def position_permutation(obs_stat,
context_counts,
context_to_mut,
seq_context,
gene_seq,
gene_vest=None,
num_permutations=10000,
stop_criteria=100,
pseudo_count=0,
max_batch=25000):
"""Performs null-permutations for position-based mutation statistics
in a single gene.
Parameters
----------
obs_stat : tuple, (recur ct, entropy, delta entropy, mean vest)
tuple containing the observed statistics
context_counts : pd.Series
number of mutations for each context
context_to_mut : dict
dictionary mapping nucleotide context to a list of observed
somatic base changes.
seq_context : SequenceContext
Sequence context for the entire gene sequence (regardless
of where mutations occur). The nucleotide contexts are
identified at positions along the gene.
gene_seq : GeneSequence
Sequence of gene of interest
num_permutations : int, default: 10000
number of permutations to create for null
stop_criteria : int
stop after stop_criteria iterations are more significant
then the observed statistic.
pseudo_count : int, default: 0
Pseudo-count for number of recurrent missense mutations for each
permutation for the null distribution. Increasing pseudo_count
makes the statistical test more stringent.
Returns
-------
num_recur_list : list
list of recurrent mutation counts under the null
entropy_list : list
list of position entropy values under the null
"""
# get contexts and somatic base
mycontexts = context_counts.index.tolist()
somatic_base = [base
for one_context in mycontexts
for base in context_to_mut[one_context]]
# calculate the # of batches for simulations
max_batch = min(num_permutations, max_batch)
num_batches = num_permutations // max_batch
remainder = num_permutations % max_batch
batch_sizes = [max_batch] * num_batches
if remainder:
batch_sizes += [remainder]
obs_recur, obs_ent, obs_delta_ent, obs_vest = obs_stat
num_sim = 0 # number of simulations
null_num_recur_ct, null_entropy_ct, null_delta_entropy_ct, null_vest_ct = 0, 0, 0, 0
for j, batch_size in enumerate(batch_sizes):
# stop iterations if reached sufficient precision
if null_vest_ct >= stop_criteria and null_entropy_ct >= stop_criteria:
break
# get random positions determined by sequence context
tmp_contxt_pos = seq_context.random_pos(context_counts.iteritems(),
batch_size)
tmp_mut_pos = np.hstack([pos_array for base, pos_array in tmp_contxt_pos])
# calculate position-based statistics as a result of random positions
for i, row in enumerate(tmp_mut_pos):
# get info about mutations
tmp_mut_info = mc.get_aa_mut_info(row,
somatic_base,
gene_seq)
# calculate position info
tmp_recur_ct, tmp_entropy, tmp_delta_entropy, _ = cutils.calc_pos_info(tmp_mut_info['Codon Pos'],
tmp_mut_info['Reference AA'],
tmp_mut_info['Somatic AA'],
pseudo_count=pseudo_count,
is_obs=0)
# get vest scores
if gene_vest:
tmp_vest = scores.compute_vest_stat(gene_vest,
tmp_mut_info['Reference AA'],
tmp_mut_info['Somatic AA'],
tmp_mut_info['Codon Pos'])
else:
tmp_vest = 0.0
# update empirical null distribution counts
if tmp_entropy-utils.epsilon <= obs_ent: null_entropy_ct += 1
if tmp_vest+utils.epsilon >= obs_vest: null_vest_ct += 1
# stop iterations if reached sufficient precision
if null_vest_ct >= stop_criteria and null_entropy_ct >= stop_criteria:
break
# update the number of simulations
num_sim += i+1
# calculate p-value from empirical null-distribution
ent_pval = float(null_entropy_ct) / (num_sim)
vest_pval = float(null_vest_ct) / (num_sim)
return ent_pval, vest_pval
def position_permutation(obs_stat,
context_counts,
context_to_mut,
seq_context,
gene_seq,
gene_vest=None,
num_permutations=10000,
stop_criteria=100,
pseudo_count=0,
max_batch=25000):
"""Performs null-permutations for position-based mutation statistics
in a single gene.
Parameters
----------
obs_stat : tuple, (recur ct, entropy, delta entropy, mean vest)
tuple containing the observed statistics
context_counts : pd.Series
number of mutations for each context
context_to_mut : dict
dictionary mapping nucleotide context to a list of observed
somatic base changes.
seq_context : SequenceContext
Sequence context for the entire gene sequence (regardless
of where mutations occur). The nucleotide contexts are
identified at positions along the gene.
gene_seq : GeneSequence
Sequence of gene of interest
num_permutations : int, default: 10000
number of permutations to create for null
stop_criteria : int
stop after stop_criteria iterations are more significant
then the observed statistic.
pseudo_count : int, default: 0
Pseudo-count for number of recurrent missense mutations for each
permutation for the null distribution. Increasing pseudo_count
makes the statistical test more stringent.
Returns
-------
num_recur_list : list
list of recurrent mutation counts under the null
entropy_list : list
list of position entropy values under the null
"""
# get contexts and somatic base
mycontexts = context_counts.index.tolist()
somatic_base = [base
for one_context in mycontexts
for base in context_to_mut[one_context]]
# calculate the # of batches for simulations
max_batch = min(num_permutations, max_batch)
num_batches = num_permutations // max_batch
remainder = num_permutations % max_batch
batch_sizes = [max_batch] * num_batches
if remainder:
batch_sizes += [remainder]
obs_recur, obs_ent, obs_delta_ent, obs_vest = obs_stat
num_sim = 0 # number of simulations
null_num_recur_ct, null_entropy_ct, null_delta_entropy_ct, null_vest_ct = 0, 0, 0, 0
for j, batch_size in enumerate(batch_sizes):
# stop iterations if reached sufficient precision
if null_vest_ct >= stop_criteria and null_entropy_ct >= stop_criteria:
break
# get random positions determined by sequence context
tmp_contxt_pos = seq_context.random_pos(context_counts.iteritems(),
batch_size)
tmp_mut_pos = np.hstack(pos_array for base, pos_array in tmp_contxt_pos)
# calculate position-based statistics as a result of random positions
for i, row in enumerate(tmp_mut_pos):
# get info about mutations
tmp_mut_info = mc.get_aa_mut_info(row,
somatic_base,
gene_seq)
# calculate position info
tmp_recur_ct, tmp_entropy, tmp_delta_entropy, _ = cutils.calc_pos_info(tmp_mut_info['Codon Pos'],
tmp_mut_info['Reference AA'],
tmp_mut_info['Somatic AA'],
pseudo_count=pseudo_count,
is_obs=0)
# get vest scores
if gene_vest:
tmp_vest = scores.compute_vest_stat(gene_vest,
tmp_mut_info['Reference AA'],
tmp_mut_info['Somatic AA'],
tmp_mut_info['Codon Pos'])
else:
tmp_vest = 0.0
# update empirical null distribution counts
if tmp_entropy-utils.epsilon <= obs_ent: null_entropy_ct += 1
if tmp_vest+utils.epsilon >= obs_vest: null_vest_ct += 1
# stop iterations if reached sufficient precision
if null_vest_ct >= stop_criteria and null_entropy_ct >= stop_criteria:
break
# update the number of simulations
num_sim += i+1
# calculate p-value from empirical null-distribution
ent_pval = float(null_entropy_ct) / (num_sim)
vest_pval = float(null_vest_ct) / (num_sim)
return ent_pval, vest_pval
def calc_position_p_value(mut_info, unmapped_mut_info, sc, gs, bed, score_dir,
num_permutations, stop_thresh, pseudo_count,
min_recurrent, min_fraction):
if len(mut_info) > 0:
mut_info['Coding Position'] = mut_info['Coding Position'].astype(int)
mut_info['Context'] = mut_info['Coding Position'].apply(
lambda x: sc.pos2context[x])
# group mutations by context
cols = ['Context', 'Tumor_Allele']
unmapped_mut_df = pd.DataFrame(unmapped_mut_info)
tmp_df = pd.concat([mut_info[cols], unmapped_mut_df[cols]])
context_cts = tmp_df['Context'].value_counts()
context_to_mutations = dict(
(name, group['Tumor_Allele'])
for name, group in tmp_df.groupby('Context'))
# get vest scores for gene if directory provided
if score_dir:
gene_vest = scores.read_vest_pickle(bed.gene_name, score_dir)
if gene_vest is None:
logger.warning(
'Could not find VEST scores for {0}, skipping . . .'.
format(bed.gene_name))
else:
gene_vest = None
# get recurrent info for actual mutations
aa_mut_info = mc.get_aa_mut_info(mut_info['Coding Position'],
mut_info['Tumor_Allele'].tolist(), gs)
codon_pos = aa_mut_info['Codon Pos'] + unmapped_mut_info['Codon Pos']
ref_aa = aa_mut_info['Reference AA'] + unmapped_mut_info['Reference AA']
somatic_aa = aa_mut_info['Somatic AA'] + unmapped_mut_info['Somatic AA']
num_recurrent, pos_ent, delta_pos_ent, pos_ct = cutils.calc_pos_info(
codon_pos,
ref_aa,
somatic_aa,
min_frac=min_fraction,
min_recur=min_recurrent)
# get vest score for actual mutations
vest_score = scores.compute_vest_stat(gene_vest,
aa_mut_info['Reference AA'],
aa_mut_info['Somatic AA'],
aa_mut_info['Codon Pos'])
# perform simulations to get p-value
observed_stats = (num_recurrent, pos_ent, delta_pos_ent, vest_score)
permutation_result = pm.position_permutation(
observed_stats,
context_cts,
context_to_mutations,
sc, # sequence context obj
gs, # gene sequence obj
gene_vest,
num_permutations,
stop_thresh,
pseudo_count)
ent_p_value, vest_p_value = permutation_result
else:
num_recurrent = 0
pos_ent = 0
vest_score = 0.0
ent_p_value = 1.0
vest_p_value = 1.0
result = [
bed.gene_name, num_recurrent, pos_ent, vest_score, ent_p_value,
vest_p_value
]
return result
def calc_position_p_value(mut_info,
unmapped_mut_info,
sc,
gs,
bed,
score_dir,
num_permutations,
stop_thresh,
pseudo_count,
min_recurrent,
min_fraction):
if len(mut_info) > 0:
mut_info['Coding Position'] = mut_info['Coding Position'].astype(int)
mut_info['Context'] = mut_info['Coding Position'].apply(lambda x: sc.pos2context[x])
# group mutations by context
cols = ['Context', 'Tumor_Allele']
unmapped_mut_df = pd.DataFrame(unmapped_mut_info)
tmp_df = pd.concat([mut_info[cols], unmapped_mut_df[cols]])
context_cts = tmp_df['Context'].value_counts()
context_to_mutations = dict((name, group['Tumor_Allele'])
for name, group in tmp_df.groupby('Context'))
# get vest scores for gene if directory provided
if score_dir:
gene_vest = scores.read_vest_pickle(bed.gene_name, score_dir)
if gene_vest is None:
logger.warning('Could not find VEST scores for {0}, skipping . . .'.format(bed.gene_name))
else:
gene_vest = None
# get recurrent info for actual mutations
aa_mut_info = mc.get_aa_mut_info(mut_info['Coding Position'],
mut_info['Tumor_Allele'].tolist(),
gs)
codon_pos = aa_mut_info['Codon Pos'] + unmapped_mut_info['Codon Pos']
ref_aa = aa_mut_info['Reference AA'] + unmapped_mut_info['Reference AA']
somatic_aa = aa_mut_info['Somatic AA'] + unmapped_mut_info['Somatic AA']
num_recurrent, pos_ent, delta_pos_ent, pos_ct = cutils.calc_pos_info(codon_pos,
ref_aa,
somatic_aa,
min_frac=min_fraction,
min_recur=min_recurrent)
# get vest score for actual mutations
vest_score = scores.compute_vest_stat(gene_vest,
aa_mut_info['Reference AA'],
aa_mut_info['Somatic AA'],
aa_mut_info['Codon Pos'])
# perform simulations to get p-value
observed_stats = (num_recurrent, pos_ent, delta_pos_ent, vest_score)
permutation_result = pm.position_permutation(observed_stats,
context_cts,
context_to_mutations,
sc, # sequence context obj
gs, # gene sequence obj
gene_vest,
num_permutations,
stop_thresh,
pseudo_count)
ent_p_value, vest_p_value = permutation_result
else:
num_recurrent = 0
pos_ent = 0
vest_score = 0.0
ent_p_value = 1.0
vest_p_value = 1.0
result = [bed.gene_name, num_recurrent, pos_ent, vest_score,
ent_p_value, vest_p_value]
return result