评估基于变压器的分子设计中的强化学习。

IF 7.1 2区 化学 Q1 CHEMISTRY, MULTIDISCIPLINARY Journal of Cheminformatics Pub Date : 2024-08-08 DOI:10.1186/s13321-024-00887-0
Jiazhen He, Alessandro Tibo, Jon Paul Janet, Eva Nittinger, Christian Tyrchan, Werngard Czechtizky, Ola Engkvist
{"title":"评估基于变压器的分子设计中的强化学习。","authors":"Jiazhen He,&nbsp;Alessandro Tibo,&nbsp;Jon Paul Janet,&nbsp;Eva Nittinger,&nbsp;Christian Tyrchan,&nbsp;Werngard Czechtizky,&nbsp;Ola Engkvist","doi":"10.1186/s13321-024-00887-0","DOIUrl":null,"url":null,"abstract":"<div><p>Designing compounds with a range of desirable properties is a fundamental challenge in drug discovery. In pre-clinical early drug discovery, novel compounds are often designed based on an already existing promising starting compound through structural modifications for further property optimization. Recently, transformer-based deep learning models have been explored for the task of molecular optimization by training on pairs of similar molecules. This provides a starting point for generating similar molecules to a given input molecule, but has limited flexibility regarding user-defined property profiles. Here, we evaluate the effect of reinforcement learning on transformer-based molecular generative models. The generative model can be considered as a pre-trained model with knowledge of the chemical space close to an input compound, while reinforcement learning can be viewed as a tuning phase, steering the model towards chemical space with user-specific desirable properties. The evaluation of two distinct tasks—molecular optimization and scaffold discovery—suggest that reinforcement learning could guide the transformer-based generative model towards the generation of more compounds of interest. Additionally, the impact of pre-trained models, learning steps and learning rates are investigated.</p><p><b>Scientific contribution</b></p><p>Our study investigates the effect of reinforcement learning on a transformer-based generative model initially trained for generating molecules similar to starting molecules. The reinforcement learning framework is applied to facilitate multiparameter optimisation of starting molecules. This approach allows for more flexibility for optimizing user-specific property profiles and helps finding more ideas of interest.</p></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"16 1","pages":""},"PeriodicalIF":7.1000,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11312936/pdf/","citationCount":"0","resultStr":"{\"title\":\"Evaluation of reinforcement learning in transformer-based molecular design\",\"authors\":\"Jiazhen He,&nbsp;Alessandro Tibo,&nbsp;Jon Paul Janet,&nbsp;Eva Nittinger,&nbsp;Christian Tyrchan,&nbsp;Werngard Czechtizky,&nbsp;Ola Engkvist\",\"doi\":\"10.1186/s13321-024-00887-0\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Designing compounds with a range of desirable properties is a fundamental challenge in drug discovery. In pre-clinical early drug discovery, novel compounds are often designed based on an already existing promising starting compound through structural modifications for further property optimization. Recently, transformer-based deep learning models have been explored for the task of molecular optimization by training on pairs of similar molecules. This provides a starting point for generating similar molecules to a given input molecule, but has limited flexibility regarding user-defined property profiles. Here, we evaluate the effect of reinforcement learning on transformer-based molecular generative models. The generative model can be considered as a pre-trained model with knowledge of the chemical space close to an input compound, while reinforcement learning can be viewed as a tuning phase, steering the model towards chemical space with user-specific desirable properties. The evaluation of two distinct tasks—molecular optimization and scaffold discovery—suggest that reinforcement learning could guide the transformer-based generative model towards the generation of more compounds of interest. Additionally, the impact of pre-trained models, learning steps and learning rates are investigated.</p><p><b>Scientific contribution</b></p><p>Our study investigates the effect of reinforcement learning on a transformer-based generative model initially trained for generating molecules similar to starting molecules. The reinforcement learning framework is applied to facilitate multiparameter optimisation of starting molecules. This approach allows for more flexibility for optimizing user-specific property profiles and helps finding more ideas of interest.</p></div>\",\"PeriodicalId\":617,\"journal\":{\"name\":\"Journal of Cheminformatics\",\"volume\":\"16 1\",\"pages\":\"\"},\"PeriodicalIF\":7.1000,\"publicationDate\":\"2024-08-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11312936/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Cheminformatics\",\"FirstCategoryId\":\"92\",\"ListUrlMain\":\"https://link.springer.com/article/10.1186/s13321-024-00887-0\",\"RegionNum\":2,\"RegionCategory\":\"化学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"CHEMISTRY, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Cheminformatics","FirstCategoryId":"92","ListUrlMain":"https://link.springer.com/article/10.1186/s13321-024-00887-0","RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CHEMISTRY, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

摘要

设计具有一系列理想特性的化合物是药物研发中的一项基本挑战。在临床前早期药物发现中,新型化合物往往是在已有的有前景的起始化合物基础上,通过结构改造进一步优化性质而设计出来的。最近,人们探索了基于转换器的深度学习模型,通过对相似分子进行训练来完成分子优化任务。这为生成与给定输入分子相似的分子提供了一个起点,但在用户定义的特性曲线方面灵活性有限。在此,我们评估了强化学习对基于变压器的分子生成模型的影响。生成模型可被视为预先训练好的模型,具有与输入化合物相近的化学空间知识,而强化学习可被视为一个调整阶段,将模型导向具有用户特定理想特性的化学空间。对分子优化和支架发现这两项不同任务的评估表明,强化学习可以引导基于转换器的生成模型生成更多感兴趣的化合物。此外,研究还探讨了预训练模型、学习步骤和学习率的影响。 科学贡献我们的研究探讨了强化学习对基于变压器的生成模型的影响,该模型最初是为生成与起始分子相似的分子而训练的。强化学习框架用于促进起始分子的多参数优化。这种方法可以更灵活地优化用户特定的属性剖面,并有助于找到更多感兴趣的想法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Evaluation of reinforcement learning in transformer-based molecular design

Designing compounds with a range of desirable properties is a fundamental challenge in drug discovery. In pre-clinical early drug discovery, novel compounds are often designed based on an already existing promising starting compound through structural modifications for further property optimization. Recently, transformer-based deep learning models have been explored for the task of molecular optimization by training on pairs of similar molecules. This provides a starting point for generating similar molecules to a given input molecule, but has limited flexibility regarding user-defined property profiles. Here, we evaluate the effect of reinforcement learning on transformer-based molecular generative models. The generative model can be considered as a pre-trained model with knowledge of the chemical space close to an input compound, while reinforcement learning can be viewed as a tuning phase, steering the model towards chemical space with user-specific desirable properties. The evaluation of two distinct tasks—molecular optimization and scaffold discovery—suggest that reinforcement learning could guide the transformer-based generative model towards the generation of more compounds of interest. Additionally, the impact of pre-trained models, learning steps and learning rates are investigated.

Scientific contribution

Our study investigates the effect of reinforcement learning on a transformer-based generative model initially trained for generating molecules similar to starting molecules. The reinforcement learning framework is applied to facilitate multiparameter optimisation of starting molecules. This approach allows for more flexibility for optimizing user-specific property profiles and helps finding more ideas of interest.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Journal of Cheminformatics
Journal of Cheminformatics CHEMISTRY, MULTIDISCIPLINARY-COMPUTER SCIENCE, INFORMATION SYSTEMS
CiteScore
14.10
自引率
7.00%
发文量
82
审稿时长
3 months
期刊介绍: Journal of Cheminformatics is an open access journal publishing original peer-reviewed research in all aspects of cheminformatics and molecular modelling. Coverage includes, but is not limited to: chemical information systems, software and databases, and molecular modelling, chemical structure representations and their use in structure, substructure, and similarity searching of chemical substance and chemical reaction databases, computer and molecular graphics, computer-aided molecular design, expert systems, QSAR, and data mining techniques.
期刊最新文献
GT-NMR: a novel graph transformer-based approach for accurate prediction of NMR chemical shifts Suitability of large language models for extraction of high-quality chemical reaction dataset from patent literature Molecular identification via molecular fingerprint extraction from atomic force microscopy images A systematic review of deep learning chemical language models in recent era Accelerated hit identification with target evaluation, deep learning and automated labs: prospective validation in IRAK1
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1