Chemical language models enable navigation in sparsely populated chemical space

生成模型 化学空间 人工智能 生成语法 计算机科学 水准点(测量) 机器学习 领域(数学) 质量(理念) 深度学习 人工神经网络 空格(标点符号) 药物发现 生物信息学 生物 数学 地理 认识论 纯数学 哲学 操作系统 大地测量学
作者
Michael A. Skinnider,R. Greg Stacey,David S. Wishart,Leonard J. Foster
出处
期刊:Nature Machine Intelligence [Nature Portfolio]
卷期号:3 (9): 759-770 被引量:113
标识
DOI:10.1038/s42256-021-00368-1
摘要

Deep generative models are powerful tools for the exploration of chemical space, enabling the on-demand generation of molecules with desired physical, chemical or biological properties. However, these models are typically thought to require training datasets comprising hundreds of thousands, or even millions, of molecules. This perception limits the application of deep generative models in regions of chemical space populated by a relatively small number of examples. Here, we systematically evaluate and optimize generative models of molecules based on recurrent neural networks in low-data settings. We find that robust models can be learned from far fewer examples than has been widely assumed. We identify strategies that further reduce the number of molecules required to learn a model of equivalent quality, notably including data augmentation by non-canonical SMILES enumeration, and demonstrate the application of these principles by learning models of bacterial, plant and fungal metabolomes. The structure of our experiments also allows us to benchmark the metrics used to evaluate generative models themselves. We find that many of the most widely used metrics in the field fail to capture model quality, but we identify a subset of well-behaved metrics that provide a sound basis for model development. Collectively, our work provides a foundation for directly learning generative models in sparsely populated regions of chemical space. Deep learning-based methods to generate new molecules can require huge amounts of data to train. Skinnider et al. show that models developed for natural language processing work well for generating molecules from small amounts of training data, and identify robust metrics to evaluate the quality of generated molecules.
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
morris完成签到,获得积分10
刚刚
热心的十二完成签到 ,获得积分10
刚刚
1秒前
Selenaxue发布了新的文献求助10
1秒前
2秒前
魔飞发布了新的文献求助10
3秒前
ClaudiaCY发布了新的文献求助10
4秒前
msy完成签到,获得积分10
4秒前
qqxx应助沈文远采纳,获得10
4秒前
qq发布了新的文献求助10
4秒前
炙热柚子完成签到,获得积分10
5秒前
CyrusSo524应助此间少年郎采纳,获得50
6秒前
7秒前
大王可爱完成签到,获得积分10
8秒前
纯情的严青完成签到,获得积分10
8秒前
风息发布了新的文献求助10
8秒前
JamesPei应助小崔采纳,获得10
9秒前
9秒前
阿明完成签到,获得积分10
9秒前
fmy完成签到,获得积分10
10秒前
11秒前
11秒前
12秒前
儒雅寒天发布了新的文献求助10
13秒前
科研通AI2S应助风息采纳,获得10
13秒前
白斯特发布了新的文献求助10
13秒前
13秒前
LL关闭了LL文献求助
14秒前
墨菲特发布了新的文献求助10
15秒前
光亮青柏发布了新的文献求助10
16秒前
wwqq完成签到,获得积分10
16秒前
充电宝应助qqqqwf采纳,获得20
16秒前
ark861023发布了新的文献求助10
17秒前
17秒前
18秒前
18秒前
18秒前
深情安青应助renyi采纳,获得10
19秒前
19秒前
iui飞发布了新的文献求助10
20秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
Toward a Combinatorial Approach for the Prediction of IgG Half-Life and Clearance 500
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
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 3969917
求助须知:如何正确求助?哪些是违规求助? 3514626
关于积分的说明 11175060
捐赠科研通 3249928
什么是DOI,文献DOI怎么找? 1795165
邀请新用户注册赠送积分活动 875617
科研通“疑难数据库(出版商)”最低求助积分说明 804891