def test_create_starts_and_stops(self):
gene = Gene()
mrna = Mock()
gene.children = {'mrna':[mrna]}
gene.create_starts_and_stops('ATGC')
mrna.create_starts_and_stops.assertCalledWith('ATGC')
def test_get_cds_length(self):
gene = Gene()
mrna = Mock()
cds = Mock()
cds.length = Mock(return_value=42)
mrna.get_cds = Mock(return_value=cds)
gene.children = {'mrna':[mrna]}
self.assertEquals(gene.get_cds_length(), 42)
def test_match_cds_and_exon_end(self):
gene = Gene()
mrna = Mock()
gene.children = {'mrna':[mrna]}
gene.match_cds_and_exon_end()
mrna.match_cds_and_exon_end.assertCalled()
def process_gene_line(self, line, gene_type):
"""Extracts arguments from a line and instantiates a Gene object."""
kwargs = self.extract_gene_args(line)
if not kwargs:
return
gene_id = kwargs['identifier']
gene = Gene(**kwargs)
if gene_type == 'pseudogene':
gene.pseudo = True
self.genes[gene_id] = gene
def process_gene_line(self, line, gene_type):
"""Extracts arguments from a line and instantiates a Gene object."""
kwargs = self.extract_gene_args(line)
if not kwargs:
return
gene_id = kwargs['identifier']
gene = Gene(**kwargs)
if gene_type == 'pseudogene':
gene.pseudo = True
self.genes[gene_id] = gene
def test_to_tbl_negative(self):
gene = Gene("seq1", "maker", [1, 50], "-", "foo_gene_1")
mrna1 = Mock()
mrna1.to_tbl.return_value = "mrna1_to_tbl...\n"
mrna2 = Mock()
mrna2.to_tbl.return_value = "mrna2_to_tbl...\n"
gene.mrnas.append(mrna1)
gene.mrnas.append(mrna2)
expected = "50\t1\tgene\n\t\t\tlocus_tag\tfoo_gene_1\nmrna1_to_tbl...\nmrna2_to_tbl...\n"
self.assertEquals(gene.to_tbl(), expected)
def test_to_tbl_negative(self):
gene = Gene("seq1", "maker", [1, 50], "-", "foo_gene_1")
mrna1 = Mock()
mrna1.to_tbl.return_value = "mrna1_to_tbl...\n"
mrna2 = Mock()
mrna2.to_tbl.return_value = "mrna2_to_tbl...\n"
gene.mrnas.append(mrna1)
gene.mrnas.append(mrna2)
expected = "50\t1\tgene\n\t\t\tlocus_tag\tfoo_gene_1\nmrna1_to_tbl...\nmrna2_to_tbl...\n"
self.assertEquals(gene.to_tbl(), expected)
def test_max_intron_length_filter(self):
intron_length = MaxIntronLengthFilter(30)
# Create a mock sequence
seq = Sequence()
# Give the sequence some genes
seq.genes = [
Gene('foo_seq', 'geib_labs', [1, 2], '+', 'foo1'),
Gene('foo_seq', 'geib_labs', [1, 2], '+', 'foo2'),
Gene('foo_seq', 'geib_labs', [1, 2], '+', 'foo3')
]
# Give the mock mrnas some exon's
test_mrna0 = Mock()
test_mrna0.identifier = 'foo1-RA'
test_mrna0.death_flagged = False
test_mrna0.exon = Mock()
test_mrna0.get_shortest_intron = Mock(return_value=20)
test_mrna0.get_longest_intron = Mock(return_value=20)
test_mrna1 = Mock()
test_mrna1.identifier = 'foo2-RA'
test_mrna1.death_flagged = False
test_mrna1.exon = Mock()
test_mrna1.get_shortest_intron = Mock(return_value=30)
test_mrna1.get_longest_intron = Mock(return_value=30)
test_mrna2 = Mock()
test_mrna2.identifier = 'foo2-RB'
test_mrna2.death_flagged = False
test_mrna2.exon = None
test_mrna3 = Mock()
test_mrna3.identifier = 'foo3-RA'
test_mrna3.death_flagged = False
test_mrna3.exon = Mock()
test_mrna3.get_shortest_intron = Mock(return_value=40)
test_mrna3.get_longest_intron = Mock(return_value=40)
# Give the mock genes some mrnas
seq.genes[0].mrnas = [test_mrna0]
seq.genes[0].death_flagged = False
seq.genes[1].mrnas = [test_mrna1, test_mrna2]
seq.genes[1].death_flagged = False
seq.genes[2].mrnas = [test_mrna3]
seq.genes[2].death_flagged = False
# Apply the filter
intron_length.apply(seq)
self.assertEqual(len(seq.genes), 3)
self.assertEqual(seq.genes[0].mrnas, [test_mrna0])
self.assertEqual(seq.genes[1].mrnas, [test_mrna1, test_mrna2])
def test_to_tbl_positive_with_name(self):
gene = Gene(seq_name="seq1", source="maker", indices=[1, 50], strand="+", identifier="foo_gene_1", name="wtfg")
self.assertFalse(gene.annotations)
gene.add_annotation('foo', 'dog')
mrna1 = Mock()
mrna1.to_tbl.return_value = "mrna1_to_tbl...\n"
mrna2 = Mock()
mrna2.to_tbl.return_value = "mrna2_to_tbl...\n"
gene.mrnas.append(mrna1)
gene.mrnas.append(mrna2)
expected = "1\t50\tgene\n\t\t\tgene\twtfg\n\t\t\tlocus_tag\tfoo_gene_1\nmrna1_to_tbl...\nmrna2_to_tbl...\n"
self.assertEquals(gene.to_tbl(), expected)
def test_max_cds_length_filter(self):
cds_length = MaxCDSLengthFilter(100)
# Create a mock sequence
seq = Sequence()
# Give the sequence some genes
seq.genes = [
Gene('foo_seq', 'geib_labs', [1, 2], '+', 'foo1'),
Gene('foo_seq', 'geib_labs', [1, 2], '+', 'foo2'),
Gene('foo_seq', 'geib_labs', [1, 2], '+', 'foo3')
]
# Give the mock mrnas some cds's
test_mrna0 = Mock()
test_mrna0.identifier = 'foo1-RA'
test_mrna0.death_flagged = False
test_mrna0.cds = Mock()
test_mrna0.cds.length = Mock(return_value=90)
test_mrna1 = Mock()
test_mrna1.identifier = 'foo2-RA'
test_mrna1.death_flagged = False
test_mrna1.cds = None
test_mrna2 = Mock()
test_mrna2.identifier = 'foo2-RB'
test_mrna2.death_flagged = False
test_mrna2.cds = Mock()
test_mrna2.cds.length = Mock(return_value=100)
test_mrna3 = Mock()
test_mrna3.identifier = 'foo3-RA'
test_mrna3.death_flagged = False
test_mrna3.cds = Mock()
test_mrna3.cds.length = Mock(return_value=110)
# Give the mock genes some mrnas
seq.genes[0].mrnas = [test_mrna0]
seq.genes[0].death_flagged = False
seq.genes[1].mrnas = [test_mrna1, test_mrna2]
seq.genes[1].death_flagged = False
seq.genes[2].mrnas = [test_mrna3]
seq.genes[2].death_flagged = False
# Apply the filter
cds_length.apply(seq)
self.assertEqual(len(seq.genes), 3)
self.assertEqual(seq.genes[0].mrnas, [test_mrna0])
self.assertEqual(seq.genes[1].mrnas, [test_mrna1, test_mrna2])
def setUp(self):
self.test_gene0 = Gene(seq_name="sctg_0080_0020", source="maker", indices=[3734, 7436], strand='+', identifier=1)
self.test_gene1 = Gene(seq_name="sctg_0080_0020", source="maker", indices=[3734, 7436], strand='+', identifier=1)
self.fake_mrna1 = Mock()
self.fake_mrna1.identifier = "fake_mrna1"
self.fake_mrna1.death_flagged = False
self.fake_mrna2 = Mock()
self.fake_mrna2.identifier = "fake_mrna2"
self.fake_mrna2.death_flagged = False
self.test_gene1.mrnas.append(self.fake_mrna1)
self.test_gene1.mrnas.append(self.fake_mrna2)
def test_make_positive(self):
seq_len = 8
gene = Gene(start=1, end=7, strand='-')
mrna = Mock()
mrna.type = 'mrna'
mrna.make_positive = Mock()
gene.add_child(mrna)
gene.make_positive(seq_len)
self.assertEqual(gene.start, 2)
self.assertEqual(gene.end, 8)
self.assertEqual(gene.strand, '+')
mrna.make_positive.assertCalledWith(seq_len)
def build_transcript_dictionary(seqs, genes):
transcripts = {}
for gene in genes:
gene = Gene.from_gff_feature(gene)
if gene == None:
print("Could not convert GFFFeature to Gene, skipping")
continue
new_mrnas = []
for mrna in gene['mrna']:
mrna = Mrna.from_gff_feature(mrna)
if mrna == None:
print("Could not convert GFFFeature to Mrna, skipping")
continue
new_mrnas.append(mrna)
gene.children['mrna'] = new_mrnas
if gene.seqid in transcripts:
transcripts[gene.seqid].genes.append(gene)
else:
if gene.seqid in seqs:
transcripts[gene.seqid] = Transcript([gene], seqs[gene.seqid])
else:
print("Gene "+gene.attributes["ID"]+" is on sequence "+gene.seqid+" which does not exist. Skipping...")
return transcripts
def test_to_tbl_positive(self):
gene = Gene(seq_name="seq1",
source="maker",
indices=[1, 50],
strand="+",
identifier="foo_gene_1")
self.assertFalse(gene.annotations)
gene.add_annotation('foo', 'dog')
mrna1 = Mock()
mrna1.to_tbl.return_value = "mrna1_to_tbl...\n"
mrna2 = Mock()
mrna2.to_tbl.return_value = "mrna2_to_tbl...\n"
gene.mrnas.append(mrna1)
gene.mrnas.append(mrna2)
expected = "1\t50\tgene\n\t\t\tlocus_tag\tfoo_gene_1\nmrna1_to_tbl...\nmrna2_to_tbl...\n"
self.assertEquals(gene.to_tbl(), expected)
def process_gene_line(self, line):
"""Extracts arguments from a line and instantiates a Gene object."""
kwargs = self.extract_gene_args(line)
if not kwargs:
return
gene_id = kwargs['identifier']
self.genes[gene_id] = Gene(**kwargs)
def test_gene_initialized_without_annotations(self):
newgene = Gene(seq_name="seq1",
source="maker",
indices=[1, 50],
strand="+",
identifier="foo_gene_1")
self.assertFalse(newgene.annotations)
self.assertEquals(0, len(newgene.annotations.keys()))
def __init__(self, population_size, filename_of_genes, max_weight, logger):
self.population_size = population_size
self.genes = Gene(filename_of_genes, logger)
self.max_weight = max_weight
self.max_score_for_run = None
self.logger = logger
self.best_chromosome = np.array([0, 0])
return
def test_gene_initialized_with_annotations(self):
newgene = Gene(seq_name="seq1",
source="maker",
indices=[1, 50],
strand="+",
identifier="foo_gene_1",
annotations={"bar": ["cat"]})
self.assertTrue(newgene.annotations)
self.assertEquals(1, len(newgene.annotations.keys()))
def setUp(self):
self.test_gene0 = Gene(seq_name="sctg_0080_0020",
source="maker",
indices=[3734, 7436],
strand='+',
identifier=1)
self.test_gene1 = Gene(seq_name="sctg_0080_0020",
source="maker",
indices=[3734, 7436],
strand='+',
identifier=1)
self.fake_mrna1 = Mock()
self.fake_mrna1.identifier = "fake_mrna1"
self.fake_mrna1.death_flagged = False
self.fake_mrna2 = Mock()
self.fake_mrna2.identifier = "fake_mrna2"
self.fake_mrna2.death_flagged = False
self.test_gene1.mrnas.append(self.fake_mrna1)
self.test_gene1.mrnas.append(self.fake_mrna2)
def setUp(self):
self.gene1 = Gene()
self.mrna1 = Mock()
self.cds1 = Mock()
self.exon1 = Mock()
self.gene1.get_mrna = Mock(return_value=self.mrna1)
self.mrna1.get_cds = Mock(return_value=self.cds1)
self.mrna1.get_exon = Mock(return_value=self.exon1)
self.gene1.start = 1
self.gene1.end = 100
self.gene1.attributes = {'ID':'foo_gene'}
self.mrna1.start = 1
self.mrna1.end = 100
self.mrna1.attributes = {'ID':'m.foo'}
self.cds1.start = 1
self.cds1.end = 100
self.cds1.phase = 0
self.exon1.start = 1
self.exon1.end = 100
class TestGene(unittest.TestCase):
def setUp(self):
self.test_gene0 = Gene(seq_name="sctg_0080_0020", source="maker", indices=[3734, 7436], strand='+', identifier=1)
self.test_gene1 = Gene(seq_name="sctg_0080_0020", source="maker", indices=[3734, 7436], strand='+', identifier=1)
self.fake_mrna1 = Mock()
self.fake_mrna1.identifier = "fake_mrna1"
self.fake_mrna1.death_flagged = False
self.fake_mrna2 = Mock()
self.fake_mrna2.identifier = "fake_mrna2"
self.fake_mrna2.death_flagged = False
self.test_gene1.mrnas.append(self.fake_mrna1)
self.test_gene1.mrnas.append(self.fake_mrna2)
def test_constructor(self):
self.assertEqual('Gene', self.test_gene0.__class__.__name__)
def test_length(self):
self.assertEqual(3703, self.test_gene0.length())
def test_gagflagged(self):
self.assertFalse(self.test_gene0.gagflagged())
self.test_gene0.annotations = [["gag_flag", "nice gene"]]
self.assertTrue(self.test_gene0.gagflagged())
def test_number_of_gagflags(self):
self.fake_mrna1.number_of_gagflags.return_value = 2
self.fake_mrna2.number_of_gagflags.return_value = 1
self.test_gene1.annotations = [["gag_flag", "nice gene"]]
self.assertEquals(4, self.test_gene1.number_of_gagflags())
def test_get_mrna_ids(self):
expected = ["fake_mrna1", "fake_mrna2"]
self.assertEquals(self.test_gene1.get_mrna_ids(), expected)
def test_remove_mrna(self):
self.assertEquals(self.test_gene1.mrnas, [self.fake_mrna1, self.fake_mrna2])
self.assertEquals(len(self.test_gene1.removed_mrnas), 0)
self.test_gene1.remove_mrna('fake_mrna1')
self.assertEquals(self.test_gene1.mrnas, [self.fake_mrna2])
self.assertEquals(self.test_gene1.removed_mrnas, [self.fake_mrna1])
def test_get_longest_exon(self):
self.fake_mrna1.get_longest_exon.return_value = 10
self.fake_mrna2.get_longest_exon.return_value = 20
self.assertEquals(20, self.test_gene1.get_longest_exon())
def test_get_shortest_exon(self):
self.fake_mrna1.get_shortest_exon.return_value = 5
self.fake_mrna2.get_shortest_exon.return_value = 8
self.assertEquals(5, self.test_gene1.get_shortest_exon())
def test_get_total_exon_length(self):
self.fake_mrna1.get_total_exon_length.return_value = 15
self.fake_mrna2.get_total_exon_length.return_value = 25
self.assertEquals(40, self.test_gene1.get_total_exon_length())
def test_get_num_exons(self):
self.fake_mrna1.get_num_exons.return_value = 5
self.fake_mrna2.get_num_exons.return_value = 4
self.assertEquals(9, self.test_gene1.get_num_exons())
def test_get_longest_intron(self):
self.fake_mrna1.get_longest_intron.return_value = 8
self.fake_mrna2.get_longest_intron.return_value = 10
self.assertEquals(10, self.test_gene1.get_longest_intron())
def test_get_shortest_intron(self):
self.fake_mrna1.get_shortest_intron.return_value = 5
self.fake_mrna2.get_shortest_intron.return_value = 8
self.assertEquals(5, self.test_gene1.get_shortest_intron())
def test_get_total_intron_length(self):
self.fake_mrna1.get_total_intron_length.return_value = 15
self.fake_mrna2.get_total_intron_length.return_value = 25
self.assertEquals(40, self.test_gene1.get_total_intron_length())
def test_get_num_introns(self):
self.fake_mrna1.get_num_introns.return_value = 3
self.fake_mrna2.get_num_introns.return_value = 2
self.assertEquals(5, self.test_gene1.get_num_introns())
def test_get_partial_info(self):
self.fake_mrna1.has_stop.return_value = True
self.fake_mrna1.has_start.return_value = True
self.fake_mrna2.has_stop.return_value = False
self.fake_mrna2.has_start.return_value = True
results = self.test_gene1.get_partial_info()
self.assertEquals(1, results["complete"])
def test_adjust_indices(self):
self.test_gene1.adjust_indices(16)
self.fake_mrna1.adjust_indices.assert_called_with(16, 1)
self.assertEquals(3750, self.test_gene1.indices[0])
# adjust them back
self.test_gene1.adjust_indices(-16)
self.fake_mrna1.adjust_indices.assert_called_with(-16, 1)
self.assertEquals(3734, self.test_gene1.indices[0])
def test_remove_mrnas_with_internal_stops(self):
helper = Mock()
helper.mrna_contains_internal_stop.return_value = True
self.assertEquals(2, len(self.test_gene1.mrnas))
self.test_gene1.remove_mrnas_with_internal_stops(helper)
self.assertEquals(0, len(self.test_gene1.mrnas))
def test_contains_mrna(self):
self.fake_mrna1.identifier = "foo_mrna"
self.fake_mrna2.identifier = "bar_mrna"
self.assertTrue(self.test_gene1.contains_mrna("foo_mrna"))
self.assertFalse(self.test_gene1.contains_mrna("zub_mrna"))
def test_cds_to_gff(self):
self.fake_mrna1.identifier = "foo_mrna"
foo = self.test_gene1.cds_to_gff("foo_seq", "foo_mrna")
self.fake_mrna1.cds_to_gff.assert_called_with("foo_seq", "maker")
def test_cds_to_gff_no_such_mrna(self):
self.fake_mrna1.identifier = "foo_mrna"
foo = self.test_gene1.cds_to_gff("foo_seq", "bar_mrna")
self.assertFalse(foo)
def test_cds_to_tbl(self):
self.fake_mrna1.identifier = "foo_mrna"
foo = self.test_gene1.cds_to_tbl("foo_mrna")
self.fake_mrna1.cds_to_tbl.assert_called_with()
def test_to_mrna_fasta(self):
helper = Mock()
helper.mrna_to_fasta.return_value = "mrna_to_fasta\n"
expected = "mrna_to_fasta\nmrna_to_fasta\n"
self.assertEquals(expected, self.test_gene1.to_mrna_fasta(helper))
def test_to_cds_fasta(self):
helper = Mock()
helper.mrna_to_cds_fasta.return_value = "mrna_to_CDS_fasta\n"
expected = "mrna_to_CDS_fasta\nmrna_to_CDS_fasta\n"
self.assertEquals(expected, self.test_gene1.to_cds_fasta(helper))
def test_to_protein_fasta(self):
helper = Mock()
helper.mrna_to_protein_fasta.return_value = "mrna_to_protein_fasta\n"
expected = "mrna_to_protein_fasta\nmrna_to_protein_fasta\n"
self.assertEquals(expected, self.test_gene1.to_protein_fasta(helper))
def test_to_gff(self):
self.fake_mrna1.to_gff.return_value = "fake mrna1 to gff here:)\n"
self.fake_mrna2.to_gff.return_value = "fake mrna2 to gff here:)\n"
expected = "sctg_0080_0020\tmaker\tgene\t3734\t7436\t.\t+\t."
expected += "\tID=1;foo=dog\n"
expected += "fake mrna1 to gff here:)\n"
expected += "fake mrna2 to gff here:)\n"
self.test_gene1.add_annotation('foo', 'dog')
self.assertEquals(expected, self.test_gene1.to_gff())
def test_to_gff_with_name(self):
self.fake_mrna1.to_gff.return_value = "fake mrna1 to gff here:)\n"
self.fake_mrna2.to_gff.return_value = "fake mrna2 to gff here:)\n"
expected = "sctg_0080_0020\tmaker\tgene\t3734\t7436\t.\t+\t."
expected += "\tID=1;Name=foo_gene;foo=dog\n"
expected += "fake mrna1 to gff here:)\n"
expected += "fake mrna2 to gff here:)\n"
self.test_gene1.add_annotation('foo', 'dog')
self.test_gene1.name = "foo_gene"
self.assertEquals(expected, self.test_gene1.to_gff())
def test_str(self):
expected = "Gene (ID=1, seq_name=sctg_0080_0020) containing 2 mrnas"
self.assertEquals(expected, str(self.test_gene1))
def test_create_starts_and_stops(self):
mrna1 = Mock()
mrna2 = Mock()
self.test_gene0.mrnas = [mrna1, mrna2]
seq_object = Mock()
self.test_gene0.create_starts_and_stops(seq_object)
mrna1.create_start_and_stop_if_necessary.assert_called_with(seq_object, '+')
mrna2.create_start_and_stop_if_necessary.assert_called_with(seq_object, '+')
def test_to_tbl_positive(self):
gene = Gene(seq_name="seq1", source="maker", indices=[1, 50], strand="+", identifier="foo_gene_1")
self.assertFalse(gene.annotations)
gene.add_annotation('foo', 'dog')
mrna1 = Mock()
mrna1.to_tbl.return_value = "mrna1_to_tbl...\n"
mrna2 = Mock()
mrna2.to_tbl.return_value = "mrna2_to_tbl...\n"
gene.mrnas.append(mrna1)
gene.mrnas.append(mrna2)
expected = "1\t50\tgene\n\t\t\tlocus_tag\tfoo_gene_1\nmrna1_to_tbl...\nmrna2_to_tbl...\n"
self.assertEquals(gene.to_tbl(), expected)
def test_to_tbl_positive_with_name(self):
gene = Gene(seq_name="seq1", source="maker", indices=[1, 50], strand="+", identifier="foo_gene_1", name="wtfg")
self.assertFalse(gene.annotations)
gene.add_annotation('foo', 'dog')
mrna1 = Mock()
mrna1.to_tbl.return_value = "mrna1_to_tbl...\n"
mrna2 = Mock()
mrna2.to_tbl.return_value = "mrna2_to_tbl...\n"
gene.mrnas.append(mrna1)
gene.mrnas.append(mrna2)
expected = "1\t50\tgene\n\t\t\tgene\twtfg\n\t\t\tlocus_tag\tfoo_gene_1\nmrna1_to_tbl...\nmrna2_to_tbl...\n"
self.assertEquals(gene.to_tbl(), expected)
def test_gene_initialized_without_annotations(self):
newgene = Gene(seq_name="seq1", source="maker", indices=[1, 50], strand="+", identifier="foo_gene_1")
self.assertFalse(newgene.annotations)
self.assertEquals(0, len(newgene.annotations))
def test_gene_initialized_with_annotations(self):
newgene = Gene(seq_name="seq1", source="maker", indices=[1, 50], strand="+", identifier="foo_gene_1",\
annotations=[["bar", "cat"]])
self.assertTrue(newgene.annotations)
self.assertEquals(1, len(newgene.annotations))
def test_to_tbl_negative(self):
gene = Gene("seq1", "maker", [1, 50], "-", "foo_gene_1")
mrna1 = Mock()
mrna1.to_tbl.return_value = "mrna1_to_tbl...\n"
mrna2 = Mock()
mrna2.to_tbl.return_value = "mrna2_to_tbl...\n"
gene.mrnas.append(mrna1)
gene.mrnas.append(mrna2)
expected = "50\t1\tgene\n\t\t\tlocus_tag\tfoo_gene_1\nmrna1_to_tbl...\nmrna2_to_tbl...\n"
self.assertEquals(gene.to_tbl(), expected)
class TestGene(unittest.TestCase):
def setUp(self):
self.gene1 = Gene()
self.mrna1 = Mock()
self.cds1 = Mock()
self.exon1 = Mock()
self.gene1.get_mrna = Mock(return_value=self.mrna1)
self.mrna1.get_cds = Mock(return_value=self.cds1)
self.mrna1.get_exon = Mock(return_value=self.exon1)
self.gene1.start = 1
self.gene1.end = 100
self.gene1.attributes = {'ID':'foo_gene'}
self.mrna1.start = 1
self.mrna1.end = 100
self.mrna1.attributes = {'ID':'m.foo'}
self.cds1.start = 1
self.cds1.end = 100
self.cds1.phase = 0
self.exon1.start = 1
self.exon1.end = 100
def test_from_gff_feature_success(self):
gff_gene = Mock()
gff_gene.type = "gene"
tran_gene = Gene.from_gff_feature(gff_gene)
self.assertTrue(tran_gene)
def test_from_gff_features_fails(self):
gff_gene = Mock()
gff_gene.type = "asdf"
tran_gene = Gene.from_gff_feature(gff_gene)
self.assertFalse(tran_gene)
def test_get_cds_length(self):
gene = Gene()
mrna = Mock()
cds = Mock()
cds.length = Mock(return_value=42)
mrna.get_cds = Mock(return_value=cds)
gene.children = {'mrna':[mrna]}
self.assertEquals(gene.get_cds_length(), 42)
def test_remove_contig_from_gene_id(self):
expected = 'g.123'
self.gene1.attributes['ID'] = 'contig123|g.123'
self.gene1.remove_contig_from_gene_id()
self.assertEquals(expected, self.gene1.attributes['ID'])
def test_gene_to_tbl_nostart_nostop(self):
expected = \
"<1\t>100\tgene\n"\
"\t\t\tlocus_tag\tfoo_gene\n"\
"<1\t>100\tCDS\n"\
"\t\t\tprotein_id\tm.foo\n"\
"\t\t\tproduct\thypothetical protein\n"
self.mrna1.__contains__ = no_start_no_stop
tbl = self.gene1.to_tbl()
self.assertEquals(tbl, expected)
def test_gene_to_tbl_start_nostop(self):
expected = \
"1\t>100\tgene\n"\
"\t\t\tlocus_tag\tfoo_gene\n"\
"1\t>100\tCDS\n"\
"\t\t\tprotein_id\tm.foo\n"\
"\t\t\tproduct\thypothetical protein\n"
self.mrna1.__contains__ = start_no_stop
tbl = self.gene1.to_tbl()
self.assertEquals(tbl, expected)
def test_gene_to_tbl_nostart_stop(self):
expected = \
"<1\t100\tgene\n"\
"\t\t\tlocus_tag\tfoo_gene\n"\
"<1\t100\tCDS\n"\
"\t\t\tprotein_id\tm.foo\n"\
"\t\t\tproduct\thypothetical protein\n"
self.mrna1.__contains__ = no_start_stop
tbl = self.gene1.to_tbl()
self.assertEquals(tbl, expected)
def test_gene_to_tbl_start_stop(self):
expected = \
"1\t100\tgene\n"\
"\t\t\tlocus_tag\tfoo_gene\n"\
"1\t100\tCDS\n"\
"\t\t\tprotein_id\tm.foo\n"\
"\t\t\tproduct\thypothetical protein\n"
self.mrna1.__contains__ = start_stop
tbl = self.gene1.to_tbl()
self.assertEquals(tbl, expected)
def test_gene_to_tbl_genename(self):
expected = \
"<1\t>100\tgene\n"\
"\t\t\tgene\tf00x4\n"\
"\t\t\tlocus_tag\tfoo_gene\n"\
"<1\t>100\tCDS\n"\
"\t\t\tprotein_id\tm.foo\n"\
"\t\t\tproduct\thypothetical protein\n"
self.gene1.attributes["Name"] = "f00x4"
self.mrna1.__contains__ = no_start_no_stop
tbl = self.gene1.to_tbl()
self.assertEquals(tbl, expected)
def test_gene_to_tbl_dbxref(self):
expected = \
"<1\t>100\tgene\n"\
"\t\t\tlocus_tag\tfoo_gene\n"\
"<1\t>100\tCDS\n"\
"\t\t\tprotein_id\tm.foo\n"\
"\t\t\tdb_xref\tPfam:foo\n"\
"\t\t\tdb_xref\tPfam:dog\n"\
"\t\t\tdb_xref\tPfam:baz\n"\
"\t\t\tproduct\thypothetical protein\n"\
self.gene1.get_mrna().attributes["Dbxref"] = "Pfam:foo,Pfam:dog,Pfam:baz"
self.mrna1.__contains__ = no_start_no_stop
tbl = self.gene1.to_tbl()
self.assertEquals(tbl, expected)
### FIX PHASE TESTS ###
def test_fix_phase(self):
self.gene1.start = 2
self.mrna1.start = 2
self.mrna1.__contains__ = no_start_stop
self.cds1.start = 2
self.cds1.phase = 0
self.assertEqual(self.cds1.phase, 0)
self.gene1.fix_phase("ATGC")
self.assertEqual(self.cds1.phase, 1)
def test_fix_phase_to_two(self):
self.gene1.start = 3
self.mrna1.start = 3
self.mrna1.__contains__ = no_start_stop
self.cds1.start = 3
self.cds1.phase = 0
self.assertEqual(self.cds1.phase, 0)
self.gene1.fix_phase("ATGC")
self.assertEqual(self.cds1.phase, 2)
def test_fix_phase_does_nothing_when_indices_too_large(self):
self.gene1.start = 4
self.mrna1.start = 4
self.mrna1.__contains__ = start_stop
self.cds1.start = 4
self.cds1.phase = 0
self.assertEqual(self.cds1.phase, 0)
self.gene1.fix_phase("ATGC")
self.assertEqual(self.cds1.phase, 0)
def test_fix_phase_works_on_cds_only(self):
self.gene1.start = 1
self.mrna1.start = 1
self.mrna1.__contains__ = no_start_stop
self.cds1.start = 3
self.cds1.phase = 0
self.assertEqual(self.cds1.phase, 0)
self.assertEqual(self.cds1.start, 3)
self.gene1.fix_phase("ATGC")
self.assertEqual(self.cds1.phase, 2)
self.assertEqual(self.cds1.start, 1)
def test_fix_phase_does_nothing_when_not_partial(self):
self.gene1.start = 2
self.mrna1.start = 2
self.mrna1.__contains__ = start_stop
self.cds1.start = 2
self.cds1.phase = 0
self.assertEqual(self.cds1.phase, 0)
self.gene1.fix_phase("ATGC")
self.assertEqual(self.cds1.phase, 0)
def test_fix_phase_adjusts_end_on_3prime_partial(self):
self.gene1.start = 2
self.mrna1.start = 2
self.mrna1.__contains__ = start_no_stop
self.cds1.start = 2
self.gene1.end = 2
self.mrna1.end = 2
self.cds1.end = 2
self.assertEqual(self.cds1.end, 2)
self.gene1.fix_phase("ATGC")
self.assertEqual(self.cds1.end, 4)
#### MAKE POSITIVE TESTS ####
def test_make_positive(self):
seq_len = 8
gene = Gene(start=1, end=7, strand='-')
mrna = Mock()
mrna.type = 'mrna'
mrna.make_positive = Mock()
gene.add_child(mrna)
gene.make_positive(seq_len)
self.assertEqual(gene.start, 2)
self.assertEqual(gene.end, 8)
self.assertEqual(gene.strand, '+')
mrna.make_positive.assertCalledWith(seq_len)
#### MATCH CDS AND EXON END TESTS ####
def test_match_cds_and_exon_end(self):
gene = Gene()
mrna = Mock()
gene.children = {'mrna':[mrna]}
gene.match_cds_and_exon_end()
mrna.match_cds_and_exon_end.assertCalled()
#### STARTS AND STOPS TESTS ####
def test_create_starts_and_stops(self):
gene = Gene()
mrna = Mock()
gene.children = {'mrna':[mrna]}
gene.create_starts_and_stops('ATGC')
mrna.create_starts_and_stops.assertCalledWith('ATGC')
class TestGene(unittest.TestCase):
def setUp(self):
self.test_gene0 = Gene(seq_name="sctg_0080_0020",
source="maker",
indices=[3734, 7436],
strand='+',
identifier=1)
self.test_gene1 = Gene(seq_name="sctg_0080_0020",
source="maker",
indices=[3734, 7436],
strand='+',
identifier=1)
self.fake_mrna1 = Mock()
self.fake_mrna1.identifier = "fake_mrna1"
self.fake_mrna1.death_flagged = False
self.fake_mrna2 = Mock()
self.fake_mrna2.identifier = "fake_mrna2"
self.fake_mrna2.death_flagged = False
self.test_gene1.mrnas.append(self.fake_mrna1)
self.test_gene1.mrnas.append(self.fake_mrna2)
def test_constructor(self):
self.assertEqual('Gene', self.test_gene0.__class__.__name__)
def test_length(self):
self.assertEqual(3703, self.test_gene0.length())
def test_gagflagged(self):
self.assertFalse(self.test_gene0.gagflagged())
self.test_gene0.annotations = {"gag_flag": ["nice gene"]}
self.assertTrue(self.test_gene0.gagflagged())
def test_number_of_gagflags(self):
self.fake_mrna1.number_of_gagflags.return_value = 2
self.fake_mrna2.number_of_gagflags.return_value = 1
self.test_gene1.annotations = {"gag_flag": ["nice gene"]}
self.assertEquals(4, self.test_gene1.number_of_gagflags())
def test_get_mrna_ids(self):
expected = ["fake_mrna1", "fake_mrna2"]
self.assertEquals(self.test_gene1.get_mrna_ids(), expected)
def test_remove_mrna(self):
self.assertEquals(self.test_gene1.mrnas,
[self.fake_mrna1, self.fake_mrna2])
self.assertEquals(len(self.test_gene1.removed_mrnas), 0)
self.test_gene1.remove_mrna('fake_mrna1')
self.assertEquals(self.test_gene1.mrnas, [self.fake_mrna2])
self.assertEquals(self.test_gene1.removed_mrnas, [self.fake_mrna1])
def test_remove_mrnas_from_list(self):
self.fake_mrna3 = Mock()
self.fake_mrna3.identifier = "fake_mrna3"
self.fake_mrna3.death_flagged = False
self.test_gene1.mrnas.append(self.fake_mrna3)
bad_mrnas = ["fake_mrna3", "fake_mrna1"]
self.assertEquals(3, len(self.test_gene1.mrnas))
self.assertEquals(0, len(self.test_gene1.removed_mrnas))
removed_mrnas = self.test_gene1.remove_mrnas_from_list(bad_mrnas)
self.assertEquals(2, len(removed_mrnas))
self.assertEquals(1, len(self.test_gene1.mrnas))
self.assertEquals(2, len(self.test_gene1.removed_mrnas))
def test_remove_empty_mrnas(self):
self.fake_mrna1.rna_type = "mRNA"
self.fake_mrna1.cds = Mock()
self.fake_mrna1.exon = None
self.fake_mrna2.rna_type = "mRNA"
self.fake_mrna2.cds = None
self.fake_mrna2.exon = Mock()
self.fake_mrna3 = Mock()
self.fake_mrna3.rna_type = "mRNA"
self.fake_mrna3.identifier = "fake_mrna3"
self.fake_mrna3.death_flagged = False
self.fake_mrna3.cds = Mock()
self.fake_mrna3.exon = Mock()
self.test_gene1.mrnas.append(self.fake_mrna3)
self.assertEquals(3, len(self.test_gene1.mrnas))
self.assertEquals(0, len(self.test_gene1.removed_mrnas))
removed_mrnas = self.test_gene1.remove_empty_mrnas()
self.assertEquals(2, len(removed_mrnas))
self.assertEquals(1, len(self.test_gene1.mrnas))
self.assertEquals(2, len(self.test_gene1.removed_mrnas))
def test_get_longest_exon(self):
self.fake_mrna1.get_longest_exon.return_value = 10
self.fake_mrna2.get_longest_exon.return_value = 20
self.assertEquals(20, self.test_gene1.get_longest_exon())
def test_get_shortest_exon(self):
self.fake_mrna1.get_shortest_exon.return_value = 5
self.fake_mrna2.get_shortest_exon.return_value = 8
self.assertEquals(5, self.test_gene1.get_shortest_exon())
def test_get_total_exon_length(self):
self.fake_mrna1.get_total_exon_length.return_value = 15
self.fake_mrna2.get_total_exon_length.return_value = 25
self.assertEquals(40, self.test_gene1.get_total_exon_length())
def test_get_num_exons(self):
self.fake_mrna1.get_num_exons.return_value = 5
self.fake_mrna2.get_num_exons.return_value = 4
self.assertEquals(9, self.test_gene1.get_num_exons())
def test_get_longest_intron(self):
self.fake_mrna1.get_longest_intron.return_value = 8
self.fake_mrna2.get_longest_intron.return_value = 10
self.assertEquals(10, self.test_gene1.get_longest_intron())
def test_get_shortest_intron(self):
self.fake_mrna1.get_shortest_intron.return_value = 5
self.fake_mrna2.get_shortest_intron.return_value = 8
self.assertEquals(5, self.test_gene1.get_shortest_intron())
def test_get_total_intron_length(self):
self.fake_mrna1.get_total_intron_length.return_value = 15
self.fake_mrna2.get_total_intron_length.return_value = 25
self.assertEquals(40, self.test_gene1.get_total_intron_length())
def test_get_num_introns(self):
self.fake_mrna1.get_num_introns.return_value = 3
self.fake_mrna2.get_num_introns.return_value = 2
self.assertEquals(5, self.test_gene1.get_num_introns())
def test_get_partial_info(self):
self.fake_mrna1.has_stop.return_value = True
self.fake_mrna1.has_start.return_value = True
self.fake_mrna2.has_stop.return_value = False
self.fake_mrna2.has_start.return_value = True
results = self.test_gene1.get_partial_info()
self.assertEquals(1, results["complete"])
def test_adjust_indices(self):
self.test_gene1.adjust_indices(16)
self.fake_mrna1.adjust_indices.assert_called_with(16, 1)
self.assertEquals(3750, self.test_gene1.indices[0])
# adjust them back
self.test_gene1.adjust_indices(-16)
self.fake_mrna1.adjust_indices.assert_called_with(-16, 1)
self.assertEquals(3734, self.test_gene1.indices[0])
def test_remove_mrnas_with_internal_stops(self):
helper = Mock()
helper.mrna_contains_internal_stop.return_value = True
self.assertEquals(2, len(self.test_gene1.mrnas))
self.test_gene1.remove_mrnas_with_internal_stops(helper)
self.assertEquals(0, len(self.test_gene1.mrnas))
def test_contains_mrna(self):
self.fake_mrna1.identifier = "foo_mrna"
self.fake_mrna2.identifier = "bar_mrna"
self.assertTrue(self.test_gene1.contains_mrna("foo_mrna"))
self.assertFalse(self.test_gene1.contains_mrna("zub_mrna"))
def test_cds_to_gff(self):
self.fake_mrna1.identifier = "foo_mrna"
foo = self.test_gene1.cds_to_gff("foo_seq", "foo_mrna")
self.fake_mrna1.cds_to_gff.assert_called_with("foo_seq", "maker")
def test_cds_to_gff_no_such_mrna(self):
self.fake_mrna1.identifier = "foo_mrna"
foo = self.test_gene1.cds_to_gff("foo_seq", "bar_mrna")
self.assertFalse(foo)
def test_cds_to_tbl(self):
self.fake_mrna1.identifier = "foo_mrna"
foo = self.test_gene1.cds_to_tbl("foo_mrna")
self.fake_mrna1.cds_to_tbl.assert_called_with()
def test_to_mrna_fasta(self):
helper = Mock()
helper.mrna_to_fasta.return_value = "mrna_to_fasta\n"
expected = "mrna_to_fasta\nmrna_to_fasta\n"
self.assertEquals(expected, self.test_gene1.to_mrna_fasta(helper))
def test_to_cds_fasta(self):
helper = Mock()
helper.mrna_to_cds_fasta.return_value = "mrna_to_CDS_fasta\n"
expected = "mrna_to_CDS_fasta\nmrna_to_CDS_fasta\n"
self.assertEquals(expected, self.test_gene1.to_cds_fasta(helper))
def test_to_protein_fasta(self):
helper = Mock()
helper.mrna_to_protein_fasta.return_value = "mrna_to_protein_fasta\n"
expected = "mrna_to_protein_fasta\nmrna_to_protein_fasta\n"
self.assertEquals(expected, self.test_gene1.to_protein_fasta(helper))
def test_to_gff(self):
self.fake_mrna1.to_gff.return_value = "fake mrna1 to gff here:)\n"
self.fake_mrna2.to_gff.return_value = "fake mrna2 to gff here:)\n"
expected = "sctg_0080_0020\tmaker\tgene\t3734\t7436\t.\t+\t."
expected += "\tID=1;foo=dog\n"
expected += "fake mrna1 to gff here:)\n"
expected += "fake mrna2 to gff here:)\n"
self.test_gene1.add_annotation('foo', 'dog')
self.assertEquals(expected, self.test_gene1.to_gff())
def test_to_gff_with_name(self):
self.fake_mrna1.to_gff.return_value = "fake mrna1 to gff here:)\n"
self.fake_mrna2.to_gff.return_value = "fake mrna2 to gff here:)\n"
expected = "sctg_0080_0020\tmaker\tgene\t3734\t7436\t.\t+\t."
expected += "\tID=1;Name=foo_gene;foo=dog\n"
expected += "fake mrna1 to gff here:)\n"
expected += "fake mrna2 to gff here:)\n"
self.test_gene1.add_annotation('foo', 'dog')
self.test_gene1.name = "foo_gene"
self.assertEquals(expected, self.test_gene1.to_gff())
def test_str(self):
expected = "Gene (ID=1, seq_name=sctg_0080_0020) containing 2 mrnas"
self.assertEquals(expected, str(self.test_gene1))
def test_create_starts_and_stops(self):
mrna1 = Mock()
mrna2 = Mock()
self.test_gene0.mrnas = [mrna1, mrna2]
seq_object = Mock()
self.test_gene0.create_starts_and_stops(seq_object)
mrna1.create_start_and_stop_if_necessary.assert_called_with(
seq_object, '+')
mrna2.create_start_and_stop_if_necessary.assert_called_with(
seq_object, '+')
def test_add_mrna_annotation(self):
mrna = Mock()
mrna.identifier = "foo_mrna"
self.test_gene0.mrnas = [mrna]
self.test_gene0.add_mrna_annotation("foo_mrna", "gag_flag",
"awesome_anno")
mrna.add_annotation.assert_called_with("gag_flag", "awesome_anno")
def test_to_tbl_positive(self):
gene = Gene(seq_name="seq1",
source="maker",
indices=[1, 50],
strand="+",
identifier="foo_gene_1")
self.assertFalse(gene.annotations)
gene.add_annotation('foo', 'dog')
mrna1 = Mock()
mrna1.to_tbl.return_value = "mrna1_to_tbl...\n"
mrna2 = Mock()
mrna2.to_tbl.return_value = "mrna2_to_tbl...\n"
gene.mrnas.append(mrna1)
gene.mrnas.append(mrna2)
expected = "1\t50\tgene\n\t\t\tlocus_tag\tfoo_gene_1\nmrna1_to_tbl...\nmrna2_to_tbl...\n"
self.assertEquals(gene.to_tbl(), expected)
def test_to_tbl_positive_start_nostop(self):
gene = Gene(seq_name="seq1",
source="maker",
indices=[1, 50],
strand="+",
identifier="foo_gene_1")
self.assertFalse(gene.annotations)
gene.add_annotation('foo', 'dog')
mrna1 = Mock()
mrna1.to_tbl.return_value = "mrna1_to_tbl...\n"
mrna2 = Mock()
mrna2.to_tbl.return_value = "mrna2_to_tbl...\n"
mrna2.has_start.return_value = True
mrna2.has_stop.return_value = False
gene.mrnas.append(mrna1)
gene.mrnas.append(mrna2)
expected = "1\t>50\tgene\n\t\t\tlocus_tag\tfoo_gene_1\nmrna1_to_tbl...\nmrna2_to_tbl...\n"
self.assertEquals(gene.to_tbl(), expected)
def test_to_tbl_positive_nostart_stop(self):
gene = Gene(seq_name="seq1",
source="maker",
indices=[1, 50],
strand="+",
identifier="foo_gene_1")
self.assertFalse(gene.annotations)
gene.add_annotation('foo', 'dog')
mrna1 = Mock()
mrna1.to_tbl.return_value = "mrna1_to_tbl...\n"
mrna2 = Mock()
mrna2.to_tbl.return_value = "mrna2_to_tbl...\n"
mrna2.has_start.return_value = False
mrna2.has_stop.return_value = True
gene.mrnas.append(mrna1)
gene.mrnas.append(mrna2)
expected = "<1\t50\tgene\n\t\t\tlocus_tag\tfoo_gene_1\nmrna1_to_tbl...\nmrna2_to_tbl...\n"
self.assertEquals(gene.to_tbl(), expected)
def test_to_tbl_positive_nostart_nostop(self):
gene = Gene(seq_name="seq1",
source="maker",
indices=[1, 50],
strand="+",
identifier="foo_gene_1")
self.assertFalse(gene.annotations)
gene.add_annotation('foo', 'dog')
mrna1 = Mock()
mrna1.to_tbl.return_value = "mrna1_to_tbl...\n"
mrna2 = Mock()
mrna2.to_tbl.return_value = "mrna2_to_tbl...\n"
mrna2.has_start.return_value = False
mrna2.has_stop.return_value = False
gene.mrnas.append(mrna1)
gene.mrnas.append(mrna2)
expected = "<1\t>50\tgene\n\t\t\tlocus_tag\tfoo_gene_1\nmrna1_to_tbl...\nmrna2_to_tbl...\n"
self.assertEquals(gene.to_tbl(), expected)
def test_to_tbl_positive_with_name(self):
gene = Gene(seq_name="seq1",
source="maker",
indices=[1, 50],
strand="+",
identifier="foo_gene_1",
name="wtfg")
self.assertFalse(gene.annotations)
gene.add_annotation('foo', 'dog')
mrna1 = Mock()
mrna1.to_tbl.return_value = "mrna1_to_tbl...\n"
mrna2 = Mock()
mrna2.to_tbl.return_value = "mrna2_to_tbl...\n"
gene.mrnas.append(mrna1)
gene.mrnas.append(mrna2)
expected = "1\t50\tgene\n\t\t\tgene\twtfg\n\t\t\tlocus_tag\tfoo_gene_1\nmrna1_to_tbl...\nmrna2_to_tbl...\n"
self.assertEquals(gene.to_tbl(), expected)
def test_to_tbl_negative(self):
gene = Gene("seq1", "maker", [1, 50], "-", "foo_gene_1")
mrna1 = Mock()
mrna1.to_tbl.return_value = "mrna1_to_tbl...\n"
mrna2 = Mock()
mrna2.to_tbl.return_value = "mrna2_to_tbl...\n"
gene.mrnas.append(mrna1)
gene.mrnas.append(mrna2)
expected = "50\t1\tgene\n\t\t\tlocus_tag\tfoo_gene_1\nmrna1_to_tbl...\nmrna2_to_tbl...\n"
self.assertEquals(gene.to_tbl(), expected)
def test_gene_initialized_without_annotations(self):
newgene = Gene(seq_name="seq1",
source="maker",
indices=[1, 50],
strand="+",
identifier="foo_gene_1")
self.assertFalse(newgene.annotations)
self.assertEquals(0, len(newgene.annotations.keys()))
def test_gene_initialized_with_annotations(self):
newgene = Gene(seq_name="seq1", source="maker", indices=[1, 50], strand="+", identifier="foo_gene_1",\
annotations={"bar": ["cat"]})
self.assertTrue(newgene.annotations)
self.assertEquals(1, len(newgene.annotations.keys()))
def test_from_gff_feature_success(self):
gff_gene = Mock()
gff_gene.type = "gene"
tran_gene = Gene.from_gff_feature(gff_gene)
self.assertTrue(tran_gene)
def test_from_gff_features_fails(self):
gff_gene = Mock()
gff_gene.type = "asdf"
tran_gene = Gene.from_gff_feature(gff_gene)
self.assertFalse(tran_gene)