HimGNN: a novel hierarchical molecular graph representation learning framework for property prediction

分子图 计算机科学 主题(音乐) 图形 理论计算机科学 人工智能 特征学习 相互依存 代表(政治) 机器学习 拓扑(电路) 数学 物理 组合数学 声学 政治学 法学 政治
作者
Seungbaek Han,Hongchao Fu,Yuyang Wu,G. Zhao,Zhenyu Song,Feng Huang,Zhongfei Zhang,Shichao Liu,Wen Zhang
出处
期刊:Briefings in Bioinformatics [Oxford University Press]
卷期号:24 (5)
标识
DOI:10.1093/bib/bbad305
摘要

Abstract Accurate prediction of molecular properties is an important topic in drug discovery. Recent works have developed various representation schemes for molecular structures to capture different chemical information in molecules. The atom and motif can be viewed as hierarchical molecular structures that are widely used for learning molecular representations to predict chemical properties. Previous works have attempted to exploit both atom and motif to address the problem of information loss in single representation learning for various tasks. To further fuse such hierarchical information, the correspondence between learned chemical features from different molecular structures should be considered. Herein, we propose a novel framework for molecular property prediction, called hierarchical molecular graph neural networks (HimGNN). HimGNN learns hierarchical topology representations by applying graph neural networks on atom- and motif-based graphs. In order to boost the representational power of the motif feature, we design a Transformer-based local augmentation module to enrich motif features by introducing heterogeneous atom information in motif representation learning. Besides, we focus on the molecular hierarchical relationship and propose a simple yet effective rescaling module, called contextual self-rescaling, that adaptively recalibrates molecular representations by explicitly modelling interdependencies between atom and motif features. Extensive computational experiments demonstrate that HimGNN can achieve promising performances over state-of-the-art baselines on both classification and regression tasks in molecular property prediction.
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
大幅提高文件上传限制,最高150M (2024-4-1)

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
srrrrr完成签到,获得积分10
4秒前
5秒前
ki发布了新的文献求助10
6秒前
童童童发布了新的文献求助10
11秒前
11秒前
Owen应助YY-Bubble采纳,获得10
12秒前
很好发布了新的文献求助10
12秒前
srrrrr发布了新的文献求助10
13秒前
今后应助白泽采纳,获得10
15秒前
16秒前
17秒前
稳重书双发布了新的文献求助10
21秒前
草拟大坝应助加了个可采纳,获得10
21秒前
竹园发布了新的文献求助30
22秒前
wddfz发布了新的文献求助30
22秒前
lizzie发布了新的文献求助10
23秒前
Jasper应助走廊邓采纳,获得30
24秒前
25秒前
27秒前
搜集达人应助池呀采纳,获得10
27秒前
28秒前
白泽发布了新的文献求助10
29秒前
通天塔发布了新的文献求助10
31秒前
Baekkk发布了新的文献求助10
32秒前
很好完成签到,获得积分20
33秒前
haoliu完成签到,获得积分10
35秒前
Jj7完成签到,获得积分10
36秒前
36秒前
可爱的函函应助白泽采纳,获得10
37秒前
coucou完成签到,获得积分10
38秒前
41秒前
呐殇发布了新的文献求助10
42秒前
英姑应助chenxi采纳,获得10
42秒前
wanci应助通天塔采纳,获得10
45秒前
45秒前
infinite完成签到,获得积分10
45秒前
阳佟人达发布了新的文献求助10
47秒前
cctv18应助细心铅笔采纳,获得10
48秒前
xiweier完成签到,获得积分10
49秒前
49秒前
高分求助中
Manual of Clinical Microbiology, 4 Volume Set (ASM Books) 13th Edition 1000
Teaching Social and Emotional Learning in Physical Education 900
Boris Pesce - Gli impiegati della Fiat dal 1955 al 1999 un percorso nella memoria 500
Chinese-English Translation Lexicon Version 3.0 500
Recherches Ethnographiques sue les Yao dans la Chine du Sud 500
Two-sample Mendelian randomization analysis reveals causal relationships between blood lipids and venous thromboembolism 500
[Lambert-Eaton syndrome without calcium channel autoantibodies] 460
热门求助领域 (近24小时)
化学 材料科学 医学 生物 有机化学 工程类 生物化学 纳米技术 物理 内科学 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 电极 光电子学 量子力学
热门帖子
关注 科研通微信公众号,转发送积分 2397676
求助须知:如何正确求助?哪些是违规求助? 2099174
关于积分的说明 5291577
捐赠科研通 1827050
什么是DOI,文献DOI怎么找? 910694
版权声明 560023
科研通“疑难数据库(出版商)”最低求助积分说明 486765