MoltiTox: a multimodal fusion model for molecular toxicity prediction.

ABSTRACT:

Introduction

We introduce MoltiTox, a novel multimodal fusion model for molecular toxicity prediction, designed to overcome the limitations of single-modality approaches in drug discovery.

Methods

MoltiTox integrates four complementary data types: molecular graphs, SMILES strings, 2D images, and ¹³C NMR spectra. The model processes these inputs using four modality-specific encoders, including a GNN, a Transformer, a 2D CNN, and a 1D CNN. These heterogeneous embeddings are fused through an attention-based mechanism, enabling the model to capture complementary structural and chemical information from multiple molecular perspectives.

Results

Evaluated on the Tox21 benchmark across 12 endpoints, MoltiTox achieves a ROC-AUC of 0.831, outperforming all single-mod

SUBMITTER: Park J 

PROVIDER: S-EPMC12756560 | biostudies-literature | 2025

REPOSITORIES: biostudies-literature