def run_analyses():
r2s_obs_dict = {}
#r2s_null_dict = {}
for treatment in ['0', '1', '2']:
r2s_obs_dict[treatment] = {}
for taxon in taxa:
r2s_all = []
ratio_f_all = []
abs_delta_f_all = []
for replicate in replicates:
population = treatment + taxon + replicate
sys.stderr.write("Processing %s...\n" % population)
mutations, depth_tuple = parse_file.parse_annotated_timecourse(
population)
population_avg_depth_times, population_avg_depths, clone_avg_depth_times, clone_avg_depths = depth_tuple
state_times, state_trajectories = parse_file.parse_well_mixed_state_timecourse(
population)
times = mutations[0][12]
Ms = np.zeros_like(times) * 1.0
fixed_Ms = np.zeros_like(times) * 1.0
for mutation_idx_i in range(0, len(mutations)):
location_i, gene_name_i, allele_i, var_type_i, codon_i, position_in_codon_i, AAs_count_i, test_statistic_i, pvalue_i, cutoff_idx_i, depth_fold_change_i, depth_change_pvalue_i, times_i, alts_i, depths_i, clone_times_i, clone_alts_i, clone_depths_i = mutations[
mutation_idx_i]
state_Ls_i = state_trajectories[mutation_idx_i]
good_idx_i, filtered_alts_i, filtered_depths_i = timecourse_utils.mask_timepoints(
times_i, alts_i, depths_i, var_type_i, cutoff_idx_i,
depth_fold_change_i, depth_change_pvalue_i)
freqs_i = timecourse_utils.estimate_frequencies(
filtered_alts_i, filtered_depths_i)
masked_times_i = times[good_idx_i]
masked_freqs_i = freqs_i[good_idx_i]
masked_state_Ls_i = state_Ls_i[good_idx_i]
P_idx_i = np.where(masked_state_Ls_i == 3)[0]
if len(P_idx_i) < min_trajectory_length:
continue
first_P_i = P_idx_i[0]
last_P_i = P_idx_i[-1]
masked_freqs_P_i = masked_freqs_i[first_P_i:last_P_i + 1]
masked_times_P_i = masked_times_i[first_P_i:last_P_i + 1]
delta_masked_freqs_P_i = masked_freqs_P_i[
1:] - masked_freqs_P_i[:-1]
delta_masked_times_P_i = masked_times_P_i[:-1]
#abs_delta_f = np.absolute(freqs_i[1:] - freqs_i[:-1])
#freqs_i_no_zero = freqs_i[freqs_i>0]
# we want to get the ratio of freqs
for freqs_i_k, freqs_i_l in zip(freqs_i[1:], freqs_i[:-1]):
if (freqs_i_k == 0) or (freqs_i_l == 0):
continue
abs_delta_f_all.append(
np.absolute(freqs_i_k - freqs_i_l))
ratio_f_all.append(freqs_i_k / freqs_i_l)
#ratio_f = freqs_i_no_zero[]
for mutation_idx_j in range(mutation_idx_i + 1,
len(mutations)):
location_j, gene_name_j, allele_j, var_type_j, codon_j, position_in_codon_j, AAs_count_j, test_statistic_j, pvalue_j, cutoff_jdx_j, depth_fold_change_j, depth_change_pvalue_j, times_j, alts_j, depths_j, clone_times_j, clone_alts_j, clone_depths_j = mutations[
mutation_idx_j]
state_Ls_j = state_trajectories[mutation_idx_j]
good_idx_j, filtered_alts_j, filtered_depths_j = timecourse_utils.mask_timepoints(
times_j, alts_j, depths_j, var_type_j,
cutoff_jdx_j, depth_fold_change_j,
depth_change_pvalue_j)
freqs_j = timecourse_utils.estimate_frequencies(
filtered_alts_j, filtered_depths_j)
masked_times_j = times[good_idx_j]
masked_freqs_j = freqs_j[good_idx_j]
masked_state_Ls_j = state_Ls_j[good_idx_j]
P_jdx_j = np.where(masked_state_Ls_j == 3)[0]
if len(P_jdx_j) < min_trajectory_length:
continue
first_P_j = P_jdx_j[0]
last_P_j = P_jdx_j[-1]
masked_freqs_P_j = masked_freqs_j[first_P_j:last_P_j +
1]
masked_times_P_j = masked_times_j[first_P_j:last_P_j +
1]
delta_masked_freqs_P_j = masked_freqs_P_j[
1:] - masked_freqs_P_j[:-1]
# delta_f = f_t_plus_1 - f_t
delta_masked_times_P_j = masked_times_P_j[:-1]
intersect_times = np.intersect1d(
delta_masked_times_P_i, delta_masked_times_P_j)
if len(intersect_times) >= 3:
intersect_idx_i = [
np.where(delta_masked_times_P_i ==
intersect_time)[0][0]
for intersect_time in intersect_times
]
intersect_delta_i = delta_masked_freqs_P_i[
intersect_idx_i]
intersect_idx_j = [
np.where(delta_masked_times_P_j ==
intersect_time)[0][0]
for intersect_time in intersect_times
]
intersect_delta_j = delta_masked_freqs_P_j[
intersect_idx_j]
if len(intersect_delta_i) != len(
intersect_delta_j):
print(len(intersect_delta_j),
len(intersect_delta_j))
r2 = stats.pearsonr(intersect_delta_i,
intersect_delta_j)[0]**2
r2s_all.append(r2)
r2s_all = np.asarray(r2s_all)
ratio_f_all = np.asarray(ratio_f_all)
abs_delta_f_all = np.asarray(abs_delta_f_all)
#r2s_obs_dict[treatment + taxon] = {}
#r2s_obs_dict[treatment + taxon]['r2'] = r2s_all
#r2s_obs_dict[treatment + taxon]['ratio_f'] = ratio_f_all
#r2s_obs_dict[treatment + taxon]['abs_delta_f'] = abs_delta_f_all
r2s_obs_dict[treatment][taxon] = {}
r2s_obs_dict[treatment][taxon]['r2'] = r2s_all
r2s_obs_dict[treatment][taxon]['ratio_f'] = ratio_f_all
r2s_obs_dict[treatment][taxon]['abs_delta_f'] = abs_delta_f_all
with open(pt.get_path() + '/data/mutation_dynamics.pickle',
'wb') as handle:
pickle.dump(r2s_obs_dict, handle, protocol=pickle.HIGHEST_PROTOCOL)
from scipy.special import gammaln as loggamma
from math import log, exp
populations = parse_file.all_lines
coverages = []
nonmutator_coverages = []
for population in populations:
sys.stderr.write("Processing %s...\t" %
parse_file.get_pretty_name(population))
# calculate mutation trajectories
# load mutations
mutations, depth_tuple = parse_file.parse_annotated_timecourse(population)
population_avg_depth_times, population_avg_depths, clone_avg_depth_times, clone_avg_depths = depth_tuple
coverages.extend(population_avg_depths[population_avg_depths >= 5])
if population in parse_file.complete_nonmutator_lines:
nonmutator_coverages.extend(
population_avg_depths[population_avg_depths >= 5])
sys.stderr.write("Done!\n")
coverages = numpy.array(coverages)
nonmutator_coverages = numpy.array(nonmutator_coverages)
print "All populations: n=%d mean=%g median=%g\n" % (
import sys
import pylab
import numpy
import bz2
import parse_file
population = sys.argv[1]
desired_locations = set([long(item) for item in sys.argv[2:]])
pylab.figure(1, figsize=(17, 2))
pylab.figure(2, figsize=(17, 2))
pylab.figure(3, figsize=(17, 2))
mutations, depth_tuple = parse_file.parse_annotated_timecourse(
population, only_passed=False)
population_avg_depth_times, population_avg_depths, clone_avg_depth_times, clone_avg_depths = depth_tuple
for mutation_idx in xrange(0, len(mutations)):
location, gene_name, allele, var_type, test_statistic, pvalue, cutoff_idx, depth_fold_change, depth_change_pvalue, times, alts, depths, clone_times, clone_alts, clone_depths = mutations[
mutation_idx]
if location in desired_locations:
depth_ratios = depths * 1.0 / population_avg_depths
times = times[population_avg_depths > 5]
alts = alts[population_avg_depths > 5]
depth_ratios = depth_ratios[population_avg_depths > 5]
depths = depths[population_avg_depths > 5]
