def setUp(self):
test_file = os.path.join('NeuralNetwork', 'enolase.fasta')
diff_file = os.path.join('NeuralNetwork', 'repeat.fasta')
self.test_records = []
self.diff_records = []
# load the records
for file, records in ((test_file, self.test_records),
(diff_file, self.diff_records)):
handle = open(file, 'r')
seq_parser = Fasta.SequenceParser(alphabet=IUPAC.unambiguous_dna)
iterator = Fasta.Iterator(handle, seq_parser)
while 1:
seq_record = iterator.next()
if seq_record is None:
break
records.append(seq_record)
handle.close()
self.num_schemas = 2
schema_ga = Schema.GeneticAlgorithmFinder()
schema_ga.min_generations = 1
self.finder = Schema.SchemaFinder(num_schemas=self.num_schemas,
schema_finder=schema_ga)
def setUp(self):
self.factory = Schema.SchemaFactory()
self.test_file = os.path.join(os.getcwd(), "NeuralNetwork", "enolase.fasta")
ambiguity_chars = {"G" : "G",
"A" : "A",
"T" : "T",
"C" : "C",
"R" : "AG",
"*" : "AGTC"}
self.schema = Schema.Schema(ambiguity_chars)
def runTest(self):
match = Schema.matches_schema("GATC", "AAAAA")
assert match == 0, "Expected no match because of length differences"
match = Schema.matches_schema("GATC", "GAT*")
assert match == 1, "Expected match"
match = Schema.matches_schema("GATC", "GATC")
assert match == 1, "Expected match"
match = Schema.matches_schema("GATC", "C*TC")
assert match == 0, "Expected no match because of char mismatch."
match = Schema.matches_schema("G*TC", "*TTC")
assert match == 1, "Expected match because of ambiguity."
def runTest(self):
match = Schema.matches_schema("GATC", "AAAAA")
assert match == 0, "Expected no match because of length differences"
match = Schema.matches_schema("GATC", "GAT*")
assert match == 1, "Expected match"
match = Schema.matches_schema("GATC", "GATC")
assert match == 1, "Expected match"
match = Schema.matches_schema("GATC", "C*TC")
assert match == 0, "Expected no match because of char mismatch."
match = Schema.matches_schema("G*TC", "*TTC")
assert match == 1, "Expected match because of ambiguity."
def test_schema_representation(self):
"""Convert sequences into schema representations.
"""
# get a set of schemas we want to code the sequence in
schema_bank = self._load_schema_repository()
top_schemas = schema_bank.get_top(25)
schema_coder = Schema.SchemaCoder(top_schemas, self.schema)
# get the sequences one at a time, and encode them
fasta_handle = open(self.test_file, 'r')
seq_parser = Fasta.SequenceParser(alphabet=IUPAC.unambiguous_dna)
iterator = Fasta.Iterator(fasta_handle, seq_parser)
while 1:
seq_record = iterator.next()
if seq_record is None:
break
schema_values = schema_coder.representation(seq_record.seq)
if VERBOSE:
print "Schema values:", schema_values
fasta_handle.close()
def runTest(self):
match = Schema.matches_schema("GATC", "AAAAA")
self.assertEqual(match, 0,
"Expected no match because of length differences")
match = Schema.matches_schema("GATC", "GAT*")
self.assertEqual(match, 1, "Expected match")
match = Schema.matches_schema("GATC", "GATC")
self.assertEqual(match, 1, "Expected match")
match = Schema.matches_schema("GATC", "C*TC")
self.assertEqual(match, 0,
"Expected no match because of char mismatch.")
match = Schema.matches_schema("G*TC", "*TTC")
self.assertEqual(match, 1, "Expected match because of ambiguity.")
def setUp(self):
ambiguity_chars = {"G" : "G",
"A" : "A",
"T" : "T",
"C" : "C",
"R" : "AG",
"*" : "AGTC"}
motif_representation = Schema.Schema(ambiguity_chars)
motifs = ("GA", "GATAG", "GA*AG", "GATRG", "*A")
self.motif_coder = Schema.SchemaCoder(motifs,
motif_representation)
self.match_strings = [("GATAG", [.5, .5, .5, .5, 1.0]),
("GAGAGATA", [float(3) / float(4), 0,
float(1) / float(4), 0,
1])]
def runTest(self):
match = Schema.matches_schema("GATC", "AAAAA")
self.assertEqual(match, 0,
"Expected no match because of length differences")
match = Schema.matches_schema("GATC", "GAT*")
self.assertEqual(match, 1,
"Expected match")
match = Schema.matches_schema("GATC", "GATC")
self.assertEqual(match, 1,
"Expected match")
match = Schema.matches_schema("GATC", "C*TC")
self.assertEqual(match, 0,
"Expected no match because of char mismatch.")
match = Schema.matches_schema("G*TC", "*TTC")
self.assertEqual(match, 1,
"Expected match because of ambiguity.")
def setUp(self):
test_file = os.path.join('NeuralNetwork', 'enolase.fasta')
diff_file = os.path.join('NeuralNetwork', 'repeat.fasta')
self.test_records = []
self.diff_records = []
# load the records
for file, records in ((test_file, self.test_records),
(diff_file, self.diff_records)):
handle = open(file, 'r')
records.extend(
SeqIO.parse(handle, "fasta", alphabet=IUPAC.unambiguous_dna))
handle.close()
self.num_schemas = 2
schema_ga = Schema.GeneticAlgorithmFinder()
schema_ga.min_generations = 1
self.finder = Schema.SchemaFinder(num_schemas=self.num_schemas,
schema_finder=schema_ga)
def test_schema_representation(self):
"""Convert sequences into schema representations."""
# get a set of schemas we want to code the sequence in
schema_bank = self._load_schema_repository()
top_schemas = schema_bank.get_top(25)
schema_coder = Schema.SchemaCoder(top_schemas, self.schema)
# get the sequences one at a time, and encode them
fasta_handle = open(self.test_file, 'r')
for seq_record in SeqIO.parse(fasta_handle, "fasta",
alphabet=IUPAC.unambiguous_dna):
schema_values = schema_coder.representation(seq_record.seq)
if VERBOSE:
print("Schema values: %s" % schema_values)
fasta_handle.close()
def setUp(self):
ambiguity_chars = {
"G": "G",
"A": "A",
"T": "T",
"C": "C",
"R": "AG",
"*": "AGTC"
}
self.motif_coder = Schema.Schema(ambiguity_chars)
self.match_string = "GATAG"
self.match_info = [("GA", ["GA"]), ("GATAG", ["GATAG"]),
("GA*AG", ["GATAG"]), ("GATRG", ["GATAG"]),
("*A", ["GA", "TA"])]
