def test_ctnnb1_get_aa_mut_info():
import pysam
from prob2020.python.gene_sequence import GeneSequence
# read fasta
ctnnb1_fasta = os.path.join(file_dir, 'data/CTNNB1.fa')
gene_fa = pysam.Fastafile(ctnnb1_fasta)
gs = GeneSequence(gene_fa, nuc_context=1)
# read CTNNB1 bed file
ctnnb1_bed = os.path.join(file_dir, 'data/CTNNB1.bed')
bed_list = [b for b in utils.bed_generator(ctnnb1_bed)]
gs.set_gene(bed_list[0])
# specify mutation
coding_pos = [0]
somatic_base = ['C']
# check mutation info
aa_info = mc.get_aa_mut_info(coding_pos, somatic_base, gs)
ref_codon_msg = 'First codon should be start codon ({0})'.format(
aa_info['Reference Codon'][0])
assert aa_info['Reference Codon'][0] == 'ATG', ref_codon_msg
assert aa_info['Somatic Codon'][
0] == 'CTG', 'First "A" should be replaced with a "C"'
assert aa_info['Codon Pos'][0] == 0, 'Start codon should be position 0'
def test_no_context_constructor():
# no context
gs = GeneSequence(gene_fa, nuc_context=0)
gs.set_gene(bed)
sc = SequenceContext(gs)
true_counts = {'None': 21}
true_ctxt2pos = {'None': range(21)}
_check_true_counts(sc, true_counts)
_check_true_context_pos(sc, true_ctxt2pos)
def test_simple_constructor():
gs = GeneSequence(gene_fa, nuc_context=1)
gs.set_gene(bed)
assert gs.exon_seq == 'ACATGAATGATAGATCCGAAA', 'Sequence is not correct'
# this should update the sequence correctly
fake_germline = ['A', 'C', 'N', 'G', 'T']
fake_pos = [1, 0, 20, 7, 15]
gs.add_germline_variants(fake_germline, fake_pos)
assert gs.exon_seq == 'CAATGAAGGATAGATTCGAAN'
def test_simple_constructor():
gs = GeneSequence(gene_fa, nuc_context=1)
gs.set_gene(bed)
assert gs.exon_seq == 'ACATGAATGATAGATCCGAAA', 'Sequence is not correct'
# this should update the sequence correctly
fake_germline = ['A', 'C', 'N', 'G', 'T']
fake_pos = [1, 0, 20, 7, 15]
gs.add_germline_variants(fake_germline, fake_pos)
assert gs.exon_seq == 'CAATGAAGGATAGATTCGAAN'
def test_pos_to_codon():
gs = GeneSequence(gene_fa, nuc_context=1)
gs.set_gene(bed)
pos_list = [1, 12, 17]
results = []
for pos in pos_list:
codon_info = cutils.pos_to_codon(gs, pos)
results.append(codon_info)
true_results = [('ACA', 0, 1, 'C'), ('GAT', 4, 0, 'G'), ('CCG', 5, 2, 'G')]
assert results == true_results, 'Codon information is incorrect'
def test_pos_to_codon():
gs = GeneSequence(gene_fa, nuc_context=1)
gs.set_gene(bed)
pos_list = [1, 12, 17]
results = []
for pos in pos_list:
codon_info = cutils.pos_to_codon(gs, pos)
results.append(codon_info)
true_results = [('ACA', 0, 1, 'C'), ('GAT', 4, 0, 'G'), ('CCG', 5, 2, 'G')]
assert results == true_results, 'Codon information is incorrect'
def is_nonsilent(mut_df, bed_dict, opts):
# convert dictionary to list for bed objects
gene_beds = [b for chrom in bed_dict for b in bed_dict[chrom]]
# initiate gene sequences
gene_fa = pysam.Fastafile(opts['input'])
gs = GeneSequence(gene_fa, nuc_context=opts['context'])
# non-silent SNV classes
non_silent_snv = [
'Nonsense_Mutation', 'Nonstop_Mutation', 'Splice_Site',
'Translation_Start_Site', 'Missense_Mutation'
]
# record indels and get only snvs
mut_df['is_nonsilent'] = 0
indel_flag = indel.is_indel_annotation(mut_df)
mut_df.loc[indel_flag, 'is_nonsilent'] = 1
snv_df = mut_df[~indel_flag]
# iterate over each gene
for bed in gene_beds:
# initiate for this gene
tmp_df = snv_df[snv_df['Gene'] == bed.gene_name]
gs.set_gene(bed)
# compute context counts and somatic bases for each context
gene_tuple = compute_mutation_context(bed, gs, tmp_df, opts)
context_cts, context_to_mutations, mutations_df, gs, sc = gene_tuple
if len(mutations_df):
# get snv information
tmp_mut_info = get_aa_mut_info(
mutations_df['Coding Position'],
mutations_df['Tumor_Allele'].tolist(), gs)
# get string describing variant
var_class = cutils.get_variant_classification(
tmp_mut_info['Reference AA'], tmp_mut_info['Somatic AA'],
tmp_mut_info['Codon Pos'])
# detect if non-silent snv
is_nonsilent_snv = [
1 if (x in non_silent_snv) else 0 for x in var_class
]
mut_df.loc[tmp_df.index, 'is_nonsilent'] = is_nonsilent_snv
# return a pandas series indicating nonsilent status
is_nonsilent_series = mut_df['is_nonsilent'].copy()
del mut_df['is_nonsilent']
return is_nonsilent_series
def test_single_context_constructor():
# single nuc context
gs = GeneSequence(gene_fa, nuc_context=1)
gs.set_gene(bed)
sc = SequenceContext(gs)
true_counts = {'A': 10,
'T': 4,
'G': 4,
'C': 3}
true_ctxt2pos = {'A': [0, 2, 5, 6, 9, 11, 13, 18, 19, 20],
'C': [1, 15, 16],
'G': [4, 8, 12, 17],
'T': [3, 7, 10, 14]}
_check_true_counts(sc, true_counts)
_check_true_context_pos(sc, true_ctxt2pos)
def test_chasm_context_constructor():
# chasm context, mixture between single and di context
gs = GeneSequence(gene_fa, nuc_context=1.5)
gs.set_gene(bed)
sc = SequenceContext(gs)
true_counts = {'A': 10,
'C': 1,
'C*pG': 1,
'CpG*': 1,
'G*pA': 3,
'T': 4,
'TpC*': 1}
true_ctxt2pos = {'A': [2, 5, 6, 9, 11, 13, 18, 19, 0, 20],
'C': [1],
'C*pG': [16],
'CpG*': [17],
'G*pA': [4, 8, 12],
'T': [3, 7, 10, 14],
'TpC*': [15]}
_check_true_counts(sc, true_counts)
_check_true_context_pos(sc, true_ctxt2pos)
def test_ctnnb1_get_aa_mut_info():
import pysam
from prob2020.python.gene_sequence import GeneSequence
# read fasta
ctnnb1_fasta = os.path.join(file_dir, 'data/CTNNB1.fa')
gene_fa = pysam.Fastafile(ctnnb1_fasta)
gs = GeneSequence(gene_fa, nuc_context=1)
# read CTNNB1 bed file
ctnnb1_bed = os.path.join(file_dir, 'data/CTNNB1.bed')
bed_list = [b for b in utils.bed_generator(ctnnb1_bed)]
gs.set_gene(bed_list[0])
# specify mutation
coding_pos = [0]
somatic_base = ['C']
# check mutation info
aa_info = mc.get_aa_mut_info(coding_pos, somatic_base, gs)
ref_codon_msg = 'First codon should be start codon ({0})'.format(aa_info['Reference Codon'][0])
assert aa_info['Reference Codon'][0] == 'ATG', ref_codon_msg
assert aa_info['Somatic Codon'][0] == 'CTG', 'First "A" should be replaced with a "C"'
assert aa_info['Codon Pos'][0] == 0, 'Start codon should be position 0'
def singleprocess_permutation(info):
# initialize input
bed_list, mut_df, opts, fs_cts_df, p_inactivating = info
current_chrom = bed_list[0].chrom
logger.info('Working on chromosome: {0} . . .'.format(current_chrom))
gene_fa = pysam.Fastafile(opts['input'])
gs = GeneSequence(gene_fa, nuc_context=opts['context'])
# list of columns that are needed
cols = [
'Chromosome',
'Start_Position',
'Reference_Allele',
'Tumor_Allele',
'Variant_Classification',
]
# conditionally add protein_change column if exists
if 'Protein_Change' in mut_df.columns:
cols += ['Protein_Change']
# figure out which genes actually have a mutation
genes_with_mut = set(mut_df['Gene'].unique())
# iterate through each gene
result = []
for bed in bed_list:
if bed.gene_name not in genes_with_mut:
# skip genes with no mutations
continue
# prepare info for running permutation test
mut_info = mut_df.loc[mut_df['Gene'] == bed.gene_name, cols]
gs.set_gene(bed)
sc = SequenceContext(gs, seed=opts['seed'])
# count total mutations in gene
total_mut = len(mut_info)
# fix nucleotide letter if gene is on - strand
if bed.strand == '-':
rc = mut_info['Tumor_Allele'].map(lambda x: utils.rev_comp(x))
mut_info.loc[:, 'Tumor_Allele'] = rc
# get coding positions, mutations unmapped to the reference tx will have
# NA for a coding position
pos_list = []
for ix, row in mut_info.iterrows():
coding_pos = bed.query_position(bed.strand, row['Chromosome'],
row['Start_Position'])
pos_list.append(coding_pos)
mut_info.loc[:, 'Coding Position'] = pos_list
# recover mutations that could not be mapped to the reference transcript
# for a gene before being dropped (next step)
unmapped_mut_info = mc.recover_unmapped_mut_info(
mut_info, bed, sc, opts)
# drop mutations wich do not map to reference tx
mut_info = mut_info.dropna(subset=['Coding Position'
]) # mutations need to map to tx
mut_info['Coding Position'] = mut_info['Coding Position'].astype(int)
num_mapped_muts = len(mut_info)
unmapped_muts = total_mut - num_mapped_muts
# construct sequence context
#gs.add_germline_variants(mut_info['Reference_Allele'].tolist(),
# mut_info['Coding Position'].tolist())
# calculate results of permutation test
if opts['kind'] == 'oncogene':
# calculate position based permutation results
tmp_result = mypval.calc_position_p_value(
mut_info,
unmapped_mut_info,
sc,
gs,
bed,
opts['score_dir'],
opts['num_iterations'],
opts['stop_criteria'],
0, # no recurrent mutation pseudo count
opts['recurrent'],
opts['fraction'])
result.append(tmp_result + [total_mut, unmapped_muts])
elif opts['kind'] == 'tsg':
# calculate results for deleterious mutation permutation test
#fs_ct = fs_cts_df['total'][bed.gene_name]
#fs_unmapped = fs_cts_df['unmapped'][bed.gene_name]
# replaced fs_ct with zero to stop using the frameshifts in
# simulation
tmp_result = mypval.calc_deleterious_p_value(
mut_info,
unmapped_mut_info,
sc,
gs,
bed,
opts['num_iterations'],
opts['stop_criteria'],
opts['deleterious'],
0, # no deleterious mutation pseudo count
opts['seed'])
result.append(tmp_result + [num_mapped_muts, unmapped_muts])
#fs_ct, fs_unmapped])
elif opts['kind'] == 'hotmaps1d':
# save null distribution if user option specified
if opts['null_distr_dir']:
if not os.path.exists(opts['null_distr_dir']):
os.mkdir(opts['null_distr_dir'])
save_path = os.path.join(opts['null_distr_dir'],
bed.gene_name + '.{0}.txt')
else:
save_path = None
# calculate position based permutation results
mywindow = list(map(int, opts['window'].split(',')))
tmp_result = mypval.calc_hotmaps_p_value(mut_info,
unmapped_mut_info,
sc,
gs,
bed,
mywindow,
opts['num_iterations'],
opts['stop_criteria'],
opts['report_index'],
null_save_path=save_path)
result.extend(tmp_result)
elif opts['kind'] == 'protein':
tmp_result = mypval.calc_protein_p_value(
mut_info, unmapped_mut_info, sc, gs, bed,
opts['neighbor_graph_dir'], opts['num_iterations'],
opts['stop_criteria'], opts['recurrent'], opts['fraction'])
result.append(tmp_result + [total_mut, unmapped_muts])
else:
# calc results for entropy-on-effect permutation test
tmp_result = mypval.calc_effect_p_value(
mut_info,
unmapped_mut_info,
sc,
gs,
bed,
opts['num_iterations'],
0, # no recurrent mutation pseudo count
opts['recurrent'],
opts['fraction'])
result.append(tmp_result + [total_mut, unmapped_muts])
gene_fa.close()
logger.info('Finished working on chromosome: {0}.'.format(current_chrom))
return result
def singleprocess_permutation(info):
# initialize input
bed_list, mut_df, opts, fs_cts_df, p_inactivating = info
current_chrom = bed_list[0].chrom
logger.info('Working on chromosome: {0} . . .'.format(current_chrom))
gene_fa = pysam.Fastafile(opts['input'])
gs = GeneSequence(gene_fa, nuc_context=opts['context'])
# list of columns that are needed
cols = ['Chromosome', 'Start_Position', 'Reference_Allele',
'Tumor_Allele', 'Variant_Classification',]
# conditionally add protein_change column if exists
if 'Protein_Change' in mut_df.columns:
cols += ['Protein_Change']
# figure out which genes actually have a mutation
genes_with_mut = set(mut_df['Gene'].unique())
# iterate through each gene
result = []
for bed in bed_list:
if bed.gene_name not in genes_with_mut:
# skip genes with no mutations
continue
# prepare info for running permutation test
mut_info = mut_df.loc[mut_df['Gene']==bed.gene_name, cols]
gs.set_gene(bed)
sc = SequenceContext(gs, seed=opts['seed'])
# count total mutations in gene
total_mut = len(mut_info)
# fix nucleotide letter if gene is on - strand
if bed.strand == '-':
rc = mut_info['Tumor_Allele'].map(lambda x: utils.rev_comp(x))
mut_info.loc[:, 'Tumor_Allele'] = rc
# get coding positions, mutations unmapped to the reference tx will have
# NA for a coding position
pos_list = []
for ix, row in mut_info.iterrows():
coding_pos = bed.query_position(bed.strand, row['Chromosome'], row['Start_Position'])
pos_list.append(coding_pos)
mut_info.loc[:, 'Coding Position'] = pos_list
# recover mutations that could not be mapped to the reference transcript
# for a gene before being dropped (next step)
unmapped_mut_info = mc.recover_unmapped_mut_info(mut_info, bed, sc, opts)
# drop mutations wich do not map to reference tx
mut_info = mut_info.dropna(subset=['Coding Position']) # mutations need to map to tx
mut_info['Coding Position'] = mut_info['Coding Position'].astype(int)
num_mapped_muts = len(mut_info)
unmapped_muts = total_mut - num_mapped_muts
# construct sequence context
#gs.add_germline_variants(mut_info['Reference_Allele'].tolist(),
# mut_info['Coding Position'].tolist())
# calculate results of permutation test
if opts['kind'] == 'oncogene':
# calculate position based permutation results
tmp_result = mypval.calc_position_p_value(mut_info, unmapped_mut_info, sc,
gs, bed, opts['score_dir'],
opts['num_iterations'],
opts['stop_criteria'],
0, # no recurrent mutation pseudo count
opts['recurrent'],
opts['fraction'])
result.append(tmp_result + [total_mut, unmapped_muts])
elif opts['kind'] == 'tsg':
# calculate results for deleterious mutation permutation test
#fs_ct = fs_cts_df['total'][bed.gene_name]
#fs_unmapped = fs_cts_df['unmapped'][bed.gene_name]
# replaced fs_ct with zero to stop using the frameshifts in
# simulation
tmp_result = mypval.calc_deleterious_p_value(mut_info, unmapped_mut_info,
sc, gs, bed,
opts['num_iterations'],
opts['stop_criteria'],
opts['deleterious'],
0, # no deleterious mutation pseudo count
opts['seed'])
result.append(tmp_result + [num_mapped_muts, unmapped_muts])
#fs_ct, fs_unmapped])
elif opts['kind'] == 'hotmaps1d':
# save null distribution if user option specified
if opts['null_distr_dir']:
if not os.path.exists(opts['null_distr_dir']): os.mkdir(opts['null_distr_dir'])
save_path = os.path.join(opts['null_distr_dir'], bed.gene_name + '.{0}.txt')
else:
save_path = None
# calculate position based permutation results
mywindow = list(map(int, opts['window'].split(',')))
tmp_result = mypval.calc_hotmaps_p_value(mut_info, unmapped_mut_info, sc,
gs, bed,
mywindow,
opts['num_iterations'],
opts['stop_criteria'],
opts['report_index'],
null_save_path=save_path)
result.extend(tmp_result)
elif opts['kind'] == 'protein':
tmp_result = mypval.calc_protein_p_value(mut_info, unmapped_mut_info,
sc, gs, bed,
opts['neighbor_graph_dir'],
opts['num_iterations'],
opts['stop_criteria'],
opts['recurrent'],
opts['fraction'])
result.append(tmp_result + [total_mut, unmapped_muts])
else:
# calc results for entropy-on-effect permutation test
tmp_result = mypval.calc_effect_p_value(mut_info, unmapped_mut_info,
sc, gs, bed,
opts['num_iterations'],
0, # no recurrent mutation pseudo count
opts['recurrent'],
opts['fraction'])
result.append(tmp_result + [total_mut, unmapped_muts])
gene_fa.close()
logger.info('Finished working on chromosome: {0}.'.format(current_chrom))
return result
def test_dinuc_context_constructor():
# dinucleotide context
gs = GeneSequence(gene_fa, nuc_context=2)
gs.set_gene(bed)
sc = SequenceContext(gs)