def test_different_remap_counts(self):
sample = Sample(
MiseqRun(target_path='run1/Results/versionX'), 'sample42',
SampleFiles(coverage_scores=[{
'project': 'HIV',
'region': 'PR',
'seed': 'HIV1-seed',
'on.score': '3'
}],
remap_counts=[{
'type': 'remap-1 HIV1-seed'
}]),
SampleFiles(coverage_scores=[{
'project': 'HIV',
'region': 'PR',
'seed': 'HIV1-seed',
'on.score': '4'
}],
remap_counts=[{
'type': 'remap-1 HIV1-seed'
}, {
'type': 'remap-2 HIV1-seed'
}]))
expected_report = ''
expected_scenario_counts = {
Scenarios.REMAP_COUNTS_CHANGED:
[' run1:sample42 coverage: HIV PR 3 => 4\n']
}
report, scenario_counts, _ = compare_sample(
sample, Scenarios.REMAP_COUNTS_CHANGED)
self.assertEqual(expected_report, report)
self.assertEqual(expected_scenario_counts, scenario_counts)
def test_equivalent_remap_counts(self):
sample = Sample(
MiseqRun(target_path='run1/Results/versionX'), 'sample42',
SampleFiles(coverage_scores=[{
'project': 'HIV',
'region': 'PR',
'seed': 'HIV1-seed',
'on.score': '3'
}],
remap_counts=[{
'type': 'remap-1 HIV1-seed',
'count': '20'
}]),
SampleFiles(coverage_scores=[{
'project': 'HIV',
'region': 'PR',
'seed': 'HIV1-seed',
'on.score': '4'
}],
remap_counts=[{
'type': 'remap-1 HIV1-seed',
'count': '21'
}]))
expected_report = 'run1:sample42 coverage: HIV PR 3 => 4\n'
expected_scenario_counts = {}
report, scenario_counts, _ = compare_sample(sample)
self.assertEqual(expected_report, report)
self.assertEqual(expected_scenario_counts, scenario_counts)
def test_missing_coverage_different_remap_counts_no_scenarios(self):
sample = Sample(
MiseqRun(target_path='run1/Results/versionX'), 'sample42',
SampleFiles(coverage_scores=[{
'project': 'HCV',
'region': 'HCV1-E1',
'seed': 'HCV1-seed',
'on.score': '2'
}, {
'project': 'HCV',
'region': 'HCV2-E1',
'seed': 'HCV2-seed',
'on.score': '3'
}],
remap_counts=[{
'type': 'remap-1 HCV1-seed'
}, {
'type': 'remap-1 HCV2-seed'
}]),
SampleFiles(coverage_scores=[{
'project': 'HCV',
'region': 'HCV1-E1',
'seed': 'HCV1-seed',
'on.score': '2'
}],
remap_counts=[{
'type': 'remap-1 HCV1-seed'
}]))
expected_report = 'run1:sample42 coverage: HCV HCV2-E1 3 => -\n'
expected_scenario_counts = {}
report, scenario_counts, _ = compare_sample(sample, Scenarios.NONE)
self.assertEqual(expected_report, report)
self.assertEqual(expected_scenario_counts, scenario_counts)
def test_multiple_coverage(self):
sample = Sample(
MiseqRun(target_path='run1/Results/versionX'), 'sample42',
SampleFiles(coverage_scores=[{
'project': 'HIV',
'region': 'PR',
'on.score': '3'
}, {
'project': 'HIV',
'region': 'RT',
'on.score': '2'
}]),
SampleFiles(coverage_scores=[{
'project': 'HIV',
'region': 'RT',
'on.score': '3'
}, {
'project': 'HIV',
'region': 'PR',
'on.score': '4'
}]))
expected_report = ('run1:sample42 coverage: HIV PR 3 => 4\n'
'run1:sample42 coverage: HIV RT 2 => 3\n')
report, _, _ = compare_sample(sample)
self.assertEqual(expected_report, report)
def test_consensus_added(self):
source_seqs = {}
target_seqs = {('R1-seed', 'R1'): make_nuc_rows('ACTTAC')}
coverage_scores = [{
'seed': 'R1-seed',
'region': 'R1',
'project': 'R1',
'on.score': '4'
}]
sample = Sample(
MiseqRun(target_path='run1/Results/versionX'), 'sample42',
SampleFiles(region_consensus=source_seqs,
coverage_scores=coverage_scores),
SampleFiles(region_consensus=target_seqs,
coverage_scores=coverage_scores))
expected_diffs = [
'run1:sample42 consensus: R1-seed R1 MAX', '+ ACTTAC'
]
expected_consensus_distances = []
diffs = []
scenarios = defaultdict(list)
consensus_distances = compare_consensus(sample, diffs, Scenarios.NONE,
scenarios)
self.assertEqual(expected_diffs, diffs)
self.assertEqual(expected_consensus_distances, consensus_distances)
def test_same_consensus(self):
source_seqs = {('R1-seed', 'R1'): make_nuc_rows('ACACAC')}
target_seqs = {('R1-seed', 'R1'): make_nuc_rows('ACACAC')}
coverage_scores = [{
'seed': 'R1-seed',
'region': 'R1',
'project': 'R1',
'on.score': '4'
}]
sample = Sample(
MiseqRun(target_path='run1/Results/versionX'), 'sample42',
SampleFiles(region_consensus=source_seqs,
coverage_scores=coverage_scores),
SampleFiles(region_consensus=target_seqs,
coverage_scores=coverage_scores))
expected_diffs = []
expected_scenarios = {}
diffs = []
scenarios = defaultdict(list)
compare_consensus(
sample, diffs, Scenarios.MAIN_CONSENSUS_CHANGED
| Scenarios.OTHER_CONSENSUS_CHANGED, scenarios)
self.assertEqual(expected_diffs, diffs)
self.assertEqual(expected_scenarios, scenarios)
def test_one_consensus_changes(self):
source_seqs = {
('R1-seed', 'R1', 'MAX'): 'ACACACGT',
('R2-seed', 'R2', 'MAX'): 'ACACACGT'
}
target_seqs = {
('R1-seed', 'R1', 'MAX'): 'ACACACGT',
('R2-seed', 'R2', 'MAX'): 'ACACAMGT'
}
sample = Sample(MiseqRun(target_path='run1/Results/versionX'),
'sample42', SampleFiles(), SampleFiles())
expected_diffs = [
'run1:sample42 consensus: R2-seed R2 MAX', '- ACACACGT',
'? ^', '+ ACACAMGT', '? ^'
]
expected_consensus_distances = [
ConsensusDistance(region='R1',
cutoff='MAX',
distance=0,
pct_diff=0),
ConsensusDistance(region='R2',
cutoff='MAX',
distance=1,
pct_diff=12.5)
]
diffs = []
scenarios = defaultdict(list)
consensus_distances = compare_consensus(sample, source_seqs,
target_seqs, diffs,
Scenarios.NONE, scenarios)
self.assertEqual(expected_diffs, diffs)
self.assertEqual(expected_consensus_distances, consensus_distances)
def test_consensus_change(self):
source_seqs = {('R1-seed', 'R1'): make_nuc_rows('ACACACGT')}
target_seqs = {('R1-seed', 'R1'): make_nuc_rows('ACACACGG')}
coverage_scores = [{
'seed': 'R1-seed',
'region': 'R1',
'project': 'R1',
'on.score': '4'
}]
sample = Sample(
MiseqRun(target_path='run1/Results/versionX'), 'sample42',
SampleFiles(region_consensus=source_seqs,
coverage_scores=coverage_scores),
SampleFiles(region_consensus=target_seqs,
coverage_scores=coverage_scores))
expected_report = ('run1:sample42 consensus: R1-seed R1 MAX\n'
'- ACACACGT\n'
'? ^\n'
'+ ACACACGG\n'
'? ^\n')
expected_consensus_distances = [
ConsensusDistance(region='R1',
cutoff='MAX',
distance=1,
pct_diff=12.5)
]
report, _, consensus_distances = compare_sample(sample)
self.assertEqual(expected_report, report)
self.assertEqual(expected_consensus_distances, consensus_distances)
def test_empty(self):
sample = Sample(MiseqRun(target_path='run1/Results/versionX'),
'sample42', SampleFiles(), SampleFiles())
expected_report = ''
report, _, _ = compare_sample(sample)
self.assertEqual(expected_report, report)
def test_blank(self):
sample = Sample(MiseqRun(target_path='run1/Results/versionX'),
'sample42',
SampleFiles(g2p_summary=[dict(X4pct='50.00')]),
SampleFiles(g2p_summary=[dict(X4pct='')]))
expected_report = 'run1:sample42 G2P: 50.00 => \n'
report, _, _ = compare_sample(sample)
self.assertEqual(expected_report, report)
def test_other_difference_with_blanks(self):
sample = Sample(MiseqRun(target_path='run1/Results/versionX'),
'sample42',
SampleFiles(g2p_summary=[dict(X4pct='', other='x')]),
SampleFiles(g2p_summary=[dict(X4pct='', other='y')]))
expected_report = ''
report, _, _ = compare_sample(sample)
self.assertEqual(expected_report, report)
def test_same_final(self):
sample = Sample(
MiseqRun(target_path='run1/Results/versionX'), 'sample42',
SampleFiles(g2p_summary=[dict(X4pct='2.99', final='X4')]),
SampleFiles(g2p_summary=[dict(X4pct='3.01', final='X4')]))
expected_report = ''
report, _, _ = compare_sample(sample)
self.assertEqual(expected_report, report)
def test_different_final(self):
sample = Sample(
MiseqRun(target_path='run1/Results/versionX'), 'sample42',
SampleFiles(g2p_summary=[dict(X4pct='1.99', final='R5')]),
SampleFiles(g2p_summary=[dict(X4pct='2.01', final='X4')]))
expected_report = 'run1:sample42 G2P: R5 1.99 => X4 2.01\n'
report, _, _ = compare_sample(sample)
self.assertEqual(expected_report, report)
def test_missing_coverage_to_low(self):
sample = Sample(
MiseqRun(target_path='run1/Results/versionX'), 'sample42',
SampleFiles(coverage_scores=None),
SampleFiles(coverage_scores=[{
'project': 'HIV',
'region': 'PR',
'on.score': '1'
}]))
expected_report = ''
report, _, _ = compare_sample(sample)
self.assertEqual(expected_report, report)
def test_one_consensus_changes(self):
source_seqs = {
('R1-seed', 'R1'): make_nuc_rows('ACACACGT'),
('R2-seed', 'R2'): make_nuc_rows('ACACACGT')
}
target_seqs = {
('R1-seed', 'R1'): make_nuc_rows('ACACACGT'),
('R2-seed', 'R2'): make_nuc_rows('ACACAMGT')
}
coverage_scores = [{
'seed': 'R1-seed',
'region': 'R1',
'project': 'R1',
'on.score': '4'
}, {
'seed': 'R2-seed',
'region': 'R2',
'project': 'R2',
'on.score': '4'
}]
sample = Sample(
MiseqRun(target_path='run1/Results/versionX'), 'sample42',
SampleFiles(region_consensus=source_seqs,
coverage_scores=coverage_scores),
SampleFiles(region_consensus=target_seqs,
coverage_scores=coverage_scores))
expected_diffs = [
'run1:sample42 consensus: R2-seed R2 MAX', '- ACACACGT',
'? ^', '+ ACACAMGT', '? ^'
]
expected_consensus_distances = [
ConsensusDistance(region='R1',
cutoff='MAX',
distance=0,
pct_diff=0),
ConsensusDistance(region='R2',
cutoff='MAX',
distance=1,
pct_diff=12.5)
]
diffs = []
scenarios = defaultdict(list)
consensus_distances = compare_consensus(sample, diffs, Scenarios.NONE,
scenarios)
self.assertEqual(expected_diffs, diffs)
self.assertEqual(expected_consensus_distances, consensus_distances)
def test_same_consensus(self):
source_seqs = {('R1-seed', 'R1', 'MAX'): 'ACACAC'}
target_seqs = {('R1-seed', 'R1', 'MAX'): 'ACACAC'}
sample = Sample(MiseqRun(target_path='run1/Results/versionX'),
'sample42', SampleFiles(), SampleFiles())
expected_diffs = []
expected_scenarios = {}
diffs = []
scenarios = defaultdict(list)
compare_consensus(
sample, source_seqs, target_seqs, diffs,
Scenarios.MAIN_CONSENSUS_CHANGED
| Scenarios.OTHER_CONSENSUS_CHANGED, scenarios)
self.assertEqual(expected_diffs, diffs)
self.assertEqual(expected_scenarios, scenarios)
def test_consensus_added(self):
source_seqs = {}
target_seqs = {('R1-seed', 'R1', 'MAX'): 'ACTTAC'}
sample = Sample(MiseqRun(target_path='run1/Results/versionX'),
'sample42', SampleFiles(), SampleFiles())
expected_diffs = [
'run1:sample42 consensus: R1-seed R1 MAX', '+ ACTTAC'
]
expected_consensus_distances = []
diffs = []
scenarios = defaultdict(list)
consensus_distances = compare_consensus(sample, source_seqs,
target_seqs, diffs,
Scenarios.NONE, scenarios)
self.assertEqual(expected_diffs, diffs)
self.assertEqual(expected_consensus_distances, consensus_distances)
def test_other_consensus_change(self):
source_seqs = {('R1-seed', 'R1', '0.250'): 'ACACAC'}
target_seqs = {('R1-seed', 'R1', '0.250'): 'ACACAT'}
sample = Sample(MiseqRun(target_path='run1/Results/versionX'),
'sample42', SampleFiles(), SampleFiles())
expected_diffs = [
'run1:sample42 consensus: R1-seed R1 0.250', '- ACACAC',
'? ^', '+ ACACAT', '? ^'
]
expected_scenarios = {}
diffs = []
scenarios = defaultdict(list)
compare_consensus(sample, source_seqs, target_seqs, diffs,
Scenarios.NONE, scenarios)
self.assertEqual(expected_diffs, diffs)
self.assertEqual(expected_scenarios, scenarios)
def test_consensus_change(self):
sample = Sample(
MiseqRun(target_path='run1/Results/versionX'), 'sample42',
SampleFiles(coverage_scores=[{
'region': 'R1',
'seed': 'R1-seed',
'on.score': '4'
}],
nuc_limits={'R1-seed': [('R1', 101, 108)]},
consensus=[{
'region': 'R1-seed',
'consensus-percent-cutoff': 'MAX',
'offset': '100',
'sequence': 'ACACACGT'
}]),
SampleFiles(coverage_scores=[{
'region': 'R1',
'seed': 'R1-seed',
'on.score': '4'
}],
nuc_limits={'R1-seed': [('R1', 101, 108)]},
consensus=[{
'region': 'R1-seed',
'consensus-percent-cutoff': 'MAX',
'offset': '100',
'sequence': 'ACACACGG'
}]))
expected_report = ('run1:sample42 consensus: R1-seed R1 MAX\n'
'- ACACACGT\n'
'? ^\n'
'+ ACACACGG\n'
'? ^\n')
expected_consensus_distances = [
ConsensusDistance(region='R1',
cutoff='MAX',
distance=1,
pct_diff=12.5)
]
report, _, consensus_distances = compare_sample(sample)
self.assertEqual(expected_report, report)
self.assertEqual(expected_consensus_distances, consensus_distances)
def test_hiv_seed_changed(self):
sample = Sample(
MiseqRun(target_path='run1/Results/versionX'), 'sample42',
SampleFiles(consensus=[{
'region': 'HIV1-X',
'consensus-percent-cutoff': 'MAX',
'offset': '100',
'sequence': 'ACACAC'
}]),
SampleFiles(consensus=[{
'region': 'HIV1-Y',
'consensus-percent-cutoff': 'MAX',
'offset': '200',
'sequence': 'ACACAC'
}]))
expected_report = ''
report, _, _ = compare_sample(sample)
self.assertEqual(expected_report, report)
def test_consensus_trailing_change(self):
source_seqs = {('R1-seed', 'R1', 'MAX'): 'ACTTAC------GTAC'}
target_seqs = {('R1-seed', 'R1', 'MAX'): 'ACTTAC'}
sample = Sample(MiseqRun(target_path='run1/Results/versionX'),
'sample42', SampleFiles(), SampleFiles())
expected_diffs = [
'run1:sample42 consensus: R1-seed R1 MAX', '- ACTTAC------GTAC',
'+ ACTTAC'
]
expected_consensus_distances = [
ConsensusDistance(region='R1',
cutoff='MAX',
distance=4,
pct_diff=25)
]
diffs = []
scenarios = defaultdict(list)
consensus_distances = compare_consensus(sample, source_seqs,
target_seqs, diffs,
Scenarios.NONE, scenarios)
self.assertEqual(expected_diffs, diffs)
self.assertEqual(expected_consensus_distances, consensus_distances)