def setUp(self):
super(TestChainSequence, self).setUp()
from csb.bio.structure import ProteinResidue, Chain
chain = Chain('A', name='desc', accession='accn')
for rank, char in enumerate('AB-CD', start=1):
chain.residues.append(ProteinResidue(rank, char))
self.sequence = sequence.ChainSequence.create(chain)
self.sequence.header = '>id desc'
self.sequence.id = 'id'
def write_ensemble(X, filename, mol_ranges=None, center=True):
"""Writes a structure ensemble to a PDB file.
:param X: coordinates of a structure ensemble
:type X: :class:`numpy.ndarray`
:param filename: file name of output PDB file
:type filename: str
:param mol_ranges: if writing structures consisting of several molecules, this
specifies start and end beads of the single molecules. Example: [0, 9, 19] for two molecules of 10 beads each
:type mol_ranges: :class:`numpy.ndarray`
:param center: if True, aligns the centers of mass of all structures
:type center: bool
"""
from csb.bio.structure import Atom, ProteinResidue, Chain, Structure, Ensemble
from csb.bio.sequence import ProteinAlphabet
if center:
X -= X.mean(1)[:, None, :]
if mol_ranges is None:
mol_ranges = np.array([0, X.shape[1]])
ensemble = Ensemble()
for i, x in enumerate(X):
structure = Structure('')
structure.model_id = i + 1
mol_coordinates = np.array([
x[start:end] for start, end in zip(mol_ranges[:-1], mol_ranges[1:])
])
for j, mol in enumerate(mol_coordinates):
structure.chains.append(Chain(chr(65 + j)))
for k, y in enumerate(mol):
atom = Atom(k + 1, 'CA', 'C', y)
residue = ProteinResidue(k, 'ALA')
residue.atoms.append(atom)
structure.chains[chr(65 + j)].residues.append(residue)
ensemble.models.append(structure)
ensemble.to_pdb(filename)
def test(type):
self.layer.residue = ProteinResidue(1, type=type)
def build_hmm():
hmm = ProfileHMM(units=ScoreUnits.Probability)
factory = StateFactory()
background = OrderedDict([(ProteinAlphabet.ALA, 0.02457563),
(ProteinAlphabet.CYS, 0.00325358),
(ProteinAlphabet.GLU, 0.01718016)])
emission = dict((aa, 1.0 / i) for i, aa in enumerate(background, start=1))
# States
# Start / End
hmm.start = State(States.Start)
hmm.start_insertion = factory.create_insertion(background)
hmm.end = State(States.End)
# L1
match1 = factory.create_match(emission, background)
insertion1 = factory.create_insertion(background)
deletion1 = factory.create_deletion()
states = {
States.Match: match1,
States.Insertion: insertion1,
States.Deletion: deletion1
}
layer1 = HMMLayer(1, ProteinResidue(1, ProteinAlphabet.ALA), states)
hmm.layers.append(layer1)
# L2
match2 = factory.create_match(emission, background)
insertion2 = factory.create_insertion(background)
deletion2 = factory.create_deletion()
states = {
States.Match: match2,
States.Insertion: insertion2,
States.Deletion: deletion2
}
layer2 = HMMLayer(2, ProteinResidue(2, ProteinAlphabet.CYS), states)
hmm.layers.append(layer2)
# Transitions
# start
hmm.start.transitions.append(Transition(hmm.start, match1, 0.8))
hmm.start.transitions.append(Transition(hmm.start, deletion1, 0.1))
hmm.start.transitions.append(
Transition(hmm.start, hmm.start_insertion, 0.1))
hmm.start_insertion.transitions.append(
Transition(hmm.start_insertion, hmm.start_insertion, 0.5))
hmm.start_insertion.transitions.append(
Transition(hmm.start_insertion, match1, 0.5))
# L1
match1.transitions.append(Transition(match1, match2, 0.8))
match1.transitions.append(Transition(match1, insertion1, 0.1))
match1.transitions.append(Transition(match1, deletion2, 0.1))
insertion1.transitions.append(Transition(insertion1, insertion1, 0.5))
insertion1.transitions.append(Transition(insertion1, match2, 0.5))
deletion1.transitions.append(Transition(deletion1, deletion2, 0.5))
deletion1.transitions.append(Transition(deletion1, match2, 0.5))
# L2
match2.transitions.append(Transition(match2, hmm.end, 0.9))
match2.transitions.append(Transition(match2, insertion2, 0.1))
insertion2.transitions.append(Transition(insertion2, insertion2, 0.5))
insertion2.transitions.append(Transition(insertion2, hmm.end, 0.5))
deletion2.transitions.append(Transition(deletion2, hmm.end, 1.0))
hmm.effective_matches = 10
hmm.version = 1.5
hmm.name = 'name'
hmm.id = 'id'
hmm.family = 'fam'
hmm.length = ProfileLength(2, 2)
return hmm