def test_handling_quoted_chr(self):
peaks = PeakSet('ChIP_peaks-ex5.txt')
self.assertEqual(len(peaks),5,
"Wrong number of lines read from ChIP-seq file")
peaks_chr = peaks.filterByChr("chr4")
self.assertEqual(len(peaks_chr),2,
"Wrong number of ChIP-seq records filtered")
def test_filter_on_peak_position(self):
peaks = PeakSet('ChIP_peaks-ex1.txt')
lower, upper = 12000000, 15000000
peaks_pos = peaks.filterByPosition(upper, lower)
self.assertEqual(len(peaks_pos), 2, "Wrong number of peaks filtered")
for peak in peaks_pos:
print(str(peak))
self.assertTrue((peak.start >= lower and peak.start <= upper),
"Peak should have been filtered out")
def test_filter_on_peak_position(self):
peaks = PeakSet('ChIP_peaks-ex1.txt')
lower,upper = 12000000,15000000
peaks_pos = peaks.filterByPosition(upper,lower)
self.assertEqual(len(peaks_pos),2,
"Wrong number of peaks filtered")
for peak in peaks_pos:
print str(peak)
self.assertTrue((peak.start >= lower and
peak.start <= upper),
"Peak should have been filtered out")
def test_filter_on_chromosome(self):
peaks_chr = PeakSet('ChIP_peaks-ex2.txt')
chromosome = 'chr2L'
self.assertEqual(len(peaks_chr),10,
"Wrong number of lines from ChIP-seq file")
peaks_chr = peaks_chr.filterByChr(chromosome)
self.assertEqual(len(peaks_chr), 5,
"Wrong number of lines from ChIP-seq after chr filter")
for peak in peaks_chr:
self.assertTrue((peak.chrom == chromosome),
"Wrong chromosome name filtered by chr")
def test_filter_on_chromosome(self):
peaks_chr = PeakSet('ChIP_peaks-ex2.txt')
chromosome = 'chr2L'
self.assertEqual(len(peaks_chr), 10,
"Wrong number of lines from ChIP-seq file")
peaks_chr = peaks_chr.filterByChr(chromosome)
self.assertEqual(
len(peaks_chr), 5,
"Wrong number of lines from ChIP-seq after chr filter")
for peak in peaks_chr:
self.assertTrue((peak.chrom == chromosome),
"Wrong chromosome name filtered by chr")
def test_sort_by_distance_from(self):
peaks_sort = PeakSet('ChIP_peaks-ex1.txt')
position = 12000000
# Do the sorting
peaks_sort.sortByDistanceFrom(position)
# Check that each distance is greater than the previous one
last_peak = None
for peak in peaks_sort:
if not last_peak:
last_peak = peak
else:
self.assertTrue((abs(peak.start - position) >=
abs(last_peak.start - position)),
"Sort by distance failed")
def test_write_peaks_summary(self):
# Set up some test data
feature = Feature('CG31973','chr2L','25402','59243','-')
peaks = PeakSet(
peaks_list=(
Peak('chr2L','66711','66911'),
Peak('chr2L','249077','249277'),
Peak('chr2L','605850','606050')))
# Temp output files
fp,summary= tempfile.mkstemp()
# Write peaks to file
ap = AnalysisReportWriter(output.MULTI_LINE,
fields=('feature.id',
'order',
'peak.chr',
'peak.start',
'peak.end',
'dist_closest',
'dist_TSS'),
summary=summary)
ap.write_nearest_peaks(feature,peaks)
ap.close()
# Expected and actual output
expected_output = \
"#feature.id\torder\tpeak.chr\tpeak.start\tpeak.end\tdist_closest\tdist_TSS\n" \
"CG31973\t1 of 3\tchr2L\t66711\t66911\t7468\t7468\n"
actual_output = open(summary,'r').read()
# Check that output matches
self.assertEqual(expected_output,actual_output)
def setUp(self):
# Set up some test data
self.feature = Feature('CG31973','chr2L','25402','59243','-')
self.peaks = PeakSet(
peaks_list=(
Peak('chr2L','66711','66911'),
Peak('chr2L','249077','249277'),
Peak('chr2L','605850','606050')))
self.single_line_fields = ('feature.id',
'number_of_results',
'list(peak.chr,peak.start,peak.end,'
'dist_closest,dist_TSS)')
self.single_line_fields_extra_data = ('feature.id',
'cutoff',
'number_of_results',
'list(peak.chr,peak.start,peak.end,'
'dist_closest,dist_TSS)')
self.multi_line_fields = ('feature.id',
'order',
'peak.chr',
'peak.start',
'peak.end',
'dist_closest',
'dist_TSS')
def test_is_summit_data(self):
peaks = PeakSet('ChIP_peaks-ex1.txt')
self.assertTrue(peaks.isSummit(),"ChIP data are summits")
peaks = PeakSet('ChIP_peaks-ex5.txt')
self.assertFalse(peaks.isSummit(),"ChIP data are not summits")
def test__eq__(self):
# Test equality of PeakSets
peak_set1 = PeakSet()
peak_set2 = PeakSet()
# Empty feature sets
self.assertEqual(peak_set1,peak_set2)
# Populate
peak_set1.addPeak(Peak('chr2L','66811','66812'))
peak_set2.addPeak(Peak('chr2L','66811','66812'))
self.assertEqual(peak_set1,peak_set2)
# Add second
peak_set1.addPeak(Peak('chr2L','249177','605951'))
self.assertNotEqual(peak_set1,peak_set2)
peak_set2.addPeak(Peak('chr2L','249177','605951'))
self.assertEqual(peak_set1,peak_set2)
# Add third
peak_set1.addPeak(Peak('chr2L','605650','605850'))
peak_set2.addPeak(Peak('chr2L','605850','606050'))
self.assertNotEqual(peak_set1,peak_set2)
def test_is_summit_data(self):
peaks = PeakSet('ChIP_peaks-ex1.txt')
self.assertTrue(peaks.isSummit(), "ChIP data are summits")
peaks = PeakSet('ChIP_peaks-ex5.txt')
self.assertFalse(peaks.isSummit(), "ChIP data are not summits")
