def get_gistic_genes(data_path, cancer, filter_with_rna=True,
collapse_on_bands=True, min_patients=5):
"""
Gets a matrix of events for high grade amplifications and homozygous
deletions.
We filter down this list by asserting that a copy number event corresponds
with a resultant expression change.
The final matrix merges gene-level events on the same band to combine
redundant events and reduce the test space.
"""
gistic = FH.get_gistic_gene_matrix(data_path, cancer, '01')
deletion = gistic[(gistic == -2).sum(1) > min_patients]
amp = gistic[(gistic == 2).sum(1) > min_patients]
ft = pd.MultiIndex.from_tuples # rediculously long pandas names
deletion.index = ft([('Deletion', s[0], s[2]) for s in deletion.index])
amp.index = ft([('Amplification', s[0], s[2]) for s in amp.index])
if filter_with_rna:
rna = FH.read_rnaSeq(data_path, cancer)
deletion = rna_filter(deletion, -2, rna)
amp = rna_filter(amp, 2, rna)
cna_genes = amp.append(deletion)
if collapse_on_bands == False:
return cna_genes
cna_genes = pd.DataFrame({(a[0], a[1], tuple(b.index.get_level_values(2))):
b.mean().round() for a, b in
cna_genes.groupby(level=[0, 1])}).T
cna_genes.index = pd.MultiIndex.from_tuples(cna_genes.index)
return cna_genes
def get_gistic_genes(data_path,
cancer,
filter_with_rna=True,
collapse_on_bands=True,
min_patients=5):
'''
Gets a matrix of events for high grade amplifications and homozygous
deletions.
We filter down this list by asserting that a copy number event corresponds
with a resultant expression change.
The final matrix merges gene-level events on the same band to combine
redundant events and reduce the test space.
'''
gistic = FH.get_gistic_gene_matrix(data_path, cancer, '01')
deletion = gistic[(gistic == -2).sum(1) > min_patients]
amp = gistic[(gistic == 2).sum(1) > min_patients]
ft = pd.MultiIndex.from_tuples # rediculously long pandas names
deletion.index = ft([('Deletion', s[0], s[2]) for s in deletion.index])
amp.index = ft([('Amplification', s[0], s[2]) for s in amp.index])
if filter_with_rna:
rna = FH.read_rnaSeq(data_path, cancer)
deletion = rna_filter(deletion, -2, rna)
amp = rna_filter(amp, 2, rna)
cna_genes = amp.append(deletion)
if collapse_on_bands == False:
return cna_genes
cna_genes = pd.DataFrame({(a[0], a[1], tuple(b.index.get_level_values(2))):
b.mean().round()
for a, b in cna_genes.groupby(level=[0, 1])}).T
cna_genes.index = pd.MultiIndex.from_tuples(cna_genes.index)
return cna_genes
def get_cna_rates(data_path, cancer, patients=None):
"""
Get copy-number aberration rates from GISTIC processing pipeline.
This function depends on the current Firehose output of this program
as of July 2013.
"""
gistic = FH.get_gistic_gene_matrix(data_path, cancer)
amp_gene_all = (gistic >= 1).astype(int).sum()
amp_gene_high = (gistic == 2).astype(int).sum()
del_gene_all = (gistic <= -1).astype(int).sum()
del_gene_homo = (gistic <= -2).astype(int).sum()
lesions = FH.get_gistic_lesions(data_path, cancer)
amp_lesion_all = (lesions.ix['Amplification'] >= 1).sum()
amp_lesion_high = (lesions.ix['Amplification'] == 2).sum()
del_lesion_all = (lesions.ix['Deletion'] <= -1).sum()
del_lesion_homo = (lesions.ix['Deletion'] == -2).sum()
arm_cn = FH.get_gistic_arm_values(data_path, cancer)
chromosomal_instability = arm_cn.abs().mean()
cna_df = {'gene_amp': amp_gene_all, 'gene_amp_high': amp_gene_high,
'gene_del': del_gene_all, 'gene_del_homo': del_gene_homo,
'lesion_amp': amp_lesion_all, 'lesion_amp_high': amp_lesion_high,
'lesion_del': del_lesion_all, 'lesion_del_homo': del_lesion_homo,
'chrom_instability': chromosomal_instability}
cna_df = pd.DataFrame(cna_df)
if patients is not None:
cna_df = cna_df.ix[patients].dropna()
return cna_df
def get_cna_rates(data_path, cancer, patients=None):
'''
Get copy-number aberration rates from GISTIC processing pipeline.
This function depends on the current Firehose output of this program
as of July 2013.
'''
gistic = FH.get_gistic_gene_matrix(data_path, cancer)
amp_gene_all = (gistic >= 1).astype(int).sum()
amp_gene_high = (gistic == 2).astype(int).sum()
del_gene_all = (gistic <= -1).astype(int).sum()
del_gene_homo = (gistic <= -2).astype(int).sum()
lesions = FH.get_gistic_lesions(data_path, cancer)
amp_lesion_all = (lesions.ix['Amplification'] >= 1).sum()
amp_lesion_high = (lesions.ix['Amplification'] == 2).sum()
del_lesion_all = (lesions.ix['Deletion'] <= -1).sum()
del_lesion_homo = (lesions.ix['Deletion'] == -2).sum()
arm_cn = FH.get_gistic_arm_values(data_path, cancer)
chromosomal_instability = arm_cn.abs().mean()
cna_df = {
'gene_amp': amp_gene_all,
'gene_amp_high': amp_gene_high,
'gene_del': del_gene_all,
'gene_del_homo': del_gene_homo,
'lesion_amp': amp_lesion_all,
'lesion_amp_high': amp_lesion_high,
'lesion_del': del_lesion_all,
'lesion_del_homo': del_lesion_homo,
'chrom_instability': chromosomal_instability
}
cna_df = pd.DataFrame(cna_df)
if patients is not None:
cna_df = cna_df.ix[patients].dropna()
return cna_df
