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 predict_results(tuples_to_predict, method, use_pair_coeffs=False, log_transform_measurements=True):
for pair in tuples_to_predict:
smm_classifier = PSSM(pair[0], use_pair_coeffs)
smm_classifier.load_peptides(pair[1], log_transform_measurements)
smm_classifier.predict()
allele_filename = pair[0].split("/")
allele_name = allele_filename[1]
mode = (allele_filename[-1].split("-")[-1])[0:-4]
print (" ".join((allele_name, method, mode)))
neg_ct = 0
for pred in smm_classifier.predicted_values:
if pred < 0:
neg_ct += 1
# if 'log' in method:
# pred = math.pow(10, pred)
print (
"there were "
+ str(neg_ct)
+ " neg predictions out of "
+ str(len(smm_classifier.predicted_values))
+ " predictions"
)
print ("that is " + str(1.0 * neg_ct / len(smm_classifier.predicted_values)) + "% negative")
trunk_cone_performance = get_performance(smm_classifier.measured_values, smm_classifier.predicted_values)
print "\t".join(["pcc", "auc", "rmsd"])
print "\t".join(map(str, trunk_cone_performance))
print ""
def get_matrix_and_pair_performance(blind_data, scoring_matrix, pair_matrix):
"""
Convienence function used for analysis. Oftentimes I've found that I just needed to get the pcc/auc values from
a model, so this function does the predictions for both with and without pair coefficients on the same blind set
:param blind_data: The blind split used to evaluate performance
:param scoring_matrix: Path to a scoring matrix without pair coefficients
:param pair_matrix: Path to a scoring matrix with pair coefficients
:return: For both matrices a performance tuple with (PCC, AUC, RMSD)
"""
matrix_pssm = PSSM(scoring_matrix, False)
matrix_pssm.load_peptides(blind_data)
matrix_pssm.predict()
matrix_performance = get_performance(matrix_pssm.measured_values, matrix_pssm.predicted_values)
pair_pssm = PSSM(pair_matrix, True)
pair_pssm.load_peptides(blind_data)
pair_pssm.predict()
pair_performance = get_performance(pair_pssm.measured_values, pair_pssm.predicted_values)
return matrix_performance, pair_performance
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()
def create_graphs():
fname_tuples = [] # (blind data, scoring matrix, scoring matrix w/ pair coeffs)
for index, blind_fname in enumerate(blind_files):
allele_name = blind_fname[:-10]
matrix_fname = get_file_by_allele(matrix_files, allele_name)
pairs_fname = get_file_by_allele(pair_files, allele_name)
if matrix_fname is None or pairs_fname is None:
continue
else:
fname_tuples.append((blind_fname, matrix_fname, pairs_fname))
matrix_pcc = []
pair_pcc = []
matrix_auc = []
pair_auc = []
position_pair_lists = []
for allele_files in fname_tuples:
allele_name = allele_files[0][:-10]
matrix_pssm = PSSM(matrix_dir + allele_files[1], False)
matrix_pssm.load_peptides(allele_data_dir + allele_files[0], True)
matrix_pssm.predict()
matrix_performance = get_performance(matrix_pssm.measured_values, matrix_pssm.predicted_values)
pair_pssm = PSSM(pairs_dir + allele_files[2], True)
pair_pssm.load_peptides(allele_data_dir + allele_files[0], True)
pair_pssm.predict()
pair_performance = get_performance(pair_pssm.measured_values, pair_pssm.predicted_values)
matrix_pcc.append(matrix_performance[0])
pair_pcc.append(pair_performance[0])
matrix_auc.append(matrix_performance[1])
pair_auc.append(pair_performance[1])
if allele_name in top_ten_allele_names:
position_pair_lists.append(pair_pssm.position_pair_vals)
if 'A-0101' in allele_name or 'A-0201' in allele_name or 'A-0202' in allele_name or 'A-0301' in allele_name:
plt.scatter(matrix_pssm.measured_values, matrix_pssm.predicted_values)
plt.plot([0, 8], [0, 8], 'k-')
plt.axis((0, 8.0, 0, 8.0))
plt.xlabel('Measured log10(IC50)')
plt.ylabel('Predicted log10(IC50)')
plt.title(allele_name + ' Matrix')
plt.savefig(output_dir + 'all_alleles_' + version + '/' + allele_name + '_matrix_meas_vs_pred.png')
plt.clf()
plt.cla()
plt.close()
plt.scatter(pair_pssm.measured_values, pair_pssm.predicted_values)
plt.plot([0, 8], [0, 8], 'k-')
plt.axis((0, 8.0, 0, 8.0))
plt.xlabel('Measured log10(IC50)')
plt.ylabel('Predicted log10(IC50)')
plt.title(allele_name + ' with ' + str(pair_pssm.num_pairs) + ' pairs selected')
plt.savefig(output_dir + 'all_alleles_' + version + '/' + allele_name + '_pair_meas_vs_pred.png')
plt.clf()
plt.cla()
plt.close()
calc_avg_pair_rms(position_pair_lists)
plt.scatter(matrix_pcc, pair_pcc)
plt.plot([0, 1], [0, 1], 'k-')
plt.axis((0.5, 1.0, 0.5, 1.0))
plt.xlabel('Pairs(-)')
plt.ylabel('Pairs(+)')
plt.title('Matrix vs Pair PCC')
plt.savefig(output_dir + 'all_alleles_' + version + '/mat_vs_pair_pcc.png')
plt.clf()
plt.cla()
plt.close()
plt.scatter(matrix_auc, pair_auc)
plt.plot([0, 1], [0, 1], 'k-')
plt.axis((0.75, 1.0, 0.75, 1.0))
plt.xlabel('Pairs(-)')
plt.ylabel('Pairs(+)')
plt.title('Matrix vs Pair AUC')
plt.savefig(output_dir + 'all_alleles_' + version + '/mat_vs_pair_auc.png')
plt.clf()
plt.cla()
plt.close()
def compare_new_and_old_results():
peptides_to_score = 'HLA-A-0250-9.txt'
header = ['pcc', 'auc', 'rmsd']
#sm stands for scoring matrix
#these were generated from trunk branch using all four lambda/covariance options
cgroup_sm = PSSM('HLA-A-0250-9.txt-cgroup.txt', False)
cgroup_sm.load_peptides(peptides_to_score)
cgroup_sm.predict()
cgroup_sm.test_results()
print 'cgroup results'
print str(cgroup_sm.peptide_predictions).replace(' ','').replace('[','').replace(']','').replace(',','\n')
cgroup_performance = get_performance(cgroup_sm.measured_values, cgroup_sm.peptide_predictions)
print '\t'.join(header)
print '\t'.join(map(str, cgroup_performance))
print ''
lgroup_sm = PSSM('HLA-A-0250-9.txt-lgroup.txt', False)
lgroup_sm.load_peptides(peptides_to_score)
lgroup_sm.predict()
print 'lgroup results'
print str(lgroup_sm.peptide_predictions).replace(' ','').replace('[','').replace(']','').replace(',','\n')
lgroup_performance = get_performance(lgroup_sm.measured_values, lgroup_sm.peptide_predictions)
print '\t'.join(header)
print '\t'.join(map(str, lgroup_performance))
print ''
cone_sm = PSSM('HLA-A-0250-9.txt-cone.txt', False)
cone_sm.load_peptides(peptides_to_score)
cone_sm.predict()
print 'cone results'
print str(cone_sm.peptide_predictions).replace(' ','').replace('[','').replace(']','').replace(',','\n')
cone_performance = get_performance(cone_sm.measured_values, cone_sm.peptide_predictions)
print '\t'.join(header)
print '\t'.join(map(str, cone_performance))
print ''
lone_sm = PSSM('HLA-A-0250-9.txt-lone.txt', False)
lone_sm.load_peptides(peptides_to_score)
lone_sm.predict()
print 'lone results'
print str(lone_sm.peptide_predictions).replace(' ','').replace('[','').replace(']','').replace(',','\n')
lone_performance = get_performance(lone_sm.measured_values, lone_sm.peptide_predictions)
print '\t'.join(header)
print '\t'.join(map(str, lone_performance))
print ''
production_sm = PSSM('HLA-A-0250-9-production.txt', False)
production_sm.load_peptides(peptides_to_score)
production_sm.predict()
print 'production results'
print str(production_sm.peptide_predictions).replace(' ','').replace('[','').replace(']','').replace(',','\n')
production_performance = get_performance(production_sm.measured_values, production_sm.peptide_predictions)
print '\t'.join(header)
print '\t'.join(map(str, production_performance))
print ''
#generated using pcoeff_one
#mat outputted before TrainPairs called
mat_sm = PSSM('mat-HLA-A-0250-9.txt', False)
mat_sm.load_peptides(peptides_to_score)
mat_sm.predict()
print 'pre pair training results'
print str(mat_sm.peptide_predictions).replace(' ','').replace('[','').replace(']','').replace(',','\n')
mat_performance = get_performance(mat_sm.measured_values, mat_sm.peptide_predictions)
print '\t'.join(header)
print '\t'.join(map(str, mat_performance))
print ''
#after TrainPairs
pair_coeff_sm = PSSM('pairs-HLA-A-0250-9.txt')
pair_coeff_sm.load_peptides(peptides_to_score)
pair_coeff_sm.predict()
print 'pcoeff_one results'
print str(pair_coeff_sm.peptide_predictions).replace(' ','').replace('[','').replace(']','').replace(',','\n')
pair_coeff_performance = get_performance(pair_coeff_sm.measured_values, pair_coeff_sm.peptide_predictions)
print '\t'.join(header)
print '\t'.join(map(str, pair_coeff_performance))
print ''
# fname_peptides_to_score = 'HLA-A-0216-9.txt'
# fname_scoring_matrix = 'pairs-HLA-A-0250-9.txt'
# fname_scoring_matrix = 'mat-HLA-A-0250-9.txt'
# fname_peptides_to_score = 'HLA-A-0250-9.txt'
# fname_scoring_matrix = 'pairs-HLA-A-2602-9.txt'
# fname_scoring_matrix = 'mat-HLA-A-2602-9.txt'
# fname_peptides_to_score = 'HLA-A-2602-9.txt'
pair_coeff_sm = PSSM('data/HLA-A-0201/HLA-A-0201-9-pcoeff_group.txt')
pair_coeff_sm.load_peptides('data/HLA-A-0201/HLA-A-0201-9.txt')
pair_coeff_sm.predict()
print '0201 pcoeff_one results'
print str(pair_coeff_sm.peptide_predictions).replace(' ','').replace('[','').replace(']','').replace(',','\n')
pair_coeff_performance = get_performance(pair_coeff_sm.measured_values, pair_coeff_sm.peptide_predictions)
print '\t'.join(['pcc', 'auc', 'rmsd'])
print '\t'.join(map(str, pair_coeff_performance))
print ''
# fname_predictions = 'pred' + fname_scoring_matrix
# pssm = PSSM(fname_scoring_matrix, False)
# pssm.load_peptides(fname_peptides_to_score)
# score_list = pssm.predict()
# print score_list
# pssm.test_results()
# compare_new_and_old_results()
print 'finished'
# header = ['peptide', 'predAffinity(log10(IC50))']