def test_coordinate_dict_indexing():
"""run the function coordinate_dict
index_gene_scaffold_coordinates
to check the gene indexing is working"""
gene_to_next_gene, gene_to_previous_gene, \
coordinate_dict, gene_list = index_gene_scaffold_coordinates(INPUT)
assert_equal(coordinate_dict, coordinate_dict_test)
def test_previous3_gene_is_as_expected_scaf_start():
"""run the function gene_to_next_
gene index_gene_scaffold_coordinates
to check the gene indexing is working"""
gene_to_next_gene, gene_to_previous_gene, \
coordinate_dict, gene_list = index_gene_scaffold_coordinates(INPUT)
result = gene_to_previous_gene["GPLIN_000000100"]
assert_equal(result, "NA")
def test_next_is_as_expected1():
"""run the function gene_to_next_
gene index_gene_scaffold_coordinates
to check the gene indexing is working"""
gene_to_next_gene, gene_to_previous_gene, \
coordinate_dict, gene_list = index_gene_scaffold_coordinates(INPUT)
result = gene_to_next_gene["GPLIN_000000500"]
# Alhough this is a differenct scaff's gene. Is it true ..
assert_equal(result, "GPLIN_000020100")
print("file not found: %s" % user_file)
os._exit(0)
logger.info(sys.version_info)
logger.info("Command-line: %s", ' '.join(sys.argv))
logger.info("Starting testing: %s", time.asctime())
logger.info("converting gff file to coordinates file")
get_starts_stops(gff_file, "temp_starts_stops.txt")
coordinate_file = os.path.join("temp_starts_stops.txt")
# index the genome with biopython
logger.info("indexing genome")
Genome_sequence = SeqIO.index(genome_sequence, "fasta")
Genome_sequence_time = time.time()
out = 'import genome file took, %.3f' % (Genome_sequence_time - start_time)
# populate the dictionaries
gene_to_next_gene, gene_to_previous_gene, coordinate_dict, \
gene_list = index_gene_scaffold_coordinates(coordinate_file)
logger.info(out)
# open the gff outfile
name_gff = options.out_file.split(".")[0] + "_upstream_" + str(
upstream) + "bp.gff"
gff_outfile = open(name_gff, "w")
gff_outfile.write("#GFF file from intergenic regions.\n")
for gene in gene_list:
# now we need to extract the genic regions, not going into other genes
final_start, final_stop, \
direction = get_coordinate_of_interest(gene,
gene_to_next_gene,
gene_to_previous_gene,
coordinate_dict)