def test_slice_up_scaff():
"""run the function slice_up_scaff"""
intergenic_region = slice_up_scaff(Genome_seq_record.seq,
"1",
"5",
"+")
assert_equal(intergenic_region, "TTTT")
def test_slice_up_scaff():
"""run the function slice_up_scaff NA start"""
intergenic_region, final_start, \
final_stop = slice_up_scaff(Genome_seq_record.seq,
"NA",
"5",
"+")
assert_equal(intergenic_region, "TTTT")
def test_slice_up_scaff():
"""run the function slice_up_scaff reverse_complment"""
intergenic_region, final_start, \
final_stop = slice_up_scaff(Genome_seq_record.seq,
"1",
"5",
"-")
assert_equal(intergenic_region, "AAAA")
def test_slice_up_scaff():
"""run the function slice_up_scaff NA stop revrse complement"""
intergenic_region, final_start, \
final_stop = slice_up_scaff(Genome_seq_record.seq,
"100",
"NA",
"-")
# note that the 100 is actually 101, and the end is len(seq) -1
assert_equal(intergenic_region, "TCACC")
out = "upstream for gene %s falls off END of scaff %s" % (gene,
scaff)
logger.warning(out)
if scaff in Genome_sequence:
Genome_seq_record = Genome_sequence[scaff]
else:
warn = "could not find scaff: %s going to skip" % (scaff)
logger.warning(warn)
length_of_contig = len(Genome_seq_record.seq)
# slice up the scaffold.
# reverse complement for negative
# this function gets the entire intergenic regions, regardless of
# the desired length.
intergenic_region, final_start, \
final_stop = slice_up_scaff(Genome_seq_record.seq,
final_start,
final_stop,
direction)
# this function then get the desired upstream chunk
upstream_ROI = get_len_upstream(intergenic_region, upstream, direction)
if description.upper() == "YES":
info = "Scaff: %s | start-stop: %s:%s %s coding direction" % (
scaff, final_start, final_stop, direction)
if len(upstream_ROI) >= min_len:
write_out_to_file(outfile, gene, upstream, upstream_ROI, info)
else:
logger.warn
write_out_gff(gff_outfile, scaff, final_start, final_stop, direction,
gene, upstream)
logger.info("gff made, this contains all intergenic regions")
outfile.close()