def loadResContacts( self ):
"""
Uncompress residue contact matrix if necessary.
@return: dict with contact matrix and parameters OR None
@rtype: dict OR None
"""
## Backwards compatibility
if self.contacts is not None and type( self.contacts ) == str:
self.contacts = t.load( self.contacts )
EHandler.warning("loading old-style pickled contacts.")
return self.contacts
## New, uncompression from list of indices into raveled array
if self.contacts is not None and \
len( N0.shape( self.contacts['result'])) == 1:
try:
lenRec, lenLig = self.contacts['shape']
except:
EHandler.warning("uncompressing contacts without shape")
lenRec = self.rec().lenResidues()
lenLig = self.lig().lenResidues()
m = N0.zeros( lenRec * lenLig )
N0.put( m, self.contacts['result'], 1 )
self.contacts['result'] = N0.reshape( m, (lenRec, lenLig) )
return self.contacts
def loadResContacts(self):
"""
Uncompress residue contact matrix if necessary.
@return: dict with contact matrix and parameters OR None
@rtype: dict OR None
"""
## Backwards compatibility
if self.contacts is not None and type(self.contacts) == str:
self.contacts = t.load(self.contacts)
EHandler.warning("loading old-style pickled contacts.")
return self.contacts
## New, uncompression from list of indices into raveled array
if self.contacts is not None and \
len( N0.shape( self.contacts['result'])) == 1:
try:
lenRec, lenLig = self.contacts['shape']
except:
EHandler.warning("uncompressing contacts without shape")
lenRec = self.rec().lenResidues()
lenLig = self.lig().lenResidues()
m = N0.zeros(lenRec * lenLig)
N0.put(m, self.contacts['result'], 1)
self.contacts['result'] = N0.reshape(m, (lenRec, lenLig))
return self.contacts
def __atomContacts(self, cutoff, rec_mask, lig_mask, cache):
"""
Intermolecular distances below cutoff after applying the two masks.
@param cutoff: cutoff for B{atom-atom} contact in \AA
@type cutoff: float
@param rec_mask: atom mask
@type rec_mask: [1|0]
@param lig_mask: atom mask
@type lig_mask: [1|0]
@param cache: cache pairwise atom distance matrix
@type cache: 1|0
@return: atom contact matrix, array sum_rec_mask x sum_lig_mask
@rtype: array
"""
## get atom coordinats as array 3 x all_atoms
rec_xyz = self.rec().getXyz()
lig_xyz = self.lig().getXyz()
## get pair-wise distances -> atoms_rec x atoms_lig
dist = getattr( self, 'pw_dist', None )
if dist is None or \
N0.shape( dist ) != ( N0.sum(rec_mask), N0.sum(lig_mask) ):
dist = self.__pairwiseDistances(N0.compress( rec_mask, rec_xyz, 0),
N0.compress( lig_mask, lig_xyz, 0) )
if cache:
self.pw_dist = dist
## reduce to 1 (distance < cutoff) or 0 -> n_atoms_rec x n_atoms_lig
return N0.less( dist, cutoff )
def __atomContacts(self, cutoff, rec_mask, lig_mask, cache):
"""
Intermolecular distances below cutoff after applying the two masks.
@param cutoff: cutoff for B{atom-atom} contact in \AA
@type cutoff: float
@param rec_mask: atom mask
@type rec_mask: [1|0]
@param lig_mask: atom mask
@type lig_mask: [1|0]
@param cache: cache pairwise atom distance matrix
@type cache: 1|0
@return: atom contact matrix, array sum_rec_mask x sum_lig_mask
@rtype: array
"""
## get atom coordinats as array 3 x all_atoms
rec_xyz = self.rec().getXyz()
lig_xyz = self.lig().getXyz()
## get pair-wise distances -> atoms_rec x atoms_lig
dist = getattr(self, 'pw_dist', None)
if dist is None or \
N0.shape( dist ) != ( N0.sum(rec_mask), N0.sum(lig_mask) ):
dist = self.__pairwiseDistances(N0.compress(rec_mask, rec_xyz, 0),
N0.compress(lig_mask, lig_xyz, 0))
if cache:
self.pw_dist = dist
## reduce to 1 (distance < cutoff) or 0 -> n_atoms_rec x n_atoms_lig
return N0.less(dist, cutoff)
def test_MatrixPlot( self ):
"""MatrixPlot test"""
n = 30
z = N0.zeros((n,n), N0.Float)
for i in range(N0.shape(z)[0]):
for j in range(N0.shape(z)[1]):
z[i,j] = N0.exp(-0.01*((i-n/2)**2+(j-n/2)**2))
self.p = MatrixPlot(z, palette='sausage', legend=1)
if self.local or self.VERBOSITY > 2:
self.p.show()
self.assertTrue( self.p is not None )
def area(curve, start=0.0, stop=1.0):
"""
Numerically add up the area under the given curve.
The curve is a 2-D array or list of tupples.
The x-axis is the first column of this array (curve[:,0]).
(originally taken from biskit.Statistics.ROCalyzer)
:param curve: a list of x,y coordinates
:type curve: [ (y,x), ] or N0.array
:param start: lower boundary (in x) (default: 0.0)
:type start: float
:param stop: upper boundary (in x) (default: 1.0)
:type stop: float
:return: the area underneath the curve between start and stop.
:rtype: float
"""
## convert and swap axes
curve = N0.array(curve)
c = N0.zeros(N0.shape(curve), curve.dtype)
c[:, 0] = curve[:, 1]
c[:, 1] = curve[:, 0]
assert len(N0.shape(c)) == 2
## apply boundaries ## here we have a problem with flat curves
mask = N0.greater_equal(c[:, 1], start)
mask *= N0.less_equal(c[:, 1], stop)
c = N0.compress(mask, c, axis=0)
## fill to boundaries -- not absolutely accurate: we actually should
## interpolate to the neighboring points instead
c = N0.concatenate((N0.array([
[c[0, 0], start],
]), c, N0.array([
[c[-1, 0], stop],
])))
x = c[:, 1]
y = c[:, 0]
dx = x[1:] - x[:-1] # distance on x between points
dy = y[1:] - y[:-1] # distance on y between points
areas1 = y[:-1] * dx # the rectangles between all points
areas2 = dx * dy / 2.0 # the triangles between all points
return N0.sum(areas1) + N0.sum(areas2)
def centers( self ):
"""
Get 'center structure' for each cluster.
@return: N0.array( n_clusters x n_atoms_masked x 3 )
@rtype: array
"""
lenAtoms = N0.shape( self.fcCenters )[1] / 3
return N0.reshape( self.fcCenters, ( self.n_clusters, lenAtoms, 3))
def area(curve, start=0.0, stop=1.0 ):
"""
Numerically add up the area under the given curve.
The curve is a 2-D array or list of tupples.
The x-axis is the first column of this array (curve[:,0]).
(originally taken from biskit.Statistics.ROCalyzer)
:param curve: a list of x,y coordinates
:type curve: [ (y,x), ] or N0.array
:param start: lower boundary (in x) (default: 0.0)
:type start: float
:param stop: upper boundary (in x) (default: 1.0)
:type stop: float
:return: the area underneath the curve between start and stop.
:rtype: float
"""
## convert and swap axes
curve = N0.array( curve )
c = N0.zeros( N0.shape(curve), curve.dtype )
c[:,0] = curve[:,1]
c[:,1] = curve[:,0]
assert len( N0.shape( c ) ) == 2
## apply boundaries ## here we have a problem with flat curves
mask = N0.greater_equal( c[:,1], start )
mask *= N0.less_equal( c[:,1], stop )
c = N0.compress( mask, c, axis=0 )
## fill to boundaries -- not absolutely accurate: we actually should
## interpolate to the neighboring points instead
c = N0.concatenate((N0.array([[c[0,0], start],]), c,
N0.array([[c[-1,0],stop ],])) )
x = c[:,1]
y = c[:,0]
dx = x[1:] - x[:-1] # distance on x between points
dy = y[1:] - y[:-1] # distance on y between points
areas1 = y[:-1] * dx # the rectangles between all points
areas2 = dx * dy / 2.0 # the triangles between all points
return N0.sum(areas1) + N0.sum(areas2)
def slim(self):
"""
Remove coordinates and atoms of ligand and receptor from memory,
if they can be restored from file, compress contact matrix.
@note: CALLED BEFORE PICKLING
"""
self.lig_transformed = None
self.pw_dist = None
## self.ligandMatrix = self.ligandMatrix.tolist()
if 'matrix' in self.info:
del self.info['matrix']
## compress contact matrix array
if self.contacts is not None and \
len(N0.shape( self.contacts['result'] ) )==2:
m = self.contacts['result']
self.contacts['shape'] = N0.shape( m )
self.contacts['result'] = N0.nonzero( N0.ravel( m ) ).astype(N0.Int32)
def slim(self):
"""
Remove coordinates and atoms of ligand and receptor from memory,
if they can be restored from file, compress contact matrix.
@note: CALLED BEFORE PICKLING
"""
self.lig_transformed = None
self.pw_dist = None
## self.ligandMatrix = self.ligandMatrix.tolist()
if 'matrix' in self.info:
del self.info['matrix']
## compress contact matrix array
if self.contacts is not None and \
len(N0.shape( self.contacts['result'] ) )==2:
m = self.contacts['result']
self.contacts['shape'] = N0.shape(m)
self.contacts['result'] = N0.nonzero(N0.ravel(m)).astype(N0.Int32)
def random2DArray( matrix, ranNr=1, mask=None):
"""
Create randomized 2D array containing ones and zeros.
:param matrix: matrix to randomize
:type matrix: 2D array
:param mask: mask OR None (default: None)
:type mask: list(1|0)
:param ranNr: number of matricies to add up (default: 1)
:type ranNr: integer
:return: 2D array or |ranNr| added contact matricies
:rtype:2D array
:raise MathUtilError: if mask does not fit matrix
"""
## get shape of matrix
a,b = N0.shape( matrix )
## get array from matrix that is to be randomized
if mask is not None:
if len(mask) == len( N0.ravel(matrix) ):
array = N0.compress( mask, N0.ravel(matrix) )
if len(mask) != len( N0.ravel(matrix) ):
raise MathUtilError(
'MatUtils.random2DArray - mask of incorrect length' +
'\tMatrix length: %i Mask length: %i'\
%(len( N0.ravel(matrix) ), len(mask)))
if not mask:
array = N0.ravel(matrix)
## number of ones and length of array
nOnes = int( N0.sum( array ) )
lenArray = len( array )
ranArray = N0.zeros( lenArray )
## create random array
for n in range(ranNr):
ranArray += randomMask( nOnes, lenArray )
## blow up to size of original matix
if mask is not None:
r = N0.zeros(a*b)
N0.put( r, N0.nonzero(mask), ranArray)
return N0.reshape( r, (a,b) )
if not mask:
return N0.reshape( ranArray, (a,b) )
def random2DArray(matrix, ranNr=1, mask=None):
"""
Create randomized 2D array containing ones and zeros.
:param matrix: matrix to randomize
:type matrix: 2D array
:param mask: mask OR None (default: None)
:type mask: list(1|0)
:param ranNr: number of matricies to add up (default: 1)
:type ranNr: integer
:return: 2D array or |ranNr| added contact matricies
:rtype:2D array
:raise MathUtilError: if mask does not fit matrix
"""
## get shape of matrix
a, b = N0.shape(matrix)
## get array from matrix that is to be randomized
if mask is not None:
if len(mask) == len(N0.ravel(matrix)):
array = N0.compress(mask, N0.ravel(matrix))
if len(mask) != len(N0.ravel(matrix)):
raise MathUtilError(
'MatUtils.random2DArray - mask of incorrect length' +
'\tMatrix length: %i Mask length: %i'\
%(len( N0.ravel(matrix) ), len(mask)))
if not mask:
array = N0.ravel(matrix)
## number of ones and length of array
nOnes = int(N0.sum(array))
lenArray = len(array)
ranArray = N0.zeros(lenArray)
## create random array
for n in range(ranNr):
ranArray += randomMask(nOnes, lenArray)
## blow up to size of original matix
if mask is not None:
r = N0.zeros(a * b)
N0.put(r, N0.nonzero(mask), ranArray)
return N0.reshape(r, (a, b))
if not mask:
return N0.reshape(ranArray, (a, b))
def ramachandran_background(self):
"""
Creates a background (favoured regions) for a ramachandran plot.
@return: list of biggles.Point objects
@rtype: [ biggles.Point ]
"""
bg = []
mat = N0.loadtxt(T.dataRoot() + '/biggles/ramachandran_bg.dat')
x, y = N0.shape(mat)
for i in range(x):
for j in range(y):
if mat[i, j] < 200:
a = (360. / y) * j - 180
b = (360. / x) * (x - i) - 180
bg += [biggles.Point(a, b, type="dot")]
return bg
def ramachandran_background( self ):
"""
Creates a background (favoured regions) for a ramachandran plot.
@return: list of biggles.Point objects
@rtype: [ biggles.Point ]
"""
bg = []
mat = N0.loadtxt( T.dataRoot() + '/biggles/ramachandran_bg.dat')
x, y = N0.shape(mat)
for i in range(x):
for j in range(y):
if mat[i,j] < 200:
a = (360./y)*j - 180
b = (360./x)*(x-i)- 180
bg += [ biggles.Point( a, b, type="dot" )]
return bg
def packBinaryMatrix( cm ):
"""
Compress sparse array of 0 and ones to list of one-positions
(space saving function, upack with :class:`unpackBinaryMatrix`).
:param cm: X by Y array of int
:type cm: 2D array
:return: {'shape':(X,Y), 'nonzero':[int] }
:rtype: dict
"""
if cm is None or type( cm ) == dict:
return cm
result = {}
result['shape'] = N0.shape( cm )
result['nonzero'] = N0.nonzero( N0.ravel( cm ) )
result['nonzero'] = result['nonzero'].tolist()
return result
def color_array( self, a, resetLimits=1 ):
"""
:param a: array of float
:type a: array of float
:param resetLimits: re-define color range on max and min of values
(default: 1)
:type resetLimits: 1|0
:return: matrix of color codes with same dimensions as a
:rtype: array of float
"""
s = N0.shape( a )
v = N0.ravel( a )
r = self.colors( v, resetLimits=resetLimits )
r = N0.reshape( r, s )
return r
def packBinaryMatrix(cm):
"""
Compress sparse array of 0 and ones to list of one-positions
(space saving function, upack with :class:`unpackBinaryMatrix`).
:param cm: X by Y array of int
:type cm: 2D array
:return: {'shape':(X,Y), 'nonzero':[int] }
:rtype: dict
"""
if cm is None or type(cm) == dict:
return cm
result = {}
result['shape'] = N0.shape(cm)
result['nonzero'] = N0.nonzero(N0.ravel(cm))
result['nonzero'] = result['nonzero'].tolist()
return result
def __init__(self, data, n_cluster, weight, seedx=0, seedy=0):
"""
@param data: cluster this
@type data: [float] OR array
@param n_cluster: number of clusters
@type n_cluster: int
@param weight: fuzziness weigth
@type weight: float
@param seedx: random seed value for RandomArray.seed (default: 0)
@type seedx: int OR 0
@param seedy: random seed value for RandomArray.seed
(default: 0, set seed from clock)
@type seedy: int OR 0
"""
self.data = N0.array(data, N0.Float)
self.w = weight
self.n_cluster = n_cluster
self.npoints, self.dimension = N0.shape(data)
self.seedx = seedx
self.seedy = seedy
def test_FuzzyCluster( self):
"""FuzzyCluster test"""
import biskit.gnuplot as G
x1 = R.random_sample((500,2))
x2 = R.random_sample((500,2)) + 1
x3 = R.random_sample((500,2)) + 2
self.x = N0.concatenate((x1, x2, x3))
self.fuzzy = FuzzyCluster(self.x, n_cluster=5, weight=1.5)
self.centers = self.fuzzy.go(1.e-30, n_iterations=50, nstep=10,
verbose=self.local)
if self.local:
print("cluster centers are displayed in green")
G.scatter( self.x, self.centers )
self.assertEqual( N0.shape(self.centers), (5, 2) )
def __init__(self, data, n_cluster, weight, seedx = 0, seedy = 0):
"""
@param data: cluster this
@type data: [float] OR array
@param n_cluster: number of clusters
@type n_cluster: int
@param weight: fuzziness weigth
@type weight: float
@param seedx: random seed value for RandomArray.seed (default: 0)
@type seedx: int OR 0
@param seedy: random seed value for RandomArray.seed
(default: 0, set seed from clock)
@type seedy: int OR 0
"""
self.data = N0.array(data, N0.Float)
self.w = weight
self.n_cluster = n_cluster
self.npoints, self.dimension = N0.shape(data)
self.seedx = seedx
self.seedy = seedy
def matrixToList(cm):
"""
Convert matrix into standard python list remembering the dimensions.
Unpack with :class:`listToMatrix`.
Note: Not used right now.
:param cm: array of int
:type cm: 2D array
:return: {'shape':(int,..), 'lst':[..] }
:rtype: dict
"""
if cm is None or type(cm) == dict:
return cm
result = {}
result['shape'] = N0.shape(cm)
result['lst'] = N0.ravel(cm).tolist()
return result
def matrixToList( cm ):
"""
Convert matrix into standard python list remembering the dimensions.
Unpack with :class:`listToMatrix`.
Note: Not used right now.
:param cm: array of int
:type cm: 2D array
:return: {'shape':(int,..), 'lst':[..] }
:rtype: dict
"""
if cm is None or type( cm ) == dict:
return cm
result = {}
result['shape'] = N0.shape( cm )
result['lst'] = N0.ravel( cm ).tolist()
return result
def test_FuzzyCluster(self):
"""FuzzyCluster test"""
import biskit.gnuplot as G
x1 = R.random_sample((500, 2))
x2 = R.random_sample((500, 2)) + 1
x3 = R.random_sample((500, 2)) + 2
self.x = N0.concatenate((x1, x2, x3))
self.fuzzy = FuzzyCluster(self.x, n_cluster=5, weight=1.5)
self.centers = self.fuzzy.go(1.e-30,
n_iterations=50,
nstep=10,
verbose=self.local)
if self.local:
print("cluster centers are displayed in green")
G.scatter(self.x, self.centers)
self.assertEqual(N0.shape(self.centers), (5, 2))
def thin( self, step=1 ):
"""
Keep only each step'th frame from trajectory with 10 ensemble members.
:param step: 1..keep all frames, 2..skip first and every second, ..
(default: 1)
:type step: int
:return: reduced EnsembleTraj
:rtype: EnsembleTraj
"""
T.ensure( step, int, forbidden=[0] )
## 10 x lenFrames/10, frame indices of each member
mI = [ self.memberIndices( i ) for i in range(self.n_members) ]
mI = N0.array( mI )
mI = N0.take( mI, range( -1, N0.shape( mI )[1], step )[1:], 1 )
mI = N0.transpose( mI )
return self.takeFrames( N0.ravel( mI ))
def thin( self, step=1 ):
"""
Keep only each step'th frame from trajectory with 10 ensemble members.
:param step: 1..keep all frames, 2..skip first and every second, ..
(default: 1)
:type step: int
:return: reduced EnsembleTraj
:rtype: EnsembleTraj
"""
T.ensure( step, int, forbidden=[0] )
## 10 x lenFrames/10, frame indices of each member
mI = [ self.memberIndices( i ) for i in range(self.n_members) ]
mI = N0.array( mI )
mI = N0.take( mI, range( -1, N0.shape( mI )[1], step )[1:], 1 )
mI = N0.transpose( mI )
return self.takeFrames( N0.ravel( mI ))
def test_getXyz( self ):
"""AmberRstParser.getXyz test"""
self.xyz = self.p.getXyz()
self.assertEqual( N0.shape(self.xyz), (11200,3) )
def __init__(self, matrix, mesh=0, palette="plasma", legend=0, step=1,
vmin=None, vmax=None):
"""
@param matrix: the 2-D array to plot
@type matrix: array
@param mesh: create a plot with a dotted mesh
@type mesh: 1|0
@param palette: color palette name see L{Biskit.ColorSpectrum}
@type palette: str
@param legend: create a legend (scale) showing the walues of the
different colors in the plot.
@type legend: 1|0
@param step: reduce matrix -- take only each step position in x and y
@type step: int
@param vmin: override minimal value, all values below will revert
to default color
@return: biggles plot object, view with biggles.FramedPlot.show() or
save with biggles.FramedPlot.write_eps(file_name).
@rtype: biggles.FramedPlot
"""
if not biggles:
raise ImportError('biggles module could not be imported.')
FramedPlot.__init__(self)
if step != 1:
matrix = self.__thinarray( matrix, step )
if vmin is None:
vmin = N0.amin( matrix )
if vmax is None:
vmax = N0.amax( matrix )
self.palette = ColorSpectrum( palette, vmin=vmin, vmax=vmax )
self.matrix = self.palette.color_array( matrix, resetLimits=0 )
s = N0.shape( self.matrix )
for i in range(s[0]):
for j in range(s[1]):
col = self.matrix[i,j]
x1 = (j, j + 1)
y1 = (i, i)
y2 = (i + 1, i + 1)
cell = biggles.FillBetween(x1, y1, x1, y2, color = col)
self.add(cell)
if mesh:
for i in range(s[0] + 1):
self.add(biggles.LineY(i, linetype='dotted'))
for i in range(s[1] + 1):
self.add(biggles.LineX(i, linetype='dotted'))
if legend:
legend = self.__make_legend()
self.add(legend)
self.add(biggles.PlotBox((-0.17, -0.1), (1.25, 1.1)))
self.aspect_ratio = 1.0
def test_getXyz(self):
"""AmberRstParser.getXyz test"""
self.xyz = self.p.getXyz()
self.assertEqual(N0.shape(self.xyz), (11200, 3))
def lenAtoms( self ):
"""
:return: number of atoms in frames
:rtype: int
"""
return N0.shape( self.frames )[1]
