CASIA OpenIR  > 模式识别实验室
Molecular Contrastive Pretraining with Collaborative Featurizations
Yanqiao Zhu1; Dingshuo Chen1; Yuanqi Du2; Yingze Wang3; Qiang Liu1; Shu Wu1
Source PublicationJournal of Chemical Information and Modeling (JCIM)
ISSN1549-9596
2024-02-25
Volume64Issue:4Pages:1112–1122
Corresponding AuthorWu, Shu(shu.wu@nlpr.ia.ac.cn)
Abstract

Molecular pretraining, which learns molecular representations over massive unlabeled data, has become a prominent paradigm to solve a variety of tasks in computational chemistry and drug discovery. Recently, prosperous progress has been made in molecular pretraining with dierent molecular featurizations, including 1D SMILES strings, 2D graphs, and 3D geometries. However, the role of molecular featurizations with their corresponding neural architectures in molecular pretraining remains largely unexamined. In this paper, through two case studies—chirality classification and aromatic ring counting—we first demonstrate that dierent featurization techniques convey chemical information dierently. In light of this observation, we propose a simple and eective MOlecular pretraining framework with COllaborative featurizations (MOCO). MOCO comprehensively leverages multiple featurizations that complement each other and outperforms existing state-of-the-art models that solely relies on one or two featurizations on a wide range of molecular property prediction tasks.

DOI10.1021/acs.jcim.3c01468
WOS KeywordLANGUAGE
URL查看原文
Indexed BySCI
Language英语
Funding ProjectNational Natural Science Foundation of China[2023ZD0120901] ; National Key Research and Development Program of China[62141608] ; National Key Research and Development Program of China[62206291] ; National Key Research and Development Program of China[62372454] ; National Natural Science Foundation of China
Funding OrganizationNational Natural Science Foundation of China ; National Key Research and Development Program of China ; National Natural Science Foundation of China
WOS Research AreaPharmacology & Pharmacy ; Chemistry ; Computer Science
WOS SubjectChemistry, Medicinal ; Chemistry, Multidisciplinary ; Computer Science, Information Systems ; Computer Science, Interdisciplinary Applications
WOS IDWOS:001163373600001
PublisherAMER CHEMICAL SOC
Sub direction classification机器学习
planning direction of the national heavy laboratory智能计算与学习
Paper associated data
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/57485
Collection模式识别实验室
Corresponding AuthorShu Wu
Affiliation1.中国科学院自动化研究所
2.Cornell University
3.北京大学
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Yanqiao Zhu,Dingshuo Chen,Yuanqi Du,et al. Molecular Contrastive Pretraining with Collaborative Featurizations[J]. Journal of Chemical Information and Modeling (JCIM),2024,64(4):1112–1122.
APA Yanqiao Zhu,Dingshuo Chen,Yuanqi Du,Yingze Wang,Qiang Liu,&Shu Wu.(2024).Molecular Contrastive Pretraining with Collaborative Featurizations.Journal of Chemical Information and Modeling (JCIM),64(4),1112–1122.
MLA Yanqiao Zhu,et al."Molecular Contrastive Pretraining with Collaborative Featurizations".Journal of Chemical Information and Modeling (JCIM) 64.4(2024):1112–1122.
Files in This Item: Download All
File Name/Size DocType Version Access License
Molecular Contrastiv(1868KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yanqiao Zhu]'s Articles
[Dingshuo Chen]'s Articles
[Yuanqi Du]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yanqiao Zhu]'s Articles
[Dingshuo Chen]'s Articles
[Yuanqi Du]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yanqiao Zhu]'s Articles
[Dingshuo Chen]'s Articles
[Yuanqi Du]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Molecular Contrastive Pretraining with Collaborative Featurizations.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.