Bi-level Contrastive Learning for Knowledge-Enhanced Molecule Representations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Pengcheng, Xiao, Cao, Fu, Tianfan, Bhatia, Parminder, Kass-Hout, Taha, Sun, Jimeng, Han, Jiawei
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910829173014528
author Jiang, Pengcheng
Xiao, Cao
Fu, Tianfan
Bhatia, Parminder
Kass-Hout, Taha
Sun, Jimeng
Han, Jiawei
author_facet Jiang, Pengcheng
Xiao, Cao
Fu, Tianfan
Bhatia, Parminder
Kass-Hout, Taha
Sun, Jimeng
Han, Jiawei
contents Molecular representation learning is vital for various downstream applications, including the analysis and prediction of molecular properties and side effects. While Graph Neural Networks (GNNs) have been a popular framework for modeling molecular data, they often struggle to capture the full complexity of molecular representations. In this paper, we introduce a novel method called GODE, which accounts for the dual-level structure inherent in molecules. Molecules possess an intrinsic graph structure and simultaneously function as nodes within a broader molecular knowledge graph. GODE integrates individual molecular graph representations with multi-domain biochemical data from knowledge graphs. By pre-training two GNNs on different graph structures and employing contrastive learning, GODE effectively fuses molecular structures with their corresponding knowledge graph substructures. This fusion yields a more robust and informative representation, enhancing molecular property predictions by leveraging both chemical and biological information. When fine-tuned across 11 chemical property tasks, our model significantly outperforms existing benchmarks, achieving an average ROC-AUC improvement of 12.7% for classification tasks and an average RMSE/MAE improvement of 34.4% for regression tasks. Notably, GODE surpasses the current leading model in property prediction, with advancements of 2.2% in classification and 7.2% in regression tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2306_01631
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Bi-level Contrastive Learning for Knowledge-Enhanced Molecule Representations
Jiang, Pengcheng
Xiao, Cao
Fu, Tianfan
Bhatia, Parminder
Kass-Hout, Taha
Sun, Jimeng
Han, Jiawei
Machine Learning
Artificial Intelligence
Quantitative Methods
Molecular representation learning is vital for various downstream applications, including the analysis and prediction of molecular properties and side effects. While Graph Neural Networks (GNNs) have been a popular framework for modeling molecular data, they often struggle to capture the full complexity of molecular representations. In this paper, we introduce a novel method called GODE, which accounts for the dual-level structure inherent in molecules. Molecules possess an intrinsic graph structure and simultaneously function as nodes within a broader molecular knowledge graph. GODE integrates individual molecular graph representations with multi-domain biochemical data from knowledge graphs. By pre-training two GNNs on different graph structures and employing contrastive learning, GODE effectively fuses molecular structures with their corresponding knowledge graph substructures. This fusion yields a more robust and informative representation, enhancing molecular property predictions by leveraging both chemical and biological information. When fine-tuned across 11 chemical property tasks, our model significantly outperforms existing benchmarks, achieving an average ROC-AUC improvement of 12.7% for classification tasks and an average RMSE/MAE improvement of 34.4% for regression tasks. Notably, GODE surpasses the current leading model in property prediction, with advancements of 2.2% in classification and 7.2% in regression tasks.
title Bi-level Contrastive Learning for Knowledge-Enhanced Molecule Representations
topic Machine Learning
Artificial Intelligence
Quantitative Methods
url https://arxiv.org/abs/2306.01631