Back

A Unified Multi-modal LLM for Dynamic Protein-Ligand Interactions and Generative Molecular Design

Jing, H.; Miao, Y.

2025-12-03 bioinformatics
10.64898/2025.12.01.691647 bioRxiv
Show abstract

BioDynaGen (Biological Dynamics and Generation) is a novel multi-modal framework unifying protein sequences, dynamic binding site conformations, small molecule ligand SMILES, and natural language text into a single discrete token representation. Built upon a general large language model, BioDynaGen employs continuous pre-training and instruction fine-tuning via next-token prediction to address critical gaps in modeling protein dynamics and ligand interactions. This framework enables a diverse range of tasks, including small molecule-protein binding prediction, dynamic pocket design, and ligand-assisted functional generation. By comprehensively integrating these modalities, BioDynaGen offers an advanced framework for understanding and designing complex biological molecular interactions.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.