Learning Hierarchical Interaction for Accurate Molecular Property Prediction
Author:
Preprint
- 30 May 2025
- preprint
- Published by Springer Nature in Research Square
Abstract
Discovering molecules with desirable molecular properties, including ADMET profiles, is of great importance in drug discovery. Existing approaches typically employ deep learning models, such as Graph Neural Networks and Transformers, to predict these molecular properties by learning from diverse chemical information. However, these models often lack mechanisms for effective interaction among multi-level features. To address these limitations, we propose a Hierarchical Interaction Message Passing Mechanism, which serves as the foundation of our novel model, the Hierarchical Interaction Message Net (HimNet). Our method enables interaction-aware representation learning across atomic, motif, and molecular levels via hierarchical attention-guided message passing. This design allows HimNet to effectively balance global and local information, ensuring rich and task-relevant feature extraction for downstream property prediction tasks. We systematically evaluate HimNet on eleven datasets, including eight widely-used MoleculeNet benchmarks and three challenging, high-value datasets for metabolic stability, malaria activity, and liver microsomal clearance, covering a broad range of pharmacologically relevant properties. Extensive experiments demonstrate that HimNet achieves the best or near-best performance in most molecular property prediction tasks. We believe that HimNet offers an accurate and efficient solution for molecular activity and ADMET property prediction, contributing significantly to advanced decision-making in the early stages of drug discovery.Keywords
All Related Versions
- Version 1, 2025-05-30, Research Square
- Published version: Communications Chemistry, 9 (1).
This publication has 12 references indexed in Scilit:
- Analyzing Learned Molecular Representations for Property PredictionJournal of Chemical Information and Modeling, 2019
- Innovation in the pharmaceutical industry: New estimates of R&D costsJournal of Health Economics, 2016
- On the Art of Compiling and Using 'Drug‐Like' Chemical Fragment SpacesChemMedChem, 2008
- In silico pharmacology for drug discovery: methods for virtual ligand screening and profilingBritish Journal of Pharmacology, 2007
- Interfaces and the driving force of hydrophobic assemblyNature, 2005
- Reoptimization of MDL Keys for Use in Drug DiscoveryJournal of Chemical Information and Computer Sciences, 2002
- Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings 1PII of original article: S0169-409X(96)00423-1. The article was originally published in Advanced Drug Delivery Reviews 23 (1997) 3–25. 1Advanced Drug Delivery Reviews, 2001
- Fast Calculation of Molecular Polar Surface Area as a Sum of Fragment-Based Contributions and Its Application to the Prediction of Drug Transport PropertiesJournal of Medicinal Chemistry, 2000
- SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rulesJournal of Chemical Information and Computer Sciences, 1988
- Atom pairs as molecular features in structure-activity studies: definition and applicationsJournal of Chemical Information and Computer Sciences, 1985