def calc_protein_p_value(mut_info, unmapped_mut_info, sc, gs, bed, graph_dir,
num_permutations, stop_thresh, min_recurrent,
min_fraction):
"""Computes the p-value for clustering on a neighbor graph composed
of codons connected with edges if they are spatially near in 3D protein
structure.
Parameters
----------
Returns
-------
"""
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 graph_dir:
gene_graph = scores.read_neighbor_graph_pickle(
bed.gene_name, graph_dir)
if gene_graph is None:
logger.warning(
'Could not find neighbor graph for {0}, skipping . . .'.
format(bed.gene_name))
else:
gene_graph = 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)
try:
# get vest score for actual mutations
graph_score, coverage = scores.compute_ng_stat(gene_graph, pos_ct)
# perform simulations to get p-value
protein_p_value, norm_graph_score = pm.protein_permutation(
graph_score,
len(pos_ct),
context_cts,
context_to_mutations,
sc, # sequence context obj
gs, # gene sequence obj
gene_graph,
num_permutations,
stop_thresh)
except Exception as err:
exc_info = sys.exc_info()
norm_graph_score = 0.0
protein_p_value = 1.0
logger.warning('Codon numbering problem with ' + bed.gene_name)
else:
norm_graph_score = 0.0
protein_p_value = 1.0
num_recurrent = 0
result = [bed.gene_name, num_recurrent, norm_graph_score, protein_p_value]
return result
def calc_protein_p_value(mut_info,
unmapped_mut_info,
sc,
gs,
bed,
graph_dir,
num_permutations,
stop_thresh,
min_recurrent,
min_fraction):
"""Computes the p-value for clustering on a neighbor graph composed
of codons connected with edges if they are spatially near in 3D protein
structure.
Parameters
----------
Returns
-------
"""
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 graph_dir:
gene_graph = scores.read_neighbor_graph_pickle(bed.gene_name, graph_dir)
if gene_graph is None:
logger.warning('Could not find neighbor graph for {0}, skipping . . .'.format(bed.gene_name))
else:
gene_graph = 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)
try:
# get vest score for actual mutations
graph_score, coverage = scores.compute_ng_stat(gene_graph, pos_ct)
# perform simulations to get p-value
protein_p_value, norm_graph_score = pm.protein_permutation(
graph_score, len(pos_ct), context_cts,
context_to_mutations,
sc, # sequence context obj
gs, # gene sequence obj
gene_graph, num_permutations, stop_thresh
)
except Exception as err:
exc_info = sys.exc_info()
norm_graph_score = 0.0
protein_p_value = 1.0
logger.warning('Codon numbering problem with '+bed.gene_name)
else:
norm_graph_score = 0.0
protein_p_value = 1.0
num_recurrent = 0
result = [bed.gene_name, num_recurrent, norm_graph_score, protein_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
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