-
Notifications
You must be signed in to change notification settings - Fork 11
/
sascorer.py
162 lines (137 loc) · 5.44 KB
/
sascorer.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
#
# calculation of synthetic accessibility score as described in:
#
# Estimation of Synthetic Accessibility Score of Drug-like Molecules based on Molecular Complexity and Fragment Contributions
# Peter Ertl and Ansgar Schuffenhauer
# Journal of Cheminformatics 1:8 (2009)
# http://www.jcheminf.com/content/1/1/8
#
# several small modifications to the original paper are included
# particularly slightly different formula for marocyclic penalty
# and taking into account also molecule symmetry (fingerprint density)
#
# for a set of 10k diverse molecules the agreement between the original method
# as implemented in PipelinePilot and this implementation is r2 = 0.97
#
# peter ertl & greg landrum, september 2013
#
from __future__ import print_function
from rdkit import Chem
from rdkit.Chem import rdMolDescriptors
from rdkit.six.moves import cPickle
from rdkit.six import iteritems
import math
from collections import defaultdict
import os.path as op
_fscores = None
def readFragmentScores(name='fpscores'):
import gzip
global _fscores
# generate the full path filename:
if name == "fpscores":
name = op.join(op.dirname(__file__), name)
_fscores = cPickle.load(gzip.open('%s.pkl.gz'%name))
outDict = {}
for i in _fscores:
for j in range(1,len(i)):
outDict[i[j]] = float(i[0])
_fscores = outDict
def numBridgeheadsAndSpiro(mol,ri=None):
nSpiro = rdMolDescriptors.CalcNumSpiroAtoms(mol)
nBridgehead = rdMolDescriptors.CalcNumBridgeheadAtoms(mol)
return nBridgehead,nSpiro
def calculateScore(m):
if _fscores is None: readFragmentScores()
# fragment score
fp = rdMolDescriptors.GetMorganFingerprint(m,2) #<- 2 is the *radius* of the circular fingerprint
fps = fp.GetNonzeroElements()
score1 = 0.
nf = 0
for bitId,v in iteritems(fps):
nf += v
sfp = bitId
score1 += _fscores.get(sfp,-4)*v
score1 /= nf
# features score
nAtoms = m.GetNumAtoms()
nChiralCenters = len(Chem.FindMolChiralCenters(m,includeUnassigned=True))
ri = m.GetRingInfo()
nBridgeheads,nSpiro=numBridgeheadsAndSpiro(m,ri)
nMacrocycles=0
for x in ri.AtomRings():
if len(x)>8: nMacrocycles+=1
sizePenalty = nAtoms**1.005 - nAtoms
stereoPenalty = math.log10(nChiralCenters+1)
spiroPenalty = math.log10(nSpiro+1)
bridgePenalty = math.log10(nBridgeheads+1)
macrocyclePenalty = 0.
# ---------------------------------------
# This differs from the paper, which defines:
# macrocyclePenalty = math.log10(nMacrocycles+1)
# This form generates better results when 2 or more macrocycles are present
if nMacrocycles > 0: macrocyclePenalty = math.log10(2)
score2 = 0. -sizePenalty -stereoPenalty -spiroPenalty -bridgePenalty -macrocyclePenalty
# correction for the fingerprint density
# not in the original publication, added in version 1.1
# to make highly symmetrical molecules easier to synthetise
score3 = 0.
if nAtoms > len(fps):
score3 = math.log(float(nAtoms) / len(fps)) * .5
sascore = score1 + score2 + score3
# need to transform "raw" value into scale between 1 and 10
min = -4.0
max = 2.5
sascore = 11. - (sascore - min + 1) / (max - min) * 9.
# smooth the 10-end
if sascore > 8.: sascore = 8. + math.log(sascore+1.-9.)
if sascore > 10.: sascore = 10.0
elif sascore < 1.: sascore = 1.0
return sascore
def processMols(mols):
print('smiles\tName\tsa_score')
for i,m in enumerate(mols):
if m is None:
continue
s = calculateScore(m)
smiles = Chem.MolToSmiles(m)
print(smiles+"\t"+m.GetProp('_Name') + "\t%3f"%s)
if __name__=='__main__':
import sys,time
t1=time.time()
readFragmentScores("fpscores")
t2=time.time()
suppl = Chem.SmilesMolSupplier(sys.argv[1])
t3=time.time()
processMols(suppl)
t4=time.time()
print('Reading took %.2f seconds. Calculating took %.2f seconds'%((t2-t1),(t4-t3)), file=sys.stderr)
#
# Copyright (c) 2013, Novartis Institutes for BioMedical Research Inc.
# All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met:
#
# * Redistributions of source code must retain the above copyright
# notice, this list of conditions and the following disclaimer.
# * Redistributions in binary form must reproduce the above
# copyright notice, this list of conditions and the following
# disclaimer in the documentation and/or other materials provided
# with the distribution.
# * Neither the name of Novartis Institutes for BioMedical Research Inc.
# nor the names of its contributors may be used to endorse or promote
# products derived from this software without specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
#