def permute_cnas(cnas, gene2chromo, chromo2genes):
samples2cnas = defaultdict(list)
for cna in cnas:
samples2cnas[cna.sample].append(cna)
permuted_cnas = []
for sample in samples2cnas:
chromo2blocks = get_cna_blocks_for_sample(samples2cnas[sample],
gene2chromo, chromo2genes)
for chromo, blocks in chromo2blocks.iteritems():
genes = chromo2genes[chromo]
invalid_indices = []
for block in blocks:
permuted_indices = get_block_indices(len(genes),
len(block.genes),
invalid_indices)
for index in permuted_indices:
permuted_cnas.append(
Mutation(sample, genes[index], block.mut_type))
new_invalid_indices = permuted_indices +\
[min(permuted_indices) - 1, max(permuted_indices) + 1]
invalid_indices.extend(new_invalid_indices)
return permuted_cnas
def permute_snvs(samples, tested_genes, gene2length, bmr, gene2bmr):
permuted_snvs = []
for sample in samples:
for gene in tested_genes:
gene_bmr = gene2bmr[gene] if gene in gene2bmr else bmr
gene_length = gene2length[gene]
prob = 1 - pow(1 - gene_bmr, gene_length)
if random.random() <= prob:
permuted_snvs.append(Mutation(sample, gene, SNV))
return permuted_snvs
def load_snvs(snv_file, gene_wlst=None, sample_wlst=None):
"""Load SNV data from a file and return as a list of Mutation tuples with mut_type == SNV.
Arguments:
snv_file -- path to TSV file containing SNVs where the first column of each line is a sample ID
and subsequent columns contain the names of SNVs with mutations in that sample.
Lines starting with "#" will be ignored.
gene_wlist -- whitelist of allowed genes (default None). Genes not in this list will be ignored.
If None, all mutated genes will be included.
sample_wlist -- whitelist of allowed samples (default None). Samples not in this list will be
ignored. If None, all samples will be included.
"""
with open(snv_file) as f:
arrs = [l.rstrip().split("\t") for l in f if not l.startswith("#")]
return [
Mutation(arr[0], gene, SNV) for arr in arrs
if include(arr[0], sample_wlst) for gene in arr[1:]
if include(gene, gene_wlst)
]
def load_cnas(cna_file, gene_wlst=None, sample_wlst=None):
"""Load CNA data from a file and return as a list of Mutation tuples with mut_type == AMP or DEL.
Arguments:
cna_file -- path to TSV file containing CNAs where the first column of each line is a sample ID
and subsequent columns contain gene names followed by "(A)" or "(D)" indicating an
ammplification or deletion in that gene for the sample. Lines starting with '#'
will be ignored.
gene_wlist -- whitelist of allowed genes (default None). Genes not in this list will be ignored.
If None, all mutated genes will be included.
sample_wlist -- whitelist of allowed samples (default None). Samples not in this list will be
ignored. If None, all samples will be included.
"""
with open(cna_file) as f:
arrs = [l.rstrip().split("\t") for l in f if not l.startswith("#")]
return [
Mutation(arr[0],
cna.split("(")[0], get_mut_type(cna)) for arr in arrs
if include(arr[0], sample_wlst) for cna in arr[1:]
if include(cna.split("(")[0], gene_wlst)
]
def load_inactivating_snvs(inactivating_snvs_file,
gene_wlst=None,
sample_wlst=None):
"""Load inactivating SNVs from a file and return as a list of Mutation tuples with
mut_type == INACTIVE_SNV.
Arguments:
inactivating_snvs_file -- path to TSV file listing inactivating SNVs where the first column of
each line is a gene name and the second column is a sample ID.
Lines starting with "#" will be ignored.
gene_wlist -- whitelist of allowed genes (default None). Genes not in this list will be ignored.
If None, all mutated genes will be included.
sample_wlist -- whitelist of allowed samples (default None). Samples not in this list will be
ignored. If None, all samples will be included.
"""
with open(inactivating_snvs_file) as f:
arrs = [line.split() for line in f if not line.startswith("#")]
return [
Mutation(arr[1], arr[0], INACTIVE_SNV) for arr in arrs
if include(arr[1], sample_wlst) and include(arr[0], gene_wlst)
]
def get_invalidated_mutation(mutation):
return Mutation(mutation.sample, mutation.gene, mutation.mut_type, False)