def __mergeSortOne(self, array : list, p : int ,q : int, r : int) -> list:
'''
一步合并两堆牌排序算法过程
Args
===
`array` : a array like
Returns
===
`sortedArray` : 排序好的数组
Raises
===
`None`
'''
# python中变量名和对象是分离的
# 此时A是array的一个引用
A = array
# 求数组的长度 然后分成两堆([p..q],[q+1..r]) ([0..q],[q+1..n-1])
n = r + 1
# 检测输入参数是否合理
if q < 0 or q > n - 1:
raise Exception("arg 'q' must not be in (0,len(array) range)")
# n1 + n2 = n
# 求两堆牌的长度
n1 = q - p + 1
n2 = r - q
# 构造两堆牌(包含“哨兵牌”)
L = _arange(n1 + 1, dtype=float)
R = _arange(n2 + 1, dtype=float)
# 将A分堆
for i in range(n1):
L[i] = A[p + i]
for j in range(n2):
R[j] = A[q + j + 1]
# 加入无穷大“哨兵牌”, 对不均匀分堆的完美解决
L[n1] = _math.inf
R[n2] = _math.inf
# 因为合并排序的前提是两堆牌是已经排序好的，所以这里排序一下
# chapter2 = Chapter2()
# L = chapter2.selectSortAscending(L)
# R = chapter2.selectSortAscending(R)
# 一直比较两堆牌的顶部大小大小放入新的堆中
i, j = 0, 0
for k in range(p, n):
if L[i] <= R[j]:
A[k] = L[i]
i += 1
else:
A[k] = R[j]
j += 1
return A
def radixsort(self, A, d):
'''
基数排序 平均时间复杂度为`Θ(nlgn)`
Args
===
`A` : 待排序的数组
`d` : 数组A中每个元素都有d位数字/长度,其中第1位是最低位，第d位是最高位
Return
===
`sortedarray` : 排序好的数组
Example
===
```python
>>> Chapter8_3().radixsort([54,43,32,21,11], 2)
>>> [11, 21, 32, 43, 54]
```
'''
length = len(A)
B = []
for i in range(d):
B.append(self.getarraystr_subarray(A, i + 1))
for k in range(d):
B[k] = self.countingsort(B[k], max(B[k]) + 1)
C = _arange(length)
for j in range(length):
for i in range(d):
C[j] += B[i][j] * 10**i
C[j] = C[j] - j
return C
def __init__(self, receptor=None, ligand=None, forcefield=None, pH=7.0, addHs=True,
mpi_comm=None):
if (receptor is not None) and (ligand is not None):
if type(receptor) == str:
receptor = Receptor(receptor,forcefield,pH,addHs,mpi_comm)
if type(ligand) == str:
ligand = Ligand(ligand,forcefield,pH,addHs,mpi_comm)
self.modeller = app.Modeller(receptor.topology, receptor.positions)
self.modeller.add(ligand.topology, ligand.positions)
self.topology = self.modeller.getTopology()
self.positions = self.modeller.getPositions() #np.vstack receptor.positions y ligand.positions
self.receptor = receptor
self.receptor_atom_indices = _arange(0,receptor.n_atoms)
self.ligand = ligand
self.ligand_atom_indices = _arange(receptor.n_atoms,receptor.n_atoms+ligand.n_atoms)
self.complex_atom_indices = _arange(receptor.n_atoms+ligand.n_atoms)
self.forcefield = self.receptor.forcefield
def on_line_maximum(self, k , n):
score = _arange(n)
bestscore = -_math.inf
for i in range(k):
if score[i] > bestscore:
bestscore = score[i]
for i in range(k, n):
if score[i] > bestscore:
return i
return n
def center(self, geometrical_center = 'heavy'):
if geometrical_center == 'heavy':
tmp_list = self._heavy_atoms_indices
elif geometrical_center == 'CA':
tmp_list = self._ca_atoms_indices
elif geometrical_center == 'All':
tmp_list = _arange(self.n_atoms)
tmp_positions = self.get_positions()
geometrical_center_positions = utils.geometrical_center(tmp_positions,tmp_list)
tmp_positions = tmp_positions - geometrical_center_positions
self.set_positions(tmp_positions)
def __init__(self,radii,mols,reference_substructure_keys={}):
self.radii = radii
self.max_radius = max(radii)
if type(mols) != list: mols = mols = [ext.mols[i] for i in _arange(0,len(mols))]
self.mols = mols
self.reference_substructure_keys = reference_substructure_keys
self.substructure_dictionary = {}
self.mols_reference_for_unhashed = None
self.columns_unhashed = None
self.substructure_ids = None
# output
self.fps_hashed_binary_quick = None
self.fps_hashed_binary = None
self.fps_hashed_counts = None
self.fps_unhashed_binary = None
self.fps_unhashed_counts = None
self.substructures_smiles = {}
def __init__(self, radii, mols, reference_substructure_keys={}):
self.radii = radii
self.max_radius = max(radii)
if type(mols) != list:
mols = [ext.mols[i] for i in _arange(0, len(mols))]
self.mols = mols
self.reference_substructure_keys = reference_substructure_keys
self.substructure_dictionary = {}
self.mols_reference_for_unhashed = None
self.columns_unhashed = None
self.substructure_ids = None
# output
self.fps_hashed_binary_quick = None
self.fps_hashed_binary = None
self.fps_hashed_counts = None
self.fps_unhashed_binary = None
self.fps_unhashed_counts = None
self.substructures_smiles = {}
def calculate_unhashed_fps(self,
draw_substructures=False,
image_directory='./images_substructures'):
# get the dictionary for the substructures
idxs = []
substr_ids = []
counts = []
for mol_index, mol in enumerate(self.mols):
info = {}
fp = _GetMorganFingerprint(mol,
radius=self.max_radius,
bitInfo=info)
substructure_dictionary = {
k: [mol_index]
for k, v in info.iteritems() if v[0][1] in self.radii
}
substr_ids.append(substructure_dictionary.keys())
idxs.append([mol_index] * len(substructure_dictionary.keys()))
counts.append([
len(info.values()[x]) for x in _arange(0, len(info))
if info.values()[x][0][1] in self.radii
])
# get the smiles for the substructures
amap = {}
substructures_smiles = {
k: [
_MolToSmiles(
_PathToSubmol(mol,
_FindAtomEnvironmentOfRadiusN(
mol, v[0][1], v[0][0]),
atomMap=amap))
]
for k, v in info.iteritems() if v[0][1] in self.radii
}
self.substructures_smiles.update(substructures_smiles)
# generate the images for the substructures if required..
if draw_substructures:
if not _exists(image_directory):
_makedirs(image_directory)
for k, v in info.iteritems():
if k not in self.substructure_dictionary.keys(
) and v[0][1] in self.radii:
image_name = "%s/Molecule_%d_substr_%d.pdf" % (
image_directory, mol_index, k)
env = _FindAtomEnvironmentOfRadiusN(
mol, v[0][1], v[0][0])
amap = {}
submol = _PathToSubmol(mol, env, atomMap=amap)
_MolToFile(mol,
image_name,
size=(300, 300),
wedgeBonds=True,
kekulize=True,
highlightAtoms=amap.keys())
self.substructure_dictionary = self._combine_dicts(
substructure_dictionary, self.substructure_dictionary)
idxs = _array([val for sublist in idxs for val in sublist])
counts = _array([val for sublist in counts for val in sublist])
substr_ids_flattened = [
val for sublist in substr_ids for val in sublist
]
substr_ids = _array(substr_ids_flattened)
self.substructure_ids = substr_ids
if len(self.reference_substructure_keys) == 0:
print(
"No input set of keys for the substructures. \nThus, the substructures present in the input molecules will be considered for the calculation of unhashed fingerprints."
)
columns = _array(list(set(self.substructure_dictionary.keys())))
columns = _sort(columns)
self.columns_unhashed = columns
dimensionality_unhashed = len(columns)
else:
columns = _array(list(set(self.reference_substructure_keys)))
columns = _sort(columns)
self.columns_unhashed = columns
dimensionality_unhashed = len(columns)
fps_unhashed_binary = _zeros((len(self.mols), dimensionality_unhashed),
dtype=int)
fps_unhashed_counts = _zeros((len(self.mols), dimensionality_unhashed),
dtype=int)
# removing the indices corresponding to the substructures in the test molecules not present in the references set of substructures..
idxs = _array([
idxs[x] for x in _arange(0, len(substr_ids))
if substr_ids[x] in self.columns_unhashed
])
counts = _array([
counts[x] for x in _arange(0, len(substr_ids))
if substr_ids[x] in self.columns_unhashed
])
substr_ids = _array([
substr_ids[x] for x in _arange(0, len(substr_ids))
if substr_ids[x] in self.columns_unhashed
])
mapping = _array([(substr_ids[x] == columns).nonzero()
for x in _arange(0, len(substr_ids))])
mapping = mapping.flatten()
if len(mapping) == 0:
print(
"There is no intersection between the substructures \n(i)provided in the reference key set, and\n(ii) the substructures found in the input molecules."
)
return
fps_unhashed_binary[idxs, mapping] = _ones(len(counts))
fps_unhashed_counts[idxs, mapping] = counts
self.fps_unhashed_binary = fps_unhashed_binary
self.fps_unhashed_counts = fps_unhashed_counts
def calculate_unhashed_fps(self,draw_substructures=False,image_directory='./images_substructures'):
# get the dictionary for the substructures
idxs = []
substr_ids = []
counts=[]
substructure_dictionaries = []
for mol_index,mol in enumerate(self.mols):
info={}
fp = _GetMorganFingerprint(mol,radius=self.max_radius,bitInfo=info)
substructure_dictionary = {k:mol_index for k,v in info.iteritems() if v[0][1] in self.radii}
substructure_dictionaries.append({k:mol_index for k,v in info.iteritems() if v[0][1] in self.radii})
substr_ids.append(substructure_dictionary.keys())
idxs.append([mol_index]*len(substructure_dictionary.keys()))
counts.append([ len(info.values()[x]) for x in _arange(0,len(info)) if info.values()[x][0][1] in self.radii])
# get the smiles for the substructures
amap = {}
substructures_smiles = {k:[_MolToSmiles(_PathToSubmol(mol,_FindAtomEnvironmentOfRadiusN(mol,v[0][1],v[0][0]),atomMap=amap))] for k,v in info.iteritems() if v[0][1] in self.radii}
self.substructures_smiles.update(substructures_smiles)
# generate the images for the substructures if required..
if draw_substructures:
if not _exists(image_directory):
_makedirs(image_directory)
for k,v in info.iteritems():
if k not in self.substructure_dictionary.keys() and v[0][1] in self.radii:
image_name="%s/Molecule_%d_substr_%d.pdf"%(image_directory,mol_index,k)
env=_FindAtomEnvironmentOfRadiusN(mol,v[0][1],v[0][0])
amap={}
submol=_PathToSubmol(mol,env,atomMap=amap)
_MolToFile(mol,image_name,size=(300,300),wedgeBonds=True,kekulize=True,highlightAtoms=amap.keys())
#self.substructure_dictionary = self._combine_dicts(substructure_dictionary,self.substructure_dictionary)
for d in substructure_dictionaries:
for k, v in d.iteritems():
l=self.substructure_dictionary.setdefault(k,[])
if v not in l:
l.append(v)
idxs = _array([val for sublist in idxs for val in sublist])
counts = _array([val for sublist in counts for val in sublist])
substr_ids_flattened = [val for sublist in substr_ids for val in sublist]
substr_ids = _array(substr_ids_flattened)
self.substructure_ids = substr_ids
if len(self.reference_substructure_keys)==0:
print "No input set of keys for the substructures. \nThus, the substructures present in the input molecules will be considered for the calculation of unhashed fingerprints."
columns = _array(list(set(self.substructure_dictionary.keys())))
columns = _sort(columns)
self.columns_unhashed = columns
dimensionality_unhashed = len(columns)
else:
columns = _array(self.reference_substructure_keys)
columns = _sort(columns)
self.columns_unhashed = columns
dimensionality_unhashed = len(columns)
fps_unhashed_binary = _zeros((len(self.mols),dimensionality_unhashed), dtype=int)
fps_unhashed_counts = _zeros((len(self.mols),dimensionality_unhashed), dtype=int)
mapping = _array([(substr_ids[x]==columns).nonzero() for x in _arange(0,len(substr_ids))])
mapping = mapping.flatten()
idxs = _array([idxs[x] for x in _arange(0,len(mapping)) if mapping[x].size != 0])
counts = _array([counts[x] for x in _arange(0,len(mapping)) if mapping[x].size != 0])
mapping = _array([mapping[x] for x in _arange(0,len(mapping)) if mapping[x].size != 0])
if len(mapping) == 0:
print "There is no intersection between the substructures \n(i)provided in the reference key set, and\n(ii) the substructures found in the input molecules."
return
fps_unhashed_binary[idxs,mapping] = _ones(len(mapping))
fps_unhashed_counts[idxs,mapping] = counts
self.fps_unhashed_binary = fps_unhashed_binary
self.fps_unhashed_counts = fps_unhashed_counts
def get_residue_indices_in_helix(self, helix=None):
return _arange(self.helices[helix][0],self.helices[helix][1]+1)
def arange(i):
return _arange(i)
