def commonNucleotidesMultiplicativeDistance(a, b):
"""
Measure the distance from one cluster to another, as the sum of the
multiplied probabilities of nucleotides.
@param a: A C{ReadCluster} instance.
@param b: A C{ReadCluster} instance.
@raise ZeroDivisionError: if C{a} or C{b} has no offsets (neither of
which should be possible in normal operation).
@return: The C{float} [0.0, 1.0] distance between C{a} and C{b}.
"""
aNucleotides = a.nucleotides
bNucleotides = b.nucleotides
commonOffsets = set(aNucleotides) & set(bNucleotides)
if commonOffsets:
similarity = sum(
# 1.0 - OffsetBases.multiplicativeDistance(
# aNucleotides[offset], bNucleotides[offset])
1.0 - min(
OffsetBases.multiplicativeDistance(aNucleotides[offset],
bNucleotides[offset]),
OffsetBases.homogeneousDistance(aNucleotides[offset],
bNucleotides[offset]))
for offset in commonOffsets)
return 1.0 - (similarity / len(commonOffsets))
else:
return 1.0
def mergeDescriptionWithOffsetScores(self, a, b, distance):
"""
Make a textual description of a cluster merge, including per-offset
score information.
@param a: An C{int} cluster number.
@param b: An C{int} cluster number.
@param distance: The C{float} [0.0, 1.0] distance between the clusters.
@return: A C{str} side-by-side descriptions of clusters C{a} and C{b}.
"""
cluster1 = self.readClusters[a]
cluster2 = self.readClusters[b]
result1 = []
result2 = []
offsetScores = []
matches = []
sharedCount = matchCount = 0
allOffsets = sorted(
set(cluster1.nucleotides) | set(cluster2.nucleotides))
for offset in allOffsets:
inCount = 0
if offset in cluster1.nucleotides:
result1.append(cluster1.nucleotides[offset].baseCountsToStr())
inCount += 1
else:
result1.append('-')
if offset in cluster2.nucleotides:
result2.append(cluster2.nucleotides[offset].baseCountsToStr())
inCount += 1
else:
result2.append('-')
if inCount == 2:
sharedCount += 1
if (cluster1.nucleotides[offset].commonest
& cluster2.nucleotides[offset].commonest):
matches.append('*')
matchCount += 1
else:
matches.append('')
offsetScores.append('%.3f' % min(
OffsetBases.multiplicativeDistance(
cluster1.nucleotides[offset],
cluster2.nucleotides[offset]),
OffsetBases.homogeneousDistance(
cluster1.nucleotides[offset],
cluster2.nucleotides[offset])))
else:
matches.append('')
offsetScores.append('')
result1Width = max(len(line) for line in result1)
result2Width = max(len(line) for line in result2)
offsetScoresWidth = max(len(line) for line in offsetScores)
return '\n'.join([
('Merging clusters %d and %d with distance %.2f' %
(a, b, distance)),
('Cluster %d has %d read%s, covering %d offset%s' %
(a, len(cluster1.reads), s(len(cluster1.reads), ),
len(cluster1.nucleotides), s(len(cluster1.nucleotides)))),
('Cluster %d has %d read%s, covering %d offset%s' %
(b, len(cluster2.reads), s(len(cluster2.reads)),
len(cluster2.nucleotides), s(len(cluster2.nucleotides)))),
('%d matches out of %d shared offsets' %
(matchCount, sharedCount)),
] + [
' %d: %*s %*s %*s %s' %
(offset + 1, result1Width, line1, result2Width, line2,
offsetScoresWidth, offsetScore, match)
for (offset, line1, line2, offsetScore, match
) in zip(allOffsets, result1, result2, offsetScores, matches)
])