A New Approach to the Design of Acyclic Chemical Compounds Using Skeleton Trees and Integer Linear Programming
A New Approach to the Design of Acyclic Chemical Compounds Using Skeleton Trees and Integer Linear Programming
复制标题
使用骨架树和整数线性规划设计无环化合物的新方法
DOI：
10.1007/s10489-021-03088-6
复制
发表时间：
2022
影响因子：
5.3
通讯作者：
T. Akutsu
中科院分区：
文献类型：
--
作者：
F. Zhang;J. Zhu;R. Chiewvanichakorn;A. Shurbevski;H. Nagamochi;T. Akutsu
智能系统在很多领域都有广泛的应用，而计算机辅助药物设计是一个非常重要的领域。药物设计的一个主要方法是定量构效关系和构效关系的逆QSAR/QSPR，最近提出了一种同时使用人工神经网络(ANN)和混合整数线性规划(MILP)的方法。该方法包括两个阶段：正向预测阶段和反向推理阶段。在预测阶段，定义了化合物的特征函数，从而将化合物G表示为描述符的向量f(G)。下面，对于给定的化学性质：\Docentclass[12pt]{Minimum}\usepackage{amsath}\usepackage{wa ysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathsfs}\usepackage{upgreek}\setlong{\oddsidemargin}{-69pt}\Begin{Document}$$\pi$\end{Document}，使用具有属性的已知值的化合物的数据集：\DocumentClass[12pt]{Minimum}\usepackage{amsath}\usepackage{wa ysym}\usepackage{amsfonts}\usepackage{amsbsy}\usepackage{mathssy}\usepackage{upgreek}\setlong{\oddsidemargin}{-69pt}\Begin{Document}$$\pi$\end{Document}，回归预测函数\Documentclass[12pt]{Minimum}\usepackage{amsath}\usepackage{wa ysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathsfs}\usepackage{upgreek}\setlong{\oddsidemargin}{-69pt}\Begin{Document}$\psi$$\end{Document}由ANN计算。需要以下内容：\Docentclass[12pt]{Minimum}\usepackage{amsath}\usepackage{wa ysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{matrsfs}\usepackage{upgreek}\setlong{\oddsidemargin}{-69pt}\Begin{Document}$$\psi(f(G))$$\end{Document}采用与属性的真实值接近的值。]{Minimal}\usepackage{amsath}\usepackage{wa ysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{matrsfs}\usepackage{upgreek}\setlong{oddsidemargin}{-69pt}\Begin{Document}$$\pi$$\end{Document}。在推理阶段，一种是以化学性质的目标值\Documentclass[12pt]{Minimum}\usepackage{amsath}\usepackage{wa ysym}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathsfs}\usepackage{upgreek}\setlong{\oddsidemargin}{-69pt}\Begin{Document}$y^*$$\end{Document}开始\usepackage{wa ysym}\usepackage{amsFonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlong{\oddsidemargin}{-69pt}\Begin{Document}$$\pi$\end{Document}，然后是一个化学结构Usepackage{waysym}\usepackage{amsFonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setLong{\oddsidemargin}{-69pt}\Begin…
Intelligent systems are applied in a wide range of areas, and computer-aided drug design is a highly important one. One major approach to drug design is the inverse QSAR/QSPR (quantitative structure-activity and structure-property relationship), for which a method that uses both artificial neural networks (ANN) and mixed integer linear programming (MILP) has been proposed recently. This method consists of two phases: a forward prediction phase, and an inverse, inference phase. In the prediction phase, a feature functionfover chemical compounds is defined, whereby a chemical compoundGis represented as a vectorf(G) of descriptors. Following, for a given chemical property \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\pi$$\end{document}, using a dataset of chemical compounds with known values for property \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\pi$$\end{document}, a regressive prediction function \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\psi$$\end{document} is computed by an ANN. It is desired that \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\psi (f(G))$$\end{document} takes a value that is close to the true value of property \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\pi$$\end{document} for the compoundGfor many of the compounds in the dataset. In the inference phase, one starts with a target value \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$y^*$$\end{document} of the chemical property \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\pi$$\end{document}, and then a chemical structure \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$G^*$$\end{document} such that \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin …