def test_genesyn_calc_ratio3c():
# syn = nonsyn = 0
gs = GeneSNP(
gene_id='A',
taxon_id=1,
exp_syn=4,
exp_nonsyn=6,
)
assert numpy.isnan(gs.calc_ratio())
def test_genesyn_calc_ratio2():
# syn = nonsyn = 0, haplotypes=True
gs = GeneSNP(
gene_id='A',
taxon_id=1,
exp_syn=4,
exp_nonsyn=6,
)
assert gs.calc_ratio(haplotypes=True) == 0.0
def test_genesyn_calc_ratio4c():
# nonsyn = 0, syn > 0
# flag_value=True
gs = GeneSNP(
gene_id='A',
taxon_id=1,
exp_syn=4,
exp_nonsyn=6,
)
assert gs.calc_ratio_flag() == -3
def test_genesyn_calc_ratio4b():
# nonsyn = 0, syn > 0
# flag_value=True
gs = GeneSNP(
gene_id='A',
taxon_id=1,
exp_syn=4,
exp_nonsyn=6,
)
gs.add_snp(1, 'A', SNPType.syn)
assert gs.calc_ratio_flag() == -2
def test_genesyn_add1():
# checks if the conserved gene_id and taxon_id is from the first instance
gs1 = GeneSNP(
gene_id='A',
taxon_id=1,
exp_syn=4,
exp_nonsyn=6
)
gs2 = GeneSNP(
exp_syn=4,
exp_nonsyn=6,
coverage=4
)
gs1.add(gs2)
assert (gs1.gene_id, gs1.taxon_id) == ('A', 1)
def test_genesyn_calc_ratio1():
# syn and nonsyn > 0
gs = GeneSNP(
gene_id='A',
taxon_id=1,
exp_syn=4,
exp_nonsyn=6,
)
gs.add_snp(1, 'A', SNPType.syn)
gs.add_snp(1, 'A', SNPType.syn)
gs.add_snp(1, 'A', SNPType.nonsyn)
gs.add_snp(1, 'A', SNPType.nonsyn)
gs.add_snp(1, 'A', SNPType.nonsyn)
assert gs.calc_ratio() == 1.0
def test_snps_gene_id1():
gene_syn = GeneSNP(gene_id='K01201')
gene_list = ['K01201', 'K02201', 'K01251']
assert filter_genesyn_by_gene_id(
gene_syn,
gene_list,
id_func=lambda x: x.gene_id
)
def test_snps_taxon2_rev(ncbi_taxonomy):
# will find it
filter_list = [
taxon.taxon_id
for taxon in ncbi_taxonomy
if 'clostridium' in taxon.s_name
]
taxon_id = ncbi_taxonomy.find_by_name('methanobrevibacter')[0]
gene_syn = GeneSNP(taxon_id=taxon_id)
assert filter_genesyn_by_taxon_id(
gene_syn,
ncbi_taxonomy,
filter_list=filter_list,
exclude=True
)
def test_snps_taxon1(ncbi_taxonomy):
# will find it
filter_list = [
taxon.taxon_id
for taxon in ncbi_taxonomy
if 'methanobrevibacter' in taxon.s_name.lower()
]
taxon_id = ncbi_taxonomy.find_by_name('methanobrevibacter')[0]
gene_syn = GeneSNP(taxon_id=taxon_id)
assert filter_genesyn_by_taxon_id(
gene_syn,
ncbi_taxonomy,
filter_list=filter_list,
exclude=False
)
def test_snps_taxon3(ncbi_taxonomy):
# will find it
filter_list = [
taxon.taxon_id
for taxon in ncbi_taxonomy
if 'clostridium' in taxon.s_name
]
taxon_id = ncbi_taxonomy.find_by_name('methanobrevibacter')[0]
gene_syn = GeneSNP(taxon_id=taxon_id)
assert not filter_genesyn_by_taxon_id(
gene_syn,
ncbi_taxonomy,
filter_list=filter_list,
exclude=False,
func=mgkit.taxon.is_ancestor
)
def test_snps_gene_coverage_exc():
gene_syn = GeneSNP(gene_id='K01201')
min_cov = None
with pytest.raises(FilterFails):
filter_genesyn_by_coverage(gene_syn, min_cov=min_cov)
def test_snps_gene_coverage2():
gene_syn = GeneSNP(gene_id='K01201', coverage=3)
min_cov = 4
assert not filter_genesyn_by_coverage(gene_syn, min_cov=min_cov)
def test_snps_gene_id_exc():
gene_syn = GeneSNP(gene_id='K01201')
gene_list = None
with pytest.raises(FilterFails):
filter_genesyn_by_gene_id(gene_syn, gene_ids=gene_list)
def test_snps_taxon4_exc2():
gene_syn = GeneSNP()
with pytest.raises(FilterFails):
filter_genesyn_by_taxon_id(
gene_syn, filter_list=None
)
def test_genesyn_add2():
# checks if the values (syn, nonsyn, exp_syn, exp_nonsyn) are added
gs1 = GeneSNP(
gene_id='A',
taxon_id=1,
exp_syn=4,
exp_nonsyn=6
)
gs1.add_snp(1, 'A', SNPType.syn)
gs1.add_snp(1, 'A', SNPType.syn)
gs1.add_snp(1, 'A', SNPType.syn)
gs1.add_snp(1, 'A', SNPType.nonsyn)
gs2 = GeneSNP(
exp_syn=3,
exp_nonsyn=5,
coverage=4
)
gs2.add_snp(1, 'A', SNPType.syn)
gs2.add_snp(1, 'A', SNPType.nonsyn)
gs2.add_snp(1, 'A', SNPType.nonsyn)
gs1.add(gs2)
assert (gs1.exp_syn, gs1.exp_nonsyn, gs1.syn, gs1.nonsyn) == (7, 11, 4, 3)
taxon_id=1,
exp_syn=4,
exp_nonsyn=6,
)
assert gs.calc_ratio_flag() == -3
SNP_DATA = {
'sample1': {
'gene1': GeneSNP(
gene_id='gene1',
taxon_id=839, # prevotella ruminicola
exp_syn=6,
exp_nonsyn=4,
snps=[
(1, 'A', SNPType.syn),
(1, 'A', SNPType.syn),
(1, 'A', SNPType.syn),
(1, 'A', SNPType.nonsyn),
(1, 'A', SNPType.nonsyn),
]
), # pN/pS = 1.0
'gene2': GeneSNP(
gene_id='gene2',
taxon_id=838, # prevotella genus
exp_syn=3,
exp_nonsyn=4,
snps=[
(1, 'A', SNPType.syn),
(1, 'A', SNPType.syn),
(1, 'A', SNPType.syn),
def test_genesyn_add3():
# checks if the values if coverage is correctly added
# coverage in gs2 is not None, in gs1 is None
gs1 = GeneSNP(
gene_id='A',
taxon_id=1,
exp_syn=4,
exp_nonsyn=6
)
gs1.add_snp(1, 'A', SNPType.syn)
gs1.add_snp(1, 'A', SNPType.syn)
gs1.add_snp(1, 'A', SNPType.syn)
gs1.add_snp(1, 'A', SNPType.nonsyn)
gs2 = GeneSNP(
exp_syn=3,
exp_nonsyn=5,
coverage=5
)
gs2.add_snp(1, 'A', SNPType.syn)
gs2.add_snp(1, 'A', SNPType.nonsyn)
gs2.add_snp(1, 'A', SNPType.nonsyn)
gs1.add(gs2)
assert gs1.coverage == 5
def test_snps_taxon4_exc1():
gene_syn = GeneSNP()
with pytest.raises(FilterFails):
filter_genesyn_by_taxon_id(
gene_syn, filter_list=range(10), taxonomy=None, func=filter
)