def DiscreteSubstitutionModel(*args, **kw):
deprecated("class",
"cogent.evolve.discrete_markov.DiscreteSubstitutionModel",
"cogent.evolve.substitution_model.DiscreteSubstitutionModel",
'1.6')
from cogent.evolve.substitution_model import DiscreteSubstitutionModel
return DiscreteSubstitutionModel(*args, **kw)
def setMotifProbs(self, motif_probs, locus=None, bin=None, is_constant=None,
is_independent=None, auto=False, **kwargs):
if 'is_const' in kwargs:
is_constant = kwargs.pop('is_const')
deprecated('argument', 'is_const', 'is_constant', 1.6)
motif_probs = self.model.adaptMotifProbs(motif_probs, auto=auto)
if is_constant is None:
is_constant = not self.optimise_motif_probs
self.model.setParamControllerMotifProbs(self, motif_probs,
is_constant=is_constant, bin=bin, locus=locus,
is_independent=is_independent, **kwargs)
if not auto:
self.mprobs_from_alignment = False # should be done per-locus
def setMotifProbsFromData(self, align, locus=None, is_constant=None,
include_ambiguity=False, is_independent=None, auto=False,
pseudocount=None, **kwargs):
if 'is_const' in kwargs:
is_constant = kwargs.pop('is_const')
deprecated('argument', 'is_const', 'is_constant', 1.6)
counts = self.model.countMotifs(align,
include_ambiguity=include_ambiguity)
if is_constant is None:
is_constant = not self.optimise_motif_probs
if pseudocount is None:
if is_constant:
pseudocount = 0.0
else:
pseudocount = 0.5
counts += pseudocount
mprobs = counts/(1.0*sum(counts))
self.setMotifProbs(mprobs, locus=locus, is_constant=is_constant,
is_independent=is_independent, auto=auto, **kwargs)
def setParamRule(self, par_name, is_independent=None, is_constant=False,
value=None, lower=None, init=None, upper=None, **scope_info):
"""Define a model constraint for par_name. Parameters can be set
constant or split according to tree/bin scopes.
Arguments:
- par_name: The model parameter being modified.
- is_constant, value: if True, the parameter is held constant at
value, if provided, or the likelihood functions current value.
- is_independent: whether the partition specified by scope/bin
arguments are to be considered independent.
- lower, init, upper: specify the lower bound, initial value and
upper bound for optimisation. Can be set separately.
- bin, bins: the name(s) of the bin to apply rule.
- locus, loci: the name of the locus/loci to apply rule.
- **scope_info: tree scope arguments
- edge, edges: The name of the tree edge(s) affected by rule. ??
- tip_names: a tuple of two tip names, specifying a tree scope
to apply rule.
- outgroup_name: A tip name that, provided along with tip_names,
ensures a consistently specified tree scope.
- is_clade: The rule applies to all edges descending from the most
recent common ancestor defined by the tip_names+outgroup_name
arguments.
- is_stem: The rule applies to the edge preceding the most recent
common ancestor defined by the tip_names+outgroup_name
arguments.
"""
if 'is_const' in scope_info:
is_constant = scope_info.pop('is_const')
deprecated('argument', 'is_const', 'is_constant', 1.6)
par_name = str(par_name)
scopes = {}
for (single, plural) in [
('bin', 'bins'),
('locus', 'loci'),
('position', 'positions'),
('motif', 'motifs'),
]:
if single in scope_info:
v = scope_info.pop(single)
if v:
assert isinstance(v, basestring), ('%s=, maybe?' % plural)
assert plural not in scope_info
scopes[single] = [v]
elif plural in scope_info:
v = scope_info.pop(plural)
if v:
scopes[single] = v
edges = self._process_scope_info(**scope_info)
if edges:
scopes['edge'] = edges
if is_constant:
assert not (init or lower or upper)
elif init is not None:
assert not value
value = init
self.assignAll(par_name, scopes, value, lower, upper, is_constant,
is_independent)
def setParamRule(self, par_name, is_independent=None, is_constant=False,
value=None, lower=None, init=None, upper=None, **scope_info):
"""Define a model constraint for par_name. Parameters can be set
constant or split according to tree/bin scopes.
Arguments:
- par_name: The model parameter being modified.
- is_constant, value: if True, the parameter is held constant at
value, if provided, or the likelihood functions current value.
- is_independent: whether the partition specified by scope/bin
arguments are to be considered independent.
- lower, init, upper: specify the lower bound, initial value and
upper bound for optimisation. Can be set separately.
- bin, bins: the name(s) of the bin to apply rule.
- locus, loci: the name of the locus/loci to apply rule.
- **scope_info: tree scope arguments
- edge, edges: The name of the tree edge(s) affected by rule. ??
- tip_names: a tuple of two tip names, specifying a tree scope
to apply rule.
- outgroup_name: A tip name that, provided along with tip_names,
ensures a consistently specified tree scope.
- is_clade: The rule applies to all edges descending from the most
recent common ancestor defined by the tip_names+outgroup_name
arguments.
- is_stem: The rule applies to the edge preceding the most recent
common ancestor defined by the tip_names+outgroup_name
arguments.
"""
if 'is_const' in scope_info:
is_constant = scope_info.pop('is_const')
deprecated('argument', 'is_const', 'is_constant', 1.6)
par_name = str(par_name)
scopes = {}
for (single, plural) in [
('bin', 'bins'),
('locus', 'loci'),
('position', 'positions'),
('motif', 'motifs'),
]:
if single in scope_info:
v = scope_info.pop(single)
if v:
assert isinstance(v, basestring), ('%s=, maybe?' % plural)
assert plural not in scope_info
scopes[single] = [v]
elif plural in scope_info:
v = scope_info.pop(plural)
if v:
scopes[single] = v
edges = self._process_scope_info(**scope_info)
if edges:
scopes['edge'] = edges
if is_constant:
assert not (init or lower or upper)
elif init is not None:
assert not value
value = init
self.assignAll(par_name, scopes, value, lower, upper, is_constant,
is_independent)
class Muscle(CommandLineApplication):
"""Muscle application controller"""
deprecated('class',
'cogent.app.muscle.Muscle',
'cogent.app.muscle_v38.Muscle',
'1.6')
_options ={
# Minimum spacing between anchor columns. [Integer]
'-anchorspacing':ValuedParameter('-',Name='anchorspacing',Delimiter=' '),
# Center parameter. Should be negative [Float]
'-center':ValuedParameter('-',Name='center',Delimiter=' '),
# Clustering method. cluster1 is used in iteration 1
# and 2, cluster2 in later iterations
'-cluster1':ValuedParameter('-',Name='cluster1',Delimiter=' '),
'-cluster2':ValuedParameter('-',Name='cluster2',Delimiter=' '),
# Minimum length of diagonal.
'-diaglength':ValuedParameter('-',Name='diaglength',Delimiter=' '),
# Discard this many positions at ends of diagonal.
'-diagmargin':ValuedParameter('-',Name='diagmargin',Delimiter=' '),
# Distance measure for iteration 1.
'-distance1':ValuedParameter('-',Name='distance1',Delimiter=' '),
# Distance measure for iterations 2, 3 ...
'-distance2':ValuedParameter('-',Name='distance2',Delimiter=' '),
# The gap open score. Must be negative.
'-gapopen':ValuedParameter('-',Name='gapopen',Delimiter=' '),
# Window size for determining whether a region is hydrophobic.
'-hydro':ValuedParameter('-',Name='hydro',Delimiter=' '),
# Multiplier for gap open/close penalties in hydrophobic regions.
'-hydrofactor':ValuedParameter('-',Name='hydrofactor',Delimiter=' '),
# Where to find the input sequences.
'-in':ValuedParameter('-',Name='in',Delimiter=' ', Quote="\""),
'-in1':ValuedParameter('-',Name='in1',Delimiter=' ', Quote="\""),
'-in2':ValuedParameter('-',Name='in2',Delimiter=' ', Quote="\""),
# Log file name (delete existing file).
'-log':ValuedParameter('-',Name='log',Delimiter=' '),
# Log file name (append to existing file).
'-loga':ValuedParameter('-',Name='loga',Delimiter=' '),
# Maximum distance between two diagonals that allows them to merge
# into one diagonal.
'-maxdiagbreak':ValuedParameter('-',Name='maxdiagbreak',Delimiter=' '),
# Maximum time to run in hours. The actual time may exceed the
# requested limit by a few minutes. Decimals are allowed, so 1.5
# means one hour and 30 minutes.
'-maxhours':ValuedParameter('-',Name='maxhours',Delimiter=' '),
# Maximum number of iterations.
'-maxiters':ValuedParameter('-',Name='maxiters',Delimiter=' '),
# Maximum memory in Mb
'-maxmb': ValuedParameter('-', Name='maxmb', Delimiter=' '),
# Maximum number of new trees to build in iteration 2.
'-maxtrees':ValuedParameter('-',Name='maxtrees',Delimiter=' '),
# Minimum score a column must have to be an anchor.
'-minbestcolscore':ValuedParameter('-',Name='minbestcolscore',Delimiter=' '),
# Minimum smoothed score a column must have to be an anchor.
'-minsmoothscore':ValuedParameter('-',Name='minsmoothscore',Delimiter=' '),
# Objective score used by tree dependent refinement.
# sp=sum-of-pairs score.
# spf=sum-of-pairs score (dimer approximation)
# spm=sp for < 100 seqs, otherwise spf
# dp=dynamic programming score.
# ps=average profile-sequence score.
# xp=cross profile score.
'-objscore':ValuedParameter('-',Name='objscore',Delimiter=' '),
# Where to write the alignment.
'-out':ValuedParameter('-',Name='out',Delimiter=' ', Quote="\""),
# Where to write the file in phylip sequenctial format (v3.6 only).
'-physout':ValuedParameter('-',Name='physout',Delimiter=' '),
# Where to write the file in phylip interleaved format (v3.6 only).
'-phyiout':ValuedParameter('-',Name='phyiout',Delimiter=' '),
# Set to profile for aligning two alignments and adding seqs to an
# existing alignment
'-profile':FlagParameter(Prefix='-',Name='profile'),
# Method used to root tree; root1 is used in iteration 1 and 2, root2
# in later iterations.
'-root1':ValuedParameter('-',Name='root1',Delimiter=' '),
'-root2':ValuedParameter('-',Name='root2',Delimiter=' '),
# Sequence type.
'-seqtype':ValuedParameter('-',Name='seqtype',Delimiter=' '),
# Maximum value of column score for smoothing purposes.
'-smoothscoreceil':ValuedParameter('-',Name='smoothscoreceil',Delimiter=' '),
# Constant used in UPGMB clustering. Determines the relative fraction
# of average linkage (SUEFF) vs. nearest-neighbor linkage (1 . SUEFF).
'-SUEFF':ValuedParameter('-',Name='SUEFF',Delimiter=' '),
# Save tree produced in first or second iteration to given file in
# Newick (Phylip-compatible) format.
'-tree1':ValuedParameter('-',Name='tree1',Delimiter=' ', Quote="\""),
'-tree2':ValuedParameter('-',Name='tree2',Delimiter=' ', Quote="\""),
# Sequence weighting scheme.
# weight1 is used in iterations 1 and 2.
# weight2 is used for tree-dependent refinement.
# none=all sequences have equal weight.
# henikoff=Henikoff & Henikoff weighting scheme.
# henikoffpb=Modified Henikoff scheme as used in PSI-BLAST.
# clustalw=CLUSTALW method.
# threeway=Gotoh three-way method.
'-weight1':ValuedParameter('-',Name='weight1',Delimiter=' '),
'-weight2':ValuedParameter('-',Name='weight2',Delimiter=' '),
# Use anchor optimization in tree dependent refinement iterations
'-anchors':FlagParameter(Prefix='-',Name='anchors'),
# Write output in CLUSTALW format (default is FASTA).
'-clw':FlagParameter(Prefix='-',Name='clw'),
# Cluster sequences
'-cluster':FlagParameter(Prefix='-',Name='cluster'),
# neighborjoining is "unrecognized"
#'-neighborjoining':FlagParameter(Prefix='-',Name='neighborjoining'),
# Write output in CLUSTALW format with the "CLUSTAL W (1.81)" header
# rather than the MUSCLE version. This is useful when a post-processing
# step is picky about the file header.
'-clwstrict':FlagParameter(Prefix='-',Name='clwstrict'),
# Do not catch exceptions.
'-core':FlagParameter(Prefix='-',Name='core'),
# Write output in FASTA format. Alternatives include .clw,
# .clwstrict, .msf and .html.
'-fasta':FlagParameter(Prefix='-',Name='fasta'),
# Group similar sequences together in the output. This is the default.
# See also .stable.
'-group':FlagParameter(Prefix='-',Name='group'),
# Write output in HTML format (default is FASTA).
'-html':FlagParameter(Prefix='-',Name='html'),
# Use log-expectation profile score (VTML240). Alternatives are to use
# -sp or -sv. This is the default for amino acid sequences.
'-le':FlagParameter(Prefix='-',Name='le'),
# Write output in MSF format (default is FASTA).
'-msf':FlagParameter(Prefix='-',Name='msf'),
# Disable anchor optimization. Default is -anchors.
'-noanchors':FlagParameter(Prefix='-',Name='noanchors'),
# Catch exceptions and give an error message if possible.
'-nocore':FlagParameter(Prefix='-',Name='nocore'),
# Do not display progress messages.
'-quiet':FlagParameter(Prefix='-',Name='quiet'),
# Input file is already aligned, skip first two iterations and begin
# tree dependent refinement.
'-refine':FlagParameter(Prefix='-',Name='refine'),
# Use sum-of-pairs protein profile score (PAM200). Default is -le.
'-sp':FlagParameter(Prefix='-',Name='sp'),
# Use sum-of-pairs nucleotide profile score (BLASTZ parameters). This
# is the only option for nucleotides, and is therefore the default.
'-spn':FlagParameter(Prefix='-',Name='spn'),
# Preserve input order of sequences in output file. Default is to group
# sequences by similarity (-group).
'-stable':FlagParameter(Prefix='-',Name='stable'),
# Use sum-of-pairs profile score (VTML240). Default is -le.
'-sv':FlagParameter(Prefix='-',Name='sv'),
# Diagonal optimization
'-diags':FlagParameter(Prefix='-',Name='diags'),
'-diags1':FlagParameter(Prefix='-',Name='diags1'),
'-diags2':FlagParameter(Prefix='-',Name='diags2'),
# Terminal gaps penalized with full penalty.
# [1] Not fully supported in this version.
'-termgapsfull':FlagParameter(Prefix='-',Name='termgapsfull'),
# Terminal gaps penalized with half penalty.
# [1] Not fully supported in this version.
'-termgapshalf':FlagParameter(Prefix='-',Name='termgapshalf'),
# Terminal gaps penalized with half penalty if gap relative to
# longer sequence, otherwise with full penalty.
# [1] Not fully supported in this version.
'-termgapshalflonger':FlagParameter(Prefix='-',Name='termgapshalflonger'),
# Write parameter settings and progress messages to log file.
'-verbose':FlagParameter(Prefix='-',Name='verbose'),
# Write version string to stdout and exit.
'-version':FlagParameter(Prefix='-',Name='version'),
}
_parameters = {}
_parameters.update(_options)
_command = "muscle"
def _input_as_seqs(self,data):
lines = []
for i,s in enumerate(data):
#will number the sequences 1,2,3,etc.
lines.append(''.join(['>',str(i+1)]))
lines.append(s)
return self._input_as_lines(lines)
def _input_as_lines(self,data):
if data:
self.Parameters['-in']\
.on(super(Muscle,self)._input_as_lines(data))
return ''
def _input_as_string(self,data):
"""Makes data the value of a specific parameter
This method returns the empty string. The parameter will be printed
automatically once set.
"""
if data:
self.Parameters['-in'].on(str(data))
return ''
def _input_as_multiline_string(self, data):
if data:
self.Parameters['-in']\
.on(super(Muscle,self)._input_as_multiline_string(data))
return ''
def _input_as_multifile(self, data):
"""For use with the -profile option
This input handler expects data to be a tuple containing two
filenames. Index 0 will be set to -in1 and index 1 to -in2
"""
if data:
try:
filename1, filename2 = data
except:
raise ValueError("Expected two filenames")
self.Parameters['-in'].off()
self.Parameters['-in1'].on(filename1)
self.Parameters['-in2'].on(filename2)
return ''
def _align_out_filename(self):
if self.Parameters['-out'].isOn():
aln_filename = self._absolute(str(self.Parameters['-out'].Value))
else:
raise ValueError("No output file specified.")
return aln_filename
def _tree1_out_filename(self):
if self.Parameters['-tree1'].isOn():
aln_filename = self._absolute(str(self.Parameters['-tree1'].Value))
else:
raise ValueError("No tree output file specified.")
return aln_filename
def _tree2_out_filename(self):
if self.Parameters['-tree2'].isOn():
tree_filename = self._absolute(str(self.Parameters['-tree2'].Value))
else:
raise ValueError("No tree output file specified.")
return tree_filename
def _get_result_paths(self,data):
result = {}
if self.Parameters['-out'].isOn():
out_name = self._align_out_filename()
result['MuscleOut'] = ResultPath(Path=out_name,IsWritten=True)
if self.Parameters['-tree1'].isOn():
out_name = self._tree1_out_filename()
result['Tree1Out'] = ResultPath(Path=out_name,IsWritten=True)
if self.Parameters['-tree2'].isOn():
out_name = self._tree2_out_filename()
result['Tree2Out'] = ResultPath(Path=out_name,IsWritten=True)
return result
def getHelp(self):
"""Muscle help"""
help_str = """
"""
return help_str
def getLocalViterbiScoreAndAlignment(self, posterior_probs=False, **kw):
deprecated('method', 'getLocalViterbiScoreAndAlignment',
'getViterbiScoreAndAlignment(local=True)', '1.7', stack_level=3)
kw['posterior_probs'] = posterior_probs
return self.getViterbiScoreAndAlignment(local=True, **kw)
def testfunction(self):
deprecated('method', 'testfunction','getLogLikelihood', '1.6')
return self.getLogLikelihood()
def setpar(self, param_name, value, edge=None, **scope):
deprecated('method', 'setpar','setParamRule', '1.6')
return self.setParamRule(param_name, edge=edge, value=value, is_constant=True, **scope)
def testfunction(self):
deprecated('method', 'testfunction', 'getLogLikelihood', '1.6')
return self.getLogLikelihood()
