def calc_performance_differences_with_selected_pairs(allele_fnames, output_fname):
"""
:param allele_fnames: list of tuples, (blind data fname, scoring matrix fname, pair matrix fname)
:param output_fname: Desired filename to save differences to
:return:
"""
pcc_diff_dict = {}
auc_diff_dict = {}
for allele in allele_fnames:
allele_name = get_allele_name_from_path(allele[0])
# if '0206' in allele_name:
# continue
matrix_pssm = PSSM(allele[1], False)
matrix_pssm.load_peptides(allele[0])
matrix_pssm.predict()
matrix_performance = get_performance(matrix_pssm.measured_values, matrix_pssm.predicted_values)
for position1 in range(1, 10):
for position2 in range(position1 + 1, 10):
position_pair = (position1, position2)
pair_pssm = PSSM(allele[2], True, position_pair)
if pair_pssm.num_pairs > 0:
pair_pssm.load_peptides(allele[0])
pair_pssm.predict()
pair_performance = get_performance(pair_pssm.measured_values, pair_pssm.predicted_values)
pcc_diff = pair_performance[0] - matrix_performance[0]
# if pcc_diff < -0.2:
# print(allele_name, str(position_pair), ' has pcc_diff of ', pcc_diff)
if position_pair not in pcc_diff_dict:
pcc_diff_dict[position_pair] = [pcc_diff]
else:
pcc_diff_dict[position_pair].append(pcc_diff)
if None not in (pair_performance[1], matrix_performance[1]):
auc_diff = pair_performance[1] - matrix_performance[1]
if position_pair not in auc_diff_dict:
auc_diff_dict[position_pair] = [auc_diff]
else:
auc_diff_dict[position_pair].append(auc_diff)
pcc_sorted_differences = []
for position_pair, coefficient_values in pcc_diff_dict.iteritems():
pcc_sorted_differences.append((position_pair, sum(coefficient_values)/float(len(coefficient_values))))
pcc_sorted_differences = sorted(pcc_sorted_differences, key=lambda x: x[1], reverse=True)
auc_sorted_differences = []
for position_pair, coefficient_values in auc_diff_dict.iteritems():
auc_sorted_differences.append((position_pair, sum(coefficient_values)/float(len(coefficient_values))))
auc_sorted_differences = sorted(auc_sorted_differences, key=lambda x: x[1], reverse=True)
pcc_file = open('../selected_pairs/pcc_' + output_fname, 'wb')
pcc_file.write('\n'.join([str(x[0]) + '\t' + str(x[1]) for x in pcc_sorted_differences]))
pcc_file.close()
auc_file = open('../selected_pairs/auc_' + output_fname, 'wb')
auc_file.write('\n'.join([str(x[0]) + '\t' + str(x[1]) for x in auc_sorted_differences]))
auc_file.close()
def zip_result_files(blind_files, matrix_files, pair_files):
m_files = list(matrix_files)
p_files = list(pair_files)
fname_tuples = [] # (blind data, scoring matrix, scoring matrix w/ pair coeffs)
for index, blind_fname in enumerate(blind_files):
allele_name = get_allele_name_from_path(blind_fname)
matrix_fname = get_file_by_allele(m_files, allele_name)
pairs_fname = get_file_by_allele(p_files, allele_name)
if matrix_fname is None or pairs_fname is None:
continue
else:
fname_tuples.append((blind_fname, matrix_fname, pairs_fname))
return fname_tuples
result_tuples = zip_result_files(blind_files, scoring_matrix_files, pair_matrix_files)
pcc_differences = []
auc_differences = []
for result_files in result_tuples:
blind = result_files[0]
scoring_matrix = result_files[1]
pair_matrix = result_files[2]
matrix_results, pair_results = get_matrix_and_pair_performance(blind, scoring_matrix, pair_matrix)
pcc_diff = pair_results[0] - matrix_results[0]
if pcc_diff < -0.2:
print(get_allele_name_from_path(blind), ' has a pcc diff of ', pcc_diff)
continue # do not add, outlier
pcc_differences.append(pcc_diff)
if None not in (pair_results[1], matrix_results[1]):
auc_differences.append(pair_results[1] - matrix_results[1])
fig = plt.figure()
print('pcc avg diff: ', sum(pcc_differences)/float(len(pcc_differences)))
fig.add_subplot(121)
plt.plot(range(1, len(pcc_differences) + 1), pcc_differences)
fig.add_subplot(122)
print('auc avg diff: ', sum(auc_differences)/float(len(auc_differences)))
plt.plot(range(1, len(auc_differences) + 1), auc_differences)
plt.show()
def calc_pair_improvements():
allele_dirs = os.listdir(output_dir + 'all_alleles_v7/')
allele_dirs = sorted(allele_dirs)
position_pair_pcc_dict = {}
position_pair_auc_dict = {}
index_offset = 0
for index, allele in enumerate(allele_dirs):
pair_matrix_files = os.listdir(output_dir + 'all_alleles_v7/' + allele)
blind_data = blind_files[index]
allele_name = get_allele_name_from_path(blind_data)
if (index - index_offset) >= len(matrix_files):
break
matrix_file = matrix_files[index - index_offset]
if allele not in matrix_file:
index_offset += 1
continue
assert allele in blind_data and allele in matrix_file
# trying to seee how improvements change when only looking at 10 biggest alleles
# if allele not in top_ten_allele_names:
# continue
matrix_pssm = PSSM(output_dir + 'all_alleles_v5/matrix/' + matrix_file, False)
matrix_pssm.load_peptides(data_dir + 'blind_subsets/' + blind_data)
matrix_pssm.predict()
matrix_performance = get_performance(matrix_pssm.measured_values, matrix_pssm.predicted_values)
for specified_pair_file in pair_matrix_files:
if specified_pair_file == 'stdout' or specified_pair_file == 'stderr':
continue
else:
position_pair = tuple(specified_pair_file[:-4].split('_')[2:4])
pair_pssm = PSSM(output_dir + 'all_alleles_v7/' + allele + '/' + specified_pair_file, True)
pair_pssm.load_peptides(data_dir + 'blind_subsets/' + blind_data)
pair_pssm.predict()
pair_performance = get_performance(pair_pssm.measured_values, pair_pssm.predicted_values)
pcc_diff = pair_performance[0] - matrix_performance[0]
if pcc_diff < -0.1:
print(allele_name, str(position_pair), ' has pcc_diff of ', pcc_diff)
continue
if position_pair not in position_pair_pcc_dict:
position_pair_pcc_dict[position_pair] = [pcc_diff]
else:
position_pair_pcc_dict[position_pair].append(pcc_diff)
if pair_performance[1] is not None and matrix_performance[1] is not None:
auc_diff = pair_performance[1] - matrix_performance[1]
if position_pair not in position_pair_auc_dict:
position_pair_auc_dict[position_pair] = [auc_diff]
else:
position_pair_auc_dict[position_pair].append(auc_diff)
position_pair_pcc_list = []
position_pair_auc_list = []
for position_pair, diff_list in position_pair_pcc_dict.iteritems():
avg = sum(diff_list)/float(len(diff_list))
position_pair_pcc_list.append((position_pair, avg))
for position_pair, diff_list in position_pair_auc_dict.iteritems():
avg = sum(diff_list)/float(len(diff_list))
position_pair_auc_list.append((position_pair, avg))
position_pair_pcc_list = sorted(position_pair_pcc_list, key=lambda x: x[1], reverse=True)
position_pair_auc_list = sorted(position_pair_auc_list, key=lambda x: x[1], reverse=True)
pcc_diff_file = open(output_dir + 'all_alleles_v7/pcc_diff_selected_pairs.txt', 'wb')
auc_diff_file = open(output_dir + 'all_alleles_v7/auc_diff_selected_pairs.txt', 'wb')
pcc_diff_file.write('\n'.join([str(x) for x in position_pair_pcc_list]))
auc_diff_file.write('\n'.join([str(x) for x in position_pair_auc_list]))
pcc_diff_file.close()
auc_diff_file.close()
