def testSummary(self):
"""
The summary method must return the correct result.
"""
titleAlignments = TitleAlignments('subject title', 10)
titleAlignments.addAlignment(
TitleAlignment(Read('id1', 'ACGT'), [
HSP(30, subjectStart=0, subjectEnd=2),
]))
titleAlignments.addAlignment(
TitleAlignment(Read('id2', 'ACGT'), [
HSP(55, subjectStart=2, subjectEnd=4),
HSP(40, subjectStart=8, subjectEnd=9),
]))
self.assertEqual(
{
'bestScore': 55,
'coverage': 0.5,
'hspCount': 3,
'medianScore': 40,
'readCount': 2,
'subjectLength': 10,
'subjectTitle': 'subject title',
},
titleAlignments.summary())
def testLength(self):
"""
Sorting on sequence length must work, including a secondary sort on
title.
"""
mockOpener = mockOpen(
read_data=(dumps(PARAMS) + '\n' + dumps(RECORD0) + '\n' +
dumps(RECORD1) + '\n' + dumps(RECORD2) + '\n' +
dumps(RECORD3) + '\n'))
with patch.object(builtins, 'open', mockOpener):
reads = Reads()
reads.add(Read('id0', 'A' * 70))
reads.add(Read('id1', 'A' * 70))
reads.add(Read('id2', 'A' * 70))
reads.add(Read('id3', 'A' * 70))
readsAlignments = BlastReadsAlignments(
reads, 'file.json', scoreClass=LowerIsBetterScore)
titlesAlignments = TitlesAlignments(readsAlignments)
result = titlesAlignments.sortTitles('length')
self.assertEqual(
[
'gi|887699|gb|DQ37780 Squirrelpox virus 55', # 38000
'gi|887699|gb|DQ37780 Squirrelpox virus 1296/99', # 37000
'gi|887699|gb|DQ37780 Monkeypox virus 456', # 35000
'gi|887699|gb|DQ37780 Mummypox virus 3000 B.C.', # 35000
'gi|887699|gb|DQ37780 Cowpox virus 15', # 30000
],
result)
def testMaxScore_EValue(self):
"""
Sorting on max score must work when scores are e values, including a
secondary sort on title.
"""
mockOpener = mock_open(read_data=(
dumps(PARAMS) + '\n' + dumps(RECORD0) + '\n' +
dumps(RECORD1) + '\n' + dumps(RECORD2) + '\n' +
dumps(RECORD3) + '\n'))
with patch.object(builtins, 'open', mockOpener):
reads = Reads()
reads.add(Read('id0', 'A' * 70))
reads.add(Read('id1', 'A' * 70))
reads.add(Read('id2', 'A' * 70))
reads.add(Read('id3', 'A' * 70))
readsAlignments = DiamondReadsAlignments(
reads, 'file.json', scoreClass=LowerIsBetterScore)
titlesAlignments = TitlesAlignments(readsAlignments)
result = titlesAlignments.sortTitles('maxScore')
# self.assertEqual([
# 'gi|887699|gb|DQ37780 Cowpox virus 15', # 1e-6
# 'gi|887699|gb|DQ37780 Mummypox virus 3000 B.C.', # 1e-7
# 'gi|887699|gb|DQ37780 Monkeypox virus 456', # 1e-8
# 'gi|887699|gb|DQ37780 Squirrelpox virus 55', # 1e-10
# 'gi|887699|gb|DQ37780 Squirrelpox virus 1296/99', # 1e-11
# ], result)
self.assertEqual([
'gi|887699|gb|DQ37780 Squirrelpox virus 1296/99', # 1e-11
'gi|887699|gb|DQ37780 Squirrelpox virus 55', # 1e-10
'gi|887699|gb|DQ37780 Monkeypox virus 456', # 1e-8
'gi|887699|gb|DQ37780 Mummypox virus 3000 B.C.', # 1e-7
'gi|887699|gb|DQ37780 Cowpox virus 15', # 1e-6
], result)
def __init__(self, id_, sequence, alignment=None):
self.significantOffsets = OrderedDict()
self._originalLength = len(sequence)
self.alignment = alignment
# Scan the sequence for initial gaps.
offset = 0
for base in sequence:
if base == '-':
offset += 1
else:
break
if offset == len(sequence):
raise ValueError('Read is all gaps.')
# Scan for final gaps.
trailing = 0
for base in sequence[::-1]:
if base == '-':
trailing += 1
else:
break
# Make sure the read is not all gaps.
assert offset + trailing < len(sequence)
self.offset = offset
Read.__init__(self, id_,
sequence[offset:len(sequence) - trailing].upper())
def testReadSetFilterAllowAnything(self):
"""
The filter function must work correctly when passed a 0.0 value for
minNewReads, i.e. that considers any read set sufficiently novel.
"""
mockOpener = mock_open(read_data=(
dumps(PARAMS) + '\n' + dumps(RECORD0) + '\n' +
dumps(RECORD1) + '\n' + dumps(RECORD2) + '\n' +
dumps(RECORD3) + '\n'))
with patch.object(builtins, 'open', mockOpener):
reads = Reads()
reads.add(Read('id0', 'A' * 70))
reads.add(Read('id1', 'A' * 70))
reads.add(Read('id2', 'A' * 70))
reads.add(Read('id3', 'A' * 70))
readsAlignments = DiamondReadsAlignments(reads, 'file.json')
titlesAlignments = TitlesAlignments(readsAlignments)
result = titlesAlignments.filter(minNewReads=0.0)
self.assertEqual(
[
'gi|887699|gb|DQ37780 Cowpox virus 15',
'gi|887699|gb|DQ37780 Monkeypox virus 456',
'gi|887699|gb|DQ37780 Mummypox virus 3000 B.C.',
'gi|887699|gb|DQ37780 Squirrelpox virus 1296/99',
'gi|887699|gb|DQ37780 Squirrelpox virus 55',
],
sorted(result))
def testCoverageIncludesSome(self):
"""
The coverage function must return an titlesAlignments instance with
only the expected titles if only some of its titles have sufficient
coverage.
"""
mockOpener = mock_open(read_data=(
dumps(PARAMS) + '\n' + dumps(RECORD0) + '\n' +
dumps(RECORD1) + '\n' + dumps(RECORD2) + '\n' +
dumps(RECORD3) + '\n'))
with patch.object(builtins, 'open', mockOpener):
reads = Reads()
reads.add(Read('id0', 'A' * 70))
reads.add(Read('id1', 'A' * 70))
reads.add(Read('id2', 'A' * 70))
reads.add(Read('id3', 'A' * 70))
readsAlignments = DiamondReadsAlignments(reads, 'file.json')
titlesAlignments = TitlesAlignments(readsAlignments)
# To understand why the following produces the result it does,
# you need to look at the HSP coverage in sample_data.py and
# calculate the coverage by hand.
result = titlesAlignments.filter(minCoverage=0.0003)
self.assertEqual(
[
'gi|887699|gb|DQ37780 Cowpox virus 15',
'gi|887699|gb|DQ37780 Monkeypox virus 456',
'gi|887699|gb|DQ37780 Mummypox virus 3000 B.C.',
],
sorted(result))
def testGapAmbiguous(self):
"""
Testing that the ambiguousOffset shows ambiguous characters paired
with gaps as expected
"""
self.assertEqual(
{
'match': {
'identicalMatchCount': 2,
'ambiguousMatchCount': 0,
'gapMismatchCount': 2,
'gapGapMismatchCount': 1,
'nonGapMismatchCount': 0,
},
'read1': {
'ambiguousOffsets': [1],
'extraCount': 0,
'gapOffsets': [2, 3],
},
'read2': {
'ambiguousOffsets': [3],
'extraCount': 0,
'gapOffsets': [1, 2],
},
}, compareDNAReads(Read('id1', 'AN--T'), Read('id2', 'A--NT')))
def testMaxMatchingReads(self):
"""
The filter function must work correctly when passed a value for
maxMatchingReads.
"""
mockOpener = mock_open(read_data=(
dumps(PARAMS) + '\n' + dumps(RECORD0) + '\n' +
dumps(RECORD1) + '\n' + dumps(RECORD2) + '\n' +
dumps(RECORD3) + '\n'))
with patch.object(builtins, 'open', mockOpener):
reads = Reads()
reads.add(Read('id0', 'A' * 70))
reads.add(Read('id1', 'A' * 70))
reads.add(Read('id2', 'A' * 70))
reads.add(Read('id3', 'A' * 70))
readsAlignments = DiamondReadsAlignments(reads, 'file.json')
titlesAlignments = TitlesAlignments(readsAlignments)
result = titlesAlignments.filter(maxMatchingReads=1)
# Cowpox virus 15 is not in the results as it is matched by two
# reads.
self.assertEqual(
sorted([
'gi|887699|gb|DQ37780 Squirrelpox virus 1296/99',
'gi|887699|gb|DQ37780 Squirrelpox virus 55',
'gi|887699|gb|DQ37780 Monkeypox virus 456',
'gi|887699|gb|DQ37780 Mummypox virus 3000 B.C.'
]),
sorted(result))
def testMatchWithIdenticalAmbiguityButStrict(self):
"""
Two sequences that match exactly, including one (identical)
ambiguity at the same location in the sequence, must compare as
expected. Strict.
"""
self.assertEqual(
{
'match': {
'identicalMatchCount': 5,
'ambiguousMatchCount': 0,
'gapMismatchCount': 0,
'gapGapMismatchCount': 0,
'nonGapMismatchCount': 1,
},
'read1': {
'ambiguousOffsets': [5],
'extraCount': 0,
'gapOffsets': [],
},
'read2': {
'ambiguousOffsets': [5],
'extraCount': 0,
'gapOffsets': [],
},
},
compareDNAReads(Read('id1', 'ACGTTN'),
Read('id2', 'ACGTTN'),
matchAmbiguous=False))
def testNonDefaultGapChars(self):
"""
We must be able to specify the gap characters.
"""
for gap in '+$':
self.assertEqual(
{
'match': {
'identicalMatchCount': 3,
'ambiguousMatchCount': 0,
'gapMismatchCount': 2,
'gapGapMismatchCount': 0,
'nonGapMismatchCount': 0,
},
'read1': {
'ambiguousOffsets': [],
'extraCount': 0,
'gapOffsets': [2],
},
'read2': {
'ambiguousOffsets': [],
'extraCount': 0,
'gapOffsets': [0],
},
},
compareDNAReads(Read('id1', 'AC%sTT' % gap),
Read('id2', '%sCGTT' % gap),
gapChars='+$'))
def testMatchWithIncompatibleAmbiguityInBoth(self):
"""
Two sequences that match exactly, apart from one (incompatible)
ambiguity at the same location in the sequence, must compare as
expected.
"""
self.assertEqual(
{
'match': {
'identicalMatchCount': 5,
'ambiguousMatchCount': 0,
'gapMismatchCount': 0,
'gapGapMismatchCount': 0,
'nonGapMismatchCount': 1,
},
'read1': {
'ambiguousOffsets': [5],
'extraCount': 0,
'gapOffsets': [],
},
'read2': {
'ambiguousOffsets': [5],
'extraCount': 0,
'gapOffsets': [],
},
}, compareDNAReads(Read('id1', 'ACGTTW'), Read('id2', 'ACGTTS')))
def testNonMatchingAmbiguityInFirst(self):
"""
Two sequences that match exactly, apart from one (incompatible)
ambiguity in the second sequence, must compare as expected.
"""
self.assertEqual(
{
'match': {
'identicalMatchCount': 5,
'ambiguousMatchCount': 0,
'gapMismatchCount': 0,
'gapGapMismatchCount': 0,
'nonGapMismatchCount': 1,
},
'read1': {
'ambiguousOffsets': [5],
'extraCount': 0,
'gapOffsets': [],
},
'read2': {
'ambiguousOffsets': [],
'extraCount': 0,
'gapOffsets': [],
},
}, compareDNAReads(Read('id1', 'ACGTTW'), Read('id2', 'ACGTTC')))
def testMatchWithAmbiguityButStrict(self):
"""
Two sequences that match exactly, apart from one ambiguity in the first
sequence, must compare as expected when we specify matchAmbiguous=False
to disallow ambiguous matching.
"""
self.assertEqual(
{
'match': {
'identicalMatchCount': 5,
'ambiguousMatchCount': 0,
'gapMismatchCount': 0,
'gapGapMismatchCount': 0,
'nonGapMismatchCount': 1,
},
'read1': {
'ambiguousOffsets': [5],
'extraCount': 0,
'gapOffsets': [],
},
'read2': {
'ambiguousOffsets': [],
'extraCount': 0,
'gapOffsets': [],
},
},
compareDNAReads(Read('id1', 'ACGTTS'),
Read('id2', 'ACGTTC'),
matchAmbiguous=False))
def testTitleCollection(self):
"""
A title that occurs in the alignments of multiple reads must have
the data from both reads collected properly.
"""
mockOpener = mock_open(read_data=(
dumps(PARAMS) + '\n' + dumps(RECORD2) + '\n' +
dumps(RECORD3) + '\n'))
with patch.object(builtins, 'open', mockOpener):
reads = Reads()
read2 = Read('id2', 'A' * 70)
read3 = Read('id3', 'A' * 70)
reads.add(read2)
reads.add(read3)
readsAlignments = DiamondReadsAlignments(reads, 'file.json')
titlesAlignments = TitlesAlignments(readsAlignments)
title = 'gi|887699|gb|DQ37780 Cowpox virus 15'
titleAlignments = titlesAlignments[title]
self.assertEqual(title, titleAlignments.subjectTitle)
self.assertEqual(30000, titleAlignments.subjectLength)
self.assertEqual(2, len(titleAlignments))
self.assertEqual(read2, titleAlignments[0].read)
self.assertEqual(HSP(20), titleAlignments[0].hsps[0])
self.assertEqual(read3, titleAlignments[1].read)
self.assertEqual(HSP(20), titleAlignments[1].hsps[0])
def testExtraInSecond(self):
"""
If the second sequence has extra bases, they must be indicated in the
extraCount.
"""
self.assertEqual(
{
'match': {
'identicalMatchCount': 5,
'ambiguousMatchCount': 0,
'gapMismatchCount': 0,
'gapGapMismatchCount': 0,
'nonGapMismatchCount': 0,
},
'read1': {
'ambiguousOffsets': [],
'extraCount': 0,
'gapOffsets': [],
},
'read2': {
'ambiguousOffsets': [],
'extraCount': 2,
'gapOffsets': [],
},
}, compareDNAReads(Read('id1', 'ACGTT'), Read('id2', 'ACGTTCC')))
def testFilterWithNoArguments(self):
"""
The filter function must return a TitlesAlignments instance with all
the titles of the original when called with no arguments.
"""
mockOpener = mock_open(read_data=(
dumps(PARAMS) + '\n' + dumps(RECORD0) + '\n' +
dumps(RECORD1) + '\n' + dumps(RECORD2) + '\n'))
with patch.object(builtins, 'open', mockOpener):
reads = Reads()
reads.add(Read('id0', 'A' * 70))
reads.add(Read('id1', 'A' * 70))
reads.add(Read('id2', 'A' * 70))
readsAlignments = DiamondReadsAlignments(reads, 'file.json')
titlesAlignments = TitlesAlignments(readsAlignments)
result = titlesAlignments.filter()
self.assertEqual(
[
'gi|887699|gb|DQ37780 Cowpox virus 15',
'gi|887699|gb|DQ37780 Monkeypox virus 456',
'gi|887699|gb|DQ37780 Mummypox virus 3000 B.C.',
'gi|887699|gb|DQ37780 Squirrelpox virus 1296/99',
'gi|887699|gb|DQ37780 Squirrelpox virus 55',
],
sorted(result))
def testExtraAmbiguous(self):
"""
If the first sequence has extra bases which are ambiguous,they must
be indicated in the extraCount and in the ambiguousOffset.
"""
self.assertEqual(
{
'match': {
'identicalMatchCount': 5,
'ambiguousMatchCount': 0,
'gapMismatchCount': 0,
'gapGapMismatchCount': 0,
'nonGapMismatchCount': 0,
},
'read1': {
'ambiguousOffsets': [6],
'extraCount': 2,
'gapOffsets': [5],
},
'read2': {
'ambiguousOffsets': [],
'extraCount': 0,
'gapOffsets': [],
},
}, compareDNAReads(Read('id1', 'ACGTT-N'), Read('id2', 'ACGTT')))
def testOffsets(self):
"""
If a set of wanted offsets is passed, the result must be restricted to
just those offsets.
"""
self.assertEqual(
{
'match': {
'identicalMatchCount': 1,
'ambiguousMatchCount': 0,
'gapMismatchCount': 0,
'gapGapMismatchCount': 0,
'nonGapMismatchCount': 1,
},
'read1': {
'ambiguousOffsets': [],
'extraCount': 0,
'gapOffsets': [],
},
'read2': {
'ambiguousOffsets': [],
'extraCount': 0,
'gapOffsets': [],
},
},
compareDNAReads(Read('id1', 'ATT-T'),
Read('id2', 'A-GTC'),
offsets=set([0, 4])))
def testMismatch(self):
"""
If the sequences have mismatched (non-ambiguous) bases, their count
must be given correctly in the nonGapMismatchCount.
"""
self.assertEqual(
{
'match': {
'identicalMatchCount': 3,
'ambiguousMatchCount': 0,
'gapMismatchCount': 0,
'gapGapMismatchCount': 0,
'nonGapMismatchCount': 2,
},
'read1': {
'ambiguousOffsets': [],
'extraCount': 0,
'gapOffsets': [],
},
'read2': {
'ambiguousOffsets': [],
'extraCount': 0,
'gapOffsets': [],
},
}, compareDNAReads(Read('id1', 'ACGTT'), Read('id2', 'ACGCC')))
def testCoverageIncludesAll(self):
"""
The coverage function must return an titlesAlignments instance with
all titles if all its titles has sufficient coverage.
"""
mockOpener = mock_open(read_data=(
dumps(PARAMS) + '\n' + dumps(RECORD0) + '\n' +
dumps(RECORD1) + '\n' + dumps(RECORD2) + '\n' +
dumps(RECORD3) + '\n'))
with patch.object(builtins, 'open', mockOpener):
reads = Reads()
reads.add(Read('id0', 'A' * 70))
reads.add(Read('id1', 'A' * 70))
reads.add(Read('id2', 'A' * 70))
reads.add(Read('id3', 'A' * 70))
readsAlignments = DiamondReadsAlignments(reads, 'file.json')
titlesAlignments = TitlesAlignments(readsAlignments)
result = titlesAlignments.filter(minCoverage=0.0)
self.assertEqual(
[
'gi|887699|gb|DQ37780 Cowpox virus 15',
'gi|887699|gb|DQ37780 Monkeypox virus 456',
'gi|887699|gb|DQ37780 Mummypox virus 3000 B.C.',
'gi|887699|gb|DQ37780 Squirrelpox virus 1296/99',
'gi|887699|gb|DQ37780 Squirrelpox virus 55',
],
sorted(result))
def testMatchWithAmbiguityAndNotStrict(self):
"""
Two sequences that match exactly, apart from one ambiguity in the first
sequence, must compare as expected when we specify matchAmbiguous=True
to allow ambiguous matching.
"""
read1 = Read('id1', 'ACGTTS')
read2 = Read('id2', 'ACGTTC')
match = compareDNAReads(read1, read2, matchAmbiguous=True)
self.assertEqual(
'''\
Exact matches: 5/6 (83.33%)
Ambiguous matches: 1/6 (16.67%)
Exact or ambiguous matches: 6/6 (100.00%)
Mismatches: 0
Not involving gaps (i.e., conflicts): 0
Involving a gap in one sequence: 0
Involving a gap in both sequences: 0
Id: id1
Length: 6
Gaps: 0
Ambiguous: 1/6 (16.67%)
Id: id2
Length: 6
Gaps: 0
Ambiguous: 0''', matchToString(match, read1, read2, matchAmbiguous=True))
def testMedianScore_Bits(self):
"""
Sorting on median score must work when scores are bit scores,
including a secondary sort on title.
"""
mockOpener = mock_open(read_data=(
dumps(PARAMS) + '\n' + dumps(RECORD0) + '\n' +
dumps(RECORD1) + '\n' + dumps(RECORD2) + '\n' +
dumps(RECORD3) + '\n' + dumps(RECORD4) + '\n'))
with patch.object(builtins, 'open', mockOpener):
reads = Reads()
reads.add(Read('id0', 'A' * 70))
reads.add(Read('id1', 'A' * 70))
reads.add(Read('id2', 'A' * 70))
reads.add(Read('id3', 'A' * 70))
reads.add(Read('id4', 'A' * 70))
readsAlignments = DiamondReadsAlignments(reads, 'file.json')
titlesAlignments = TitlesAlignments(readsAlignments)
result = titlesAlignments.sortTitles('medianScore')
self.assertEqual([
'gi|887699|gb|DQ37780 Squirrelpox virus 55', # 25
'gi|887699|gb|DQ37780 Monkeypox virus 456', # 20
'gi|887699|gb|DQ37780 Mummypox virus 3000 B.C.', # 20
'gi|887699|gb|DQ37780 Squirrelpox virus 1296/99', # 20
'gi|887699|gb|DQ37780 Cowpox virus 15', # 20
], result)
def testResidueCountsTwoReadsTwoHSPsLeftOverhang(self):
"""
The residueCounts method must return the correct result when two
reads, each with one HSP are aligned to a title and the leftmost HSP
is aligned before the left edge of the subject (i.e, will include
negative subject offsets).
Subject: GTT
HSP1: ACGT
HSP2: CGTT
"""
read1 = Read('id', 'ACGT')
hsp1 = HSP(33, readStart=0, readEnd=4, readStartInSubject=-2,
readEndInSubject=2, subjectStart=0, subjectEnd=2,
readMatchedSequence='GT', subjectMatchedSequence='GT')
read2 = Read('id', 'CGTT')
hsp2 = HSP(33, readStart=0, readEnd=4, readStartInSubject=-1,
readEndInSubject=3, subjectStart=0, subjectEnd=3,
readMatchedSequence='GTT', subjectMatchedSequence='GTT')
titleAlignments = TitleAlignments('subject title', 55)
titleAlignment = TitleAlignment(read1, [hsp1])
titleAlignments.addAlignment(titleAlignment)
titleAlignment = TitleAlignment(read2, [hsp2])
titleAlignments.addAlignment(titleAlignment)
self.assertEqual(
{
-2: {'A': 1},
-1: {'C': 2},
0: {'G': 2},
1: {'T': 2},
2: {'T': 1},
},
titleAlignments.residueCounts())
def testTitle(self):
"""
Sorting on title must work.
"""
mockOpener = mock_open(read_data=(
dumps(PARAMS) + '\n' + dumps(RECORD0) + '\n' +
dumps(RECORD1) + '\n' + dumps(RECORD2) + '\n' +
dumps(RECORD3) + '\n'))
with patch.object(builtins, 'open', mockOpener):
reads = Reads()
reads.add(Read('id0', 'A' * 70))
reads.add(Read('id1', 'A' * 70))
reads.add(Read('id2', 'A' * 70))
reads.add(Read('id3', 'A' * 70))
readsAlignments = DiamondReadsAlignments(
reads, 'file.json', scoreClass=LowerIsBetterScore)
titlesAlignments = TitlesAlignments(readsAlignments)
result = titlesAlignments.sortTitles('title')
self.assertEqual([
'gi|887699|gb|DQ37780 Cowpox virus 15',
'gi|887699|gb|DQ37780 Monkeypox virus 456',
'gi|887699|gb|DQ37780 Mummypox virus 3000 B.C.',
'gi|887699|gb|DQ37780 Squirrelpox virus 1296/99',
'gi|887699|gb|DQ37780 Squirrelpox virus 55',
], result)
def testMinMedianScore_EValue(self):
"""
The filter function must work correctly when passed a value for
minMedianScore when using e values.
"""
mockOpener = mock_open(read_data=(
dumps(PARAMS) + '\n' + dumps(RECORD0) + '\n' +
dumps(RECORD1) + '\n' + dumps(RECORD2) + '\n' +
dumps(RECORD3) + '\n'))
with patch.object(builtins, 'open', mockOpener):
reads = Reads()
reads.add(Read('id0', 'A' * 70))
reads.add(Read('id1', 'A' * 70))
reads.add(Read('id2', 'A' * 70))
reads.add(Read('id3', 'A' * 70))
readsAlignments = DiamondReadsAlignments(
reads, 'file.json', scoreClass=LowerIsBetterScore)
titlesAlignments = TitlesAlignments(readsAlignments)
result = titlesAlignments.filter(minMedianScore=1e-9)
self.assertEqual(
[
'gi|887699|gb|DQ37780 Squirrelpox virus 1296/99',
'gi|887699|gb|DQ37780 Squirrelpox virus 55',
],
sorted(result))
def testYP_009259545(self):
"""
Test for a match against YP_009259545
"""
proteinAccession = 'YP_009259545.1'
proteinSequence = SAMPLE_DATA['proteins'][proteinAccession]['protein']
proteinId = SAMPLE_DATA['proteins'][proteinAccession]['id']
qid = 'query'
qseq = ''.join(CODONS[aa][0] for aa in proteinSequence[10:50])
qqual = 'E' * len(qseq)
with DiamondExecutor() as de:
de.addSubject(Read(proteinId, proteinSequence))
queries = Reads([Read(qid, qseq, qqual)])
(result, ) = list(de.search(queries))
self.assertEqual(
{
'bitscore': 83.6,
'btop': '40',
'qframe': 1,
'qend': 120,
'full_qqual': qqual,
'qlen': len(qseq),
'full_qseq': qseq,
'qseqid': 'query',
'qstart': 1,
'slen': len(proteinSequence),
'sstart': 11,
'stitle': proteinId,
}, result)
def testNoOffsets(self):
"""
If an empty set of wanted offsets is passed, the result must be empty.
"""
self.assertEqual(
{
'match': {
'identicalMatchCount': 0,
'ambiguousMatchCount': 0,
'gapMismatchCount': 0,
'gapGapMismatchCount': 0,
'nonGapMismatchCount': 0,
},
'read1': {
'ambiguousOffsets': [],
'extraCount': 0,
'gapOffsets': [],
},
'read2': {
'ambiguousOffsets': [],
'extraCount': 0,
'gapOffsets': [],
},
},
compareDNAReads(Read('id1', 'ATT-T'),
Read('id2', 'A-GTC'),
offsets=set()))
def testWikiAnswerAsDict(self):
"""
Test the example given in Wikipedia:
http://en.wikipedia.org/wiki/Smith%E2%80%93Waterman_algorithm
with the return result being a dict.
"""
seq1 = Read('seq1', 'ACACACTA')
seq2 = Read('seq2', 'AGCACACA')
align = LocalAlignment(seq1, seq2, match=2)
result = align.createAlignment()
self.assertEqual(
{
'cigar':
'1=1I5=1D1=',
'sequence1Start':
1,
'sequence1End':
8,
'sequence2Start':
1,
'sequence2End':
8,
'text': [
'seq1 1 A-CACACTA 8',
' | ||||| |',
'seq2 1 AGCACAC-A 8',
]
}, result)
def testWikiAnswerWithMatchOneAsDict(self):
"""
Test the example given in Wikipedia
http://en.wikipedia.org/wiki/Smith%E2%80%93Waterman_algorithm
Wikipedia uses a match score of two, here we use a score of one.
Get the result as a dict.
"""
seq1 = Read('seq1', 'ACACACTA')
seq2 = Read('seq2', 'AGCACACA')
align = LocalAlignment(seq1, seq2, match=1)
result = align.createAlignment()
self.assertEqual(
{
'cigar':
'5=1D1=',
'sequence1Start':
2,
'sequence1End':
8,
'sequence2Start':
3,
'sequence2End':
8,
'text': [
'seq1 2 CACACTA 8',
' ||||| |',
'seq2 3 CACAC-A 8',
]
}, result)
def testLengthOne(self):
"""
A FASTA list with just one item gets de-duped to the same one item.
"""
reads = Reads()
reads.add(Read('id', 'GGG'))
self.assertEqual(list(dedupFasta(reads)), [Read('id', 'GGG')])
def testReverseComplementAmbiguousRNA(self):
"""
The reverseComplement function must work for RNA that includes
ambiguous bases.
"""
read = Read('id', 'aucgmrwsykvhxn', type='rna')
self.assertEqual('NXDBMRSWYKCGAU', read.reverseComplement().sequence)
def testReverseComplementAA(self):
"""
The reverseComplement function must raise a C{ValueError} when called
on an amino acid sequence.
"""
read = Read('id', 'atcg', type='aa')
error = 'Cannot reverse complement an amino acid sequence'
with self.assertRaisesRegexp(ValueError, error):
read.reverseComplement()
def queries(self, rcSuffix='', rcNeeded=False, padChar='-',
queryInsertionChar='N', unknownQualityChar='!',
allowDuplicateIds=False, addAlignment=False):
"""
Produce padded (with gaps) queries according to the CIGAR string and
reference sequence length for each matching query sequence.
@param rcSuffix: A C{str} to add to the end of query names that are
reverse complemented. This is added before the /1, /2, etc., that
are added for duplicated ids (if there are duplicates and
C{allowDuplicateIds} is C{False}.
@param rcNeeded: If C{True}, queries that are flagged as matching when
reverse complemented should have reverse complementing when
preparing the output sequences. This must be used if the program
that created the SAM/BAM input flags reversed matches but does not
also store the reverse complemented query.
@param padChar: A C{str} of length one to use to pad queries with to
make them the same length as the reference sequence.
@param queryInsertionChar: A C{str} of length one to use to insert
into queries when the CIGAR string indicates that the alignment
of a query would cause a deletion in the reference. This character
is inserted as a 'missing' query character (i.e., a base that can
be assumed to have been lost due to an error) whose existence is
necessary for the match to continue.
@param unknownQualityChar: The character to put into the quality
string when unknown bases are inserted in the query or the query
is padded on the left/right with gaps.
@param allowDuplicateIds: If C{True}, repeated query ids (due to
secondary or supplemental matches) will not have /1, /2, etc.
appended to their ids. So repeated ids may appear in the yielded
FASTA.
@param addAlignment: If C{True} the reads yielded by the returned
generator will also have an C{alignment} attribute, being the
C{pysam.AlignedSegment} for the query.
@raises InvalidSAM: If a query has an empty SEQ field and either there
is no previous alignment or the alignment is not marked as
secondary or supplementary.
@return: A generator that yields C{Read} instances that are padded
with gap characters to align them to the length of the reference
sequence. See C{addAlignment}, above, to yield reads with the
corresponding C{pysam.AlignedSegment}.
"""
referenceLength = self.referenceLength
# Hold the count for each id so we can add /1, /2 etc to duplicate
# ids (unless --allowDuplicateIds was given).
idCount = Counter()
MATCH_OPERATIONS = {CMATCH, CEQUAL, CDIFF}
for lineNumber, alignment in enumerate(
self.samFilter.alignments(), start=1):
query = alignment.query_sequence
quality = ''.join(chr(q + 33) for q in alignment.query_qualities)
if alignment.is_reverse:
if rcNeeded:
query = DNARead('id', query).reverseComplement().sequence
quality = quality[::-1]
if rcSuffix:
alignment.query_name += rcSuffix
# Adjust the query id if it's a duplicate and we're not allowing
# duplicates.
if allowDuplicateIds:
queryId = alignment.query_name
else:
count = idCount[alignment.query_name]
idCount[alignment.query_name] += 1
queryId = alignment.query_name + (
'' if count == 0 else '/%d' % count)
referenceStart = alignment.reference_start
atStart = True
queryIndex = 0
referenceIndex = referenceStart
alignedSequence = ''
alignedQuality = ''
for operation, length in alignment.cigartuples:
# The operations are tested in the order they appear in
# https://samtools.github.io/hts-specs/SAMv1.pdf It would be
# more efficient to test them in order of frequency of
# occurrence.
if operation in MATCH_OPERATIONS:
atStart = False
alignedSequence += query[queryIndex:queryIndex + length]
alignedQuality += quality[queryIndex:queryIndex + length]
elif operation == CINS:
# Insertion to the reference. This consumes query bases but
# we don't output them because the reference cannot be
# changed. I.e., these bases in the query would need to be
# inserted into the reference. Remove these bases from the
# query but record what would have been inserted into the
# reference.
atStart = False
self.referenceInsertions[queryId].append(
(referenceIndex,
query[queryIndex:queryIndex + length]))
elif operation == CDEL:
# Delete from the reference. Some bases from the reference
# would need to be deleted to continue the match. So we put
# an insertion into the query to compensate.
atStart = False
alignedSequence += queryInsertionChar * length
alignedQuality += unknownQualityChar * length
elif operation == CREF_SKIP:
# Skipped reference. Opens a gap in the query. For
# mRNA-to-genome alignment, an N operation represents an
# intron. For other types of alignments, the
# interpretation of N is not defined. So this is unlikely
# to occur.
atStart = False
alignedSequence += queryInsertionChar * length
alignedQuality += unknownQualityChar * length
elif operation == CSOFT_CLIP:
# Bases in the query that are not part of the match. We
# remove these from the query if they protrude before the
# start or after the end of the reference. According to the
# SAM docs, 'S' operations may only have 'H' operations
# between them and the ends of the CIGAR string.
if atStart:
# Don't set atStart=False, in case there's another 'S'
# operation.
unwantedLeft = length - referenceStart
if unwantedLeft > 0:
# The query protrudes left. Copy its right part.
alignedSequence += query[
queryIndex + unwantedLeft:queryIndex + length]
alignedQuality += quality[
queryIndex + unwantedLeft:queryIndex + length]
referenceStart = 0
else:
referenceStart -= length
alignedSequence += query[
queryIndex:queryIndex + length]
alignedQuality += quality[
queryIndex:queryIndex + length]
else:
unwantedRight = (
(referenceStart + len(alignedSequence) + length) -
referenceLength)
if unwantedRight > 0:
# The query protrudes right. Copy its left part.
alignedSequence += query[
queryIndex:queryIndex + length - unwantedRight]
alignedQuality += quality[
queryIndex:queryIndex + length - unwantedRight]
else:
alignedSequence += query[
queryIndex:queryIndex + length]
alignedQuality += quality[
queryIndex:queryIndex + length]
elif operation == CHARD_CLIP:
# Some bases have been completely removed from the query.
# This (H) can only be present as the first and/or last
# operation. There is nothing to do as the bases are simply
# not present in the query string in the SAM/BAM file.
pass
elif operation == CPAD:
# This is "silent deletion from the padded reference",
# which consumes neither query nor reference.
atStart = False
else:
raise ValueError('Unknown CIGAR operation:', operation)
if operation in _CONSUMES_QUERY:
queryIndex += length
if operation in _CONSUMES_REFERENCE:
referenceIndex += length
if queryIndex != len(query):
# Oops, we did not consume the entire query.
raise ValueError(
'Query %r not fully consumed when parsing CIGAR string. '
'Query %r (len %d), final query index %d, CIGAR: %r' %
(alignment.query_name, query, len(query), queryIndex,
alignment.cigartuples))
# We cannot test we consumed the entire reference. The CIGAR
# string applies to (and exhausts) the query but is silent
# about the part of the reference that lies to the right of the
# aligned query.
# Put gap characters before and after the aligned sequence so that
# it is offset properly and matches the length of the reference.
padRightLength = (referenceLength -
(referenceStart + len(alignedSequence)))
paddedSequence = (padChar * referenceStart +
alignedSequence +
padChar * padRightLength)
paddedQuality = (unknownQualityChar * referenceStart +
alignedQuality +
unknownQualityChar * padRightLength)
read = Read(queryId, paddedSequence, paddedQuality)
if addAlignment:
read.alignment = alignment
yield read
def testReverseComplementRNA(self):
"""
The reverseComplement function must work for RNA
"""
read = Read('id', 'aucg', type='rna')
self.assertEqual('CGAU', read.reverseComplement().sequence)
def testReverseComplementDNA(self):
"""
The reverseComplement function must work for DNA
"""
read = Read('id', 'atcg', quality='!@#$', type='dna')
self.assertEqual('CGAT', read.reverseComplement().sequence)
def testReverseComplementReversesQuality(self):
"""
The reverseComplement function must return a reversed quality string.
"""
read = Read('id', 'atcg', quality='!@#$')
self.assertEqual('$#@!', read.reverseComplement().quality)
