2022-10-04T18:59:32Zhttps://ipsj.ixsq.nii.ac.jp/ej/?action=repository_oaipmhoai:ipsj.ixsq.nii.ac.jp:001977132020-04-01T00:33:29Z01164:02735:09724:09827
A Method for the Inverse QSAR/QSPR Based on Artificial Neural Networks and Mixed Integer Linear ProgrammingA Method for the Inverse QSAR/QSPR Based on Artificial Neural Networks and Mixed Integer Linear Programmingenghttp://id.nii.ac.jp/1001/00197623/Technical Reporthttps://ipsj.ixsq.nii.ac.jp/ej/?action=repository_action_common_download&item_id=197713&item_no=1&attribute_id=1&file_no=1Copyright (c) 2019 by the Information Processing Society of JapanGraduate School of Informatics, Kyoto UniversityGraduate School of Informatics, Kyoto UniversityGraduate School of Informatics, Kyoto UniversityGraduate School of Informatics, Kyoto UniversityGraduate School of Informatics, Kyoto UniversityBioinformatics Center, Institute for Chemical Research, Kyoto UniversityRachaya, ChiewvanichakornChenxi, WangZhe, ZhangAleksandar, ShurbevskiHiroshi, NagamochiTatsuya, AkutsuIn this study, we propose a novel method for the inverse QSAR/QSPR. Given a set of chemical compounds G and their values a(G) of a chemical property, we define a feature vector f(G) of each chemical compound G. By using a set of feature vectors as training data, the first phase of our method constructs a prediction function ψwith an artificial neural network (ANN) so that ψ(f(G)) takes a value nearly equal to a(G) for many chemical compounds G in the set. Given a target value a* of the chemical property, the second phase infers a chemical structure G* such that a(G*) = a* in the following way. We compute a vector f* such that ψ(f*) = a*, where finding such a vector f* is formulated as a mixed integer linear programming problem (MILP). Finally we generate a chemical structure G* such that f(G*) = f*. For acyclic chemical compounds and some chemical properties such as heat of formation, boiling point, and retention time, we conducted some computational experiments with our method.In this study, we propose a novel method for the inverse QSAR/QSPR. Given a set of chemical compounds G and their values a(G) of a chemical property, we define a feature vector f(G) of each chemical compound G. By using a set of feature vectors as training data, the first phase of our method constructs a prediction function ψwith an artificial neural network (ANN) so that ψ(f(G)) takes a value nearly equal to a(G) for many chemical compounds G in the set. Given a target value a* of the chemical property, the second phase infers a chemical structure G* such that a(G*) = a* in the following way. We compute a vector f* such that ψ(f*) = a*, where finding such a vector f* is formulated as a mixed integer linear programming problem (MILP). Finally we generate a chemical structure G* such that f(G*) = f*. For acyclic chemical compounds and some chemical properties such as heat of formation, boiling point, and retention time, we conducted some computational experiments with our method.AN10505667研究報告数理モデル化と問題解決（MPS）2019-MPS-12351172019-06-102188-88332019-06-07