arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.29329q-bio.QMcs.LG
收藏

基于混合整数线性规划的共聚物推断的混合向量模型

Mixing Vector Model for Copolymer Inference via Mixed Integer Linear Programming

Department of Information Science and Technology, Tokyo University of Science(东京科学大学信息科学与技术系);Discrete Mathematics and Computational Intelligence Laboratory, Department of Mathematics, Quaid-i-Azam University(夸齐-阿扎姆大学数学系离散数学与计算智能实验室);Graduate School of Informatics, Kyoto University(京都大学信息研究生院);Graduate School of Advanced Integrated Studies in Human Survivability (Shishu-Kan), Kyoto University(京都大学人类生存高级综合研究研究生院(Shishu-Kan));Bioinformatics Center, Institute for Chemical Research, Kyoto University(京都大学化学研究所生物信息中心)

Jianshen Zhu, Raveena Rai, Taiyo Sohkawa, Naveed Ahmed Azam, Kazuya Haraguchi, Liang Zhao, Tatsuya Akutsu

AI总结:

提出混合向量模型,通过混合整数线性规划实现共聚物的逆设计,在多个物化数据集上取得高预测精度并保持可解性。

摘要:

最近开发了一种新颖的两阶段分子推断框架mol-infer,通过两层模型下的混合整数线性规划(MILP),在给定学习预测函数和结构约束的条件下,以最优性和精确性推断具有规定抽象结构和期望性质值的化学图。在本研究中,我们通过引入一种称为混合向量(MV)模型的简单特征表示,将该框架扩展到共聚物。在所提出的模型中,共聚物特征向量表示为MILT可处理单体描述符的凸组合,加权系数为组成单体的混合比例。这种表示不需要明确的序列类别信息,因此自然兼容基于MILP的逆设计。在该模型下,我们使用人工神经网络、简化二次多元线性回归和随机森林为多个共聚物性质数据集构建预测函数。所提出的表示在多个物理化学性质数据集上实现了实际有用的预测性能;特别地,十个数据集中有九个的最佳测试R²分数超过0.7,六个数据集超过0.9。我们还制定了在MV表示下具有规定混合比例的多单体逆设计问题,并表明即使在三单体设置下,生成的MILP实例仍然可解。最后,我们通过重新评估推断的候选物并将重新计算的性质值与学习模型预测的值进行比较,进行外部一致性检查。总体而言,所提出的框架为在两层模型下实现共聚物的模型级精确逆设计提供了可处理的第一步。

英文摘要:

A novel two-phase molecule inference framework, mol-infer, has recently been developed to infer chemical graphs with prescribed abstract structures and desired property values through mixed integer linear programming (MILP) under the two-layered model, with guaranteed optimality and exactness relative to the given learned prediction function and structural constraints. In this study, we extend this framework to copolymers by introducing a simple feature representation, called the mixing vector (MV) model. In the proposed model, a copolymer feature vector is represented as a convex combination of MILP-tractable monomer descriptors weighted by the mixing ratio of the constituent monomers. This representation does not require explicit sequence-class information and is therefore naturally compatible with MILP-based inverse design. Under this model, we construct prediction functions for several copolymer property datasets using artificial neural networks, reduced quadratic multiple linear regression, and random forests. The proposed representation achieves practically useful predictive performance across multiple physicochemical property datasets; in particular, the best test R^2 score exceeds 0.7 for nine of the ten datasets and exceeds 0.9 for six datasets. We also formulate a multi-monomer inverse-design problem under the MV representation with a prescribed mixing ratio and show that the resulting MILP instances remain tractable, even for three-monomer settings. Finally, we perform an external consistency check by re-evaluating the inferred candidates and comparing the re-computed property values with those predicted by the learned model. Overall, the proposed framework gives a tractable first step toward model-level exact inverse design of copolymers under the two-layered model.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑