def chipdata(self, data):
"""Input data: [(dirname0, [et0, et1, ...]), ...]
"""
self.numRowsMissingChipData = 0
self._chipdataMA = []
if data != None:
self._chipdata = data
numValsAll = 0
numValsNonMasked = 0
numFiles = 0
numExamplesList = []
attribDict = {}
numColMissing = 0
for (name, etList) in data:
numFiles += len(etList)
self._chipdataMA.append((name, []))
for et in etList:
attribDict.update(
dict(
zip(map(lambda x: x.name, et.domain.attributes),
et.domain.attributes)))
numExamplesList.append(len(et))
etm = et.toNumpyMA("a")[0]
colNonMissingInd = Numeric.compress(
Numeric.not_equal(MA.count(etm, 0), 0),
Numeric.arange(etm.shape[1])
) # indices of columns that are not completely missing
numColMissing += etm.shape[1] - colNonMissingInd.shape[0]
self.numRowsMissingChipData += int(
Numeric.add.reduce(
Numeric.less(
MA.count(etm.take(colNonMissingInd, 1), 1),
etm.shape[1])))
numValsAll += int(Numeric.multiply.reduce(etm.shape))
numValsNonMasked += int(MA.count(etm))
self._chipdataMA[-1][1].append(etm)
# info text
self.infoc.setText(
"Structured Data: %i data files with %i profiles on %i points"
% (numFiles, numExamplesList[0], len(attribDict)))
numTotalMissing = numValsAll - numValsNonMasked
if numTotalMissing > 0:
print numTotalMissing, numColMissing, self.numRowsMissingChipData
print type(numTotalMissing), type(numColMissing), type(
self.numRowsMissingChipData)
self.infod.setText(
"missing %i values, %i column%s completely, %i row%s partially"
% (numTotalMissing, numColMissing, [
"", "s"
][numColMissing != 1], self.numRowsMissingChipData,
["", "s"][self.numRowsMissingChipData != 1]))
else:
self.infod.setText("")
else:
self._chipdata = None
self.infoc.setText("No structured data on input")
self.infod.setText("")
self.setGuiCommonExpChip()
if self.commitOnChange:
self.senddata(2)
def filter(self, dlg):
fptr = open(dlg)
dlg_lines = fptr.readlines()
fptr.close()
#STEP 1:accumulate lines of various poses
model_lines = []
#keep all of them
all_models = []
in_model = False
for ll in dlg_lines:
if ll.find("DOCKED:") == 0:
#check for a new model
if ll.find("DOCKED: MODEL") == 0:
model_lines = []
in_model = True
model_lines.append(ll)
if ll.find("_") == 0 and in_model:
all_models.append(model_lines)
model_lines = []
in_model = False
#initialize this ligand
# loop over the models:
for model_lines in all_models:
self.setup_ligand(model_lines)
bigR = self.bigRC[:self.lenK]
bigM = self.bigC[:self.lenK]
cutoff = bigR + self.keyRadii
d = bigM - self.smallM
dSQ = d * d
dSQMAT = Numeric.sum(dSQ, 2)
cutoffSQMAT = cutoff * cutoff
ansMat = Numeric.logical_and(Numeric.less(dSQMAT, cutoffSQMAT),
Numeric.not_equal(dSQMAT, 0.))
rowIndices = Numeric.nonzero(Numeric.sum(ansMat, 1))
num_contacts = 0
for ind in rowIndices:
for j in ansMat[ind]:
if j: num_contacts += 1
if num_contacts > 0:
break
return num_contacts
def filter(self, dlg):
fptr = open(dlg)
dlg_lines = fptr.readlines()
fptr.close()
#STEP 1:accumulate lines of various poses
model_lines = []
#keep all of them
all_models = []
in_model = False
for ll in dlg_lines:
if ll.find("DOCKED:")==0:
#check for a new model
if ll.find("DOCKED: MODEL")==0:
model_lines = []
in_model = True
model_lines.append(ll)
if ll.find("_")==0 and in_model:
all_models.append(model_lines)
model_lines = []
in_model = False
#initialize this ligand
# loop over the models:
for model_lines in all_models:
self.setup_ligand(model_lines)
bigR = self.bigRC[:self.lenK]
bigM = self.bigC[:self.lenK]
cutoff = bigR + self.keyRadii
d = bigM - self.smallM
dSQ = d*d
dSQMAT = Numeric.sum(dSQ,2)
cutoffSQMAT = cutoff*cutoff
ansMat = Numeric.logical_and(Numeric.less(dSQMAT, cutoffSQMAT),Numeric.not_equal(dSQMAT, 0.))
rowIndices = Numeric.nonzero(Numeric.sum(ansMat,1))
num_contacts = 0
for ind in rowIndices:
for j in ansMat[ind]:
if j: num_contacts+=1
if num_contacts > 0:
break
return num_contacts
def select(self, keyAts, checkAts, cutoff=3.0, percentCutoff=1.0,
keyMat=None, checkMat=None):
""" keyAts, checkAts, cutoff, percentCutoff
keyAts: first set of atoms
checkAts: a second set of atoms which is checked vs. keyAts
cutoff:
either a single float by default 3.0
or a matrix with shape:
(max(len(keyAts),len(checkAts)), min(len(keyAts),len(checkAts)))
percentCutoff: by default 1.0 (cutoff is multiplied by this value)
keyMat: transformation of keyAts
checkMat: transformation of checkAts
returns 'pairDict' whose keys are atoms used as reference points and whose
values are atoms within cutoff distance of corresponding key.
If 'return_dist' flag is set,
'distDict' is returned also, whose keys are
the same atoms which are used as reference points and whose values are
lists of distances to atoms within cutoff distance of corresponding key
"""
lenK = len(keyAts)
lenC = len(checkAts)
#data arrays are used to find atoms with given indices quickly
atar = Numeric.array(checkAts.data)
keyAtar = Numeric.array(keyAts.data)
#basic arrays of coords used to build others
c = Numeric.array(checkAts.coords, 'f')
if checkMat:
c = self.mul(c, checkMat)
k = Numeric.array(keyAts.coords, 'f')
if keyMat:
k = self.mul(k, keyMat)
# first build matrix of distances between all pairs of ats
# rows correspond to ats in larger set, columns to those in smaller
# first build square matrix
if lenC >= lenK:
bigC = Numeric.resize(c, (lenC, lenC, 3))
k.shape = (lenK,1,3)
bigM = bigC[:lenK]
smallM = k
cutoff = self.setupCutoff(checkAts, keyAts, cutoff)
#print "0a:cutoff[0][0]=", cutoff[0][0]
cutoff.shape = (lenK, -1)
else:
bigK = Numeric.resize(k, (lenK, lenK, 3))
c.shape = (lenC,1,3)
bigM = bigK[:lenC]
smallM = c
cutoff = self.setupCutoff(keyAts, checkAts, cutoff)
#print "0b:cutoff[0][0]=", cutoff[0][0]
cutoff.shape = (lenC, -1)
# distance matrix
d = bigM - smallM
# distance squared matrix
dSQ = d * d
# next step sums deltaX**2, deltaY**2, deltaZ**2
dSQMAT = Numeric.sum(dSQ,2)
#percentCutoff lets user relax sum of radii
#the smaller the percentCutoff the smaller the key
#dSQ has to be less than
cutoff = cutoff * percentCutoff
cutoffSQMAT = cutoff * cutoff
#cutoffSQMAT = cutoffSQMAT * percentCutoff
# ansMat has 1 where sq dist. is smaller than cutoff
ansMat = Numeric.logical_and(self.func(dSQMAT, cutoffSQMAT) , \
Numeric.not_equal(dSQMAT, 0.))
if lenK > lenC:
# in this case need to rearrange matrix
# which got shuffled in if-else above
ansMat = Numeric.swapaxes(ansMat, 0, 1)
dSQMAT = Numeric.swapaxes(dSQMAT, 0, 1)
# finally, build result dictionaries which have atom keys:
# pairDict has values which are lists of close atoms
# distDict has values which are lists of distances
pairDict = {}
distDict = {}
# get a list of rows which have non-zero entries
# to loop over in next section
rowIndices = Numeric.nonzero(Numeric.sum(ansMat,1))
# rows correspond to ats in keyAts
# columns correspond to ats in checkAts
for i in rowIndices:
# atindex is a list [7 8 9] indexing into checkAts
atindex = Numeric.nonzero(ansMat[i])
# keyAtar[i] is ith atom in keyAts
keyAt = keyAtar[i]
pairDict[keyAt] = Numeric.take(atar, atindex)
if self.return_dist:
distDict[keyAt] = []
for ind in atindex:
distDict[keyAt].append(math.sqrt(dSQMAT[i][ind]))
#getting distDict back is optional
if self.return_dist: return pairDict, distDict
else: return pairDict
