Molecular property prediction by semantic-invariant contrastive learning.

Molecular property prediction by semantic-invariant contrastive learning.
复制标题

DOI:
10.1093/bioinformatics/btad462
复制
发表时间:
2023-08-01
期刊:
Bioinformatics (Oxford, England)
影响因子:
--
通讯作者:
--
中科院分区:
其他
文献类型:
--
作者:

文献摘要

参考文献

相似文献

在人工智能辅助药物设计和发现中,对比学习已被广泛用作自监督预训练分子表征学习模型的借口任务。然而,现有的通过添加噪声操作生成分子视图进行对比学习的方法可能面临语义不一致的问题,从而导致假阳性对,从而导致预测性能差。为了解决这个问题,在本文中,我们首先提出了一种语义不变的视图生成方法,通过适当地将分子图分解成片段对。然后,我们在此基础上开发了基于片段的语义不变对比学习(FraSICL)模型,用于分子性质预测。FraSICL模型由两个分支组成,用于生成视图的表示进行对比学习,同时引入多视图融合和辅助相似性损失,以更好地利用不同片段对视图中包含的信息。在各种基准数据集上进行的大量实验表明,与现有主要的同类模型相比,FraSICL可以使用最少的预训练样本达到最先进的性能。该代码可在https://github.com/ZiqiaoZhang/FraSICL上公开获得。
Contrastive learning has been widely used as pretext tasks for self-supervised pre-trained molecular representation learning models in AI-aided drug design and discovery. However, existing methods that generate molecular views by noise-adding operations for contrastive learning may face the semantic inconsistency problem, which leads to false positive pairs and consequently poor prediction performance. To address this problem, in this article, we first propose a semantic-invariant view generation method by properly breaking molecular graphs into fragment pairs. Then, we develop a Fragment-based Semantic-Invariant Contrastive Learning (FraSICL) model based on this view generation method for molecular property prediction. The FraSICL model consists of two branches to generate representations of views for contrastive learning, meanwhile a multi-view fusion and an auxiliary similarity loss are introduced to make better use of the information contained in different fragment-pair views. Extensive experiments on various benchmark datasets show that with the least number of pre-training samples, FraSICL can achieve state-of-the-art performance, compared with major existing counterpart models. The code is publicly available at https://github.com/ZiqiaoZhang/FraSICL.
DOI: 10.1039/c7sc02664a
发表时间: 2018-01-14
期刊: Chemical science
影响因子: 8.4
作者:
Wu Z;Ramsundar B;Feinberg EN;Gomes J;Geniesse C;Pappu AS;Leswing K;Pande V
通讯作者: Pande V
DOI: 10.1021/acs.jcim.0c00675
发表时间: 2020-12-28
影响因子: 5.6
作者:
Irwin JJ;Tang KG;Young J;Dandarchuluun C;Wong BR;Khurelbaatar M;Moroz YS;Mayfield J;Sayle RA
通讯作者: Sayle RA
DOI: 10.1093/nar/gkw1074
发表时间: 2017-01-04
影响因子: 14.9
作者:
Gaulton A;Hersey A;Nowotka M;Bento AP;Chambers J;Mendez D;Mutowo P;Atkinson F;Bellis LJ;Cibrián-Uhalte E;Davies M;Dedman N;Karlsson A;Magariños MP;Overington JP;Papadatos G;Smit I;Leach AR
通讯作者: Leach AR
DOI: 10.1021/acs.jmedchem.9b00959
发表时间: 2020-08-27
影响因子: 7.3
作者:
Xiong, Zhaoping;Wang, Dingyan;Zheng, Mingyue
通讯作者: Zheng, Mingyue
DOI: 10.1021/ci00057a005
发表时间: 1988-02-01
期刊: JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES
影响因子: --
作者:
WEININGER, D
通讯作者: WEININGER, D