def test_no_alligned_reads_no_bc(self):
inBam = tests.get_file("no_mapped_reads.bam")
outBam = tests.get_file("test_barcode_collapse.bc.bam")
total_count, removed_count = barcode_collapse.barcode_collapse(inBam,
outBam,
False,
em=True)
def test_get_five_prime_utr_sequences(self):
"""
Tests 5' UTR dictionary creation
"""
gff_file = pybedtools.BedTool(tests.get_file("gff_uorf_test.gff"))
fa_file = tests.get_file("gff_uorf_test.fa")
intervals = pybedtools.BedTool(""" chr1 5 10 ENSG1 0 +
chr1 15 20 ENSG2 0 -
chr1 25 30 ENSG3 0 +
chr1 35 40 ENSG3 0 +
chr1 45 50 ENSG4 0 -
chr1 55 60 ENSG4 0 -
""", from_string=True)
detector = UORF_detector()
test_dict = detector._get_five_prime_utr_sequences(gff_file, fa_file)
test_dict = {name : [(interval, str(seq.seq)) for interval, seq in tuple]
for name, tuple in test_dict.items()}
true_dict = {
"ENSG1" : [(intervals[0], "GGGGG")],
"ENSG2" : [(intervals[1], "AAAAA")],
"ENSG3" : [(intervals[2], "GGGGG"), (intervals[3], "TTTTT")],
"ENSG4" : [(intervals[5], "GAAAA"), (intervals[4], "CCCCG")],
}
self.assertDictEqual(test_dict, true_dict)
def test_duplicate_pos(self):
"""
same start / with target having both a matching and not matching randomer at that location
"""
bam1 = tests.get_file("test_cross_contamination/positive1.bam")
bam2 = tests.get_file("test_cross_contamination/positive_duplicate.bam")
matched, total = correlation(bam1, bam2, "out.sam")
self.assertEqual(total, 1)
self.assertEqual(matched, 1)
def test_randomer_match_neg2(self):
"""
same start same randomer neg, with the other offset
"""
bam1 = tests.get_file("test_cross_contamination/negative2.bam")
bam2 = tests.get_file("test_cross_contamination/negative_match.bam")
matched, total = correlation(bam1, bam2, "out.sam")
self.assertEqual(total, 1)
self.assertEqual(matched, 1)
def test_randomer_match_pos(self):
"""
same start same randomer pos
"""
bam1 = tests.get_file("test_cross_contamination/positive1.bam")
bam2 = tests.get_file("test_cross_contamination/positive_match.bam")
matched, total = correlation(bam1, bam2, "out.sam")
self.assertEqual(total, 1)
self.assertEqual(matched, 1)
def test_randomer_mismatch_neg(self):
"""
same start different randomer neg
"""
bam1 = tests.get_file("test_cross_contamination/negative1.bam")
bam2 = tests.get_file("test_cross_contamination/negative_mismatch.bam")
matched, total = correlation(bam1, bam2, "out.sam")
self.assertEqual(total, 1)
self.assertEqual(matched, 0)
def test_randomer_off_by_one_neg(self):
"""
test off by one bug same randomer by off by one neg
"""
bam1 = tests.get_file("test_cross_contamination/negative1.bam")
bam2 = tests.get_file("test_cross_contamination/negative_off_by_one.bam")
matched, total = correlation(bam1, bam2, "out.sam")
self.assertEqual(total, 1)
self.assertEqual(matched, 0)
def test_main(self):
rpkm_file = "rpkm_test.rpkm"
single_RPKM.main(tests.get_file("test_single_RPKM.count"), os.path.join(tests.get_test_dir(), rpkm_file ))
true_result = ["gene flag RPKM",
"ENSG1 0 5025125.62814",
"ENSG2 0 0.0"]
for true, test in zip(true_result, open(tests.get_file(rpkm_file))):
self.assertEqual(true.strip().split(), test.strip().split())
def test_randomer_match_neg2(self):
"""
same start same randomer neg, with the other offset
"""
bam1 = tests.get_file("test_cross_contamination/negative2.bam")
bam2 = tests.get_file("test_cross_contamination/negative_match.bam")
matched, total = correlation(bam1, bam2, "out.sam")
self.assertEqual(total, 1)
self.assertEqual(matched, 1)
def test_pos_vs_neg(self):
"""
tests same read with same barcode but different strand
"""
bam1 = tests.get_file("test_cross_contamination/positive1.bam")
bam2 = tests.get_file("test_cross_contamination/negative1.bam")
matched, total = correlation(bam1, bam2, "out.sam")
self.assertEqual(total, 1)
self.assertEqual(matched, 0)
def test_randomer_mismatch_neg(self):
"""
same start different randomer neg
"""
bam1 = tests.get_file("test_cross_contamination/negative1.bam")
bam2 = tests.get_file("test_cross_contamination/negative_mismatch.bam")
matched, total = correlation(bam1, bam2, "out.sam")
self.assertEqual(total, 1)
self.assertEqual(matched, 0)
def test_randomer_match_pos(self):
"""
same start same randomer pos
"""
bam1 = tests.get_file("test_cross_contamination/positive1.bam")
bam2 = tests.get_file("test_cross_contamination/positive_match.bam")
matched, total = correlation(bam1, bam2, "out.sam")
self.assertEqual(total, 1)
self.assertEqual(matched, 1)
def test_pos_vs_neg(self):
"""
tests same read with same barcode but different strand
"""
bam1 = tests.get_file("test_cross_contamination/positive1.bam")
bam2 = tests.get_file("test_cross_contamination/negative1.bam")
matched, total = correlation(bam1, bam2, "out.sam")
self.assertEqual(total, 1)
self.assertEqual(matched, 0)
def test_randomer_off_by_one_neg(self):
"""
test off by one bug same randomer by off by one neg
"""
bam1 = tests.get_file("test_cross_contamination/negative1.bam")
bam2 = tests.get_file(
"test_cross_contamination/negative_off_by_one.bam")
matched, total = correlation(bam1, bam2, "out.sam")
self.assertEqual(total, 1)
self.assertEqual(matched, 0)
def test_duplicate_pos(self):
"""
same start / with target having both a matching and not matching randomer at that location
"""
bam1 = tests.get_file("test_cross_contamination/positive1.bam")
bam2 = tests.get_file(
"test_cross_contamination/positive_duplicate.bam")
matched, total = correlation(bam1, bam2, "out.sam")
self.assertEqual(total, 1)
self.assertEqual(matched, 1)
def test_main(self):
rpkm_file = "rpkm_test.rpkm"
single_RPKM.main(tests.get_file("test_single_RPKM.count"),
os.path.join(tests.get_test_dir(), rpkm_file))
true_result = [
"gene flag RPKM", "ENSG1 0 5025125.62814",
"ENSG2 0 0.0"
]
for true, test in zip(true_result, open(tests.get_file(rpkm_file))):
self.assertEqual(true.strip().split(), test.strip().split())
def test_barcode_collapse_bacoded(self):
"""
Tests on duplciate removal for barcoded samples
"""
inBam = tests.get_file("test_barcode_collapse.bam")
outBam = tests.get_file("test_barcode_collapse.bc.bam")
total_count, removed_count = barcode_collapse.barcode_collapse(
inBam, outBam, True)
true_total_count = {"AAGGGTCGC": 3, "AAGGGTCGT": 4}
true_removed_count = {"AAGGGTCGC": 1, "AAGGGTCGT": 2}
self.assertDictEqual(true_total_count, total_count)
self.assertDictEqual(true_removed_count, removed_count)
def test_count_gene(self):
"""
Tests count_gene, makes sure it runs and outputs proper counts
"""
result = count_tags.count_gene(
tests.get_file("test.bam"), {
'start': 1,
'stop': 500,
'chrom': 'chr1',
'strand': "+",
"frea": "0",
'raw_count': 0,
'gene_id': 'ENSG1',
"regions": [(1, 100), (399, 500)]
}, "none")
self.assertEqual(result[0][0], "ENSG1:1-100")
self.assertAlmostEqual(result[0][1]['counts'].gene_count, 12, delta=3)
self.assertAlmostEqual(result[0][1]['counts'].region_count, 4, delta=3)
self.assertEqual(result[0][1]['start'], 1)
self.assertEqual(result[0][1]['stop'], 100)
self.assertEqual(result[1][0], "ENSG1:399-500")
self.assertAlmostEqual(result[1][1]['counts'].gene_count, 12, delta=3)
self.assertAlmostEqual(result[1][1]['counts'].region_count, 8, delta=3)
self.assertEqual(result[1][1]['start'], 399)
self.assertEqual(result[1][1]['stop'], 500)
def test_count_to_regions(self):
"""
Tests annotation building
"""
result = count_tags.count_to_regions(
tests.get_file("count_tags_annotation.bed"))
true_result = {
"ENSG1": {
'start': 1,
'stop': 300,
'chrom': 'chr1',
'strand': "+",
"frea": "0",
'gene_id': 'ENSG1',
"regions": [(1, 100), (200, 300)]
},
"ENSG2": {
'start': 400,
'stop': 700,
'chrom': 'chr1',
'strand': "-",
"frea": "0",
'gene_id': 'ENSG2',
"regions": [(600, 700), (400, 500)]
}
}
self.assertDictEqual(true_result, dict(result))
def test_submit_oldsplice(self):
true_result = """#!/bin/bash
#PBS -N oldsplice
#PBS -o test_output/runOldsplice.sh.out
#PBS -e test_output/runOldsplice.sh.err
#PBS -V
#PBS -l walltime=0:30:00
#PBS -l nodes=1:ppn=16
#PBS -A yeo-group
#PBS -q home
#PBS -t 1-4%1000
# Go to the directory from which the script was called
cd $PBS_O_WORKDIR
cmd[1]="oldsplice.py -b test1.bam -s hg19 -o test1.splices --splice_type SE --splice_type MXE --processors 16"
cmd[2]="oldsplice.py -f -b test1.bam -s hg19 -o test1.flip.splices --splice_type SE --splice_type MXE --processors 16"
cmd[3]="oldsplice.py -b test2.bam -s hg19 -o test2.splices --splice_type SE --splice_type MXE --processors 16"
cmd[4]="oldsplice.py -f -b test2.bam -s hg19 -o test2.flip.splices --splice_type SE --splice_type MXE --processors 16"
eval ${cmd[$PBS_ARRAYID]}
"""
true_result = true_result.split('\n')
out_sh = '{}/runOldsplice.sh'.format(self.out_dir)
OldspliceSubmitter(tests.get_file('sample_info.txt'),
submit=False,
queue_type='PBS',
out_sh=out_sh)
for true, test in zip(true_result, open(out_sh)):
self.assertEqual(true.strip().split(), test.strip().split())
def test_barcode_collapse_not_barcoded(self):
"""
Tests duplicate removal for non barcoded samples
"""
inBam = tests.get_file("test_barcode_collapse.bam")
outBam = tests.get_file("test_barcode_collapse.bc.bam")
total_count, removed_count = barcode_collapse.barcode_collapse(inBam, outBam, False)
true_total_count = {"total": 7}
true_removed_count = {"total": 5}
self.assertDictEqual(true_total_count, total_count)
self.assertDictEqual(true_removed_count, removed_count)
def test_submit_oldsplice(self):
true_result = """#!/bin/bash
#PBS -N oldsplice
#PBS -o test_output/runOldsplice.sh.out
#PBS -e test_output/runOldsplice.sh.err
#PBS -V
#PBS -l walltime=0:30:00
#PBS -l nodes=1:ppn=16
#PBS -A yeo-group
#PBS -q home
#PBS -t 1-4%1000
# Go to the directory from which the script was called
cd $PBS_O_WORKDIR
cmd[1]="oldsplice.py -b test1.bam -s hg19 -o test1.splices --splice_type SE --splice_type MXE --processors 16"
cmd[2]="oldsplice.py -f -b test1.bam -s hg19 -o test1.flip.splices --splice_type SE --splice_type MXE --processors 16"
cmd[3]="oldsplice.py -b test2.bam -s hg19 -o test2.splices --splice_type SE --splice_type MXE --processors 16"
cmd[4]="oldsplice.py -f -b test2.bam -s hg19 -o test2.flip.splices --splice_type SE --splice_type MXE --processors 16"
eval ${cmd[$PBS_ARRAYID]}
"""
true_result = true_result.split('\n')
out_sh = '{}/runOldsplice.sh'.format(self.out_dir)
OldspliceSubmitter(tests.get_file('sample_info.txt'), submit=False,
queue_type='PBS', out_sh=out_sh)
for true, test in zip(true_result, open(out_sh)):
self.assertEqual(true.strip().split(), test.strip().split())
def test_barcode_collapse_not_barcoded(self):
"""
Tests duplicate removal for non barcoded samples
"""
inBam = tests.get_file("test_barcode_collapse.bam")
outBam = tests.get_file("test_barcode_collapse.bc.bam")
total_count, removed_count = barcode_collapse.barcode_collapse(
inBam, outBam, False)
true_total_count = {"total": 7}
true_removed_count = {"total": 5}
self.assertDictEqual(true_total_count, total_count)
self.assertDictEqual(true_removed_count, removed_count)
def test_barcode_collapse_bacoded(self):
"""
Tests on duplciate removal for barcoded samples
"""
inBam = tests.get_file("test_barcode_collapse.bam")
outBam = tests.get_file("test_barcode_collapse.bc.bam")
total_count, removed_count = barcode_collapse.barcode_collapse(inBam, outBam, True)
true_total_count = {"AAGGGTCGC": 3,
"AAGGGTCGT": 4}
true_removed_count = {"AAGGGTCGC": 1,
"AAGGGTCGT": 2}
self.assertDictEqual(true_total_count, total_count)
self.assertDictEqual(true_removed_count, removed_count)
def test_count_to_regions(self):
"""
Tests annotation building
"""
result = count_tags.count_to_regions(tests.get_file("count_tags_annotation.bed"))
true_result = {"ENSG1" : {'start' : 1, 'stop' : 300,
'chrom' : 'chr1', 'strand' : "+",
"frea" : "0", 'gene_id' : 'ENSG1' ,
"regions" : [(1, 100), (200, 300)]},
"ENSG2" : {'start' : 400, 'stop' : 700,
'chrom' : 'chr1', 'strand' : "-",
"frea" : "0", 'gene_id' : 'ENSG2',
"regions" : [(600,700), (400, 500)] }}
self.assertDictEqual(true_result, dict(result))
def test_count_gene(self):
"""
Tests count_gene, makes sure it runs and outputs proper counts
"""
result = count_tags.count_gene(tests.get_file("test.bam"), {'start' : 1, 'stop' : 500,
'chrom' : 'chr1', 'strand' : "+",
"frea" : "0", 'raw_count' : 0, 'gene_id' : 'ENSG1' ,
"regions" : [(1, 100), (399, 500)]}, "none")
self.assertEqual(result[0][0], "ENSG1:1-100")
self.assertAlmostEqual(result[0][1]['counts'].gene_count, 12, delta=3)
self.assertAlmostEqual(result[0][1]['counts'].region_count, 4, delta=3)
self.assertEqual(result[0][1]['start'], 1)
self.assertEqual(result[0][1]['stop'], 100)
self.assertEqual(result[1][0], "ENSG1:399-500")
self.assertAlmostEqual(result[1][1]['counts'].gene_count, 12, delta=3)
self.assertAlmostEqual(result[1][1]['counts'].region_count, 8, delta=3)
self.assertEqual(result[1][1]['start'], 399)
self.assertEqual(result[1][1]['stop'], 500)
def test_no_alligned_reads_no_bc(self):
inBam = tests.get_file("no_mapped_reads.bam")
outBam = tests.get_file("test_barcode_collapse.bc.bam")
total_count, removed_count = barcode_collapse.barcode_collapse(inBam, outBam, False, em=True)