反应T5:预训练过的变压器模型,用于准确预测有限数据的化学反应
Tatsuya Sagawa1,2, Ryosuke Kojima3,4
1Graduate School of Pharmaceutical Sciences, Kyoto University, Kyoto, 606-8501, Japan.
Journal of cheminformatics
|August 20, 2025
概括
反应T5是一个新的AI模型, 准确地预测化学反应, 加快药物发现. 它在产品,复合和产量预测方面表现出色,即使数据有限.
科学领域:
- 计算化学
- 药物发现中的人工智能
- 化学过程的机器学习
背景情况:
- 精确的化学反应预测对于有效的药物开发至关重要.
- 现有的模型在预测反应结果和产量方面面临挑战.
- 大规模的反应数据集对于训练可靠模型至关重要.
研究的目的:
- 介绍一个基于变压器的化学反应预测基础模型 ReactionT5.
- 评估 ReactionT5 在关键药物开发任务上的表现:产品预测,回合成和产量预测.
- 评估模型学习化学反应特性及其数据效率的能力.
主要方法:
- 在全面的开放反应数据库上进行预培训.
- 与现有的产品预测,回归合成和产量预测模型进行比较.
- 对有限的反应数据集进行微调反应T5,以评估数据效率.
- 可视化 ReactionT5 嵌入式以解释已学习的化学反应空间.
主要成果:
- 反应T5实现了最先进的性能:产品预测准确率为97.5%,反合成准确率为71.0%,产量预测准确率为0. 947.
- 即使在有限的反应数据上进行微调时,模型也表现出了显著的性能.
- 嵌入式可视化证实了 ReactionT5 的有效捕获和表现化学反应特性.
结论:
- 反应T5显著提升了化学反应预测能力.
- 这种模式为加速成本和时间密集的药物开发过程提供了强大的工具.
- 反应T5的数据效率表明在化学研究和开发中具有更广泛的应用潜力.
相关概念视频
Predicting Reaction Outcomes
8.6K
Kinetics describes the rate and path by which a reaction occurs. In contrast, thermodynamics deals with state functions and describes the properties, behavior, and components of a system. It is not concerned with the path taken by the process and cannot address the rate at which a reaction occurs. Although it does provide information about what can happen during a reaction process, it does not describe the detailed steps of what appears on an atomic or a molecular level. On the other hand,...
8.6K
Transformers with Off-Nominal Turns Ratios
205
In scenarios involving parallel transformers with disparate ratings, developing per-unit models requires accommodating off-nominal turns ratios. This situation arises when the selected base voltages are not proportional to the transformer’s voltage ratings. Consider a transformer where the rated voltages are related by the term a. If the chosen voltage bases satisfy a relationship involving term b, term c is defined as the ratio of these bases. This ratio is then substituted into the...
205
Chemical Reactions
10.1K
A balanced chemical equation provides the information of chemical formulas of the reactants and products involved in the chemical change. A reaction’s stoichiometry helps predict how much of the reactant is needed to produce the desired amount of product, or in some cases, how much product will be formed from a specific amount of the reactant.
The relative amounts of reactants and products represented in a balanced chemical equation are often referred to as stoichiometric amounts.
The relative amounts of reactants and products represented in a balanced chemical equation are often referred to as stoichiometric amounts.
10.1K
Reaction Quotient
49.1K
The status of a reversible reaction is conveniently assessed by evaluating its reaction quotient (Q). For a reversible reaction described by m A + n B ⇌ x C + y D, the reaction quotient is derived directly from the stoichiometry of the balanced equation as
49.1K
Multi-Step Reactions
7.5K
Chemical reactions often occur in a stepwise fashion involving two or more distinct reactions taking place in a sequence. A balanced equation indicates the reacting species and the product species, but it reveals no details about how the reaction occurs at the molecular level. The reaction mechanism (or reaction path) provides details regarding the precise, step-by-step process by which a reaction occurs. Each of the steps in a reaction mechanism is called an elementary reaction. These...
7.5K
Reaction Rate
54.5K
The rate of reaction is the change in the amount of a reactant or product per unit time. Reaction rates are therefore determined by measuring the time dependence of some property that can be related to reactant or product amounts. Rates of reactions that consume or produce gaseous substances, for example, are conveniently determined by measuring changes in volume or pressure.
The mathematical representation of the change in the concentration of reactants and products, over time, is the rate...
The mathematical representation of the change in the concentration of reactants and products, over time, is the rate...
54.5K


