相关实验视频

Updated: Mar 13, 2026

Using Cholesky Decomposition to Explore Individual Differences in Longitudinal Relations between Reading Skills

Using Cholesky Decomposition to Explore Individual Differences in Longitudinal Relations between Reading Skills

Published on: September 17, 2019

通过层次隐藏变量增强模板自由回复合成预测的多样性

Huibin Wang¹, Yueqing Zhang², Zehui Wang¹

¹Shanghai Frontiers Science Center of Molecule Intelligent Syntheses, School of Computer Science and Technology, East China Normal University, Shanghai 200062, China.

Journal of chemical information and modeling

|March 11, 2026

概括

一个新的层次条件变化自编码器 (HCVAE) 模块通过更好地捕捉化学反应关系来增强无模板回复合成. 这提高了用于合成目标分子的多重反应物的预测.

科学领域:

计算化学计算化学
化学中的人工智能.
机器学习用于化学合成.

背景情况:

逆合成识别了用于目标分子合成的反应物.
无模板的序列转换模型提供了效率和准确性.
一个关键的挑战是模拟化学反应中的一对多关系.

研究的目的:

提出一个层次条件变量自动编码器 (HCVAE) 模块,用于无模板的回复合成.
通过将一个产品与多个反应物联系起来,提高多候选合成方案的覆盖范围.
为了增强现有的回归合成框架,用一种新的层次潜伏空间来增强现有的回归合成框架.

主要方法:

开发了一个HCVAE模块,具有从连续到离散表示过渡的层次隐藏空间.
将HCVAE集成到现有的无模板回复合成框架中.
通过使用公共基准来评估HCVAE的单步预测和多步规划任务.

主要成果:

在各种骨干架构中,HCVAE 始终提高了性能.
在USPTO-50k.上,RootAligned模型的Top-10精确匹配精度从90.5%增加到91.6%.
对DirectMultistep模型的PaRoutes数据集显示出显著的改进 (例如,在n1上从49.3%到53.1%).

结论:

HCVAE有效地解决了回复合成中的化学反应的一对多性质.
学习的潜伏空间为探索替代反应途径提供了一个结构化的方法.
方便复杂的,类似药物的分子的实际多步合成.

更多相关视频

Heuristic Mining of Hierarchical Genotypes and Accessory Genome Loci in Bacterial Populations

Heuristic Mining of Hierarchical Genotypes and Accessory Genome Loci in Bacterial Populations

Published on: December 7, 2021

Hierarchical and Programmable One-Pot Oligosaccharide Synthesis

Hierarchical and Programmable One-Pot Oligosaccharide Synthesis

Published on: September 6, 2019

相关概念视频

Predicting Reaction Outcomes

Predicting Reaction Outcomes

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,...

Predicting Molecular Geometry

Predicting Molecular Geometry

VSEPR Theory for Determination of Electron Pair Geometries

Predicting Products: Substitution vs. Elimination

Predicting Products: Substitution vs. Elimination

When a nucleophile and an alkyl halide react, nucleophilic substitution and β-elimination reactions compete to generate products.
The following factors can influence the mechanisms competing against each other:

Synthesis and Decomposition Reactions

Synthesis and Decomposition Reactions

Synthesis and decomposition are two types of redox reactions. Synthesis means to make something, whereas decomposition means to break something. The reactions are accompanied by chemical and energy changes.

Predicting Products: SN1 vs. SN2

Predicting Products: S_N1 vs. S_N2

Nucleophilic substitution reactions of alkyl halides can proceed via an SN1 or an SN2 mechanism. While in SN2 reactions, the nucleophile attacks the substrate simultaneously as the leaving group departs, in SN1 reactions, the substrate first dissociates to give the carbocation intermediate. Various factors such as the structure of the substrate, the strength of the nucleophile, and the nature of the solvent promote one mechanism over the other.
With increased substitution on the alkyl halide,...

Diels–Alder vs Retro-Diels–Alder Reaction: Thermodynamic Factors

Diels–Alder vs Retro-Diels–Alder Reaction: Thermodynamic Factors

The Diels–Alder reaction is thermally reversible, meaning that the reaction reverts to the starting diene and dienophile under suitable temperatures. The forward reaction gives a cyclohexene derivative and is favored at low to medium temperatures. The reverse process, also called retro-Diels–Alder reaction, is a ring-opening process favored at high temperatures.