def clade_frequency_correlations_func_polarizer(params):
# set up the prediction and pass all parameters to the wrapper function
params.diffusion=1.0
params.gamma = 1.0
prediction = test_flu.predict_params(['polarizer'],
params)
# define the methodes for which the predictions are to be evaluated
methods = [('polarizer', '_ext', prediction.terminals),
('polarizer', '_int', prediction.non_terminals)]
distances, distances_epi, test_data = test_flu.evaluate(prediction, methods, params)
tbins_eval = [date(year=params.year, month = 6, day=1), date(year=params.year+1, month = 6, day=1)]
combined_data = test_flu.make_combined_data(prediction, test_data, collapse = params.collapse)
combined_tree = flu.flu_ranking(combined_data, time_bins = tbins_eval, pseudo_count = 0)
combined_tree.expansion_score()
tree_utils.find_internal_nodes(prediction.T,combined_tree.T)
freqs = [node.mirror_node.temporal_frequency for node in prediction.non_terminals]
polarizers= []
for tau in mem_scale:
prediction.calculate_polarizers(mem = tau)
polarizers.append([node.polarizer for node in prediction.non_terminals])
polarizers_and_freqs = np.hstack( (np.array(polarizers).T, np.array(freqs)))
return polarizers_and_freqs
def clade_frequency_correlations_func(params):
# set up the prediction and pass all parameters to the wrapper function
prediction = test_flu.predict_params(['mean_fitness'],
params)
# define the methodes for which the predictions are to be evaluated
methods = [('mean_fitness', '_ext', prediction.terminals),
('mean_fitness', '_int', prediction.non_terminals)]
distances, distances_epi, test_data = test_flu.evaluate(prediction, methods, params)
tbins_eval = [date(year=params.year, month = 6, day=1), date(year=params.year+1, month = 6, day=1)]
combined_data = test_flu.make_combined_data(prediction, test_data, collapse = params.collapse)
combined_tree = flu.flu_ranking(combined_data, time_bins = tbins_eval, pseudo_count = 0)
combined_tree.expansion_score()
tree_utils.find_internal_nodes(prediction.T,combined_tree.T)
fitness_and_freqs = []
for node in prediction.non_terminals:
fitness_and_freqs.append([node.mean_fitness, node.polarizer]+list(node.mirror_node.temporal_frequency))
fitness_and_freqs = np.array(fitness_and_freqs)
return fitness_and_freqs
def clade_frequency_correlations_func(params):
# set up the prediction and pass all parameters to the wrapper function
prediction = test_flu.predict_params(['mean_fitness'], params)
# define the methodes for which the predictions are to be evaluated
methods = [('mean_fitness', '_ext', prediction.terminals),
('mean_fitness', '_int', prediction.non_terminals)]
distances, distances_epi, test_data = test_flu.evaluate(
prediction, methods, params)
tbins_eval = [
date(year=params.year, month=6, day=1),
date(year=params.year + 1, month=6, day=1)
]
combined_data = test_flu.make_combined_data(prediction,
test_data,
collapse=params.collapse)
combined_tree = flu.flu_ranking(combined_data,
time_bins=tbins_eval,
pseudo_count=0)
combined_tree.expansion_score()
tree_utils.find_internal_nodes(prediction.T, combined_tree.T)
fitness_and_freqs = []
for node in prediction.non_terminals:
fitness_and_freqs.append([node.mean_fitness, node.polarizer] +
list(node.mirror_node.temporal_frequency))
fitness_and_freqs = np.array(fitness_and_freqs)
return fitness_and_freqs
def clade_frequency_correlations_func_polarizer(params):
# set up the prediction and pass all parameters to the wrapper function
params.diffusion = 1.0
params.gamma = 1.0
prediction = test_flu.predict_params(['polarizer'], params)
# define the methodes for which the predictions are to be evaluated
methods = [('polarizer', '_ext', prediction.terminals),
('polarizer', '_int', prediction.non_terminals)]
distances, distances_epi, test_data = test_flu.evaluate(
prediction, methods, params)
tbins_eval = [
date(year=params.year, month=6, day=1),
date(year=params.year + 1, month=6, day=1)
]
combined_data = test_flu.make_combined_data(prediction,
test_data,
collapse=params.collapse)
combined_tree = flu.flu_ranking(combined_data,
time_bins=tbins_eval,
pseudo_count=0)
combined_tree.expansion_score()
tree_utils.find_internal_nodes(prediction.T, combined_tree.T)
freqs = [
node.mirror_node.temporal_frequency
for node in prediction.non_terminals
]
polarizers = []
for tau in mem_scale:
prediction.calculate_polarizers(mem=tau)
polarizers.append(
[node.polarizer for node in prediction.non_terminals])
polarizers_and_freqs = np.hstack((np.array(polarizers).T, np.array(freqs)))
return polarizers_and_freqs
prediction = test_flu.predict_params([
'mean_fitness', 'expansion_score', 'depth', 'polarizer',
flu.combined_ranking_internal, flu.combined_ranking_external
], params)
# define the methodes for which the predictions are to be evaluated
methods = [('mean_fitness', '_ext', prediction.terminals),
('mean_fitness', '_int', prediction.non_terminals),
('expansion_score', '_int', prediction.non_terminals),
('expansion_fitness', '', prediction.non_terminals),
('time_fitness', '', prediction.terminals),
('ladder_rank', '', prediction.terminals),
('date', '', prediction.terminals),
('polarizer', '_ext', prediction.terminals),
('polarizer', '_int', prediction.non_terminals)]
distances, distances_epi, test_data = test_flu.evaluate(
prediction, methods, params)
nuc_dist_array[ii,:] = [distances['average'],distances['minimal'],distances['L&L']]\
+[distances[m[0]+m[1]] for m in methods]
epi_dist_array[ii,:] = [distances_epi['average'],distances_epi['minimal'],distances_epi['L&L']]\
+[distances_epi[m[0]+m[1]] for m in methods]
# memorize the strain predicted best
top_strains.append(
prediction.best_node(method=top_strain_method,
nodes=prediction.terminals))
#if file does not exist, create and write header
fname_nuc = analysis_folder + '_'.join([fname_base, name_mod, 'nuc.dat'])
if not os.path.isfile(fname_nuc):
with open(fname_nuc, 'w') as outfile:
outfile.write('#average\tminimal\tL&L\t' +
'\t'.join([m[0] + m[1] for m in methods]) + '\n')
parser = test_flu.make_flu_parser()
parser.add_argument('--tau', default = 1.0, type = float, help= 'memory time scale of the tree polarizer')
params=parser.parse_args()
# get name snippets to link output files to run parameters
base_name, name_mod = test_flu.get_fname(params)
params.gamma=1.0
params.diffusion=1.0
# set up the prediction and pass all parameters to the wrapper function
prediction = test_flu.predict_params(['polarizer'], params)
prediction.calculate_polarizers(params.tau)
# define the methodes for which the predictions are to be evaluated
methods = [ ('polarizer', '_ext', prediction.terminals),
('polarizer', '_int', prediction.non_terminals)]
distances, distances_epi, test_data = test_flu.evaluate(prediction, methods, params)
# calculate the fitness differentials for each internal branch and associate with
# different types of mutations that happen on these branches
dfit = []
for node in prediction.non_terminals:
for child in node.clades:
delta_fitness = child.polarizer - node.polarizer
muts = child.mutations
aa_muts = child.aa_mutations
if child.branch_length<0.01:
dfit.append((delta_fitness,child.is_terminal(), len(muts), len(aa_muts),
len([m[0] for m in aa_muts if m[0] in flu.HA1_antigenic_sites]),
len([m[0] for m in aa_muts if m[0] in flu.cluster_positions])))
else:
print child,'excluded due to long branch length'