def test_dicts():
with tempfile.NamedTemporaryFile("wt", suffix=".gff") as gff_temp:
print(gff_ends_at_directive, file=gff_temp)
gff_temp.flush()
r1 = GFFReader(gff_temp.name)
r2 = GFFReader(gff_temp.name)
r1.uids.add("Test")
assert r1.uids != r2.uids
def test_ids_are_unique():
with tempfile.NamedTemporaryFile("wt", suffix=".gff") as gff_temp:
print(gff_non_unique_ids, file=gff_temp)
gff_temp.flush()
with pytest.raises(Exception):
for _ in GFFReader(gff_temp.name):
pass
def test_wrong_number_of_fields():
with tempfile.NamedTemporaryFile("wt", suffix=".gff") as gff_temp:
print(gff_wrong_number_of_fields, file=gff_temp)
gff_temp.flush()
with pytest.raises(IOError):
for _ in GFFReader(gff_temp.name):
pass
def test_ends_mid_comment():
with tempfile.NamedTemporaryFile("wt", suffix=".gff") as gff_temp:
print(gff_ends_at_comment, file=gff_temp)
gff_temp.flush()
for _ in GFFReader(gff_temp.name):
result = _
assert result.start == 2
def test_gene_parented():
with tempfile.NamedTemporaryFile("wt", suffix=".gff") as gff_temp:
print(gff_gene_parented_CDS, file=gff_temp)
gff_temp.flush()
for _ in GFFReader(gff_temp.name):
pass
assert _
def test_invalid_mid_file():
with tempfile.NamedTemporaryFile("wt", suffix=".gff") as gff_temp:
print(gff_not_valid_file_content, file=gff_temp)
gff_temp.flush()
with pytest.raises(AssertionError):
for _ in GFFReader(gff_temp.name):
pass
def test_with_construct():
with tempfile.NamedTemporaryFile("wt", suffix=".gff") as gff_temp:
print(gff_file_content, file=gff_temp)
gff_temp.flush()
with GFFReader(gff_temp.name) as reader:
result = next(reader)
assert result.start == 2
def test_gff_gnomon():
num_genes = 0
total_transcripts = 0
total_exons = 0
monoexonic_cds = 0
monoexonic = 0
for gene in GFFReader("tests/unit/data/ncbi_annot.gff"):
num_transcripts = 0
for mrna_id, mrna in gene.mrnas.items():
num_coding_exons = len(mrna.cds_exons)
if num_coding_exons > 0:
total_exons += len(mrna.exons)
num_transcripts += 1
if len(mrna.cds_exons) == 1:
monoexonic_cds += 1
if len(mrna.exons) == 1:
monoexonic += 1
if num_transcripts > 0:
num_genes += 1
total_transcripts += num_transcripts
assert num_genes == 3
assert total_transcripts == 3
assert monoexonic_cds == 2
assert monoexonic == 2
assert total_exons == 11
s = gene.mrnas["rna-XM_003689506.3"].to_bed(cds_only=True)
bed_line = "NW_003789112.1\t4846\t25552\trna-XM_003689506.3\t0\t-\t4846\t25552\t0,0,0\t9\t38,131,245,228,185,186,198,115,315\t0,548,1486,3275,5756,6363,7036,16397,20391"
assert s.split('\t')[:12] == bed_line.split('\t')[:12]
def test_cds_w_no_phase():
with tempfile.NamedTemporaryFile("wt", suffix=".gff") as tmp:
print(gff_CDS_w_no_phase, file=tmp)
tmp.flush()
for _ in GFFReader(tmp.name):
pass
for mrna in _.mrnas.values():
for cds in mrna.cds_exons:
assert cds.phase != '.'
def test_with_directives():
with tempfile.NamedTemporaryFile("wt", suffix=".gff") as gff_temp:
print(gff_file_content_with_directives, file=gff_temp)
gff_temp.flush()
count = 0
for _ in GFFReader(gff_temp.name):
if count == 1:
result = _
count += 1
assert result.start == 3306
assert _.uid == "AL1G10030.v2.1"
def test_eden():
with tempfile.NamedTemporaryFile("wt", suffix=".gff") as gff_temp:
print(gff_file_eden, file=gff_temp)
gff_temp.flush()
gene_count = 0
for _ in GFFReader(gff_temp.name):
gene_count += 1
assert gene_count == 1
assert _.uid == "gene00001"
assert len(_.mrnas) == 3
assert _.mrnas[next(iter(_.mrnas.keys()))].cds_exons[0].uid == "cds00001"
def test_ends_at_directive():
with tempfile.NamedTemporaryFile("wt", suffix=".gff") as gff_temp:
print(gff_ends_at_directive, file=gff_temp)
gff_temp.flush()
for _ in GFFReader(gff_temp.name):
result = _
assert result.start == 2
assert result.mrnas[next(iter(
result.mrnas.keys()))].attr['Alias'] == ['gene1', 'gene2', 'gnee3']
assert result.mrnas[next(iter(
result.mrnas.keys()))].attr['Ontology_term'] == ['t1', 't2']
assert result.attr['Dbxref'] == ['db1']
def test_int_exon_mitochondrial_gff():
genes = {}
for gene in GFFReader("tests/unit/data/int_mitochondrial.gff"):
genes[gene.uid] = gene
assert genes['gene-CYTB'] is not None
assert len(genes['gene-CYTB'].mrnas) > 0
assert len(genes['gene-CYTB'].mrnas['gene-CYTB'].exons) > 0
assert genes['gene-CYTB'].mrnas['gene-CYTB'].exons[0].uid[:5] == 'virt_'
assert genes['gene-ND1'].mrnas['gene-ND1'].cds_exons[0].uid[:5] != 'virt_'
assert genes['gene-ND1'].mrnas['gene-ND1'].exons[0].uid[:5] == 'virt_'
assert genes['gene-ND1'].mrnas['gene-ND1'].cds_exons[0].uid[:5] != 'virt_'
def test_eden_integer_chr():
with tempfile.NamedTemporaryFile("wt", suffix=".gff") as gff_temp:
print(gff_file_eden_integerableChr, file=gff_temp)
gff_temp.flush()
gene_count = 0
for _ in GFFReader(gff_temp.name):
gene_count += 1
assert gene_count == 1
assert _.uid == "gene00001"
assert len(_.mrnas) == 3
assert _.mrnas[next(iter(_.mrnas.keys()))].cds_exons[0].uid == "cds00001"
_.print_gff()
for mrna in _.mrnas.values():
print(mrna.to_bed(cds_only=True))
def test_check_splicing_sites(self):
genes = [g for g in GFFReader("tests/unit/data/refseq/pstrand_c.gff")]
genome = pyfaidx.Fasta("tests/unit/data/refseq/pstrand_c.fa")
long_intron, short_intron, nc_splicing, intron_len = check_splicing_sites(genome,
genes[0].mrnas["rna-XM_625167.6.m1"],
200000, 59)
os.remove("tests/unit/data/refseq/pstrand_c.fa.fai")
assert nc_splicing == 0
assert short_intron == 1
genes = [g for g in GFFReader("tests/unit/data/refseq/mstrand_c.gff")]
genome = pyfaidx.Fasta("tests/unit/data/refseq/mstrand_c.fa")
long_intron, short_intron, nc_splicing, intron_len = check_splicing_sites(genome,
genes[0].mrnas["rna-XM_392640.7.m1"],
200000)
os.remove("tests/unit/data/refseq/mstrand_c.fa.fai")
assert nc_splicing == 0
assert short_intron == 0
genes = [g for g in GFFReader("tests/unit/data/refseq/pstrand_nc.gff")]
genome = pyfaidx.Fasta("tests/unit/data/refseq/pstrand_nc.fa")
long_intron, short_intron, nc_splicing, intron_len = check_splicing_sites(genome,
genes[0].mrnas[
"rna-XM_006567179.3.m1"],
200000)
os.remove("tests/unit/data/refseq/pstrand_nc.fa.fai")
assert nc_splicing == 1
genes = [g for g in GFFReader("tests/unit/data/refseq/mstrand_nc.gff")]
genome = pyfaidx.Fasta("tests/unit/data/refseq/mstrand_nc.fa")
long_intron, short_intron, nc_splicing, intron_len = check_splicing_sites(genome,
genes[0].mrnas[
"rna-XM_026443867.1.m1"],
200000)
os.remove("tests/unit/data/refseq/mstrand_nc.fa.fai")
assert nc_splicing == 1
def test_get_spliced_cds_seq(self):
genes = [g for g in GFFReader("tests/unit/data/refseq/mstrand_e.gff")]
genome = pyfaidx.Fasta("tests/unit/data/refseq/mstrand_e.fa")
seq, seq_len, intron_len, last_codon = get_spliced_cds_seq(genome,
genes[0].mrnas["rna-XM_033456960.1.m1"],
True)
os.remove("tests/unit/data/refseq/mstrand_e.fa.fai")
assert last_codon in stop_codons
genes = [g for g in GFFReader("tests/unit/data/refseq/pstrand_e.gff")]
genome = pyfaidx.Fasta("tests/unit/data/refseq/pstrand_e.fa")
seq, seq_len, intron_len, last_codon = get_spliced_cds_seq(genome,
genes[0].mrnas["rna-XM_033441273.1.m1"],
True)
os.remove("tests/unit/data/refseq/pstrand_e.fa.fai")
assert last_codon in stop_codons
genes = [g for g in GFFReader("tests/unit/data/refseq/mstrand_e2.gff")]
genome = pyfaidx.Fasta("tests/unit/data/refseq/mstrand_e2.fa")
seq, seq_len, intron_len, last_codon = get_spliced_cds_seq(genome,
genes[0].mrnas["rna-XM_392669.6.m1"],
True)
os.remove("tests/unit/data/refseq/mstrand_e2.fa.fai")
assert last_codon in stop_codons
def test_for_construct():
with tempfile.NamedTemporaryFile("wt", suffix=".gff") as gff_temp:
print(gff_file_content, file=gff_temp)
gff_temp.flush()
count = 0
with GFFReader(gff_temp.name) as parser:
for _ in parser:
if count == 1:
result = _
count += 1
assert count == 3
assert result.start == 3306
assert _.uid == "AL1G10030.v2.1"
assert _.mrnas["AL1G10030.t1.v2.1"].attr["Note"] == "cov:100|id:97.65"
assert _.mrnas["AL1G10030.t1.v2.1"].fp_utr == 7449
assert _.mrnas["AL1G10030.t1.v2.1"].tp_utr == 7610
def test_bter_CDS():
genes_bed = []
genes_gff = []
for gene_bed in BEDReader("tests/unit/data/bter_top.coding.bed"):
genes_bed.append(gene_bed)
for gene_gff in GFFReader("tests/unit/data/bter_top.gff"):
genes_gff.append(gene_gff)
for gene_bed, gene_gff in zip(genes_bed, genes_gff):
for mrna_bed, mrna_gff in zip(gene_bed.mrnas.values(),
gene_gff.mrnas.values()):
bed_string_repr = mrna_bed.to_bed().split('\t')
coding_gff_string_repr = mrna_gff.to_bed(cds_only=True).split('\t')
bed_string_repr = bed_string_repr[0:4] + bed_string_repr[5:12]
coding_gff_string_repr = coding_gff_string_repr[
0:4] + coding_gff_string_repr[5:12]
assert bed_string_repr == coding_gff_string_repr
def test_bter():
genes_bed = []
genes_gff = []
for gene_bed in BEDReader("tests/unit/data/bter_top.bed"):
genes_bed.append(gene_bed)
for gene_gff in GFFReader("tests/unit/data/bter_top.gff"):
genes_gff.append(gene_gff)
assert genes_bed == genes_gff
for gene_bed, gene_gff in zip(genes_bed, genes_gff):
for mrna_bed, mrna_gff in zip(gene_bed.mrnas.values(),
gene_gff.mrnas.values()):
bed_string_repr = mrna_bed.to_bed().split('\t')
gff_string_repr = mrna_gff.to_bed().split('\t')
bed_string_repr = bed_string_repr[0:4] + bed_string_repr[5:12]
gff_string_repr = gff_string_repr[0:4] + gff_string_repr[5:12]
assert bed_string_repr == gff_string_repr
def test_insufficient_permissions_file():
with tempfile.NamedTemporaryFile("wt") as tmp:
os.chmod(tmp.name, 0o000)
with pytest.raises(PermissionError):
_ = GFFReader(tmp.name)
def test_empty_file():
with tempfile.NamedTemporaryFile() as tmp:
with pytest.raises(EmptyFileError):
for _ in GFFReader(tmp.name):
pass
def test_invalid_file():
with pytest.raises(FileNotFoundError):
_ = GFFReader("foo")
