MolFusion: Multimodal Fusion Learning for Molecular Representations via Multi-granularity Views

TL;DR

MolFusion is a novel multimodal fusion method that aligns molecular representations at both molecular and atomic levels, significantly improving drug property prediction accuracy by effectively leveraging complementary information from different molecular views.

Contribution

The paper introduces MolFusion, a multi-granularity fusion approach that aligns molecular and atomic features across modalities, addressing limitations of previous methods that only used molecular-level information.

Findings

MolFusion outperforms existing methods on multiple drug property prediction tasks.

The approach effectively captures intra-molecular alignment information.

Experimental results demonstrate significant performance improvements.

Abstract

Artificial Intelligence predicts drug properties by encoding drug molecules, aiding in the rapid screening of candidates. Different molecular representations, such as SMILES and molecule graphs, contain complementary information for molecular encoding. Thus exploiting complementary information from different molecular representations is one of the research priorities in molecular encoding. Most existing methods for combining molecular multi-modalities only use molecular-level information, making it hard to encode intra-molecular alignment information between different modalities. To address this issue, we propose a multi-granularity fusion method that is MolFusion. The proposed MolFusion consists of two key components: (1) MolSim, a molecular-level encoding component that achieves molecular-level alignment between different molecular representations. and (2) AtomAlign, an atomic-level encoding component that achieves atomic-level alignment between different molecular representations. Experimental results show that MolFusion effectively utilizes complementary multimodal information, leading to significant improvements in performance across various classification and regression tasks.