def test_makeContinuousPsubDefn():
standard_params = {'is_independent': True, 'is_constant': False}
lf_gen = inflate_likelihood_function(_General)
model = GeneralBen(DNA.Alphabet,
recode_gaps=True,
model_gaps=False,
optimise_motif_probs=True,
name='GeneralBen')
lf_ben = model.makeLikelihoodFunction(lf_gen.tree)
populate_parameters(lf_ben, lf_gen, **standard_params)
ben_ens = get_expected_no_subs(lf_ben)
ben_lens = lf_ben.getParamValueDict(['edge'])['length']
gen_ens = get_expected_no_subs(lf_gen)
for edge in lf_gen.tree.getTipNames():
assert_array_almost_equal(
np.array(lf_ben.getRateMatrixForEdge(edge)) *
lf_ben.getParamValue('length', edge),
np.array(lf_gen.getRateMatrixForEdge(edge)) *
lf_gen.getParamValue('length', edge))
assert_almost_equal(ben_ens[edge], gen_ens[edge])
assert_almost_equal(ben_lens[edge], ben_ens[edge])
def test_hetero_fit():
"""hetero_fit should fit GTR plus Gamma models"""
pre_lf = nest.inflate_likelihood_function(_GTRplusGamma)
prefit = nest.get_expected_no_subs(pre_lf)
aln = get_aln('GTRplusGamma', 100000)
lfs = nest.hetero_fit(aln, pre_lf.tree, param_limit=20, return_lfs=True)
postfit = nest.get_expected_no_subs(lfs[-1])
for taxon in prefit:
assert_almost_equal(postfit[taxon], prefit[taxon], decimal=2)
def test_hetero_clock_fit():
"""hetero_clock_fit should fit a molecular clock constrained GTR plus Gamma
model nested in a GTR plus Gamma model"""
pre_lf = nest.inflate_likelihood_function(_GTRplusGammaClockTest)
prefit = nest.get_expected_no_subs(pre_lf)
aln = get_aln('GTRplusGammaClockTest', 100000)
lfs = nest.hetero_clock_fit(aln, pre_lf.tree, outgroup='Opossum',
param_limit=20, return_lfs=True)
lf_equal_length, lf = lfs
assert_less(lf_equal_length.getLogLikelihood(), lf.getLogLikelihood())
postfit = nest.get_expected_no_subs(lf)
postfit_equal_length = nest.get_expected_no_subs(lf_equal_length)
for taxon in prefit:
assert_almost_equal(postfit[taxon], prefit[taxon], decimal=2)
assert_almost_equal(postfit_equal_length[taxon], prefit[taxon], decimal=2)
def test_seq_fit():
"""seq_fit should fit nested GTR and General models"""
for model in 'GTR', 'General':
pre_lf = nest.inflate_likelihood_function(eval('_'+model))
prefit = nest.get_expected_no_subs(pre_lf)
aln = get_aln(model, 100000)
lfs = nest.seq_fit(aln, pre_lf.tree, param_limit=20, return_lfs=model)
if model == 'General':
assert_less(lfs[0].getLogLikelihood(),
lfs[1].getLogLikelihood())
lf = lfs[-1]
postfit = nest.get_expected_no_subs(lf)
for taxon in prefit:
assert_almost_equal(postfit[taxon], prefit[taxon], decimal=2)
def test_deflate_likelihood_function():
"""deflate_likelihood_function produces internally consistent statistics"""
lf = nest.inflate_likelihood_function(_General)
aln = get_aln('General', _General['aln_length'])
lf.setAlignment(aln)
EN = nest.deflate_likelihood_function(lf)['EN']
assert_equal(EN, nest.get_expected_no_subs(lf))
def param_bootstrap(stats, num_reps=None, model_pos=None, fitter=None, **kw):
gene, f_stats, g_stats = stats
try:
f_row = f_stats[model_pos]
except IndexError:
logging.error(' Skipping ' + '/'.join(f_stats[0]['tip_names']) +
' in ' + gene + ': position ' + model_pos + ' invalid')
return
model = f_row['name']
if model_pos in g_stats:
g_row = g_stats[model_pos]
else:
g_row = {
'name': model,
'tip_names': f_row['tip_names'],
'gs_samples': [],
'll_samples': [],
'en_samples': []
}
g_stats[model_pos] = g_row
gs_samples = g_row['gs_samples']
ll_samples = g_row['ll_samples']
en_samples = g_row['en_samples']
if 'state' in g_row:
random.setstate(eval(g_row['state']))
lf = nest.inflate_likelihood_function(f_row)
aln_length = f_row['aln_length']
start = time.time()
for i in 10 * range(num_reps):
if len(gs_samples) >= num_reps:
break
try:
aln = lf.simulateAlignment(aln_length, random_series=random)
lfs = fitter(aln, lf.tree, return_lfs=model, **kw)
fitted_lf = lfs[model_pos]
ll_samples.append(fitted_lf.getLogLikelihood())
gs_samples.append(fitted_lf.getGStatistic())
if 'Q' in fitted_lf.defn_for:
en_samples.append(nest.get_expected_no_subs(fitted_lf))
except:
logging.warning(' Missed a G stat for ' + model + ' and ' +
'/'.join(f_row['tip_names']) + ' in ' + gene +
':\n' + format_exc())
else:
logging.error(
' Failed to compile sufficient bootstrap repetitions for ' +
model + ' and ' + '/'.join(f_row['tip_names']) + ' in ' + gene)
g_row['state'] = repr(random.getstate())
f_row['gs_p'] = (sum(1 for g in gs_samples
if g < f_row['gs']), len(gs_samples) + 1)
f_row['ll_p'] = (sum(1 for l in ll_samples
if l < f_row['ll']), len(ll_samples) + 1)
logging.info(' Done ' + model + ' and ' + '/'.join(f_row['tip_names']) +
' in ' + gene + ' in ' + str(time.time() - start) + ' secs')
return gene, f_stats, g_stats
def test_clock_fit():
"""clock_fit should fit nested GTR, General, and GeneralBen models,
some with equal branch lengths"""
for modelname in ('GTRClockTest', 'GeneralBen'):
model = eval('_' + modelname)
pre_lf = nest.inflate_likelihood_function(model)
prefit = nest.get_expected_no_subs(pre_lf)
aln = get_aln(modelname, 100000)
lfs = nest.clock_fit(aln, pre_lf.tree, outgroup='Opossum', param_limit=20,
return_lfs='GTR' if modelname.startswith('GTR') else 'General')
lf_equal_length, lf = lfs[:2] if modelname[:3] == 'GTR' else lfs[2:]
assert_less(lf_equal_length.getLogLikelihood(), lf.getLogLikelihood())
if modelname == 'GeneralBen':
assert_less(lfs[0].getLogLikelihood(),
lf_equal_length.getLogLikelihood())
postfit = nest.get_expected_no_subs(lf)
postfit_equal_length = nest.get_expected_no_subs(lf_equal_length)
for taxon in prefit:
assert_almost_equal(postfit[taxon], prefit[taxon], decimal=2)
assert_almost_equal(postfit_equal_length[taxon], prefit[taxon],
decimal=2)
def test_constrain_lengths():
lf_gen = inflate_likelihood_function(_General)
aln = get_aln('General', _General['aln_length'])
model = GeneralBen(DNA.Alphabet,
recode_gaps=True,
model_gaps=False,
optimise_motif_probs=True)
lf_ben = model.makeLikelihoodFunction(lf_gen.tree)
for param in lf_ben.getParamNames():
if '/' in param:
lf_ben.setParamRule(param, is_independent=True, is_constant=False)
lf_ben.setParamRule('length', is_independent=False)
lf_ben.setParamRule('length', edge='Opossum', is_independent=True)
lf_ben.setAlignment(aln)
lf_ben.optimise(local=True, show_progress=False)
ens = get_expected_no_subs(lf_ben)
lens = lf_ben.getParamValueDict(['edge'])['length']
assert_almost_equal(lens['Mouse'], lens['Human'])
for edge in lf_ben.tree.getTipNames():
assert_almost_equal(lens[edge], ens[edge])
def test_get_expected_no_subs():
"""expected_no_subs should return dictionary of ENS by edge"""
GS_lf = nest.inflate_likelihood_function(_GeneralStationary)
EN = nest.get_expected_no_subs(GS_lf)
for name in GS_lf.tree.getTipNames():
assert_almost_equal(EN[name], GS_lf.getParamValue('length', name))