Meta-MolNet: A Cross-Domain Benchmark for Few Examples Drug Discovery
文献类型：期刊论文
| 作者 | Lv, Qiujie6; Chen, Guanxing6; Yang, Ziduo6; Zhong, Weihe5; Chen, Calvin Yu-Chian1,2,3,4 |
| 刊名 | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
 |
| 出版日期 | 2024-02-14 |
| 页码 | 15 |
| 关键词 | Benchmark platform cross-domain meta-learning drug discovery few examples Meta-MolNet molecular property |
| ISSN号 | 2162-237X |
| DOI | 10.1109/TNNLS.2024.3359657 |
| 通讯作者 | Chen, Calvin Yu-Chian() |
| 英文摘要 | Predicting the pharmacological activity, toxicity, and pharmacokinetic properties of molecules is a central task in drug discovery. Existing machine learning methods are transferred from one resource rich molecular property to another data scarce property in the same scaffold dataset. However, existing models may produce fragile and highly uncertain predictions for new scaffold molecules. And these models were tested on different benchmarks, which seriously affected the quality of their evaluation results. In this article, we introduce Meta-MolNet, a collection of data benchmark and algorithms, which is a standard benchmark platform for measuring model generalization and uncertainty quantification capabilities. Meta-MolNet manages a wide range of molecular datasets with high ratio of molecules/scaffolds, which often leads to more difficult data shift and generalization problems. Furthermore, we propose a graph attention network based on cross-domain meta-learning, Meta-GAT, which uses bilevel optimization to learn meta-knowledge from the scaffold family molecular dataset in the source domain. Meta-GAT benefits from meta-knowledge that reduces the requirement of sample complexity to enable reliable predictions of new scaffold molecules in the target domain through internal iteration of a few examples. We evaluate existing methods as baselines for the community, and the Meta-MolNet benchmark demonstrates the effectiveness of measuring the proposed algorithm in domain generalization and uncertainty quantification. Extensive experiments demonstrate that the Meta-GAT model has state-of-the-art domain generalization performance and robustly estimates uncertainty under few examples constraints. By publishing AI-ready data, evaluation frameworks, and baseline results, we hope to see the Meta-MolNet suite become a comprehensive resource for the AI-assisted drug discovery community. Meta-MolNet is freely accessible at https://github.com/lol88/Meta-MolNet. |
| WOS关键词 | MOLECULAR-PROPERTIES ; PREDICTION ; NETWORK |
| 资助项目 | National Natural Science Foundation of China |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:001164241200001 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://119.78.100.183/handle/2S10ELR8/309892]  |
| 专题 | 中国科学院上海药物研究所 |
| 通讯作者 | Chen, Calvin Yu-Chian |
| 作者单位 | 1.Asia Univ, Dept Bioinformat & Med Engn, Taichung 41354, Taiwan 2.China Med Univ Hosp, Dept Med Res, Taichung 40447, Taiwan 3.Peking Univ, Sch Elect & Comp Engn, Shenzhen Grad Sch, Shenzhen 518055, Guangdong, Peoples R China 4.Peking Univ, AI Sci Preferred Program AI4S, Shenzhen Grad Sch, Shenzhen 518055, Guangdong, Peoples R China 5.Chinese Acad Sci, Shanghai Inst Mat Med, Zhongshan Inst Drug Discovery, Zhongshan 528400, Peoples R China 6.Sun Yat Sen Univ, Artificial Intelligence Med Res Ctr, Sch Intelligent Syst Engn, Shenzhen Campus, Shenzhen 518107, Peoples R China |
| 推荐引用方式 GB/T 7714 | Lv, Qiujie,Chen, Guanxing,Yang, Ziduo,et al. Meta-MolNet: A Cross-Domain Benchmark for Few Examples Drug Discovery[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2024:15. |
| APA | Lv, Qiujie,Chen, Guanxing,Yang, Ziduo,Zhong, Weihe,&Chen, Calvin Yu-Chian.(2024).Meta-MolNet: A Cross-Domain Benchmark for Few Examples Drug Discovery.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,15. |
| MLA | Lv, Qiujie,et al."Meta-MolNet: A Cross-Domain Benchmark for Few Examples Drug Discovery".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2024):15. |
入库方式： OAI收割
来源：上海药物研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。