def main():
clinical_dir, output_dir, header_file = get_options()
headers = pd.read_csv(header_file, index_col=0, header=None)
clinical_files = os.listdir(clinical_dir)
clinical_files = util.remove_extraneous_files(clinical_files)
zscore_data = {}
for f in clinical_files:
clinical_path = os.path.join(clinical_dir, f)
cancer_type = util.get_cancer_type(f)
purity_header = headers.get_value(cancer_type, 1)
clinical = util.get_clinical_data(clinical_path,
extra_rows=[purity_header])
cox_dict = analysis.do_cox(clinical.time, clinical.censor,
clinical[purity_header])
zscore_data[cancer_type] = cox_dict
purity_mean = clinical[purity_header].mean()
print purity_mean
clinical['km_split'] = np.where(clinical[purity_header] <= purity_mean,
0, 1)
analysis.do_km(cancer_type, clinical.time, clinical.censor,
clinical.km_split, output_dir)
out_df = pd.DataFrame(zscore_data).transpose()
out_df.to_csv(os.path.join(output_dir, 'simple_purity_zscores.csv'))
def main():
clinical_dir, output_dir, extra_data_dir = get_options()
clinical_files = os.listdir(clinical_dir)
clinical_files = util.remove_extraneous_files(clinical_files)
zscore_data = {}
for f in clinical_files:
clinical_path = os.path.join(clinical_dir, f)
cancer_type = util.get_cancer_type(f)
if cancer_type == 'COADREAD':
extra_data = prep_extra_data(extra_data_dir, 'COAD')
else:
extra_data = prep_extra_data(extra_data_dir, cancer_type)
clinical = util.get_clinical_data(clinical_path)
clinical = clinical.join(extra_data)
purity_header = 'Purity_InfiniumPurify'
cox_dict = analysis.do_cox(clinical.time, clinical.censor,
clinical[purity_header])
zscore_data[cancer_type] = cox_dict
purity_mean = clinical[purity_header].mean()
print purity_mean
clinical['km_split'] = np.where(clinical[purity_header] <= purity_mean,
0, 1)
analysis.do_km(cancer_type, clinical.time, clinical.censor,
clinical.km_split, output_dir)
out_df = pd.DataFrame(zscore_data).transpose()
out_df.to_csv(
os.path.join(output_dir, 'add_data_simple_purity_zscores.csv'))
def calculate_cox(mutation, clinical_data, key, outdir):
df, clinical_data_with_sequenced_patients, num_patients = prep_data(
mutation, clinical_data, key)
#prep output file
cancer_type = os.path.basename(mutation).split('_')[0].split('.')[0]
print cancer_type
outfile = os.path.join(
outdir, (cancer_type + '_mutation-fraction-' + str(MUTATION_PERCENT) +
'_vaf_cutoff-' + str(VARIANT_ALLELE_FREQ_CUTOFF) +
'.zscores.out.csv'))
formatstring = '\'{0}, {1}, {2}, {3}, {4}\n'
with open(outfile, 'w') as out:
out.write('gene,zscore,pvalue,num mutations,num patients\n')
#for every gene, collect the clinical data with the mutation data.
# only for non-silent mutations
patients_with_gene = df.groupby(level=u'Hugo_Symbol')
for gene, gene_df in patients_with_gene:
# Remove silent mutations
non_silent = gene_df.where(
gene_df[u'Variant_Classification'] != 'Silent')
non_silent = non_silent.dropna(subset=[u'Variant_Classification'])
mutated_patient_list = non_silent.index.get_level_values(
'identifier').unique()
num_mutations = len(mutated_patient_list)
if num_mutations >= MUTATION_PERCENT * num_patients:
# Get "effectively mutated" patients: those who's VAF >= median
median_vaf = non_silent['VAF'].median()
greater_than_median = non_silent[
non_silent['VAF'] >= median_vaf]
effectively_mutated_patients = greater_than_median.index.get_level_values(
'identifier').unique()
num_effective_mutations = len(effectively_mutated_patients)
# take the patients with mutations and without, and build an analysis dataframe with time and censor.
analysis_data = pd.DataFrame(
{'mutated': np.ones(num_effective_mutations)},
index=effectively_mutated_patients)
analysis_data = analysis_data.join(
clinical_data_with_sequenced_patients, how='right')
analysis_data['mutated'].fillna(0, inplace=True)
#Do analysis!
print 'Doing analysis for ', gene, num_mutations
time = analysis_data['time']
censor = analysis_data['censor']
split = analysis_data['mutated']
name = cancer_type + '_' + gene
analysis.do_km(name, time, censor, split, outdir)
cox_dict = analysis.do_cox(time, censor, split)
if cox_dict['n'] != len(analysis_data['time']):
print 'ERROR'
out.write(
formatstring.format(gene, cox_dict['z'], cox_dict['p'],
num_mutations, cox_dict['n']))
analysis_data.to_csv(os.path.join(outdir, name + '_data.csv'),
columns=['time', 'censor', 'mutated'])
def calculate_cox(mutation,
clinical,
outdir,
metagene_file=None,
make_km=False):
clinical_data = util.get_clinical_data(clinical)
df = mutation_base.prep_mutation_data(mutation, clinical_data)
clinical_and_data = df.join(clinical_data, how='inner')
num_patients = len(clinical_and_data)
#prep output file
cancer_type = os.path.basename(mutation).split('_')[0].split('.')[0]
if metagene_file:
formatstring = '{0}, {1}, {2}, {3}, {4}, {5}\n'
outfile = os.path.join(
outdir, cancer_type + '_mutation-fraction-' +
str(MUTATION_PERCENT) + '_metagene_zscores.csv')
print "Processing metagene..."
metagene = metagene_lib.get_metagene_data(metagene_file, cancer_type)
print "Complete"
else:
outfile = os.path.join(
outdir, cancer_type + '_mutation-fraction-' +
str(MUTATION_PERCENT) + '.zscores.out.csv')
formatstring = '{0}, {1}, {2}, {3}, {4}\n'
with open(outfile, 'w') as out:
if metagene_file:
out.write(
'gene,zscore,pvalue,metagene-zscore,metagene-pvalue,num patients\n'
)
else:
out.write('gene,zscore,pvalue,num mutations,num patients\n')
for gene in clinical_and_data:
if gene in ['time', 'censor']:
continue
num_mutations = int(clinical_and_data[gene].sum())
if num_mutations >= MUTATION_PERCENT * num_patients:
time = clinical_and_data['time']
censor = clinical_and_data['censor']
data = clinical_and_data[gene]
if metagene_file:
cox_dict = analysis.do_metagene_cox(
time, censor, data, metagene)
out.write(
formatstring.format(gene, cox_dict['z'], cox_dict['p'],
cox_dict['metagene-z'],
cox_dict['metagene-p'],
cox_dict['n']))
else:
name = cancer_type + '_' + gene
if make_km:
analysis.do_km(name, time, censor, data, outdir)
clinical_and_data['time', 'censor', gene].to_csv(
os.path.join(outdir, name + '_data.csv'),
columns=['time', 'censor', 'mutated'])
cox_dict = analysis.do_cox(time, censor, data)
out.write(
formatstring.format(gene, cox_dict['z'], cox_dict['p'],
num_mutations, cox_dict['n']))