def testEmptyReads(self):
"""
heterogeneousSites must return an empty dictionary if no reads are given.
"""
reads = Reads()
self.assertEqual(({}, {}, []), heterogeneousSites(reads, 0, 1))
def testHomogeneousReads(self):
"""
heterogeneousSites must return an empty dictionary if homogenous reads are given.
"""
read = Read('id', 'ACCG')
reads = Reads([read, Read('id2', 'ACCG')])
self.assertEqual(({}, {}, []), heterogeneousSites(reads, len(read), 1))
def testOneRead(self):
"""
heterogeneousSites must return an empty dictionary if only one read is given.
"""
read = Read('id', 'ACCG')
reads = Reads([read])
self.assertEqual(({}, {}, []), heterogeneousSites(reads, len(read), 1))
def testGaps(self):
"""
heterogeneousSites must return an empty dictionary if reads given differ only by gaps;
gaps do not count towards heterogeneity.
"""
read = Read('id', 'ACCG')
reads = Reads([read, Read('id2', '-CC-')])
self.assertEqual(({}, {}, []), heterogeneousSites(reads, len(read), 1))
def testHeterogeneousReadsFractionLow(self):
"""
heterogeneousSites must return an empty dictionary if reads given differ and
are more homogeneous than specified by the homogeneity cutoff fraction.
"""
read = Read('id', 'ACCG')
reads = Reads([read, Read('id2', 'ACCC'), Read('id3', 'ACCC')])
self.assertEqual(({}, {}, []), heterogeneousSites(reads, len(read), 0.6))
def testHeterogeneousReadsOneDifference(self):
"""
heterogeneousSites must return a dictionary with one entry as expected if
reads given differ at one site.
"""
read = Read('id', 'ACCG')
reads = Reads([read, Read('id2', 'ACCC')])
self.assertEqual(({3: {'G': 1, 'C': 1}},
{3: {'G': ['id'], 'C': ['id2']}}, [3]),
heterogeneousSites(reads, len(read), 1))
def testHeterogeneousReadsFractionHigh(self):
"""
heterogeneousSites must return a dictionary with one entry as expected if
reads given differ and are less homogeneous than specified by the homogeneity
cutoff fraction.
"""
read = Read('id', 'ACCG')
reads = Reads([read, Read('id2', 'ACCC'), Read('id3', 'ACCC')])
self.assertEqual(({3: {'C': 2, 'G': 1}},
{3: {'G': ['id'], 'C': ['id2', 'id3']}}, [3]),
heterogeneousSites(reads, len(read), 0.7))
def testHeterogeneousReadsTwoDifferences(self):
"""
heterogeneousSites must return a dictionary with two entries as expected if
reads given differ at two sites.
"""
read = Read('id', 'ACCG')
reads = Reads([read, Read('id2', 'TCCC')])
self.assertEqual(({0: {'A': 1, 'T': 1}, 3: {'G': 1, 'C': 1}},
{0: {'A': ['id'], 'T': ['id2']},
3: {'C': ['id2'], 'G': ['id']}}, [0, 3]),
heterogeneousSites(reads, len(read), 1))
def testHeterogeneousReadsFractionLowWithOneDifference(self):
"""
heterogeneousSites must return a dictionary with one entry if reads given differ
at two sites and at one site are more homogeneous than specified by the homogeneity
cutoff fraction; at the other site less homogeneous than specified by the
homogeneity cutoff fraction.
"""
read = Read('id', 'ACCG')
reads = Reads([read, Read('id2', 'TCCG'), Read('id3', 'TCCG'), Read('id4', 'ACCG')])
self.assertEqual(({0: {'A': 2, 'T': 2}},
{0: {'A': ['id', 'id4'], 'T': ['id2', 'id3']}}, [0]),
heterogeneousSites(reads, len(read), 0.6))
args = parser.parse_args()
homogenFraction = args.homogenFraction
bestSNP = args.bestSNP
reads = list(parseFASTACommandLineOptions(args))
if not 0 < homogenFraction <= 1:
raise ValueError('--homogenFraction needs to be between 0 and 1.')
if len(set(len(read) for read in reads)) != 1:
raise ValueError('Not all read lengths are the same.....')
else:
length = len(reads[0])
count, ids, indexes = heterogeneousSites(reads, length, homogenFraction)
width = int(log10(length)) + 1
for index in indexes:
print('A SNP is detected at index %*d.' % (width, index + 1))
print('Detected bases: %s' % (str(count[index])[9:-2]))
if 'A' in count[index].keys():
print('A:')
for id in ids[index]['A']:
print(id)
if 'C' in count[index].keys():
print('C:')
for id in ids[index]['C']:
print(id)