# DFusMol: predicting molecular properties based on dual-channel attention

## TL;DR

DFusMol is a new method for predicting molecular properties by combining atomic and motif-level information using a dual-channel attention mechanism, leading to improved accuracy in drug discovery.

## Contribution

DFusMol introduces a dual-channel attention framework that integrates atomic and motif-level features for enhanced molecular property prediction.

## Key findings

- DFusMol outperforms state-of-the-art models on six of nine benchmark datasets.
- The dual-channel attention mechanism effectively captures hierarchical molecular complexity.
- The method shows strong potential for drug design and lead compound screening.

## Abstract

Accurate molecular property prediction is fundamental to modern drug discovery and materials design. However, prevailing computational methods are often insufficient, as they rely on single-granularity structural representations that fail to capture the hierarchical complexity of molecular systems. To address this challenge, we propose a new approach to molecular representation learning that incorporates structural information across multiple scales. We design DFusMol (Dual Fusion with Global and Local Attention), a novel framework inspired by multi-modal learning. DFusMol employs graph encoders to capture features from both atomic-level molecular graphs and motif-level graphs derived from chemical rules. A customized global-local attention mechanism then blends these diverse features to build comprehensive molecular representations. Experiments on nine public benchmark datasets reveal that DFusMol delivers top-tier predictive performance across all tasks, outperforming state-of-the-art self-supervised learning models on six of them. By effectively integrating atomic- and motif-level information, DFusMol provides an innovative and efficient solution for molecular property prediction, enhancing representation learning methodologies and demonstrating strong potential for applications in drug design and lead compound screening.