def test_calculate_motif_distance(self):
cluster_regions = {
"exon": {
'real':
pybedtools.BedTool(
clipper.test_file(
"clip_analysis_test_peak_results.bed.exon.real.BED")),
'rand': {
0:
pybedtools.BedTool(
clipper.test_file(
"clip_analysis_test_peak_results.bed.exon.rand.0.BED"
))
}
}
}
region_sizes = {'all': 30, "exon": 30}
#doesn't matter if I output actual results
result = calculate_motif_distance(
cluster_regions, region_sizes,
pybedtools.BedTool(
clipper.test_file("motif_distance_test_motif.bed")))
#make sure dict structure is sound
self.assertListEqual(result.keys(), ['all', 'exon'])
self.assertListEqual(result['all'].keys(), ['real', 'rand'])
self.assertListEqual(result['all']['real'].keys(), ['dist', 'size'])
def test_assign_to_regions(self):
"""
Basic test of assign to regions
"""
tool = pybedtools.BedTool(
clipper.test_file(
"FOX2Brain-05.15.09.polyATrim.adapterTrim.rmRep.sorted.rmDup.peaks.bed"
))
assign_to_regions(tool=tool,
clusters="test",
speciesFA=clipper.test_file("mm9.fa"),
regions_dir=os.path.join(clipper.test_dir(),
"regions"),
regions={
"exons": "Exon",
"utr3": "3' UTR",
"utr5": "5' UTR",
"proxintron500": "Proximal Intron",
"distintron500": "Distal Intron"
},
assigned_dir=clipper.test_dir(),
fasta_dir=clipper.test_dir(),
species="mm9",
nrand=3,
getseq=False)
def test_count_total_reads(self):
"""
Makes sure we are counting the correct number of reads in genes
"""
bam = pybedtools.BedTool(clipper.test_file("allup_test.bam"))
gene_dfn = pybedtools.BedTool(clipper.test_file("hg19_genes.bed"))
result = count_total_reads(bam, gene_dfn)
self.assertEqual(result, 2086)
def test_get_motif_distance(self):
"""
Tests get motif distance
"""
result = get_motif_distance(pybedtools.BedTool(clipper.test_file("motif_distance_test_cluster.bed")),
pybedtools.BedTool(clipper.test_file("motif_distance_test_motif.bed")))
#hand calculated results from motif distance
self.assertListEqual(result, [-12,112, 12])
def test_count_total_reads(self):
"""
Makes sure we are counting the correct number of reads in genes
"""
bam = pybedtools.BedTool(clipper.test_file("allup_test.bam"))
gene_dfn = pybedtools.BedTool(clipper.test_file("hg19_genes.bed"))
result = count_total_reads(bam, gene_dfn)
self.assertEqual(result, 2086)
def test_calculate_motif_distance(self):
cluster_regions = {"exon" :
{'real' : pybedtools.BedTool(clipper.test_file("clip_analysis_test_peak_results.bed.exon.real.BED")),
'rand' : {0: pybedtools.BedTool(clipper.test_file("clip_analysis_test_peak_results.bed.exon.rand.0.BED"))}}
}
region_sizes = {'all' : 30, "exon" : 30}
#doesn't matter if I output actual results
result = calculate_motif_distance(cluster_regions, region_sizes,
pybedtools.BedTool(clipper.test_file("motif_distance_test_motif.bed")))
#make sure dict structure is sound
self.assertListEqual(result.keys(), ['all', 'exon'])
self.assertListEqual(result['all'].keys(), ['real', 'rand'])
self.assertListEqual(result['all']['real'].keys(), ['dist', 'size'])
def test_get_motif_distance(self):
"""
Tests get motif distance
"""
result = get_motif_distance(
pybedtools.BedTool(
clipper.test_file("motif_distance_test_cluster.bed")),
pybedtools.BedTool(
clipper.test_file("motif_distance_test_motif.bed")))
#hand calculated results from motif distance
self.assertListEqual(result, [-12, 112, 12])
def test_allup_parallel(self):
"""
Performs basic all up test on entire program (except for main), running in parallel to
try to detect crashes
"""
args = [
"--bam",
clipper.test_file("allup_test.bam"),
"--species",
"hg19",
"--gene",
"ENSG00000198901",
"--outfile",
os.getcwd() + "/allup_peak_results.bed",
"--debug",
]
parser = option_parser()
(options, args) = parser.parse_args(args)
options = override_options(options)
main(options)
tested = open(os.getcwd() + "/allup_peak_results.bed")
correct = open(clipper.test_file("peak_results_no_overlap.BED"))
# problem with tracks being different
tested_tool = pybedtools.BedTool(tested)
correct_tool = pybedtools.BedTool(correct)
# checks to make sure files are equal and there are not exact dups
print(len(tested_tool))
print(len(correct_tool))
self.assertAlmostEqual(len(tested_tool), len(correct_tool), delta=3)
print(len(tested_tool))
print(len(correct_tool))
# assert False
"""
for test, correct in zip(tested_tool, correct_tool):
self.assertEqual(test, correct)
"""
# cleanup
os.remove(os.getcwd() + "/allup_peak_results.bed")
def test_parse_compseq(self):
"""
Tests the resut of parse compseq
"""
file = clipper.test_file("compseq_test.out")
diff, dict = parse_compseq(file)
self.assertEqual(diff, 11.0)
self.assertDictEqual(
dict, {
'AA': 2.0,
'AC': 0.0,
'AG': 0.0,
'AT': 1.0,
'CA': 0.0,
'CC': 2.0,
'CG': 0.0,
'CT': 0.0,
'GA': 0.0,
'GC': 1.0,
'GG': 2.0,
'GT': 0.0,
'TA': 0.0,
'TC': 0.0,
'TG': 1.0,
'TT': 2.0,
})
def test_parse_compseq(self):
"""
Tests the resut of parse compseq
"""
file = clipper.test_file("compseq_test.out")
diff, dict = parse_compseq(file)
self.assertEqual(diff, 11.0)
self.assertDictEqual(dict, {
'AA' : 2.0,
'AC' : 0.0,
'AG' : 0.0,
'AT' : 1.0,
'CA' : 0.0,
'CC' : 2.0,
'CG' : 0.0,
'CT' : 0.0,
'GA' : 0.0,
'GC' : 1.0,
'GG' : 2.0,
'GT' : 0.0,
'TA' : 0.0,
'TC' : 0.0,
'TG' : 1.0,
'TT' : 2.0,
})
def test_check_overlaps(self):
"""
Checks for overlapping results, we don't want this
overlaps have been borken for a while, disabling test until its really a problem
"""
args = [
"--bam",
clipper.test_file("allup_test.bam"), "--species", "hg19", "--gene",
"ENSG00000198901", "--outfile",
os.getcwd() + "/overlap_peak_results.bed", "-q", "--debug"
]
parser = option_parser()
(options, args) = parser.parse_args(args)
options = override_options(options)
main(options)
# tests to make sure there are no overlaps
tested = open(os.getcwd() + "/overlap_peak_results.bed")
tested_tool2 = pybedtools.BedTool(tested).saveas(os.getcwd() +
"/overlaps.bed")
result = tested_tool2.intersect(tested_tool2)
self.assertEqual(len(result), len(tested_tool2),
"there are overlaps in the output file")
# cleanup
os.remove(os.getcwd() + "/overlap_peak_results.bed")
os.remove(os.getcwd() + "/overlaps.bed")
def test_allup(self):
""" runs entire program on small test dataset """
args = ["--clusters", clipper.test_file("clip_analysis_test_peak_results.bed"),
"-s", "mm9",
"--bam", clipper.test_file("allup_test.bam"),
"--AS_Structure", "/home/gabrielp/bioinformatics/Yeo_Lab/clip_analysis_metadata/mm9data4",
'--genome_location', '/home/gabrielp/bioinformatics/Yeo_Lab/clip_analysis_metadata/mm9/mm9.fa',
"--regions_location", '/home/gabrielp/bioinformatics/Yeo_Lab/clip_analysis_metadata/regions',
'--phastcons_location', '/home/gabrielp/bioinformatics/Yeo_Lab/clip_analysis_metadata/phastcons/mm9_phastcons.bw',
'--motif', 'AAAAAA',
'--nrand', '1',
'--rePhast',
'--runPhast'
]
(options, args) = self.parser.parse_args(args)
CLIP_analysis.main(options)
def test_kmer_diff(self):
"""
Tests all of kmer diff
(note checked for identity to original perl module seperatly)
"""
Motif = namedtuple('Motif', ['freq1', 'freq2', 'delta'])
file1 = clipper.test_file("compseq_test.fasta")
file2 = clipper.test_file("compseq_test_2.fasta")
result, n1, n2 = kmer_diff(file1, file2, 2)
self.assertEqual(n1, 11.0)
self.assertEqual(n2, 11.0)
true = {
'AA': Motif(2.0, 1.0, 0.621260744197396),
'AC': Motif(0.0, 0.0, 0.0),
'AG': Motif(0.0, 0.0, 0.0),
'AT': Motif(1.0, 2.0, -0.621260744197396),
'CA': Motif(0.0, 0.0, 0.0),
'CC': Motif(2.0, 2.0, 0.0),
'CG': Motif(0.0, 0.0, 0.0),
'CT': Motif(0.0, 0.0, 0.0),
'GA': Motif(0.0, 0.0, 0.0),
'GC': Motif(1.0, 1.0, 0.0),
'GG': Motif(2.0, 2.0, 0.0),
'GT': Motif(0.0, 0.0, 0.0),
'TA': Motif(0.0, 1.0, -1.02353263143832),
'TC': Motif(0.0, 0.0, 0.0),
'TG': Motif(1.0, 1.0, 0.0),
'TT': Motif(2.0, 1.0, 0.621260744197396),
}
#almost equal dict assertion
self.assertSetEqual(set(result.keys()), set(true.keys()))
for key in result.keys():
self.assertEqual(true[key].freq1, result[key].freq1,
"failed at %s" % (key))
self.assertEqual(true[key].freq2, result[key].freq2,
"failed at %s" % (key))
self.assertAlmostEqual(true[key].delta, result[key].delta, delta=3)
def test_kmer_diff(self):
"""
Tests all of kmer diff
(note checked for identity to original perl module seperatly)
"""
Motif = namedtuple('Motif', ['freq1', 'freq2', 'delta'])
file1 = clipper.test_file("compseq_test.fasta")
file2 = clipper.test_file("compseq_test_2.fasta")
result, n1, n2 = kmer_diff(file1, file2, 2)
self.assertEqual(n1, 11.0)
self.assertEqual(n2, 11.0)
true = {
'AA' : Motif(2.0, 1.0, 0.621260744197396 ),
'AC' : Motif(0.0, 0.0, 0.0),
'AG' : Motif(0.0, 0.0, 0.0),
'AT' : Motif(1.0, 2.0, -0.621260744197396),
'CA' : Motif(0.0, 0.0, 0.0),
'CC' : Motif(2.0, 2.0, 0.0),
'CG' : Motif(0.0, 0.0, 0.0),
'CT' : Motif(0.0, 0.0, 0.0),
'GA' : Motif(0.0, 0.0, 0.0),
'GC' : Motif(1.0, 1.0, 0.0),
'GG' : Motif(2.0, 2.0, 0.0),
'GT' : Motif(0.0, 0.0, 0.0),
'TA' : Motif(0.0, 1.0, -1.02353263143832),
'TC' : Motif(0.0, 0.0, 0.0),
'TG' : Motif(1.0, 1.0, 0.0),
'TT' : Motif(2.0, 1.0, 0.621260744197396),
}
#almost equal dict assertion
self.assertSetEqual(set(result.keys()), set(true.keys()))
for key in result.keys():
self.assertEqual(true[key].freq1, result[key].freq1, "failed at %s" % (key))
self.assertEqual(true[key].freq2, result[key].freq2, "failed at %s" % (key))
self.assertAlmostEqual(true[key].delta, result[key].delta, delta=3)
def test_calculate_phastcons(self):
"""
Tests calculate phastcons
Only tests that stucture of file is correct
"""
cluster_regions = {"exon" :
{'real' : pybedtools.BedTool(clipper.test_file("clip_analysis_test_peak_results.bed.exon.real.BED")),
'rand' : {0: pybedtools.BedTool(clipper.test_file("clip_analysis_test_peak_results.bed.exon.rand.0.BED"))}}
}
regions = (["all", "exon", "UTR3", "UTR5", "proxintron500", "distintron500"])
phastcons = '/home/gabrielp/bioinformatics/Yeo_Lab/clip_analysis_metadata/phastcons/mm9_phastcons.bw'
result = calculate_phastcons(regions, cluster_regions, phastcons)
self.assertListEqual(result.keys(), ['real', 'rand'])
self.assertListEqual(result['real'].keys(), ['all', 'exon'])
def test_get_offsets_bed12(self):
"""
Very lazy test of bed12 offsets
"""
bedtool = pybedtools.BedTool(
clipper.test_file("clip_analysis_test_peak_results.bed"))
result = get_offsets_bed12(bedtool)
self.assertDictContainsSubset({"ENSMUSG00000051951_1_147": 5}, result)
def test_get_offsets_bed12(self):
"""
Very lazy test of bed12 offsets
"""
bedtool = pybedtools.BedTool(clipper.test_file("clip_analysis_test_peak_results.bed"))
result = get_offsets_bed12(bedtool)
self.assertDictContainsSubset({"ENSMUSG00000051951_1_147" : 5}, result)
def test_allup(self):
""" runs entire program on small test dataset """
args = [
"--clusters",
clipper.test_file("clip_analysis_test_peak_results.bed"),
"-s",
"mm9",
"--bam",
clipper.test_file("allup_test.bam"),
"--AS_Structure",
os.path.join(clipper.test_dir(), "mm9data4"),
'--genome_location',
clipper.test_file('mm9.fa'),
#'--regions_location', clipper.test_file("knownGene_sample.gtf"),
"--regions_location",
os.path.join(clipper.test_dir(), "regions"),
'--phastcons_location',
clipper.test_file("allup_test.bam"),
'--motifs',
'AAAAAA',
'--nrand',
'1',
#'--runPhast',
'--runMotif',
'--bw_pos',
clipper.test_file("allup_test.pos.bw"),
'--bw_neg',
clipper.test_file("allup_test.neg.bw"),
]
(options, args) = self.parser.parse_args(args)
#self.assertTrue(False, "allup test is slow and has been removed for now")
main(options)
def test_assign_to_regions(self):
"""
Basic test of assign to regions
"""
tool = pybedtools.BedTool(clipper.test_file("FOX2Brain-05.15.09.polyATrim.adapterTrim.rmRep.sorted.rmDup.peaks.bed"))
assign_to_regions(tool=tool,
clusters="test",
speciesFA= clipper.test_file("mm9.fa"),
regions_dir=os.path.join(clipper.test_dir(), "regions"),
regions={"exons" : "Exon", "utr3" : "3' UTR",
"utr5" : "5' UTR", "proxintron500" : "Proximal Intron",
"distintron500" : "Distal Intron"} ,
assigned_dir = clipper.test_dir(),
fasta_dir = clipper.test_dir(),
species="mm9",
nrand = 3,
getseq=False)
def test_check_for_index(self):
"""
Performs unit tests on check_for_index function
"""
# Test if string is null, expected result is operation
# throws file not exist exception
handle = None
self.assertRaises(TypeError, check_for_index, handle)
# Test if bam file doesn't exist, expected result is operation throws
# file does not exist exception
handle = "/foo/bar"
self.assertRaises(NameError, check_for_index, handle)
# Test if file is not bam, but exists expected
# result is to throw improper file error
handle = clipper.test_file("test_peakfinder.py")
self.assertRaises(NameError, check_for_index, handle)
# Test if file is bam and indexed expected
# result is returns 1 and succedes
# should also check if file exists, but I'm lazy
handle = clipper.test_file("indexed_test.bam")
result = check_for_index(handle)
assert result == None
# Test if file is bam and not indexed, expected
# result is returns one and succedes
# should also check if file exists, but I'm lazy
handle = clipper.test_file("not_indexed_test.bam")
result = check_for_index(handle)
assert result == None
# cleanup (should be in taredown)
os.remove(clipper.test_file("not_indexed_test.bam.bai"))
def test_count_reads_per_cluster(self):
"""
Tests count reads per cluster
"""
bedtool = pybedtools.BedTool(clipper.test_file("clip_analysis_test_peak_results.bed"))
total_reads, reads_per_cluster = count_reads_per_cluster(bedtool)
self.assertListEqual([147,52, 239, 85, 47, 119, 58, 588, 92, 59, 196, 36], reads_per_cluster)
self.assertEqual(sum([147,52, 239, 85, 47, 119, 58, 588, 92, 59, 196, 36]), total_reads)
def test_get_mean_phastcons(self):
"""
Tests get_mean phastcons
"""
phastcons = clipper.test_file("mm9_phastcons.bw")
tool = pybedtools.BedTool("chr15 91512755 91512836 ENSG00000198901_1_147 0 -", from_string=True)
result = get_mean_phastcons(tool, phastcons)
#pre-computed correct answer
self.assertAlmostEqual(result[0], 0.01738272, delta=5)
def test_calculate_phastcons(self):
"""
Tests calculate phastcons
Only tests that stucture of file is correct
"""
cluster_regions = {
"exon": {
'real':
pybedtools.BedTool(
clipper.test_file(
"clip_analysis_test_peak_results.bed.exon.real.BED")),
'rand': {
0:
pybedtools.BedTool(
clipper.test_file(
"clip_analysis_test_peak_results.bed.exon.rand.0.BED"
)),
1:
pybedtools.BedTool(
clipper.test_file(
"clip_analysis_test_peak_results.bed.exon.rand.0.BED"
))
}
}
}
regions = ([
"all", "exon", "UTR3", "UTR5", "proxintron500", "distintron500"
])
phastcons = clipper.test_file('mm9_phastcons.bw')
result = calculate_phastcons(regions, cluster_regions, phastcons)
self.assertListEqual(result.keys(), ['real', 'rand'])
self.assertListEqual(result['real'].keys(), ['all', 'exon'])
def test_get_mean_phastcons(self):
"""
Tests get_mean phastcons
"""
phastcons = clipper.test_file("mm9_phastcons.bw")
tool = pybedtools.BedTool(
"chr15 91512755 91512836 ENSG00000198901_1_147 0 -",
from_string=True)
result = get_mean_phastcons(tool, phastcons)
#pre-computed correct answer
self.assertAlmostEqual(result[0], 0.01738272, delta=5)
def test_build_genomic_regions(self):
"""
Tests build genomic regions
"""
CDS = pybedtools.BedTool("""chr1\t7700\t7900\tfoo\t0\t+\n
chr1\t7999\t8500\tfoo\t0\t+\n""",
from_string=True)
UTR5 = pybedtools.BedTool("""chr1\t7499\t7700\tfoo\t0\t+\n""",
from_string=True)
UTR3 = pybedtools.BedTool("""chr1\t8500\t9000\tfoo\t0\t+\n""",
from_string=True)
proxintron = pybedtools.BedTool("""chr1\t100\t300\tfoo\t0\t+\n
chr1\t798\t998\tfoo\t0\t+\n
chr1\t2000\t2200\tfoo\t0\t+\n
chr1\t2798\t2998\tfoo\t0\t+\n
chr1\t6000\t6200\tfoo\t0\t+\n
chr1\t6798\t6998\tfoo\t0\t+\n
chr1\t7900\t7998\tfoo\t0\t+\n""",
from_string=True)
distintron = pybedtools.BedTool("""chr1\t301\t797\tfoo\t0\t+\n
chr1\t2201\t2797\tfoo\t0\t+\n
chr1\t6201\t6797\tfoo\t0\t+\n""",
from_string=True)
regions = build_genomic_regions(pybedtools.BedTool(
clipper.test_file("test.gtf")),
prox_distance=200)
#print UTR3
#print regions['UTR3']
print proxintron
print regions['proxintron']
#print regions['distintron']
self.assertEqual(len(CDS.intersect(regions['CDS'], f=1.0, r=True)), 2)
self.assertEqual(len(UTR5.intersect(regions['UTR5'], f=1.0, r=True)),
1)
self.assertEqual(len(UTR3.intersect(regions['UTR3'], f=1.0, r=True)),
1)
self.assertEqual(
len(proxintron.intersect(regions['proxintron'], f=1.0, r=True)), 7)
self.assertEqual(
len(distintron.intersect(regions['distintron'], f=1.0, r=True)), 3)
def test_count_reads_per_cluster(self):
"""
Tests count reads per cluster
"""
bedtool = pybedtools.BedTool(
clipper.test_file("clip_analysis_test_peak_results.bed"))
total_reads, reads_per_cluster = count_reads_per_cluster(bedtool, None)
self.assertListEqual(
[147, 52, 239, 85, 47, 119, 58, 588, 92, 59, 196, 36],
reads_per_cluster)
self.assertEqual(
sum([147, 52, 239, 85, 47, 119, 58, 588, 92, 59, 196, 36]),
total_reads)
def test_adjust_offsets(self):
"""
Tests adjust offsets, only on bed12 files
"""
offsets = {"ENSMUSG00000051951_1_147" : 10,
"ENSG00000198901_2_52" : 10 ,
"ENSG00000198901_3_239" : 10,
"ENSG00000198901_4_85" : 10 ,
"ENSG00000198901_5_47" : 10 ,
"ENSG00000198901_6_119" : 10 ,
"ENSG00000198901_7_58" : 10 ,
"ENSG00000198901_8_588" : 10 ,
"ENSG00000198901_10_92" : 10 ,
"ENSG00000198901_11_59" : 10 ,
"ENSG00000198901_12_196" : 10 ,
"ENSG00000198901_13_36" : 10 ,
}
bedtool = pybedtools.BedTool(clipper.test_file("clip_analysis_test_peak_results.bed"))
results = adjust_offsets(bedtool, offsets)
true_results = ((3206126, 3206130),
(91513660, 91513664),
(91517394, 91517398),
(91517935, 91517939),
(91522404, 91522408),
(91523607, 91523611),
(91524250, 91524254),
(91525137, 91525141),
(91527347, 91527351),
(91527937, 91527941),
(91528034, 91528038),
(91537658, 91537662),
)
for result, true_result in zip(results, true_results):
self.assertEqual(int(result[6]), true_result[0])
self.assertEqual(int(result[7]), true_result[1])
def test_adjust_offsets(self):
"""
Tests adjust offsets, only on bed12 files
"""
offsets = {
"ENSMUSG00000051951_1_147": 10,
"ENSG00000198901_2_52": 10,
"ENSG00000198901_3_239": 10,
"ENSG00000198901_4_85": 10,
"ENSG00000198901_5_47": 10,
"ENSG00000198901_6_119": 10,
"ENSG00000198901_7_58": 10,
"ENSG00000198901_8_588": 10,
"ENSG00000198901_10_92": 10,
"ENSG00000198901_11_59": 10,
"ENSG00000198901_12_196": 10,
"ENSG00000198901_13_36": 10,
}
bedtool = pybedtools.BedTool(
clipper.test_file("clip_analysis_test_peak_results.bed"))
results = adjust_offsets(bedtool, offsets)
true_results = (
(3206126, 3206130),
(91513660, 91513664),
(91517394, 91517398),
(91517935, 91517939),
(91522404, 91522408),
(91523607, 91523611),
(91524250, 91524254),
(91525137, 91525141),
(91527347, 91527351),
(91527937, 91527941),
(91528034, 91528038),
(91537658, 91537662),
)
for result, true_result in zip(results, true_results):
self.assertEqual(int(result[6]), true_result[0])
self.assertEqual(int(result[7]), true_result[1])
def test_build_genomic_regions(self):
"""
Tests build genomic regions
"""
CDS = pybedtools.BedTool("""chr1\t7700\t7900\tfoo\t0\t+\n
chr1\t7999\t8500\tfoo\t0\t+\n""", from_string = True)
UTR5 = pybedtools.BedTool("""chr1\t7499\t7700\tfoo\t0\t+\n""", from_string = True)
UTR3 = pybedtools.BedTool("""chr1\t8500\t9000\tfoo\t0\t+\n""", from_string = True)
proxintron = pybedtools.BedTool("""chr1\t100\t300\tfoo\t0\t+\n
chr1\t798\t998\tfoo\t0\t+\n
chr1\t2000\t2200\tfoo\t0\t+\n
chr1\t2798\t2998\tfoo\t0\t+\n
chr1\t6000\t6200\tfoo\t0\t+\n
chr1\t6798\t6998\tfoo\t0\t+\n
chr1\t7900\t7998\tfoo\t0\t+\n""", from_string = True
)
distintron = pybedtools.BedTool("""chr1\t301\t797\tfoo\t0\t+\n
chr1\t2201\t2797\tfoo\t0\t+\n
chr1\t6201\t6797\tfoo\t0\t+\n""", from_string = True)
regions = build_genomic_regions(pybedtools.BedTool(clipper.test_file("test.gtf")), prox_distance=200)
#print UTR3
#print regions['UTR3']
print proxintron
print regions['proxintron']
#print regions['distintron']
self.assertEqual(len(CDS.intersect(regions['CDS'], f= 1.0, r = True)), 2)
self.assertEqual(len(UTR5.intersect(regions['UTR5'], f= 1.0, r = True)), 1)
self.assertEqual(len(UTR3.intersect(regions['UTR3'], f= 1.0, r = True)), 1)
self.assertEqual(len(proxintron.intersect(regions['proxintron'], f= 1.0, r = True)), 7)
self.assertEqual(len(distintron.intersect(regions['distintron'], f= 1.0, r = True)), 3)
def test_allup(self):
""" runs entire program on small test dataset """
args = ["--clusters", clipper.test_file("clip_analysis_test_peak_results.bed"),
"-s", "mm9",
"--bam", clipper.test_file("allup_test.bam"),
"--AS_Structure", os.path.join(clipper.test_dir(), "mm9data4"),
'--genome_location', clipper.test_file('mm9.fa'),
#'--regions_location', clipper.test_file("knownGene_sample.gtf"),
"--regions_location", os.path.join(clipper.test_dir(), "regions"),
'--phastcons_location', clipper.test_file("allup_test.bam"),
'--motifs', 'AAAAAA',
'--nrand', '1',
#'--runPhast',
'--runMotif',
'--bw_pos', clipper.test_file("allup_test.pos.bw"),
'--bw_neg', clipper.test_file("allup_test.neg.bw"),
]
(options, args) = self.parser.parse_args(args)
#self.assertTrue(False, "allup test is slow and has been removed for now")
main(options)
