def test_map_sequence_to_gene_annotation_iso(self):
gene_annotation_manager = GeneAnnotationManager()
gene_annotation_manager.load_gene_annotation_data()
expected_row = gene_annotation_manager.iso_gene_annotation_data[1]
expected_row = re.split(r'\t+', expected_row.rstrip('\t'))
sequence_no = expected_row[0]
expected_annotation_desc = expected_row[1]
result_row = gene_annotation_manager.map_sequence_to_gene_annotation(sequence_no)
self.assertEqual(expected_annotation_desc, result_row[1])
def test_load_gene_annotation_data_ehux(self):
gene_annotation_manager = GeneAnnotationManager()
gene_annotation_manager.load_gene_annotation_data()
ehux_result_count = len(gene_annotation_manager.ehux_gene_annotation_data)
expected_count = 30448
self.assertEqual(ehux_result_count, expected_count)
def test_load_gene_annotation_data_geph(self):
gene_annotation_manager = GeneAnnotationManager()
gene_annotation_manager.load_gene_annotation_data()
geph_result_count = len(gene_annotation_manager.geph_gene_annotation_data)
expected_count = 52679
self.assertEqual(geph_result_count, expected_count)
def test_load_gene_annotation_data_iso(self):
gene_annotation_manager = GeneAnnotationManager()
gene_annotation_manager.load_gene_annotation_data()
iso_result_count = len(gene_annotation_manager.iso_gene_annotation_data)
expected_count = 18712
self.assertEqual(iso_result_count, expected_count)
f_handle.write(
str(v) + ',' + self.get_species_name(str(v)) + str(
[value for value in self.blast_graph.node[v].itervalues()]).strip(
'[]') + ',')
f_handle.write(
str(edata['evalue']) + ',' + str(edata['identpct']) + ',' + str(edata['mismatchno']) + ',' +
str(edata['aln']) + ',' + str(edata['alnspn']) + ',' +
str(edata['gapopenno']) + ',' + str(edata['bitscore']) + '\n')
# if self.generate_gml_files:
# file_name = "{}/blast_graph.gml".format(self.blast_output_path)
# with open(file_name, "a") as f_handle:
# nx.write_gml(self.blast_graph, f_handle)
if __name__ == "__main__":
# Instantiate Gene Expression Manager object
gene_expression_manager = GeneExpressionManager()
gene_expression_manager.load_gene_expression_data()
# Instantiate Gene Annotation Manager object
gene_annotation_manager = GeneAnnotationManager()
gene_annotation_manager.load_gene_annotation_data()
# Filter By Target sequences
target_sequences = np.genfromtxt("../data/protein_sequence_files/elong.txt", delimiter='\n', dtype=str)
print target_sequences
print 'Total Target Sequences:', target_sequences.shape
similarity_networks = SimilarityNetworks(gene_expression_manager, gene_annotation_manager, evalue=1e-05,
by_sequence=target_sequences)
similarity_networks.output_file_identifier = "_elong_for_all_blast_data"
similarity_networks.generate_blast_data()
similarity_networks.write_blast_graph_file()
