def test_write_si_pos_from_exons(self):
exons = {
"FBtr0077958":
[[
'2L', 'FlyBase', 'CDS', 1143371, 1143410, '.', '+', '0',
'gene_id "FBgn0031307"; gene_symbol "MFS3"; transcript_id "FBtr0077958"; transcript_symbol "MFS3-RA";'
],
[
'2L', 'FlyBase', 'CDS', 1145444, 1146472, '.', '+', '2',
'gene_id "FBgn0031307"; gene_symbol "MFS3"; transcript_id "FBtr0077958"; transcript_symbol "MFS3-RA";'
],
[
'2L', 'FlyBase', 'CDS', 1146539, 1146825, '.', '+', '2',
'gene_id "FBgn0031307"; gene_symbol "MFS3"; transcript_id "FBtr0077958"; transcript_symbol "MFS3-RA";'
]],
"FBtr0077959":
[[
'2L', 'FlyBase', 'CDS', 1143371, 1143410, '.', '-', '0',
'gene_id "FBgn0031307"; gene_symbol "MFS3"; transcript_id "FBtr0077959"; transcript_symbol "MFS3-RA";'
],
[
'2L', 'FlyBase', 'CDS', 1145444, 1146472, '.', '-', '2',
'gene_id "FBgn0031307"; gene_symbol "MFS3"; transcript_id "FBtr0077959"; transcript_symbol "MFS3-RA";'
],
[
'2L', 'FlyBase', 'CDS', 1146539, 1146825, '.', '-', '2',
'gene_id "FBgn0031307"; gene_symbol "MFS3"; transcript_id "FBtr0077959"; transcript_symbol "MFS3-RA";'
]]
}
outbed = "tests/write_si_pos_from_exons_observed.bed"
expected = "tests/write_si_pos_from_exons_expected.bed"
write_si_pos_from_exons(exons, outbed, add_chr=False)
observed = rw.read_as_string(outbed)
expected = rw.read_as_string(expected)
self.assertEqual(expected, observed)
def test_get_spliced_reads_exon_filters_exon_start_window(self):
reads_file = "tests/get_spliced_reads_exon_start_window_input_reads.bed"
output_file_spliced = "tests/get_spliced_reads_exon_filters_exon_start_window_observed_spliced.bed"
output_file_unspliced = "tests/get_spliced_reads_exon_filters_exon_start_window_observed_unspliced.bed"
exon_junctions_file = "tests/get_spliced_reads_input_junctions.bed"
expected_file_spliced = "tests/get_spliced_reads_exon_filters_exon_start_window_expected_spliced.bed"
expected_file_unspliced = "tests/get_spliced_reads_exon_start_window_expected_unspliced.bed"
exons = {}
exons["FBtr0078168"] = [
["chr2L", "havana", "exon", 2, 6, "FBtr0078168", ".", "+"],
["chr2L", "havana", "exon", 11, 13, "FBtr0078168", ".", "+"],
["chr2L", "havana", "exon", 17, 19, "FBtr0078168", ".", "+"],
["chr2L", "havana", "exon", 22, 26, "FBtr0078168", ".", "+"]
]
exons["FBtr0078169"] = [
["chr2L", "havana", "exon", 22, 26, "FBtr0078169", ".", "-"],
["chr2L", "havana", "exon", 17, 19, "FBtr0078169", ".", "-"],
["chr2L", "havana", "exon", 11, 13, "FBtr0078169", ".", "-"],
["chr2L", "havana", "exon", 2, 6, "FBtr0078169", ".", "-"]
]
get_spliced_reads(reads_file,
exon_junctions_file,
output_file_spliced,
output_file_unspliced,
exons=exons,
overhang=0,
filter_start=1,
filter_end=3)
expected_spliced = rw.read_as_string(expected_file_spliced)
expected_unspliced = rw.read_as_string(expected_file_unspliced)
expected = expected_spliced + expected_unspliced
observed_spliced = rw.read_as_string(output_file_spliced)
observed_unspliced = rw.read_as_string(output_file_unspliced)
observed = observed_spliced + observed_unspliced
self.assertEqual(expected, observed)
def test_snr_bed(self):
inbed = "tests/snr_bed_input.bed"
outbed = "tests/snr_bed_observed.bed"
snr_bed(inbed, outbed)
expected = rw.read_as_string("tests/snr_bed_expected.bed")
observed = rw.read_as_string(outbed)
self.assertEqual(expected, observed)
def test_snr_bed_fiveprime(self):
inbed = "tests/snr_bed_fiveprime_input.bed"
outbed = "tests/snr_bed_fiveprime_observed.bed"
snr_bed(inbed, outbed, five_prime_most=True)
expected = rw.read_as_string("tests/snr_bed_fiveprime_expected.bed")
observed = rw.read_as_string(outbed)
self.assertEqual(expected, observed)
def test_get_transcripts(self):
gtf = "tests/get_transcripts_input.gtf"
observed_file = "tests/get_transcripts_observed.bed"
expected_file = "tests/get_transcripts_expected.bed"
get_transcripts(gtf, observed_file)
expected = rw.read_as_string(expected_file)
observed = rw.read_as_string(observed_file)
self.assertEqual(expected, observed)
def test_density_per_transcript(self):
exon_file = "tests/density_per_transcript_input_exons.gtf"
polII_bed = "tests/density_per_transcript_input_polII.bed"
observed = "tests/density_per_transcript_observed.txt"
expected = "tests/density_per_transcript_expected.txt"
density_per_transcript(exon_file, polII_bed, observed)
expected = rw.read_as_string(expected)
observed = rw.read_as_string(observed)
self.assertEqual(expected, observed)
def test_merge_bed(self):
in_bed = "tests/merge_bed_input.bed"
out_bed = "tests/merge_bed_output.bed"
expected_bed = "tests/merge_bed_expected.bed"
distance = 2
merge_bed(in_bed, out_bed, distance)
expected = rw.read_as_string(expected_bed)
observed = rw.read_as_string(out_bed)
self.assertEqual(expected, observed)
def test_extend_intervals(self):
input_file = "tests/extend_intervals_input.bed"
expected = "tests/extend_intervals_expected.bed"
observed = "tests/extend_intervals_observed.bed"
left_shift = 4
right_shift = 5
extend_intervals(input_file, observed, left_shift, right_shift)
expected = rw.read_as_string(expected)
observed = rw.read_as_string(observed)
self.assertEqual(expected, observed)
def test_extend_intervals_three_prime(self):
input_file = "tests/extend_intervals_input.bed"
expected = "tests/extend_intervals_three_prime_expected.bed"
observed = "tests/extend_intervals_three_prime_observed.bed"
left_shift = 4
right_shift = 2
extend_intervals(input_file,
observed,
left_shift,
right_shift,
three_prime=True)
expected = rw.read_as_string(expected)
observed = rw.read_as_string(observed)
self.assertEqual(expected, observed)
def test_extract_3ss(self):
exons = {}
exons["FBgn1"] = [
[
"2L", "FlyBase", "exon", 1, 4, ".", "+", ".",
"gene_id \"FBgn1\"; gene_symbol \"drl\"; transcript_id \"FBtr33\"; transcript_symbol \"drl-RA\";"
],
[
"2L", "FlyBase", "exon", 9, 10, ".", "+", ".",
"gene_id \"FBgn1\"; gene_symbol \"drl\"; transcript_id \"FBtr33\"; transcript_symbol \"drl-RA\";"
],
[
"2L", "FlyBase", "exon", 12, 14, ".", "+", ".",
"gene_id \"FBgn1\"; gene_symbol \"drl\"; transcript_id \"FBtr33\"; transcript_symbol \"drl-RA\";"
],
[
"2L", "FlyBase", "exon", 17, 18, ".", "+", ".",
"gene_id \"FBgn1\"; gene_symbol \"drl\"; transcript_id \"FBtr33\"; transcript_symbol \"drl-RA\";"
],
[
"2L", "FlyBase", "exon", 21, 23, ".", "+", ".",
"gene_id \"FBgn1\"; gene_symbol \"drl\"; transcript_id \"FBtr33\"; transcript_symbol \"drl-RA\";"
]
]
exons["FBgn2"] = [
[
"2L", "FlyBase", "exon", 22, 23, ".", "-", ".",
"gene_id \"FBgn2\"; gene_symbol \"drl\"; transcript_id \"FBtr3\"; transcript_symbol \"drl-RA\";"
],
[
"2L", "FlyBase", "exon", 18, 19, ".", "-", ".",
"gene_id \"FBgn2\"; gene_symbol \"drl\"; transcript_id \"FBtr3\"; transcript_symbol \"drl-RA\";"
],
[
"2L", "FlyBase", "exon", 13, 14, ".", "-", ".",
"gene_id \"FBgn2\"; gene_symbol \"drl\"; transcript_id \"FBtr3\"; transcript_symbol \"drl-RA\";"
],
[
"2L", "FlyBase", "exon", 4, 7, ".", "-", ".",
"gene_id \"FBgn2\"; gene_symbol \"drl\"; transcript_id \"FBtr3\"; transcript_symbol \"drl-RA\";"
]
]
output_file = "tests/extract_3ss_observed.bed"
expected = rw.read_as_string("tests/extract_3ss_expected.bed")
extract_3ss(exons, output_file)
observed = rw.read_as_string(output_file)
self.assertEqual(expected, observed)
def extend_intervals(input_file, output_file, left_shift, right_shift, remove_chr=False, add_chr=False, names_file=None, three_prime = False):
"""
Given a BED file, make a new BED file with intervals that start _left_shift_ nt upstream
of the interval starts in the original file and end _right_shift_ nt to the right.
Note that for intervals on the negative strand, right and left will be
reversed.
:param input_file: input BED file
:param output_file: output BED file
:param left_shift: distance between old and new interval start
:param right_shift: distance between old interval start and new interval end
:param remove_chr: if True, remove "chr" from the chromosome name in the output
:param add_chr: if True, prefix "chr" to the chromosome name in the output
:param names_file: if specified, then reads will only be processed
if the ID is in the specified file
:param three_prime: if True, extend around interval ends instead
:return: None
"""
remove_counter = 0
names = []
if names_file:
names = rw.read_as_string(names_file).split("\n")
plus = "+"
if three_prime:
plus = "-"
temp_left = left_shift
left_shift = right_shift
right_shift = temp_left
with open(input_file) as bed, open(output_file, "w") as out_bed:
reader = csv.reader(bed, delimiter="\t")
writer = csv.writer(out_bed, delimiter="\t")
for line in reader:
if (not names_file) or (line[3] in names):
if names_file:
names.remove(line[3])
template = line.copy()
# make a BED interval starting _left_shift_ nt before the 5' end and ending _right_shift_ nt after it.
if len(line) >= 6:
template = line[:6]
if line[5] == plus:
template[1] = int(line[1]) - left_shift
template[2] = int(line[1]) + right_shift
else:
template[1] = int(line[2]) - right_shift
template[2] = int(line[2]) + left_shift
# write the interval into a BED file, ignoring cases where the
# read is so close to the start of the chromosome that you end up with a
# negative coordinate
if template[1] >= 0:
if remove_chr:
template[0] = template[0].lstrip("chr")
if add_chr:
template[0] = "chr{0}".format(template[0])
writer.writerow(template)
else:
remove_counter = remove_counter + 1
print("Removed because would have exceeded the chromosome: {0}.".format(remove_counter))
def test_get_spliced_reads_no_filters(self):
reads_file = "tests/get_spliced_reads_input_reads.bed"
output_file_spliced = "tests/get_spliced_reads_observed_spliced.bed"
output_file_unspliced = "tests/get_spliced_reads_observed_unspliced.bed"
exon_junctions_file = "tests/get_spliced_reads_input_junctions.bed"
expected_file_spliced = "tests/get_spliced_reads_expected_spliced.bed"
expected_file_unspliced = "tests/get_spliced_reads_expected_unspliced.bed"
get_spliced_reads(reads_file,
exon_junctions_file,
output_file_spliced,
output_file_unspliced,
exons=False,
overhang=0)
expected_spliced = rw.read_as_string(expected_file_spliced)
expected_unspliced = rw.read_as_string(expected_file_unspliced)
expected = expected_spliced + expected_unspliced
observed_spliced = rw.read_as_string(output_file_spliced)
observed_unspliced = rw.read_as_string(output_file_unspliced)
observed = observed_spliced + observed_unspliced
self.assertEqual(expected, observed)