Year: 2026
Type: preprint
Abstract: Accurate molecular property prediction requires effective molecular representations that can describe a molecule from multiple complementary perspectives. Existing deep learning approaches typically use SMILES strings, two-dimensional molecular graphs, or three-dimensional conformations as inputs. These representations capture different aspects of molecular information: SMILES encodes a sequential description, molecular graphs describe atom-bond connectivity, and 3D conformations provide spatial information from atomic coordinates. However, these modalities are often learned separately or merged with low effective fusion operations, which may not sufficiently capture interactions among sequential, topological, and geometric features. In this work, we propose Tri-Modality Cross-Attention (TMCA), a multimodal framework that integrates 1D SMILES, 2D molecular graphs, and 3D molecular conformations for molecular property prediction. TMCA uses pretrained encoders for the 1D and 3D branches, with a SMILES-based Transformer for the 1D branch and a recent conformation-aware pretrained model for the 3D branch. At the same time, a trainable 2D graph encoder is designed to support modality fusion. All the parameters from the pretrained models are frozen to make overall training more efficient. We evaluate TMCA on four datasets (i.e., BBBP, BACE, ClinTox, and HIV) from the MoleculeNet database for classification tasks and compare its performance with state-of-the-art competing approaches. Experimental results show that TMCA achieves the best overall performance, demonstrating the value of multi-modality integration for drug property prediction and the effectiveness of our cross-attention-based fusion strategy. The source code of TMCA is available at: https://github.com/Ay-Zhao/TMCA.
Authors: Anyin Zhao, Jing Li
Institution: Case Western Reserve University
Language: English
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: FET: CCF: Small: Computational Drug Prediction through Joint Learning, RAPID:Genomic Variation Analysis of Coronavirus to Better Understand the Spread of COVID-19, PIPP Phase I: Comprehensive, Integrated, Intelligent System for Early and Accurate Pandemic Prediction, Prevention, and Preparation at Personal and Population Levels, Robust mapping of chromatin loops from sparse or single cell Hi-C data with DeepLoop, Alzheimer's MultiOme Data Repurposing: Artificial Intelligence, Network Medicine, and Therapeutics Discovery
OpenAlex ID: W7214605702