def loadOligoFeaturesAndReadCounts(oligo_id, sample_names):
oligo_idx = getOligoIdxFromId(oligo_id)
oligo_subdir, _ = getFileForOligoIdx(oligo_idx, ext='')
features_file = FEATURES_DIR + '/' + oligo_subdir + '/%s_gen_indel_features.txt' % oligo_id
reads_file = READS_DIR + '/' + oligo_subdir + '/%s_gen_indel_reads.txt' % oligo_id
cut_site = getCutSite(features_file)
indel_feature_data, feature_cols = readFeaturesData(features_file)
if len(sample_names) > 0:
read_data = pd.read_csv(reads_file, skiprows=1, sep='\t')
read_data['Sum Sample Reads'] = read_data[sample_names].sum(
axis=1) + 0.5
read_data = read_data.loc[read_data['Indel'] != 'All Mutated']
total_mut_reads = read_data['Sum Sample Reads'].sum()
if total_mut_reads == 0:
raise Exception('No Mutated Reads in %s' % reads_file)
read_data['Frac Sample Reads'] = read_data[
'Sum Sample Reads'] / total_mut_reads
merged_data = pd.merge(indel_feature_data,
read_data[['Indel', 'Frac Sample Reads']],
left_index=True,
right_on='Indel',
how='inner')
else:
merged_data = indel_feature_data
merged_data['Indel'] = merged_data.index
return merged_data
def predictMutations(theta_file, target_seq, pam_idx, add_null=True):
theta, train_set, theta_feature_columns = readTheta(theta_file)
#generate indels
left_trim = 0
tmp_genindels_file = 'tmp_genindels_%s_%d.txt' % (target_seq, random.randint(0,100000))
cmd = INDELGENTARGET_EXE + ' %s %d %s' % (target_seq, pam_idx, tmp_genindels_file)
print(cmd); subprocess.check_call(cmd.split())
rep_reads = fetchRepReads(tmp_genindels_file)
isize, smallest_indel = min([(tokFullIndel(x)[1],x) for x in rep_reads]) if len(rep_reads) > 0 else (0,'-')
if isize > 0: left_trim = target_seq.find(rep_reads[smallest_indel][:10])
#compute features for all generated indels
tmp_features_file = 'tmp_features_%s_%d.txt' % (target_seq, random.randint(0,100000))
calculateFeaturesForGenIndelFile( tmp_genindels_file, target_seq, pam_idx-3, tmp_features_file)
os.remove(tmp_genindels_file)
feature_data, feature_columns = readFeaturesData(tmp_features_file)
os.remove(tmp_features_file)
if len(set(theta_feature_columns).difference(set(feature_columns))) != 0:
raise Exception('Stored feature names associated with model thetas are not contained in those computed')
if len(set(theta_feature_columns).union(set(feature_columns))) != len(theta_feature_columns):
feature_data = feature_data[['Indel'] + theta_feature_columns]
feature_columns = theta_feature_columns
#Predict the profile
p_predict, _ = computePredictedProfile(feature_data, theta, theta_feature_columns)
in_frame, out_frame, _ = fetchIndelSizeCounts(p_predict)
in_frame_perc = in_frame*100.0/(in_frame + out_frame)
if add_null:
p_predict['-'] = 1000
rep_reads['-'] = target_seq[left_trim:]
return p_predict, rep_reads, in_frame_perc