arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.16882physics.chem-phcs.AIcs.LGq-bio.BM
收藏

利用对比学习揭示发表偏倚与化学反应性之间的关系

Revealing the Relationship Between Publication Bias and Chemical Reactivity with Contrastive Learning

Massachusetts Institute of Technology(麻省理工学院)

Wenhao Gao, Priyanka Raghavan, Ron Shprints, Connor W. Coley

AI总结:

本文提出底物范围对比学习,将已报道与未报道底物分别作为正负样本,从历史文献中学习分子嵌入,揭示发表偏倚与反应性的关联,并可用于产率和区域选择性预测。

摘要:

合成方法的底物耐受性和普适性通常在“底物范围”表中展示。然而,底物选择表现出一种常被讨论的发表偏倚:不成功的实验或低产率结果很少被报道。在本研究中,我们采用一种新颖的神经网络训练策略——底物范围对比学习,更深入地探究了这种发表偏倚与化学反应性之间的关系,而不只是简单分析产率分布。通过将已报道的底物视为正样本、未报道的底物视为负样本,我们的对比学习策略根据已发表底物范围表中的历史趋势,教模型在数值嵌入空间中对分子进行分组。我们在 CAS Content Collection™ 中 20,798 种芳基卤化物上进行训练,这些数据涵盖 2010–2015 年的数千篇出版物;结果表明,通过直观可视化和定量回归分析,所学嵌入与物理有机反应性描述符之间呈现相关性。此外,这些嵌入可用于多种反应建模任务,如产率预测和区域选择性预测,突显了将历史反应数据用作预训练任务的潜力。本工作不仅提出了一种化学专用的机器学习训练策略,以新的方式从文献数据中学习,也提供了一种独特方法,用于揭示由出版物中底物选择趋势所反映的化学反应性趋势。

英文摘要:

A synthetic method's substrate tolerance and generality are often showcased in a "substrate scope" table. However, substrate selection exhibits a frequently discussed publication bias: unsuccessful experiments or low-yielding results are rarely reported. In this work, we explore more deeply the relationship between such publication bias and chemical reactivity beyond the simple analysis of yield distributions using a novel neural network training strategy, substrate scope contrastive learning. By treating reported substrates as positive samples and non-reported substrates as negative samples, our contrastive learning strategy teaches a model to group molecules within a numerical embedding space, based on historical trends in published substrate scope tables. Training on 20,798 aryl halides in the CAS Content Collection$^{\text{TM}}$, spanning thousands of publications from 2010-2015, we demonstrate that the learned embeddings exhibit a correlation with physical organic reactivity descriptors through both intuitive visualizations and quantitative regression analyses. Additionally, these embeddings are applicable to various reaction modeling tasks like yield prediction and regioselectivity prediction, underscoring the potential to use historical reaction data as a pre-training task. This work not only presents a chemistry-specific machine learning training strategy to learn from literature data in a new way, but also represents a unique approach to uncover trends in chemical reactivity reflected by trends in substrate selection in publications.

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。

↑