Molecular Contrastive Learning with Chemical Element Knowledge Graph

分子图 计算机科学 编码 图形 理论计算机科学 知识图 编码器 特征学习 领域知识 代表(政治) 人工智能 自然语言处理 化学 政治 基因 操作系统 法学 生物化学 政治学
作者
Fang‐Fang Yin,Qiang Zhang,Hengquan Yang,Xiang Zhuang,Shumin Deng,Wen Zhang,Ming Qin,Zhuo Chen,Xiaohui Fan,Huajun Chen
出处
期刊:Cornell University - arXiv
标识
DOI:10.48550/arxiv.2112.00544
摘要

Molecular representation learning contributes to multiple downstream tasks such as molecular property prediction and drug design. To properly represent molecules, graph contrastive learning is a promising paradigm as it utilizes self-supervision signals and has no requirements for human annotations. However, prior works fail to incorporate fundamental domain knowledge into graph semantics and thus ignore the correlations between atoms that have common attributes but are not directly connected by bonds. To address these issues, we construct a Chemical Element Knowledge Graph (KG) to summarize microscopic associations between elements and propose a novel Knowledge-enhanced Contrastive Learning (KCL) framework for molecular representation learning. KCL framework consists of three modules. The first module, knowledge-guided graph augmentation, augments the original molecular graph based on the Chemical Element KG. The second module, knowledge-aware graph representation, extracts molecular representations with a common graph encoder for the original molecular graph and a Knowledge-aware Message Passing Neural Network (KMPNN) to encode complex information in the augmented molecular graph. The final module is a contrastive objective, where we maximize agreement between these two views of molecular graphs. Extensive experiments demonstrated that KCL obtained superior performances against state-of-the-art baselines on eight molecular datasets. Visualization experiments properly interpret what KCL has learned from atoms and attributes in the augmented molecular graphs. Our codes and data are available at https://github.com/ZJU-Fangyin/KCL.

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
雨兔儿完成签到,获得积分10
刚刚
刚刚
斯文败类应助赵星瑶采纳,获得10
1秒前
1秒前
12完成签到,获得积分10
1秒前
2秒前
斯文败类应助wangjing11采纳,获得10
3秒前
霜霜完成签到,获得积分10
3秒前
4秒前
4秒前
yiyi发布了新的文献求助30
5秒前
chenyuyuan完成签到,获得积分10
5秒前
赘婿应助酷笑采纳,获得10
5秒前
5秒前
5秒前
6秒前
liminghao发布了新的文献求助30
6秒前
6秒前
wpf7848发布了新的文献求助10
7秒前
Candy发布了新的文献求助30
7秒前
tachang完成签到,获得积分10
7秒前
鱼洞完成签到,获得积分10
8秒前
冷艳的半凡完成签到,获得积分10
8秒前
腾飞完成签到,获得积分10
9秒前
所所应助konglingjie采纳,获得10
10秒前
无所谓666发布了新的文献求助10
11秒前
wanci应助有魅力老头采纳,获得10
11秒前
11秒前
赘婿应助有魅力老头采纳,获得10
11秒前
慕青应助有魅力老头采纳,获得10
11秒前
科目三应助有魅力老头采纳,获得10
11秒前
充电宝应助有魅力老头采纳,获得10
11秒前
隐形曼青应助有魅力老头采纳,获得10
11秒前
小马甲应助有魅力老头采纳,获得10
11秒前
慕青应助有魅力老头采纳,获得10
12秒前
研友_VZG7GZ应助有魅力老头采纳,获得10
12秒前
川川发布了新的文献求助10
12秒前
yiyi完成签到,获得积分10
13秒前
暴躁的马里奥完成签到,获得积分10
13秒前
13秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
List of 1,091 Public Pension Profiles by Region 1581
以液相層析串聯質譜法分析糖漿產品中活性雙羰基化合物 / 吳瑋元[撰] = Analysis of reactive dicarbonyl species in syrup products by LC-MS/MS / Wei-Yuan Wu 1000
Biology of the Reptilia. Volume 21. Morphology I. The Skull and Appendicular Locomotor Apparatus of Lepidosauria 600
The Scope of Slavic Aspect 600
Foregrounding Marking Shift in Sundanese Written Narrative Segments 600
Rousseau, le chemin de ronde 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 纳米技术 计算机科学 内科学 化学工程 复合材料 物理化学 基因 遗传学 催化作用 冶金 量子力学 光电子学
热门帖子
关注 科研通微信公众号,转发送积分 5540561
求助须知:如何正确求助?哪些是违规求助? 4627197
关于积分的说明 14602739
捐赠科研通 4568254
什么是DOI,文献DOI怎么找? 2504430
邀请新用户注册赠送积分活动 1482011
关于科研通互助平台的介绍 1453645