Mapping the space of chemical reactions using attention-based neural networks

计算机科学 化学空间 聚类分析 试剂 化学反应 人工神经网络 人工智能 班级(哲学) 背景(考古学) 化学 有机化学 生物化学 药物发现 生物 古生物学
作者
Philippe Schwaller,Daniel Probst,Alain C. Vaucher,Vishnu H Nair,David Kreutter,Teodoro Laino,Jean‐Louis Reymond
出处
期刊:Nature Machine Intelligence [Nature Portfolio]
卷期号:3 (2): 144-152 被引量:205
标识
DOI:10.1038/s42256-020-00284-w
摘要

Organic reactions are usually assigned to classes containing reactions with similar reagents and mechanisms. Reaction classes facilitate the communication of complex concepts and efficient navigation through chemical reaction space. However, the classification process is a tedious task. It requires identification of the corresponding reaction class template via annotation of the number of molecules in the reactions, the reaction centre and the distinction between reactants and reagents. Here, we show that transformer-based models can infer reaction classes from non-annotated, simple text-based representations of chemical reactions. Our best model reaches a classification accuracy of 98.2%. We also show that the learned representations can be used as reaction fingerprints that capture fine-grained differences between reaction classes better than traditional reaction fingerprints. The insights into chemical reaction space enabled by our learned fingerprints are illustrated by an interactive reaction atlas providing visual clustering and similarity searching. Organic chemical reactions can be divided into classes that allow chemists to use the knowledge they have about optimal conditions for specific reactions in the context of other reactions of similar type. Schwaller et al. present here an efficient method based on transformer neural networks that learns a chemical space in which reactions of a similar class are grouped together.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
蓝桉完成签到 ,获得积分10
刚刚
Ray完成签到,获得积分10
1秒前
甜美的月饼完成签到,获得积分10
2秒前
Lucas应助兴奋的小虾米采纳,获得10
2秒前
开心完成签到 ,获得积分10
2秒前
汉堡包应助娇气的雁兰采纳,获得10
2秒前
相信相信的力量完成签到,获得积分10
2秒前
心心完成签到 ,获得积分10
2秒前
N维完成签到,获得积分10
3秒前
熊小子爱学习完成签到,获得积分10
3秒前
wsq完成签到 ,获得积分10
3秒前
清风在侧完成签到,获得积分10
4秒前
邓邓发布了新的文献求助10
4秒前
wangyue完成签到,获得积分10
5秒前
5秒前
可宝想当富婆完成签到,获得积分10
5秒前
完美世界应助lian采纳,获得10
5秒前
无所谓完成签到,获得积分10
6秒前
6秒前
petrichor完成签到 ,获得积分10
6秒前
学术通zzz完成签到,获得积分10
7秒前
所所应助小鱼采纳,获得10
7秒前
wendinfgmei发布了新的文献求助10
7秒前
顺心的芝麻关注了科研通微信公众号
8秒前
帝钰发布了新的文献求助10
8秒前
AeroY发布了新的文献求助20
9秒前
演化的蛙鱼完成签到,获得积分10
10秒前
无所谓发布了新的文献求助10
10秒前
Akim应助hjc采纳,获得10
10秒前
碧蓝可乐完成签到,获得积分10
11秒前
andou完成签到,获得积分10
11秒前
天真涵双完成签到,获得积分10
11秒前
王洒洒发布了新的文献求助10
11秒前
李爱国应助辞清采纳,获得10
11秒前
12秒前
Orange应助okghy采纳,获得10
13秒前
13秒前
星辰大海应助公卫小白采纳,获得10
13秒前
14秒前
温婉的蘑菇完成签到,获得积分10
14秒前
高分求助中
The Mother of All Tableaux Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 2400
Ophthalmic Equipment Market by Devices(surgical: vitreorentinal,IOLs,OVDs,contact lens,RGP lens,backflush,diagnostic&monitoring:OCT,actorefractor,keratometer,tonometer,ophthalmoscpe,OVD), End User,Buying Criteria-Global Forecast to2029 2000
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind (Sixth Edition) 1000
Optimal Transport: A Comprehensive Introduction to Modeling, Analysis, Simulation, Applications 800
Official Methods of Analysis of AOAC INTERNATIONAL 600
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 588
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3960337
求助须知:如何正确求助?哪些是违规求助? 3506438
关于积分的说明 11130396
捐赠科研通 3238607
什么是DOI,文献DOI怎么找? 1789826
邀请新用户注册赠送积分活动 871947
科研通“疑难数据库(出版商)”最低求助积分说明 803099