9)._getArray()
expected = FASTA._getArray()[:, FASTA_ALPHA.sum(0) / NUMSEQ >= 0.9]
assert_array_equal(refined, expected)
def testRowocc(self):
refined = refineMSA(FASTA, rowocc=0.9)._getArray()
expected = FASTA._getArray()[FASTA_ALPHA.sum(1) / 112. >= 0.9, :]
assert_array_equal(refined, expected)
