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 test_tss_distances_peak_contains_TSS(self):
self.assertEqual(
tss_distances(Peak('chr1', '100', '250'),
Feature('NM3', 'chr1', '200', '400', '+')), (0, 75))
self.assertEqual(
tss_distances(Peak('chr1', '250', '350'),
Feature('NM4', 'chr1', '200', '300', '-')), (0, 50))
def test_tss_distances_TSS_before_peak(self):
self.assertEqual(
tss_distances(Peak('chr1', '250', '400'),
Feature('NM2', 'chr1', '100', '200', '+')),
(150, 300))
self.assertEqual(
tss_distances(Peak('chr1', '250', '400'),
Feature('NM2', 'chr1', '100', '200', '-')),
(50, 200))
def test_reading_in_ChIPseq_data_custom_columns(self):
peaks = PeakSet('ChIP_peaks_multi_columns-ex1.txt', columns=(2, 4, 5))
self.assertEqual(peaks.source_file, 'ChIP_peaks_multi_columns-ex1.txt')
self.assertEqual(len(peaks), 5,
"Wrong number of lines read from ChIP-seq file")
self.assertEqual(peaks[0], Peak('chr3L', 4252919, 4252920))
self.assertEqual(peaks[1], Peak('chr3L', 9502640, 9502641))
self.assertEqual(peaks[2], Peak('chr3L', 12139192, 12139193))
self.assertEqual(peaks[3], Peak('chr3L', 14983597, 14983598))
self.assertEqual(peaks[4], Peak('chr3L', 17004143, 17004144))
def test_write_features_summary(self):
# Set up some test data
peak = Peak('chr2L',66811,66812)
features = FeatureSet(
features_list=(
Feature('CG31973','chr2L',25402,59243,'-'),
Feature('CG2674-RE','chr2L',106903,114433,'+'),
Feature('CG2674-RC','chr2L',107926,114433,'+')))
# Temp output file
fp,summary = tempfile.mkstemp()
# Write peaks to file
ap = AnalysisReportWriter(output.MULTI_LINE,
fields=('peak.chr',
'peak.start',
'peak.end',
'order',
'feature.id',
'dist_closest',
'dist_TSS'),
summary=summary)
ap.write_nearest_features(peak,features)
ap.close()
# Expected and actual output
expected_output = \
"#peak.chr\tpeak.start\tpeak.end\torder\tfeature.id\tdist_closest\tdist_TSS\n" \
"chr2L\t66811\t66812\t1 of 3\tCG31973\t7568\t7568\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.peak = Peak('chr2L',66811,66812)
self.features = FeatureSet(
features_list=(
Feature('CG31973','chr2L',25402,59243,'-'),
Feature('CG2674-RE','chr2L',106903,114433,'+'),
Feature('CG2674-RC','chr2L',107926,114433,'+')))
self.single_line_fields = ('peak.chr',
'peak.start',
'peak.end',
'number_of_results',
'list(feature.id,'
'dist_closest,dist_TSS)')
self.single_line_fields_extra_data = ('peak.chr',
'peak.start',
'peak.end',
'cutoff',
'number_of_results',
'list(feature.id,'
'dist_closest,dist_TSS)')
self.multi_line_fields = ('peak.chr',
'peak.start',
'peak.end',
'order',
'feature.id',
'dist_closest',
'dist_TSS')
def test_peak_with_id(self):
peak = Peak('chr2L', '66811', '66812', id='Peak001')
self.assertEqual(peak.chrom, 'chr2L')
self.assertEqual(peak.start, 66811)
self.assertEqual(peak.end, 66812)
self.assertEqual(peak.id, 'Peak001')
self.assertEqual(str(peak), "Peak001\tchr2L\t66811\t66812")
self.assertEqual(peak.source_file, None)
def test_peak_properties(self):
peak = Peak('chr2L', '66811', '66812')
self.assertEqual(peak.chrom, 'chr2L')
self.assertEqual(peak.start, 66811)
self.assertEqual(peak.end, 66812)
self.assertEqual(peak.id, None)
self.assertEqual(peak.source_file, None)
self.assertEqual(str(peak), "chr2L\t66811\t66812")
def test_peak_with_source_file(self):
peak = Peak('chr2L', '66811', '66812', source_file="Peaks1.txt")
self.assertEqual(peak.chrom, 'chr2L')
self.assertEqual(peak.start, 66811)
self.assertEqual(peak.end, 66812)
self.assertEqual(peak.id, None)
self.assertEqual(str(peak), "chr2L\t66811\t66812")
self.assertEqual(peak.source_file, "Peaks1.txt")
def test_reading_in_ChIPseq_with_id_column(self):
peaks = PeakSet('ChIP_peaks_multi_columns-ex1.txt',
columns=(2, 4, 5),
id_column=1)
self.assertEqual(peaks.source_file, 'ChIP_peaks_multi_columns-ex1.txt')
self.assertEqual(len(peaks), 5,
"Wrong number of lines read from ChIP-seq file")
self.assertEqual(peaks[0], Peak('chr3L', 4252919, 4252920, id="peak1"))
self.assertEqual(peaks[1], Peak('chr3L', 9502640, 9502641, id="peak2"))
self.assertEqual(peaks[2], Peak('chr3L',
12139192,
12139193,
id="peak3"))
self.assertEqual(peaks[3], Peak('chr3L',
14983597,
14983598,
id="peak4"))
self.assertEqual(peaks[4], Peak('chr3L',
17004143,
17004144,
id="peak5"))
def test_populate_from_list_of_peaks(self):
peaks = PeakSet(peaks_list=(Peak('chr2L', 66711, 66911),
Peak('chr2L', 605850, 606050),
Peak('chr3L', 2258089, 2258289)))
self.assertEqual(peaks.source_file, None)
self.assertEqual(peaks[0], Peak('chr2L', 66711, 66911))
self.assertEqual(peaks[1], Peak('chr2L', 605850, 606050))
self.assertEqual(peaks[2], Peak('chr3L', 2258089, 2258289))
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_write_features_append(self):
# Set up some test data
peak = Peak('chr2L',66811,66812)
features1 = FeatureSet(
features_list=(
Feature('CG31973','chr2L',25402,59243,'-'),
Feature('CG2674-RE','chr2L',106903,114433,'+'),))
features2 = FeatureSet(
features_list=(
Feature('CG2674-RC','chr2L',107926,114433,'+'),))
# Temp output file
fp,outfile = tempfile.mkstemp()
# Write first set of nearest features
ap = AnalysisReportWriter(output.MULTI_LINE,
fields=('peak.chr',
'peak.start',
'peak.end',
'order',
'feature.id',
'dist_closest',
'dist_TSS'),
outfile=outfile)
ap.write_nearest_features(peak,features1)
ap.close()
# Write second set of nearest features
ap = AnalysisReportWriter(output.MULTI_LINE,
fields=('peak.chr',
'peak.start',
'peak.end',
'order',
'feature.id',
'dist_closest',
'dist_TSS'),
outfile=outfile,
append=True)
ap.write_nearest_features(peak,features2)
ap.close()
# Expected and actual output
expected_output = \
"#peak.chr\tpeak.start\tpeak.end\torder\tfeature.id\tdist_closest\tdist_TSS\n" \
"chr2L\t66811\t66812\t1 of 2\tCG31973\t7568\t7568\n" \
"chr2L\t66811\t66812\t2 of 2\tCG2674-RE\t40091\t40091\n" \
"chr2L\t66811\t66812\t1 of 1\tCG2674-RC\t41114\t41114\n"
actual_output = open(outfile,'r').read()
# Check that output matches
self.assertEqual(expected_output,actual_output)
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_feature_upstream_from_peak_neg_strand(self):
peak = Peak('chr1', '100', '200')
feature = Feature('NM1', 'chr1', '250', '400', '-')
self.assertEqual(direction(peak, feature), UPSTREAM)
def test_feature_upstream_from_peak_partial_overlap(self):
peak = Peak('chr1', '350', '550')
feature = Feature('NM1', 'chr1', '250', '400', '+')
self.assertEqual(direction(peak, feature), UPSTREAM)
def test_feature_downstream_from_peak(self):
peak = Peak('chr1', '100', '200')
feature = Feature('NM1', 'chr1', '250', '400', '+')
self.assertEqual(direction(peak, feature), DOWNSTREAM)
def test_peak_upstream_from_feature_neg_strand_partial_overlap(self):
peak = Peak('chr1', '100', '300')
feature = Feature('NM1', 'chr1', '250', '400', '-')
self.assertEqual(direction(feature, peak), DOWNSTREAM)
def test_peak_downstream_from_feature_neg_strand(self):
peak = Peak('chr1', '450', '550')
feature = Feature('NM1', 'chr1', '250', '400', '-')
self.assertEqual(direction(feature, peak), UPSTREAM)
def test_peak_full_overlap_feature(self):
peak = Peak('chr1', '200', '450')
feature = Feature('NM1', 'chr1', '250', '400', '+')
self.assertEqual(direction(feature, peak), OVERLAP)
def test_peak_downstream_from_feature_partial_overlap(self):
peak = Peak('chr1', '350', '550')
feature = Feature('NM1', 'chr1', '250', '400', '+')
self.assertEqual(direction(feature, peak), DOWNSTREAM)
def test_peak_upstream_from_feature(self):
peak = Peak('chr1', '100', '200')
feature = Feature('NM1', 'chr1', '250', '400', '+')
self.assertEqual(direction(feature, peak), UPSTREAM)
def test_get_item(self):
peaks = PeakSet('ChIP_peaks-ex1.txt')
peak = peaks[2]
self.assertEqual(peak, Peak('chr3L', '12139192', '12139193'))
def test_distances_feature_contains_peak(self):
self.assertEqual(
edge_distances(Peak('chr1', '250', '350'),
Feature('NM6', 'chr1', '100', '400', '+')), (0, 0))
def test_distances_feature_overlaps_peak_start(self):
self.assertEqual(
edge_distances(Peak('chr1', '250', '350'),
Feature('NM4', 'chr1', '300', '400', '+')), (0, 50))
def test_feature_downstream_from_peak_neg_strand_partial_overlap(self):
peak = Peak('chr1', '350', '550')
feature = Feature('NM1', 'chr1', '250', '400', '-')
self.assertEqual(direction(peak, feature), DOWNSTREAM)
def test__eq__(self):
self.assertEqual(Peak('chr2L', '66811', '66812'),
Peak('chr2L', '66811', '66812'))
self.assertNotEqual(Peak('chr2L', '66811', '66812'),
Peak('chr2L', '249177', '605951'))
def test_feature_full_overlap_peak_neg_strand(self):
peak = Peak('chr1', '200', '450')
feature = Feature('NM1', 'chr1', '250', '400', '-')
self.assertEqual(direction(peak, feature), OVERLAP)
def test_distances_feature_before_peak(self):
self.assertEqual(
edge_distances(Peak('chr1', '250', '400'),
Feature('NM2', 'chr1', '100', '200', '+')),
(50, 150))
