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 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 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 setUp(self):
# Set up Feature objects to be used in the tests
# Forward strand example
self.rna_data = \
Feature('CG9130-RB','chr3L','1252012','1255989','+')
# Reverse strand example
self.rna_data_2 = \
Feature('CG13051-RA','chr3L','16257914','16258166','-')
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_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_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 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_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_downstream_from_peak(self):
peak = Peak('chr1', '100', '200')
feature = Feature('NM1', 'chr1', '250', '400', '+')
self.assertEqual(direction(peak, feature), DOWNSTREAM)
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_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_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_partial_overlap(self):
peak = Peak('chr1', '350', '550')
feature = Feature('NM1', 'chr1', '250', '400', '+')
self.assertEqual(direction(feature, peak), DOWNSTREAM)
def test_peak_full_overlap_feature(self):
peak = Peak('chr1', '200', '450')
feature = Feature('NM1', 'chr1', '250', '400', '+')
self.assertEqual(direction(feature, peak), OVERLAP)
class TestFeature(unittest.TestCase):
def setUp(self):
# Set up Feature objects to be used in the tests
# Forward strand example
self.rna_data = \
Feature('CG9130-RB','chr3L','1252012','1255989','+')
# Reverse strand example
self.rna_data_2 = \
Feature('CG13051-RA','chr3L','16257914','16258166','-')
def test_properties(self):
self.assertEqual(self.rna_data.chrom,'chr3L')
self.assertEqual(self.rna_data_2.chrom,'chr3L')
def test__eq__(self):
self.assertEqual(self.rna_data,Feature('CG9130-RB',
'chr3L',
'1252012',
'1255989','+'))
self.assertNotEqual(self.rna_data,self.rna_data_2)
def test_contains_position(self):
position = 1253000
self.assertTrue(self.rna_data.containsPosition(position),
"Transcript should contain position")
position = 4250000
self.assertFalse(self.rna_data.containsPosition(position),
"Transcript should not contain position")
position = 10000
self.assertFalse(self.rna_data.containsPosition(position),
"Transcript should not contain position")
def test_get_closest_edge_distance(self):
# Single position
position = 1200000
# Single reference position
self.assertEqual(self.rna_data.getClosestEdgeDistanceTo(position),
abs(self.rna_data.start-position),
"Incorrect closest edge distance #1")
position = 1300000
self.assertEqual(self.rna_data.getClosestEdgeDistanceTo(position),
abs(self.rna_data.end-position),
"Incorrect closest edge distance #2")
def test_get_closest_edge_distance_outside_region(self):
# Reference region (2 positions)
position1 = 1100000
position2 = 1200000
self.assertEqual(self.rna_data.getClosestEdgeDistanceTo(position1,
position2),
abs(self.rna_data.start-position2),
"Incorrect closest edge distance (region #1)")
position1 = 1300000
position2 = 1400000
self.assertEqual(self.rna_data.getClosestEdgeDistanceTo(position1,
position2),
abs(self.rna_data.end-position1),
"Incorrect closest edge distance (region #2)")
def test_get_closest_edge_distance_partially_inside_region(self):
# Partially inside reference region
position1 = 1200000
position2 = 1255000
self.assertEqual(self.rna_data.getClosestEdgeDistanceTo(position1,
position2),
abs(self.rna_data.end-position2),
"Incorrect closest edge distance (inside region #1)")
self.assertEqual(self.rna_data.getClosestEdgeDistanceTo(position1,
position2,
zero_inside_region=True),
0,
"Incorrect closest edge distance (inside region #2)")
def test_get_closest_edge_distance_completely_inside_region(self):
# Completely inside reference region
position1 = 1250000
position2 = 1300000
self.assertEqual(self.rna_data.getClosestEdgeDistanceTo(position1,
position2),
abs(self.rna_data.start-position1),
"Incorrect closest edge distance (inside region #3)")
self.assertEqual(self.rna_data.getClosestEdgeDistanceTo(position1,
position2,
zero_inside_region=True),
0,
"Incorrect closest edge distance (inside region #4)")
def test_get_promoter_region(self):
leading = 10000
trailing = 2500
promoter = self.rna_data.getPromoterRegion(leading,trailing)
self.assertEqual(promoter,
(self.rna_data.getTSS()-leading,
self.rna_data.getTSS()+trailing),
"Incorrect promoter region for + strand example")
promoter = self.rna_data_2.getPromoterRegion(leading,trailing)
self.assertEqual(promoter,
(self.rna_data_2.getTSS()+leading,
self.rna_data_2.getTSS()-trailing),
"Incorrect promoter region for - strand example")
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_distances_feature_before_peak(self):
self.assertEqual(
edge_distances(Peak('chr1', '250', '400'),
Feature('NM2', 'chr1', '100', '200', '+')),
(50, 150))
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_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_peak_upstream_from_feature(self):
peak = Peak('chr1', '100', '200')
feature = Feature('NM1', 'chr1', '250', '400', '+')
self.assertEqual(direction(feature, peak), UPSTREAM)
