TRIDENT: Tri-Modal Molecular Representation Learning with Taxonomic Annotations and Local Correspondence

TL;DR

TRIDENT is a multimodal framework that integrates molecular structures, textual descriptions, and taxonomic annotations to improve molecular property prediction by aligning features at both global and local levels.

Contribution

It introduces a novel tri-modal learning approach with a volume-based and local alignment strategy, utilizing a curated dataset and a dynamic balancing mechanism.

Findings

Achieves state-of-the-art results on 11 downstream tasks.

Effectively captures both broad and fine-grained structure-function relationships.

Demonstrates the benefit of integrating textual and taxonomic information in molecular representations.

Abstract

Molecular property prediction aims to learn representations that map chemical structures to functional properties. While multimodal learning has emerged as a powerful paradigm to learn molecular representations, prior works have largely overlooked textual and taxonomic information of molecules for representation learning. We introduce TRIDENT, a novel framework that integrates molecular SMILES, textual descriptions, and taxonomic functional annotations to learn rich molecular representations. To achieve this, we curate a comprehensive dataset of molecule-text pairs with structured, multi-level functional annotations. Instead of relying on conventional contrastive loss, TRIDENT employs a volume-based alignment objective to jointly align tri-modal features at the global level, enabling soft, geometry-aware alignment across modalities. Additionally, TRIDENT introduces a novel local alignment objective that captures detailed relationships between molecular substructures and their corresponding sub-textual descriptions. A momentum-based mechanism dynamically balances global and local alignment, enabling the model to learn both broad functional semantics and fine-grained structure-function mappings. TRIDENT achieves state-of-the-art performance on 11 downstream tasks, demonstrating the value of combining SMILES, textual, and taxonomic functional annotations for molecular property prediction.