Uni-Mol3: A Multi-Molecular Foundation Model for Advancing Organic Reaction Modeling

2025-07-29

AI Summary

Modeling organic reactions faces challenges in capturing complex multi-molecule relational dependencies and achieving deep mechanistic understanding. Method: We propose the first foundational pre-trained model specifically designed for multi-molecule systems. Our approach introduces a hierarchical learning framework coupled with a multi-scale 3D molecular tokenizer, establishing the first geometry-aware molecular language system. We further design a two-stage pre-training paradigm—operating at both molecular and reaction levels—and incorporate prompt-aware fine-tuning and cross-task transfer strategies. Contribution/Results: Evaluated on ten benchmark datasets spanning four reaction prediction tasks—reaction classification, condition prediction, retrosynthesis, and more—the model consistently outperforms state-of-the-art methods, delivering significant improvements in prediction accuracy and generalization. These results demonstrate its capacity to effectively capture intricate organic reaction mechanisms and intermolecular interactions.

Technology Category

• Machine Learning: Multimodal Learning
• Multiagent Systems: Multiagent Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Organic reaction, the foundation of modern chemical industry, is crucial for new material development and drug discovery. However, deciphering reaction mechanisms and modeling multi-molecular relationships remain formidable challenges due to the complexity of molecular dynamics. While several state-of-the-art models like Uni-Mol2 have revolutionized single-molecular representation learning, their extension to multi-molecular systems, where chemical reactions inherently occur, has been underexplored. This paper introduces Uni-Mol3, a novel deep learning framework that employs a hierarchical pipeline for multi-molecular reaction modeling. At its core, Uni-Mol3 adopts a multi-scale molecular tokenizer (Mol-Tokenizer) that encodes 3D structures of molecules and other features into discrete tokens, creating a 3D-aware molecular language. The framework innovatively combines two pre-training stages: molecular pre-training to learn the molecular grammars and reaction pre-training to capture fundamental reaction principles, forming a progressive learning paradigm from single- to multi-molecular systems. With prompt-aware downstream fine-tuning, Uni-Mol3 demonstrates exceptional performance in diverse organic reaction tasks and supports multi-task prediction with strong generalizability. Experimental results across 10 datasets spanning 4 downstream tasks show that Uni-Mol3 outperforms existing methods, validating its effectiveness in modeling complex organic reactions. This work not only ushers in an alternative paradigm for multi-molecular computational modeling but also charts a course for intelligent organic reaction by bridging molecular representation with reaction mechanism understanding.

Problem

• Modeling complex multi-molecular organic reaction mechanisms
• Extending single-molecular representation to multi-molecular systems
• Bridging 3D molecular structures with reaction principles

Innovation

• Hierarchical pipeline for multi-molecular reaction modeling
• Multi-scale molecular tokenizer encoding 3D structures
• Two-stage pre-training for molecular and reaction principles