Authors:
Naveed Ahmed Azam
1
;
Rachaya Chiewvanichakorn
1
;
Fan Zhang
1
;
Aleksandar Shurbevski
1
;
Hiroshi Nagamochi
1
and
Tatsuya Akutsu
2
Affiliations:
1
Department of Applied Mathematics and Physics, Kyoto University, Kyoto, Japan
;
2
Bioinformatics Center, Institute for Chemical Research, Kyoto University, Uji-city, Japan
Keyword(s):
QSAR/QSPR, Artificial Neural Networks, Mixed Integer Programming, Feature Vectors, Chemical Graphs.
Abstract:
Inverse QSAR/QSPR is a well-known approach for computer-aided drug design. In this study, we propose a novel method for inverse QSAR/QSPR using artificial neural network (ANNs) and mixed integer linear programming. In this method, we introduce a feature function f that converts each chemical compound G into a vector f (G) of several descriptors of G. Next, given a set of chemical compounds along with their chemical properties, we construct a prediction function Ψ with an ANN so that Ψ( f (G)) takes a value nearly equal to a given chemical property for many chemical compounds G in the set. Then, given a target value y* of the chemical property, we conversely infer a chemical structure G* having the desired property y* in the following way. We formulate the problem of finding a vector x* such that (i) Ψ(x*) = y* and (ii) there exists a chemical compound G* such that f (G*) = x* (if one exists over all vectors x* in (i)) as a mixed integer linear programming problem (MILP). In an existi
ng method for the inverse QSAR/QSPR, the second condition (ii) was not guaranteed. For acyclic chemical compounds and some chemical properties such as heat of formation, boiling point, and retention time, we conducted computational experiments.
(More)