def testPopulationFromCommandLineSequencesAndFastaFile(self):
"""
Using both command line sequences and --databaseFasta must result in
all the command line subjects and those in the file being added to the
returned database.
"""
parser = argparse.ArgumentParser()
specifier = DatabaseSpecifier()
specifier.addArgsToParser(parser)
args = parser.parse_args([
'--databaseFasta', 'file.fasta', '--databaseSequence', 'id1 FFF',
'--databaseSequence', 'id2 RRR'
])
data = '\n'.join(['>id3', 'FFFF', '>id4', 'RRRR'])
mockOpener = mockOpen(read_data=data)
with patch.object(builtins, 'open', mockOpener):
db = specifier.getDatabaseFromArgs(args)
allSubjects = [subject.read for subject in db.getSubjects()]
self.assertEqual(
{
AARead('id1', 'FFF'),
AARead('id2', 'RRR'),
AARead('id3', 'FFFF'),
AARead('id4', 'RRRR'),
}, set(allSubjects))
def testPopulationNotAllowed(self):
"""
Using --databaseFasta must result in a ValueError if database
population has not been enabled.
"""
parser = argparse.ArgumentParser()
specifier = DatabaseSpecifier(allowPopulation=False)
specifier.addArgsToParser(parser)
def testNoArgs(self):
"""
If no arguments are given, getDatabaseFromArgs must return a database.
"""
parser = argparse.ArgumentParser()
specifier = DatabaseSpecifier()
specifier.addArgsToParser(parser)
args = parser.parse_args([])
db = specifier.getDatabaseFromArgs(args)
self.assertIsInstance(db, Database)
def testPassedParamsAreUsed(self):
"""
If specific parameters are given, they must be used.
"""
parser = argparse.ArgumentParser()
specifier = DatabaseSpecifier()
specifier.addArgsToParser(parser)
args = parser.parse_args([])
dbParams = DatabaseParameters()
db = specifier.getDatabaseFromArgs(args, dbParams)
self.assertIs(db.dbParams, dbParams)
def testNoArgsDefaultParameters(self):
"""
The database returned from getDatabaseFromKeywords when it is
passed no keywords must have the default database parameters.
"""
parser = argparse.ArgumentParser()
specifier = DatabaseSpecifier()
specifier.addArgsToParser(parser)
args = parser.parse_args([])
db = specifier.getDatabaseFromArgs(args)
self.assertIs(None, db.dbParams.compare(DatabaseParameters()))
def testPopulationByInMemorySubjects(self):
"""
Passing a subjects keyword must result in the subjects being added
to the returned database.
"""
subjects = Reads()
subject1 = AARead('id1', 'FFF')
subject2 = AARead('id2', 'RRR')
subjects.add(subject1)
subjects.add(subject2)
db = DatabaseSpecifier().getDatabaseFromKeywords(subjects=subjects)
allSubjects = [subject.read for subject in db.getSubjects()]
self.assertEqual({subject1, subject2}, set(allSubjects))
def testCreationNotAllowed(self):
"""
Not passing any arguments when creation (or a WAMP connection)
is not allowed must result in a RuntimeError.
"""
parser = argparse.ArgumentParser()
specifier = DatabaseSpecifier(allowCreation=False, allowWamp=False)
specifier.addArgsToParser(parser)
args = parser.parse_args([])
error = ('^Not enough information given to specify a database, '
'database creation is not enabled, and '
'no remote WAMP database could be found\.$')
six.assertRaisesRegex(self, RuntimeError, error,
specifier.getDatabaseFromArgs, args)
def testPopulationFromCommandLineSequences(self):
"""
Passing --databaseSequence arguments must result in the subjects in the
sequences being added to the returned database.
"""
parser = argparse.ArgumentParser()
specifier = DatabaseSpecifier()
specifier.addArgsToParser(parser)
args = parser.parse_args(
['--databaseSequence', 'id1 FFF', '--databaseSequence', 'id2 RRR'])
db = specifier.getDatabaseFromArgs(args)
allSubjects = [subject.read for subject in db.getSubjects()]
self.assertEqual(
{AARead('id1', 'FFF'), AARead('id2', 'RRR')}, set(allSubjects))
def testPopulationFromFastaFile(self):
"""
Passing a databaseFasta keyword must result in the subjects in the
file being added to the returned database.
"""
data = '\n'.join(['>id1', 'FFF', '>id2', 'RRR'])
mockOpener = mockOpen(read_data=data)
with patch.object(builtins, 'open', mockOpener):
db = DatabaseSpecifier().getDatabaseFromKeywords(
databaseFasta='file.fasta')
allSubjects = [subject.read for subject in db.getSubjects()]
self.assertEqual(
{AARead('id1', 'FFF'), AARead('id2', 'RRR')}, set(allSubjects))
def testInMemoryDatabaseIsPopulated(self):
"""
Passing a database keyword with an in-memory database results in that
database being populated.
"""
original = Database()
subjects = Reads()
subject1 = AARead('id1', 'FFF')
subject2 = AARead('id2', 'RRR')
subjects.add(subject1)
subjects.add(subject2)
db = DatabaseSpecifier().getDatabaseFromKeywords(database=original,
subjects=subjects)
allSubjects = [subject.read for subject in db.getSubjects()]
self.assertEqual({subject1, subject2}, set(allSubjects))
def getFractionOfStructuresCovered(self):
"""
Return the fraction of known structures matched by at least one
substring in the subset that is being evaluated.
"""
hit = 0
total = 0
db = DatabaseSpecifier().getDatabaseFromKeywords(
trigPoints=[],
landmarks=['AC ' + self.structureType],
acAlphaHelixFilename=self.acAlphaHelixFilename,
acAlphaHelix310Filename=self.acAlphaHelix310Filename,
acAlphaHelixCombinedFilename=self.acAlphaHelixCombinedFilename,
acAlphaHelixPiFilename=self.acAlphaHelixPiFilename,
acExtendedStrandFilename=self.acExtendedStrandFilename)
backend = Backend()
backend.configure(db.dbParams)
for read in FastaReads(self.structureFile,
readClass=AAReadWithX,
checkAlphabet=0):
total += 1
scannedRead = backend.scan(read)
if len(scannedRead.landmarks) > 0:
hit += 1
return hit / total if total else 0.0
def testNoKeywordsDefaultParameters(self):
"""
The database returned from getDatabaseFromKeywords when it is
passed no keywords must have the default database parameters.
"""
db = DatabaseSpecifier().getDatabaseFromKeywords()
self.assertIs(None, db.dbParams.compare(DatabaseParameters()))
def testNoKeywords(self):
"""
The getDatabaseFromKeywords method must return a database when
it is passed no keywords.
"""
db = DatabaseSpecifier().getDatabaseFromKeywords()
self.assertIsInstance(db, Database)
def testPopulationFromFastaFile(self):
"""
Passing a --databaseFasta argument must result in the subjects in the
file being added to the returned database.
"""
parser = argparse.ArgumentParser()
specifier = DatabaseSpecifier()
specifier.addArgsToParser(parser)
args = parser.parse_args(['--databaseFasta', 'file.fasta'])
data = '\n'.join(['>id1', 'FFF', '>id2', 'RRR'])
mockOpener = mockOpen(read_data=data)
with patch.object(builtins, 'open', mockOpener):
db = specifier.getDatabaseFromArgs(args)
allSubjects = [subject.read for subject in db.getSubjects()]
self.assertEqual(
{AARead('id1', 'FFF'), AARead('id2', 'RRR')}, set(allSubjects))
def testInMemoryDatabaseIsReturned(self):
"""
Passing a database keyword with an in-memory database results in that
database being returned.
"""
original = Database()
db = DatabaseSpecifier().getDatabaseFromKeywords(database=original)
self.assertIs(original, db)
def testCreationNotAllowed(self):
"""
Not passing a database keyword when creation (or a WAMP connection)
is not allowed must result in a RuntimeError.
"""
specifier = DatabaseSpecifier(allowCreation=False, allowWamp=False)
error = ('^Not enough information given to specify a database, '
'database creation is not enabled, and '
'no remote WAMP database could be found\.$')
six.assertRaisesRegex(self, RuntimeError, error,
specifier.getDatabaseFromKeywords)
def testPopulationNotAllowed(self):
"""
Passing a subjects keyword must result in a ValueError if database
population has not been enabled.
"""
subjects = Reads()
specifier = DatabaseSpecifier(allowPopulation=False)
error = '^Database population is not enabled.$'
six.assertRaisesRegex(self,
ValueError,
error,
specifier.getDatabaseFromKeywords,
subjects=subjects)
def testInMemoryDatabaseNotAllowed(self):
"""
Passing a database keyword results in a ValueError if an in-memory
database is not allowed.
"""
original = Database()
specifier = DatabaseSpecifier(allowInMemory=False)
error = '^In-memory database specification not enabled.$'
six.assertRaisesRegex(self,
ValueError,
error,
specifier.getDatabaseFromKeywords,
database=original)
def testPopulationFromInMemoryAndFastaFile(self):
"""
Passing both subjects and databaseFasta keywords must result in
all the subjects in memory and in the file being added to the returned
database.
"""
subjects = Reads()
subject1 = AARead('id1', 'FFF')
subject2 = AARead('id2', 'RRR')
subjects.add(subject1)
subjects.add(subject2)
data = '\n'.join(['>id3', 'FFFF', '>id4', 'RRRR'])
mockOpener = mockOpen(read_data=data)
with patch.object(builtins, 'open', mockOpener):
db = DatabaseSpecifier().getDatabaseFromKeywords(
subjects=subjects, databaseFasta='file.fasta')
allSubjects = [subject.read for subject in db.getSubjects()]
self.assertEqual(
{subject1, subject2,
AARead('id3', 'FFFF'),
AARead('id4', 'RRRR')}, set(allSubjects))
def __init__(self, **kwargs):
# Set default landmark and trig point finders.
if 'landmarks' not in kwargs:
kwargs['landmarks'] = ALL_LANDMARK_CLASSES + [
c for c in DEV_LANDMARK_CLASSES if c.NAME.startswith('PDB ')
]
if 'trigPoints' not in kwargs:
kwargs['trigPoints'] = [
c for c in ALL_TRIG_CLASSES if c.NAME != 'Volume'
]
db = DatabaseSpecifier().getDatabaseFromKeywords(**kwargs)
self._backend = Backend()
self._backend.configure(db.dbParams)
self._names = (db.dbParams.landmarkFinderNames() +
db.dbParams.trigPointFinderNames())
def affinityMatrix(queries,
findParams=None,
subjects=None,
symmetric=True,
computeDiagonal=False,
diagonalValue=1.0,
progressFunc=None,
returnDict=False,
returnAnalysis=False,
**kwargs):
"""
Produce an affinity matrix containing scores for a set of reads matched
against a set of subjects.
@param queries: Either A C{str} filename of sequences to consider or
a C{light.reads.Reads} instance.
@param findParams: A C{light.parameters.FindParameters} instance.
@param subjects: Either 1) a C{str} filename of sequences to consider, or
2) a C{light.reads.Reads} instance, or 3) C{None}, in which case
the C{queries} will also be used as the subjects.
@param symmetric: If C{True}, corresponding off-diagonal scores will be
assumed to be equal and only computed once. I.e., this is a speedup
when scores (affinities) are symmetric. This option gives the biggest
speed up on a square matrix, but can also be used when the matrix is
not square (e.g., when making a 2x4 matrix comparing {A, B} against
{A, B, C, D}, the A->B distance can be used to set the B->A distance).
@param computeDiagonal: If C{True}, values on the diagonal will be computed
(i.e., obtained from find). Otherwise, all diagonal values will be set
to C{diagonalValue}.
@param diagonalValue: The result that diagonal values will all be set to if
C{computeDiagonal} is C{False}.
@param progressFunc: If not C{None}, a function that takes two arguments.
The function will be called before each query sequence is processed.
The arguments will be the C{int} (zero-based) number of the query and
the query (an AAReadWithX instance) itself.
@param returnDict: If C{True}, return a C{dict} keyed by query id, whose
values are C{dict}s keyed by subject id, whose values are C{float}
scores. In other words, a 2-level deep C{dict} that allows the caller
to look up a score via something like C{result[query.id][subject.id]}.
@param returnAnalysis: This determines what information is returned in each
affinity matrix location. If C{False}, the default, each location will
contain the overall score for the corresponding query/subject pair, or
0.0 if the query did not match the subject. If C{True}, the location
will contain the analysis C{dict} computed by the
C{light.result.Result} instance, or C{None} if the query did not match
the subject.
@param kwargs: See
C{database.DatabaseSpecifier.getDatabaseFromKeywords} for
additional keywords, all of which are optional.
@raise ValueError: If C{returnDict} is C{True} and there is a duplicated
query or subject id.
@return: If C{returnDict} is C{True}, a C{dict} as described above, else a
two-dimensional array whose dimensions are the query index (in
C{queries}, and then the subject index (in C{subjects}). The values in
the returned structure are as described in C{returnAnalysis}, above.
"""
if isinstance(queries, str):
queries = list(
FastaReads(queries, readClass=AAReadWithX, upperCase=True))
if subjects is None:
subjects = queries
else:
if isinstance(subjects, str):
subjects = list(
FastaReads(subjects, readClass=AAReadWithX, upperCase=True))
findParams = findParams or FindParameters()
db = DatabaseSpecifier().getDatabaseFromKeywords(**kwargs)
subjectIndices = []
for subject in subjects:
_, subjectIndex, _ = db.addSubject(subject)
subjectIndices.append(subjectIndex)
nQueries = len(queries)
nSubjects = len(subjectIndices)
# Prepare a result array (we'll walk through this later to make a dict
# if returnDict is True).
affinity = []
noMatchValue = None if returnAnalysis else 0.0
for _ in range(nQueries):
affinity.append([noMatchValue] * nSubjects)
for i, query in enumerate(queries):
if progressFunc:
progressFunc(i, query)
if symmetric:
# We don't have to consider all subjects in the find, so pass a
# restricted set of subject indices to restrict the search to.
# The ones we omit have already been looked up.
#
# For clarity, there's a little code repetition here.
if computeDiagonal:
wantedIndices = set(subjectIndices[i:])
else:
wantedIndices = set(subjectIndices[i + 1:])
result = db.find(query,
findParams,
storeFullAnalysis=returnAnalysis,
subjectIndices=wantedIndices)
else:
result = db.find(query,
findParams,
storeFullAnalysis=returnAnalysis)
analysis = result.analysis
for j in range(nSubjects):
if j < i and symmetric:
score = affinity[j][i]
elif j == i and not computeDiagonal:
score = diagonalValue
else:
# Be careful how we access the analysis. It is a defaultdict,
# so its keys are created on access. I.e., we must use 'in'
# to test for membership not try/except, because
# analysis[subjectIndex] will never raise a KeyError.
if subjectIndices[j] in analysis:
if returnAnalysis:
score = analysis[subjectIndices[j]]
else:
score = analysis[subjectIndices[j]]['overallScore']
else:
# The query didn't match the subject. We don't actually
# need to set this value as it is already present due
# to the initialization of affinity above, but it
# simplifies the code to do so.
score = noMatchValue
affinity[i][j] = score
if returnDict:
result = {}
for i, query in enumerate(queries):
if query.id in result:
raise ValueError('Query id %r appears more than once.' %
query.id)
result[query.id] = values = {}
for j, subject in enumerate(subjects):
if subject.id in values:
raise ValueError('Subject id %r appears more than once.' %
subject.id)
values[subject.id] = affinity[i][j]
return result
else:
return affinity
#!/usr/bin/env python
import argparse
from autobahn.asyncio.wamp import ApplicationRunner
from light.autobahn.database import DatabaseComponent
from light.database import DatabaseSpecifier
if __name__ == '__main__':
parser = argparse.ArgumentParser(
description='Start a WAMP-based distributed light-matter database.')
databaseSpecifier = DatabaseSpecifier(allowInMemory=False)
databaseSpecifier.addArgsToParser(parser)
args = parser.parse_args()
# We're always using WAMP for distributed databases.
args.wampServer = True
database = databaseSpecifier.getDatabaseFromArgs(args)
runner = ApplicationRunner(args.wampUrl,
args.realm,
extra=dict(database=database))
runner.run(DatabaseComponent)
def __init__(self, sequences, cutoff, **kwargs):
"""
A class to work with hashes.
For a set of given sequences, find all hashes and for each sequence
make a string of 1 or 0 denoting whether a hash is present in that
sequence or not. Only include hashes if they occur in more than at '
least a specified percentage of all given sequences.
@param sequences: A C{str} filename with a fasta file of sequences to
be used or a C{dark.reads.Reads} object.
@param cutoff: A C{float} between 0.0 and 1.0 of the fraction of
sequences in which a hash has to be present to be included in the
final string.
@param kwargs: See
C{database.DatabaseSpecifier.getDatabaseFromKeywords} for
additional keywords, all of which are optional.
"""
if isinstance(sequences, str):
reads = FastaReads(sequences,
readClass=AAReadWithX,
upperCase=True)
else:
reads = sequences
database = DatabaseSpecifier().getDatabaseFromKeywords(**kwargs)
backend = Backend()
backend.configure(database.dbParams)
# Make a dictionary where the keys are the sequence ids and the value
# is an orderedDict of hashes as returned from getHashes().
hashes = {}
for read in reads:
scannedRead = backend.scan(read)
readHashes = backend.getHashes(scannedRead)
hashes[read.id] = readHashes
# Make a list of all unique hashes that occur.
totalHashes = set()
for read in hashes:
totalHashes.update(hashes[read].keys())
# Make a dictionary where the key is a hash and the value is a list of
# the reads in which the hash occurs.
byHashes = {}
for hash_ in totalHashes:
viruses = []
for readId in hashes:
try:
hashes[readId][hash_]
except KeyError:
continue
viruses.append(readId)
byHashes[hash_] = viruses
# Make a dictionary where the key is a readId and the value is a string
# of 1 and 0 denoting which hashes occur in which read.
co = cutoff * len(reads)
self.hashString = {read.id: '' for read in reads}
for hash_ in byHashes:
if len(byHashes[hash_]) > co:
for virus in self.hashString:
if virus in byHashes[hash_]:
self.hashString[virus] += '1'
else:
self.hashString[virus] += '0'
#!/usr/bin/env python
import sys
import argparse
from autobahn.asyncio.wamp import ApplicationRunner
from light.autobahn.backend import BackendComponent
from light.database import DatabaseSpecifier
if sys.version_info < (3, 3):
raise Exception('The light matter autobahn code needs Python 3.3 or '
'later.')
if __name__ == '__main__':
parser = argparse.ArgumentParser(
description=('Start a WAMP-based distributed light-matter database '
'backend.'))
databaseSpecifier = DatabaseSpecifier(allowInMemory=False)
databaseSpecifier.addArgsToParser(parser)
args = parser.parse_args()
runner = ApplicationRunner(args.wampUrl, args.realm, extra=dict(args=args))
runner.run(BackendComponent)
def __init__(self, sequences, labels, defaultLabel=None, **kwargs):
"""
Base class for using cluster analysis to evaluate how well various
feature finders and database parameter settings can separate a set of
sequences. The clustering is based on feature offset deltas.
@param sequences: Either A C{str} filename of sequences to consider or
a C{light.reads.Reads} instance.
@param labels: A C{dict} with a label for each sequence id in
C{sequences}. These are the known categories of each sequence.
@param defaultLabel: If not C{None}, a label to use for reads whose ids
are not present in C{labels}. If C{None} and a read id has no label
a ValueError is raised.
@param kwargs: See
C{database.DatabaseSpecifier.getDatabaseFromKeywords} for
additional keywords, all of which are optional.
@raises ValueError: If the id of a read is not in labels and no default
label has been set, or if there are no reads in C{sequences}.
"""
if isinstance(sequences, str):
reads = FastaReads(sequences,
readClass=AAReadWithX,
upperCase=True)
else:
reads = sequences
database = DatabaseSpecifier().getDatabaseFromKeywords(**kwargs)
backend = Backend()
backend.configure(database.dbParams)
allOffsetDeltas = []
trueLabels = []
for read in reads:
trueLabel = labels.get(read.id, defaultLabel)
if trueLabel is None:
raise ValueError('Read %r has no corresponding label' %
read.id)
trueLabels.append(trueLabel)
offsetDeltas = Counter()
scannedRead = backend.scan(read)
for landmark, trigPoint in backend.getScannedPairs(scannedRead):
delta = scaleLog(trigPoint.offset - landmark.offset,
database.dbParams.distanceBase)
offsetDeltas[delta] += 1
allOffsetDeltas.append(offsetDeltas)
nReads = len(reads)
if nReads == 0:
raise ValueError('No sequences were found in %r' % sequences)
# Don't check that len(reads) == len(labels). I.e., ignore extra labels
# to make using this class interactively more convenient.
# Create an affinity matrix. Initially set all values to 1.0 so we
# don't need to later initialize the diagonal.
affinity = np.ones((nReads, nReads))
for row, offsetDeltas in enumerate(allOffsetDeltas):
for col in range(row + 1, nReads):
affinity[row,
col] = affinity[col,
row] = (self.affinityFromOffsetDeltas(
allOffsetDeltas[row],
allOffsetDeltas[col]))
self.nReads = nReads
self.affinity = affinity
self.trueLabels = trueLabels
