def _countPositionsFewPoints(self, xyzData, tolerance):
'''for a list of list of xyz data, count the number of positions each
atom takes based on the tolerance and the distance. tolerance is compared
to the euclidean difference squared to determine if a position is equal.
actually uses a clustering algorithm and uses a unionfind data structure.'''
self.posCount = []
self.posClusters = [] #just save all the data since we made it
self.posClusterLists = [] #just save all the data since we made it
tolerance2 = tolerance ** 2. #square the tolerance since it is compared
for oneSet in xrange(len(xyzData[0])): #goes from 0 to atom count
clusters = unionFind()
xyzList = []
for oneIndex in xrange(len(xyzData)): #0 to number of positions (mol2#s)
clusters.find(oneIndex) #initiate each position
xyzList.append(xyzData[oneIndex][oneSet])
for oneIndex in xrange(len(xyzData)): #0 to positions
oneXyz = xyzList[oneIndex]
for twoIndex in xrange(oneIndex+1, len(xyzData)): #oneIndex to positions
if geometry_basic.distL2Squared3(oneXyz, xyzList[twoIndex]) \
< tolerance2:
clusters.union(oneIndex, twoIndex)
tempLists = clusters.toLists()
self.posCount.append(len(tempLists))
self.posClusters.append(clusters)
self.posClusterLists.append(tempLists)
def getRMSD(self, xyzOne, xyzTwo):
'''calculates just the rmsd of the two conformations'''
sumSquared = 0.0
for atomIndex in xrange(len(self.atomXyz[xyzOne])):
sumSquared += geometry_basic.distL2Squared3( \
self.atomXyz[xyzOne][atomIndex],
self.atomXyz[xyzTwo][atomIndex])
rmsd = (sumSquared / len(self.atomXyz[xyzOne])) ** 0.5
return rmsd
def getWithin(self):
'''returns pairs of points within the tolerance.
only compare within buckets. slower but doesn't require unionfind
data structure, kept for testing, etc.'''
returnPairs = set()
for bucket in self.possiblyNearbyPoints:
for oneIndex, oneXyzIndex in enumerate(bucket):
oneXyz = self.pointList[oneXyzIndex]
for twoIndex in xrange(oneIndex + 1, len(bucket)):
twoXyzIndex = bucket[twoIndex]
twoXyz = self.pointList[twoXyzIndex]
if distL2Squared3(oneXyz, twoXyz) < self.tolerance2:
if twoXyzIndex < oneXyzIndex:
oneXyzIndex, twoXyzIndex = twoXyzIndex, oneXyzIndex
returnPairs.add((oneXyzIndex, twoXyzIndex))
return returnPairs
def decide(self, mol2data, xyzData):
'''mol2data is the mol2.Mol2 object. xyzData is a list of coords.
use self.rules to return True (clashed) or False (not clashed).'''
dists = defaultdict(list) #format is atomNum -> (otherNum, dist, bondDist)
#all dists in list are euclidean distance squared
atomNums = range(len(xyzData))
atomNums.sort()
for atomNumOne in atomNums:
for atomNumTwo in atomNums:
if atomNumTwo > atomNumOne:
thisDist = distL2Squared3(xyzData[atomNumOne], xyzData[atomNumTwo])
bondDist = mol2data.bondsBetweenActual(atomNumOne, atomNumTwo)
dists[atomNumOne].append((atomNumTwo, thisDist, bondDist))
dists[atomNumTwo].append((atomNumOne, thisDist, bondDist))
for rule in self.rules:
#match atom types first
for atomNum in atomNums:
if rule[3] == "*" or \
0 == string.find(mol2data.atomType[atomNum], rule[3]):
for dist in dists[atomNum]: #for every distance
if rule[4] == "*" or \
0 == string.find(mol2data.atomType[dist[0]], rule[4]):
brokeRule = False
if rule[0] == "max": #is a max distance constraint
if dist[1] > rule[6]: #broke the rule
brokeRule = True
elif rule[0] == "min": #is a min distance constraint
if dist[1] < rule[6]: #broke the rule
brokeRule = True
if brokeRule: #check to make sure actually broken
if not cmp(dist[2], rule[1]) == rule[2]: #this basically amounts
#to checking to see if the right number of bonds lie between
#the atoms in question.
brokeRule = False
if brokeRule: #rule has been broken so there is a clash
#print rule, atomNum, dist #debug the rules broken
return True #can quit after first broken rule
#if everything passed, return False indicating no clashes
return False
def getWithinCluster(self, clusters):
'''souped up for speed version of code. puts nearby points into the
unionfind data structure 'clusters'. does every possible shortcut i can
think of for now. super fast now.'''
#for bucket in self.possiblyNearbyPoints:
# print len(bucket),
#print "bucket lengths"
for bucket in self.possiblyNearbyPoints:
#print len(bucket), len(self.pointList)
indicesLeft = set(xrange(len(bucket)))
while len(indicesLeft) > 0:
oneIndex = indicesLeft.pop()
oneXyzIndex = bucket[oneIndex]
if len(bucket) > self.bigBucket:
thisCluster = clusters.getList(oneXyzIndex) #this is O(n), don't do lots
#print "trying to skip", len(thisCluster), len(bucket)
if len(thisCluster) >= len(bucket): #means we should at least quit
#doing this bucket, nothing left to union
break
oneXyz = self.pointList[oneXyzIndex]
for twoIndex in xrange(len(bucket)):
twoXyzIndex = bucket[twoIndex]
if len(bucket) > self.bigBucket:
if twoXyzIndex in thisCluster:
continue #skip this iteration of the twoIndex for loop
twoXyz = self.pointList[twoXyzIndex]
if distL2Squared3(oneXyz, twoXyz) < self.tolerance2:
clusters.union(oneXyzIndex, twoXyzIndex)
try:
indicesLeft.remove(twoIndex)
except KeyError:
pass #really quite okay
if len(bucket) == len(self.pointList): #might be able to quit now if all
#unioned together already after a single pass.
clusterList = clusters.toLists()
if len(clusterList) == 1: #only one cluster means quit now
return None #just quit entirely