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 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 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 testTwoCompletelyDifferentSequences(self):
"""
When two completely different sequences are given, the result
should be the two sequences with an empty alignment.
"""
seq1 = SeqRecord(Seq('aaaaaa'), id='seq1')
seq2 = SeqRecord(Seq('gggggg'), id='seq2')
align = LocalAlignment(seq1, seq2)
result = align.createAlignment()
alignment = ("\nNo alignment between seq1 and seq2 \n")
self.assertEqual(result, alignment)
def testTwoCompletelyDifferentSequences(self):
"""
When two completely different sequences are given, the result
should be the two sequences with an empty alignment.
"""
seq1 = Read('seq1', 'aaaaaa')
seq2 = Read('seq2', 'gggggg')
align = LocalAlignment(seq1, seq2)
result = align.createAlignment(resultFormat=str)
alignment = ('\nNo alignment between seq1 and seq2\n')
self.assertEqual(result, alignment)
def testTwoCompletelyDifferentSequences(self):
"""
When two completely different sequences are given, the result
should be the two sequences with an empty alignment.
"""
seq1 = SeqRecord(Seq('aaaaaa'), id='seq1')
seq2 = SeqRecord(Seq('gggggg'), id='seq2')
align = LocalAlignment(seq1, seq2)
result = align.createAlignment()
alignment = ("\nNo alignment between seq1 and seq2 \n")
self.assertEqual(result, alignment)
def testTwoCompletelyDifferentSequences(self):
"""
When two completely different sequences are given, the result
should be the two sequences with an empty alignment.
"""
seq1 = Read('seq1', 'aaaaaa')
seq2 = Read('seq2', 'gggggg')
align = LocalAlignment(seq1, seq2)
result = align.createAlignment(resultFormat=str)
alignment = ('\nNo alignment between seq1 and seq2\n')
self.assertEqual(result, alignment)
def testAlignmentWithGapInMiddle(self):
seq1 = Read('seq1', 'agtcagtcagtc')
seq2 = Read('seq2', 'cgaatcg')
align = LocalAlignment(seq1, seq2)
result = align.createAlignment(resultFormat=str)
alignment = ('\nCigar string of aligned region: 2=1D1=\n'
'seq1 Match start: 7 Match end: 10\n'
'seq2 Match start: 5 Match end: 7\n'
'seq1 7 TCAG 10\n'
' || |\n'
'seq2 5 TC-G 7')
self.assertEqual(result, alignment)
def testGapAtBothEndsOfSeq1(self):
seq1 = Read('seq1', 'gaatc')
seq2 = Read('seq2', 'cgaatcg')
align = LocalAlignment(seq1, seq2)
result = align.createAlignment(resultFormat=str)
alignment = ('\nCigar string of aligned region: 5=\n'
'seq1 Match start: 1 Match end: 5\n'
'seq2 Match start: 2 Match end: 6\n'
'seq1 1 GAATC 5\n'
' |||||\n'
'seq2 2 GAATC 6')
self.assertEqual(result, alignment)
def testGapAtStartOfSeq2(self):
seq1 = Read('seq1', 'cgaatcg')
seq2 = Read('seq2', 'gaatcg')
align = LocalAlignment(seq1, seq2)
result = align.createAlignment(resultFormat=str)
alignment = ('\nCigar string of aligned region: 6=\n'
'seq1 Match start: 2 Match end: 7\n'
'seq2 Match start: 1 Match end: 6\n'
'seq1 2 GAATCG 7\n'
' ||||||\n'
'seq2 1 GAATCG 6')
self.assertEqual(result, alignment)
def testAlignmentWithGapInMiddle(self):
seq1 = SeqRecord(Seq('agtcagtcagtc'), id='seq1')
seq2 = SeqRecord(Seq('cgaatcg'), id='seq2')
align = LocalAlignment(seq1, seq2)
result = align.createAlignment()
alignment = ("\nCigar string of aligned region: 2=1D1=\n"
"seq1 Match start: 7 Match end: 10\n"
"seq2 Match start: 5 Match end: 7\n"
"seq1 7 TCAG 10\n"
" || |\n"
"seq2 5 TC-G 7")
self.assertEqual(result, alignment)
def testGapAtStartOfSeq2(self):
seq1 = SeqRecord(Seq('cgaatcg'), id='seq1')
seq2 = SeqRecord(Seq('gaatcg'), id='seq2')
align = LocalAlignment(seq1, seq2)
result = align.createAlignment()
alignment = ("\nCigar string of aligned region: 6=\n"
"seq1 Match start: 2 Match end: 7\n"
"seq2 Match start: 1 Match end: 6\n"
"seq1 2 GAATCG 7\n"
" ||||||\n"
"seq2 1 GAATCG 6")
self.assertEqual(result, alignment)
def testGapAtBothEndsOfSeq1(self):
seq1 = SeqRecord(Seq('gaatc'), id='seq1')
seq2 = SeqRecord(Seq('cgaatcg'), id='seq2')
align = LocalAlignment(seq1, seq2)
result = align.createAlignment()
alignment = ("\nCigar string of aligned region: 5=\n"
"seq1 Match start: 1 Match end: 5\n"
"seq2 Match start: 2 Match end: 6\n"
"seq1 1 GAATC 5\n"
" |||||\n"
"seq2 2 GAATC 6")
self.assertEqual(result, alignment)
def testAlignmentWithGapInMiddle(self):
seq1 = SeqRecord(Seq('agtcagtcagtc'), id='seq1')
seq2 = SeqRecord(Seq('cgaatcg'), id='seq2')
align = LocalAlignment(seq1, seq2)
result = align.createAlignment()
alignment = ("\nCigar string of aligned region: 2=1D1=\n"
"seq1 Match start: 7 Match end: 10\n"
"seq2 Match start: 5 Match end: 7\n"
"seq1 7 TCAG 10\n"
" || |\n"
"seq2 5 TC-G 7")
self.assertEqual(result, alignment)
def testGapAtStartOfSeq2(self):
seq1 = Read('seq1', 'cgaatcg')
seq2 = Read('seq2', 'gaatcg')
align = LocalAlignment(seq1, seq2)
result = align.createAlignment(resultFormat=str)
alignment = ('\nCigar string of aligned region: 6=\n'
'seq1 Match start: 2 Match end: 7\n'
'seq2 Match start: 1 Match end: 6\n'
'seq1 2 GAATCG 7\n'
' ||||||\n'
'seq2 1 GAATCG 6')
self.assertEqual(result, alignment)
def testGapAtStartOfSeq2(self):
seq1 = SeqRecord(Seq('cgaatcg'), id='seq1')
seq2 = SeqRecord(Seq('gaatcg'), id='seq2')
align = LocalAlignment(seq1, seq2)
result = align.createAlignment()
alignment = ("\nCigar string of aligned region: 6=\n"
"seq1 Match start: 2 Match end: 7\n"
"seq2 Match start: 1 Match end: 6\n"
"seq1 2 GAATCG 7\n"
" ||||||\n"
"seq2 1 GAATCG 6")
self.assertEqual(result, alignment)
def testGapAtBothEndsOfSeq1(self):
seq1 = SeqRecord(Seq('gaatc'), id='seq1')
seq2 = SeqRecord(Seq('cgaatcg'), id='seq2')
align = LocalAlignment(seq1, seq2)
result = align.createAlignment()
alignment = ("\nCigar string of aligned region: 5=\n"
"seq1 Match start: 1 Match end: 5\n"
"seq2 Match start: 2 Match end: 6\n"
"seq1 1 GAATC 5\n"
" |||||\n"
"seq2 2 GAATC 6")
self.assertEqual(result, alignment)
def testGapAtBothEndsOfSeq1(self):
seq1 = Read('seq1', 'gaatc')
seq2 = Read('seq2', 'cgaatcg')
align = LocalAlignment(seq1, seq2)
result = align.createAlignment(resultFormat=str)
alignment = ('\nCigar string of aligned region: 5=\n'
'seq1 Match start: 1 Match end: 5\n'
'seq2 Match start: 2 Match end: 6\n'
'seq1 1 GAATC 5\n'
' |||||\n'
'seq2 2 GAATC 6')
self.assertEqual(result, alignment)
def testAlignmentWithGapInMiddle(self):
seq1 = Read('seq1', 'agtcagtcagtc')
seq2 = Read('seq2', 'cgaatcg')
align = LocalAlignment(seq1, seq2)
result = align.createAlignment(resultFormat=str)
alignment = ('\nCigar string of aligned region: 2=1D1=\n'
'seq1 Match start: 7 Match end: 10\n'
'seq2 Match start: 5 Match end: 7\n'
'seq1 7 TCAG 10\n'
' || |\n'
'seq2 5 TC-G 7')
self.assertEqual(result, alignment)
def testTwoEqualSequences(self):
"""
When two identical sequences are given, the result should
show that the sequences completely match.
"""
seq1 = SeqRecord(Seq('cgaatcg'), id='seq1')
seq2 = SeqRecord(Seq('cgaatcg'), id='seq2')
align = LocalAlignment(seq1, seq2)
result = align.createAlignment()
alignment = ("\nCigar string of aligned region: 7=\n"
"seq1 Match start: 1 Match end: 7\n"
"seq2 Match start: 1 Match end: 7\n"
"seq1 1 CGAATCG 7\n"
" |||||||\n"
"seq2 1 CGAATCG 7")
self.assertEqual(result, alignment)
def testWikiAnswer(self):
"""
Test the example given in Wikipedia:
http://en.wikipedia.org/wiki/Smith%E2%80%93Waterman_algorithm
"""
seq1 = SeqRecord(Seq('ACACACTA'), id='seq1')
seq2 = SeqRecord(Seq('AGCACACA'), id='seq2')
align = LocalAlignment(seq1, seq2, match=2)
result = align.createAlignment()
alignment = ("\nCigar string of aligned region: 1=1I5=1D1=\n"
"seq1 Match start: 1 Match end: 8\n"
"seq2 Match start: 1 Match end: 8\n"
"seq1 1 A-CACACTA 8\n"
" | ||||| |\n"
"seq2 1 AGCACAC-A 8")
self.assertEqual(result, alignment)
def testTwoEqualSequences(self):
"""
When two identical sequences are given, the result should
show that the sequences completely match.
"""
seq1 = Read('seq1', 'cgaatcg')
seq2 = Read('seq2', 'cgaatcg')
align = LocalAlignment(seq1, seq2)
result = align.createAlignment(resultFormat=str)
alignment = ('\nCigar string of aligned region: 7=\n'
'seq1 Match start: 1 Match end: 7\n'
'seq2 Match start: 1 Match end: 7\n'
'seq1 1 CGAATCG 7\n'
' |||||||\n'
'seq2 1 CGAATCG 7')
self.assertEqual(result, alignment)
def testWikiAnswer(self):
"""
Test the example given in Wikipedia:
http://en.wikipedia.org/wiki/Smith%E2%80%93Waterman_algorithm
"""
seq1 = SeqRecord(Seq('ACACACTA'), id='seq1')
seq2 = SeqRecord(Seq('AGCACACA'), id='seq2')
align = LocalAlignment(seq1, seq2, match=2)
result = align.createAlignment()
alignment = ("\nCigar string of aligned region: 1=1I5=1D1=\n"
"seq1 Match start: 1 Match end: 8\n"
"seq2 Match start: 1 Match end: 8\n"
"seq1 1 A-CACACTA 8\n"
" | ||||| |\n"
"seq2 1 AGCACAC-A 8")
self.assertEqual(result, alignment)
def testTwoEqualSequences(self):
"""
When two identical sequences are given, the result should
show that the sequences completely match.
"""
seq1 = SeqRecord(Seq('cgaatcg'), id='seq1')
seq2 = SeqRecord(Seq('cgaatcg'), id='seq2')
align = LocalAlignment(seq1, seq2)
result = align.createAlignment()
alignment = ("\nCigar string of aligned region: 7=\n"
"seq1 Match start: 1 Match end: 7\n"
"seq2 Match start: 1 Match end: 7\n"
"seq1 1 CGAATCG 7\n"
" |||||||\n"
"seq2 1 CGAATCG 7")
self.assertEqual(result, alignment)
def testWikiAnswer(self):
"""
Test the example given in Wikipedia:
http://en.wikipedia.org/wiki/Smith%E2%80%93Waterman_algorithm
"""
seq1 = Read('seq1', 'ACACACTA')
seq2 = Read('seq2', 'AGCACACA')
align = LocalAlignment(seq1, seq2, match=2)
result = align.createAlignment(resultFormat=str)
alignment = ('\nCigar string of aligned region: 1=1I5=1D1=\n'
'seq1 Match start: 1 Match end: 8\n'
'seq2 Match start: 1 Match end: 8\n'
'seq1 1 A-CACACTA 8\n'
' | ||||| |\n'
'seq2 1 AGCACAC-A 8')
self.assertEqual(result, alignment)
def testWikiAnswer(self):
"""
Test the example given in Wikipedia:
http://en.wikipedia.org/wiki/Smith%E2%80%93Waterman_algorithm
"""
seq1 = Read('seq1', 'ACACACTA')
seq2 = Read('seq2', 'AGCACACA')
align = LocalAlignment(seq1, seq2, match=2)
result = align.createAlignment(resultFormat=str)
alignment = ('\nCigar string of aligned region: 1=1I5=1D1=\n'
'seq1 Match start: 1 Match end: 8\n'
'seq2 Match start: 1 Match end: 8\n'
'seq1 1 A-CACACTA 8\n'
' | ||||| |\n'
'seq2 1 AGCACAC-A 8')
self.assertEqual(result, alignment)
def testTwoEqualSequences(self):
"""
When two identical sequences are given, the result should
show that the sequences completely match.
"""
seq1 = Read('seq1', 'cgaatcg')
seq2 = Read('seq2', 'cgaatcg')
align = LocalAlignment(seq1, seq2)
result = align.createAlignment(resultFormat=str)
alignment = ('\nCigar string of aligned region: 7=\n'
'seq1 Match start: 1 Match end: 7\n'
'seq2 Match start: 1 Match end: 7\n'
'seq1 1 CGAATCG 7\n'
' |||||||\n'
'seq2 1 CGAATCG 7')
self.assertEqual(result, alignment)
def testWikiAnswerWithMatchOne(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.
"""
seq1 = Read('seq1', 'ACACACTA')
seq2 = Read('seq2', 'AGCACACA')
align = LocalAlignment(seq1, seq2, match=1)
result = align.createAlignment(resultFormat=str)
alignment = ('\nCigar string of aligned region: 5=1D1=\n'
'seq1 Match start: 2 Match end: 8\n'
'seq2 Match start: 3 Match end: 8\n'
'seq1 2 CACACTA 8\n'
' ||||| |\n'
'seq2 3 CACAC-A 8')
self.assertEqual(result, alignment)
def testWikiAnswerWithMatchOne(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.
"""
seq1 = SeqRecord(Seq('ACACACTA'), id='seq1')
seq2 = SeqRecord(Seq('AGCACACA'), id='seq2')
align = LocalAlignment(seq1, seq2, match=1)
result = align.createAlignment()
alignment = ("\nCigar string of aligned region: 5=1D1=\n"
"seq1 Match start: 2 Match end: 8\n"
"seq2 Match start: 3 Match end: 8\n"
"seq1 2 CACACTA 8\n"
" ||||| |\n"
"seq2 3 CACAC-A 8")
self.assertEqual(result, alignment)
help='The mismatch score.')
parser.add_argument('--gapOpenScore',
type=int,
default=-1,
help='The gap open score.')
parser.add_argument('--gapExtendScore',
type=int,
default=-1,
help='The gap extend score.')
parser.add_argument('--gapExtendDecay',
type=float,
default=0.0,
help='The gap extend decay.')
args = parser.parse_args()
for seq1 in FastaReads(args.fastaFile1):
for seq2 in FastaReads(args.fastaFile2):
alignment = LocalAlignment(seq1,
seq2,
match=args.matchScore,
mismatch=args.mismatchScore,
gap=args.gapOpenScore,
gapExtend=args.gapExtendScore,
gapExtendDecay=args.gapExtendDecay)
print(alignment.createAlignment(resultFormat=str))
'--fastaFile2', required=True, help='The second FASTA file.')
parser.add_argument(
'--matchScore', type=int, default=1, help='The match score.')
parser.add_argument(
'--mismatchScore', type=int, default=-1, help='The mismatch score.')
parser.add_argument(
'--gapOpenScore', type=int, default=-1, help='The gap open score.')
parser.add_argument(
'--gapExtendScore', type=int, default=-1, help='The gap extend score.')
parser.add_argument(
'--gapExtendDecay', type=float, default=0.0, help='The gap extend decay.')
args = parser.parse_args()
for seq1 in FastaReads(args.fastaFile1):
for seq2 in FastaReads(args.fastaFile2):
alignment = LocalAlignment(
seq1, seq2,
match=args.matchScore,
mismatch=args.mismatchScore,
gap=args.gapOpenScore,
gapExtend=args.gapExtendScore,
gapExtendDecay=args.gapExtendDecay)
print(alignment.createAlignment(resultFormat=str))
sys.exit(1)
else:
fileHandle1 = sys.argv[1]
fileHandle2 = sys.argv[2]
if len(sys.argv) == 3:
matchScore = 1
mismatchScore = -1
gapOpenScore = -1
gapExtendScore = -1
gapExtendDecay = 0.0
else:
matchScore = int(sys.argv[3])
mismatchScore = int(sys.argv[4])
gapOpenScore = int(sys.argv[5])
gapExtendScore = int(sys.argv[6])
gapExtendDecay = float(sys.argv[7])
for record in SeqIO.parse(fileHandle1, "fasta"):
input1 = record
for record in SeqIO.parse(fileHandle2, "fasta"):
input2 = record
alignment = LocalAlignment(
input1,
input2,
match=matchScore,
mismatch=mismatchScore,
gap=gapOpenScore,
gapExtend=gapExtendScore,
gapDecay=gapExtendDecay,
)
print(alignment.createAlignment())
'gapExtendDecay)' % sys.argv[0],
file=sys.stderr)
sys.exit(1)
else:
fileHandle1 = sys.argv[1]
fileHandle2 = sys.argv[2]
if len(sys.argv) == 3:
matchScore = 1
mismatchScore = -1
gapOpenScore = -1
gapExtendScore = -1
gapExtendDecay = 0.0
else:
matchScore = int(sys.argv[3])
mismatchScore = int(sys.argv[4])
gapOpenScore = int(sys.argv[5])
gapExtendScore = int(sys.argv[6])
gapExtendDecay = float(sys.argv[7])
for record in SeqIO.parse(fileHandle1, 'fasta'):
input1 = record
for record in SeqIO.parse(fileHandle2, 'fasta'):
input2 = record
alignment = LocalAlignment(input1,
input2,
match=matchScore,
mismatch=mismatchScore,
gap=gapOpenScore,
gapExtend=gapExtendScore,
gapDecay=gapExtendDecay)
print(alignment.createAlignment())
print >>sys.stderr, ("Usage: %s filename1, filename2, (matchScore, "
"mismatchScore, gapOpenScore, gapExtendScore, "
"gapExtendDecay)"
% sys.argv[0])
sys.exit(1)
else:
fileHandle1 = sys.argv[1]
fileHandle2 = sys.argv[2]
if len(sys.argv) == 3:
matchScore = 1
mismatchScore = -1
gapOpenScore = -1
gapExtendScore = -1
gapExtendDecay = 0.0
else:
matchScore = int(sys.argv[3])
mismatchScore = int(sys.argv[4])
gapOpenScore = int(sys.argv[5])
gapExtendScore = int(sys.argv[6])
gapExtendDecay = float(sys.argv[7])
for record in SeqIO.parse(fileHandle1, "fasta"):
input1 = record
for record in SeqIO.parse(fileHandle2, "fasta"):
input2 = record
alignment = LocalAlignment(input1, input2, match=matchScore,
mismatch=mismatchScore,
gap=gapOpenScore,
gapExtend=gapExtendScore,
gapDecay=gapExtendDecay)
print alignment.createAlignment()