Cross-view Contrastive Unification Guides Generative Pretraining for Molecular Property Prediction

Junyu Lin, Yan Zheng, Xinyue Chen, Yazhou Ren, Xiaorong Pu, Jing He

Abstract: Multi-view based molecular properties prediction learning has received widely attention in recent years in terms of its potential for the downstream tasks in the field of drug discovery. However, the consistency of different molecular view representations and the full utilization of complementary information among them in existing multi-view molecular property prediction methods remain to be further explored. Furthermore, most current methods focus on generating global level representations at the graph level with information from different molecular views (e.g., 2D and 3D views) assuming that the information can be corresponded to each other. In fact it is not unusual that for example the conformation change or computational errors may lead to discrepancies between views. To addressing these issues, we propose a new Cross-View contrastive unification guides Generative Molcular pre-trained model, call MolCVG. We first focus on common and private information extraction from 2D graph views and 3D geometric views of molecules, Minimizing the impact of noise in private information on subsequent strategies. To exploit both types of information in a more refined way, we propose a cross-view contrastive unification strategy to learn cross-view global information and guide the reconstruction of masked nodes, thus effectively optimizing global features and local descriptions. Extensive experiments on real-world molecular data sets demonstrate the effectiveness of our approach for molecular property prediction task.

Primary Subject Area: [Content] Multimodal Fusion

Relevance To Conference: Our contributions in this work are as follows: (1) We propose a new multi-view learning method for molecular property prediction called MolCVG. It deeply unites molecular 2d topological views and 3d geometric views to mine effective features. (2) To the best of our knowledge, we are the first to propose molecular cross-view contrastive unification to guide node-level generative pretraining tasks. While ensuring that overall consistency is fully emphasized, we also focus on learning local detailed features. (3) In MolCVG, we introduce the Common and Private Information Separation strategy to better capture molecular universality pattern and differences between molecular views. (4) Extensive experiments demonstrate the effectiveness of MolCVG, achieving superior performance on multiple molecular property prediction benchmark datasets.

Submission Number: 2970