[论文解读] AI-driven Inverse Design System for Organic Molecules

Seiji Takeda, Toshiyuki Hama+8 more|arXiv (Cornell University)|Jan 20, 2020

Machine Learning in Materials Science参考文献 19被引用 7

一句话总结

本文提出了一种端到端的、由人工智能驱动的有机分子逆向设计系统，整合了数据处理、性质预测建模和结构生成，以发现具有目标物理性质的新化学结构。通过在分子数据上训练回归模型并求解逆问题，该系统生成符合用户指定性质目标的化学上有效的候选分子，展示了在工业应用中材料发现的完整工作流程。

ABSTRACT

Designing novel materials that possess desired properties is a central need across many manufacturing industries. Driven by that industrial need, a variety of algorithms and tools have been developed that combine AI (machine learning and analytics) with domain knowledge in physics, chemistry, and materials science. AI-driven materials design can be divided to mainly two stages; the first one is the modeling stage, where the goal is to build an accurate regression or classification model to predict material properties (e.g. glass transition temperature) or attributes (e.g. toxic/non-toxic). The next stage is design, where the goal is to assemble or tune material structures so that they can achieve user-demanded target property values based on a prediction model that is trained in the modeling stage. For maximum benefit, these two stages should be architected to form a coherent workflow. Today there are several emerging services and tools for AI-driven material design, however, most of them provide only partial technical components (e.g. data analyzer, regression model, structure generator, etc.), that are useful for specific purposes, but for comprehensive material design, those components need to be orchestrated appropriately. Our material design system provides an end-to-end solution to this problem, with a workflow that consists of data input, feature encoding, prediction modeling, solution search, and structure generation. The system builds a regression model to predict properties, solves an inverse problem on the trained model, and generates novel chemical structure candidates that satisfy the target properties. In this paper we will introduce the methodology of our system, and demonstrate a simple example of inverse design generating new chemical structures that satisfy targeted physical property values.

研究动机与目标

• 为满足工业界对设计具有特定物理性质的新有机材料的需求。
• 通过将数据输入、特征编码、预测建模、解法搜索和结构生成整合到单一工作流中，克服现有AI工具的碎片化问题。
• 通过求解能够实现期望目标性质值的分子结构，实现逆向设计，方法基于训练好的回归模型。
• 展示通过自动化、人工智能驱动的设计流程生成化学上有效且新颖的有机分子的可行性。

提出的方法

• 系统从分子结构及其相关物理性质的数据输入开始。
• 应用特征编码，将分子结构转换为适合机器学习的数值表示。
• 训练回归模型，以从分子特征预测目标物理性质（例如玻璃化转变温度）。
• 利用训练好的模型制定并求解逆问题，以识别能够产生期望性质值的分子结构。
• 结构生成模块生成满足目标性质约束的新颖且化学上有效的有机分子。
• 工作流被组织为统一的端到端管道，实现从目标性质到候选分子的完整逆向设计。

实验结果

研究问题

• RQ1 集成的AI驱动系统是否能有效生成具有用户定义目标物理性质的新颖有机分子？
• RQ2 机器学习模型从分子结构表示中预测关键物理性质的准确性如何？
• RQ3 逆向建模在多大程度上能够识别出满足特定性质目标的可行分子结构？
• RQ4 该系统在通过端到端自动化生成化学上有效且多样的分子候选物方面具有多强的鲁棒性？

主要发现

• 该系统通过逆向设计成功生成了满足用户定义目标物理性质值的新颖有机分子结构。
• 将数据处理、回归建模和结构生成整合到单一工作流中，实现了高效且自动化的材料发现。
• 该方法展示了利用人工智能解决分子设计中逆问题的可行性，实现了从正向预测到目标结构生成的跨越。
• 该系统架构支持可扩展性和可适应性，适用于多种材料和性质目标，具备广泛的工业适用性。