def makeForwardTreeDefn(subst_model, tree, bin_names,
with_indel_params=True, kn=True):
"""Pairwise Fwd"""
indel = makeIndelModelDefn(with_indel_params, kn)
subst = subst_model.makeFundamentalParamControllerDefns(bin_names)
leaf = NonParamDefn('leaf', dimensions=('edge',))
if len(bin_names) > 1:
switch = ProbabilityParamDefn('bin_switch', dimensions=['locus'])
bprobs = PartitionDefn(
[1.0/len(bin_names) for bin in bin_names], name = "bprobs",
dimensions=['locus'], dimension=('bin', bin_names))
edge_args = [switch, bprobs]
edge_defn_constructor = EdgeSumAndAlignDefnWithBins
else:
edge_args = []
edge_defn_constructor = EdgeSumAndAlignDefn
mprobs = subst['word_probs']
bin_data = CalcDefn(BinData)(mprobs, indel, subst['Qd'])
bin_data = bin_data.acrossDimension('bin', bin_names)
edge_args.extend(bin_data)
(top, scores) = _recursive_defns(tree, subst, leaf, edge_defn_constructor,
edge_args)
defn = FwdDefn(top)
#defn = SumDefn(*scores)
return AnnotateFloatDefn(defn, top)
def makeForwardTreeDefn(subst_model,
tree,
bin_names,
with_indel_params=True,
kn=True):
"""Pairwise Fwd"""
indel = makeIndelModelDefn(with_indel_params, kn)
subst = subst_model.makeFundamentalParamControllerDefns(bin_names)
leaf = NonParamDefn('leaf', dimensions=('edge', ))
if len(bin_names) > 1:
switch = ProbabilityParamDefn('bin_switch', dimensions=['locus'])
bprobs = PartitionDefn([1.0 / len(bin_names) for bin in bin_names],
name="bprobs",
dimensions=['locus'],
dimension=('bin', bin_names))
edge_args = [switch, bprobs]
edge_defn_constructor = EdgeSumAndAlignDefnWithBins
else:
edge_args = []
edge_defn_constructor = EdgeSumAndAlignDefn
mprobs = subst['word_probs']
bin_data = CalcDefn(BinData)(mprobs, indel, subst['Qd'])
bin_data = bin_data.acrossDimension('bin', bin_names)
edge_args.extend(bin_data)
(top, scores) = _recursive_defns(tree, subst, leaf, edge_defn_constructor,
edge_args)
defn = FwdDefn(top)
#defn = SumDefn(*scores)
return AnnotateFloatDefn(defn, top)
def makeTotalLogLikelihoodDefn(tree, leaves, psubs, mprobs, bprobs, bin_names,
locus_names, sites_independent):
fixed_motifs = NonParamDefn('fixed_motif', ['edge'])
lht = LikelihoodTreeDefn(leaves, tree=tree)
# Split up the alignment columns between the available CPUs.
parallel_context = NonParamDefn('parallel_context')
lht = LikelihoodTreeAlignmentSplitterDefn(parallel_context, lht)
plh = makePartialLikelihoodDefns(tree, lht, psubs, fixed_motifs)
# After the root partial likelihoods have been calculated it remains to
# sum over the motifs, local sites, other sites (ie: cpus), bins and loci.
# The motifs are always done first, but after that it gets complicated.
# If a bin HMM is being used then the sites from the different CPUs must
# be interleaved first, otherwise summing over the CPUs is done last to
# minimise inter-CPU communicaton.
root_mprobs = mprobs.selectFromDimension('edge', 'root')
lh = CalcDefn(numpy.inner, name='lh')(plh, root_mprobs)
if len(bin_names) > 1:
if sites_independent:
site_pattern = CalcDefn(BinnedSiteDistribution, name='bdist')(
bprobs)
else:
parallel_context = None # hmm does the gathering over CPUs
switch = ProbabilityParamDefn('bin_switch', dimensions=['locus'])
site_pattern = CalcDefn(PatchSiteDistribution, name='bdist')(
switch, bprobs)
blh = CallDefn(site_pattern, lht, name='bindex')
tll = CallDefn(blh, *lh.acrossDimension('bin', bin_names),
**dict(name='tll'))
else:
lh = lh.selectFromDimension('bin', bin_names[0])
tll = CalcDefn(log_sum_across_sites, name='logsum')(lht, lh)
if len(locus_names) > 1 or parallel_context is None:
# "or parallel_context is None" only because SelectFromDimension
# currently has no .makeParamController() method.
tll = SumDefn(*tll.acrossDimension('locus', locus_names))
else:
tll = tll.selectFromDimension('locus', locus_names[0])
if parallel_context is not None:
tll = ParallelSumDefn(parallel_context, tll)
return tll
def makeIndelModelDefn(with_indel_params=True, kn=True):
if kn:
klass = indel_model.KnudsenMiyamotoIndelModel
else:
klass = indel_model.SimpleIndelModel
if with_indel_params:
a = IndelParameterDefn('indel_length') # P(extend indel)
r = IndelParameterDefn('indel_rate') # indels per substitution
return CalcDefn(klass, name='indels')(r, a)
else:
# not optimisable parameter, a constant. Another example is the alignment in an LikFunc
return NonParamDefn('indel_model')
def makeTotalLogLikelihoodDefn(tree, leaves, psubs, mprobs, bprobs, bin_names,
locus_names, sites_independent):
fixed_motifs = NonParamDefn('fixed_motif', ['edge'])
lht = LikelihoodTreeDefn(leaves, tree=tree)
# Split up the alignment columns between the available CPUs.
parallel_context = NonParamDefn('parallel_context')
lht = LikelihoodTreeAlignmentSplitterDefn(parallel_context, lht)
plh = makePartialLikelihoodDefns(tree, lht, psubs, fixed_motifs)
# After the root partial likelihoods have been calculated it remains to
# sum over the motifs, local sites, other sites (ie: cpus), bins and loci.
# The motifs are always done first, but after that it gets complicated.
# If a bin HMM is being used then the sites from the different CPUs must
# be interleaved first, otherwise summing over the CPUs is done last to
# minimise inter-CPU communicaton.
root_mprobs = mprobs.selectFromDimension('edge', 'root')
lh = CalcDefn(numpy.inner, name='lh')(plh, root_mprobs)
if len(bin_names) > 1:
if sites_independent:
site_pattern = CalcDefn(BinnedSiteDistribution,
name='bdist')(bprobs)
else:
parallel_context = None # hmm does the gathering over CPUs
switch = ProbabilityParamDefn('bin_switch', dimensions=['locus'])
site_pattern = CalcDefn(PatchSiteDistribution,
name='bdist')(switch, bprobs)
blh = CallDefn(site_pattern, lht, name='bindex')
tll = CallDefn(blh, *lh.acrossDimension('bin', bin_names),
**dict(name='tll'))
else:
lh = lh.selectFromDimension('bin', bin_names[0])
tll = CalcDefn(log_sum_across_sites, name='logsum')(lht, lh)
if len(locus_names) > 1 or parallel_context is None:
# "or parallel_context is None" only because SelectFromDimension
# currently has no .makeParamController() method.
tll = SumDefn(*tll.acrossDimension('locus', locus_names))
else:
tll = tll.selectFromDimension('locus', locus_names[0])
if parallel_context is not None:
tll = ParallelSumDefn(parallel_context, tll)
return tll
def makePartialLikelihoodDefns(edge, lht, psubs, fixed_motifs):
kw = {'edge_name': edge.Name}
if edge.istip():
plh = LeafPartialLikelihoodDefn(lht, **kw)
else:
lht_edge = LhtEdgeLookupDefn(lht, **kw)
children = []
for child in edge.Children:
child_plh = makePartialLikelihoodDefns(child, lht, psubs,
fixed_motifs)
psub = psubs.selectFromDimension('edge', child.Name)
child_plh = CalcDefn(numpy.inner)(child_plh, psub)
children.append(child_plh)
if fixed_motifs:
fixed_motif = fixed_motifs.selectFromDimension('edge', edge.Name)
plh = PartialLikelihoodProductDefnFixedMotif(
fixed_motif, lht_edge, *children, **kw)
else:
plh = PartialLikelihoodProductDefn(lht, *children, **kw)
return plh