metadata
license: mit
InstructBioMol: A Multimodal LLM for Biomolecule Understanding and Design
Paper • Project • Quickstart • Citation
Model Description
InstructBioMol is a multimodal large language model that bridges natural language with biomolecules (proteins and small molecules). It achieves any-to-any alignment between natural language, molecules, and proteins through comprehensive instruction tuning.
For detailed information, please refer to our paper and code repository.
Released Variants
| Model Name | Stage | Multimodal | Description |
|---|---|---|---|
| InstructBioMol-base | Pretraining | ❎ | Continual pretrained model on molecular sequences, protein sequences, and scientific literature. |
| InstructBioMol-instruct-stage1 | Instruction tuning (stage 1) | ✅ | Stage1 instruction-tuned model with biomolecular multimodal processing capabilities. (e.g., 3D molecules/proteins) |
| InstructBioMol-instruct (This Model) | Instruction tuning (stage 1 and 2) | ✅ | Fully instruction-tuned model (stage1 & stage2) with biomolecular multimodal processing capabilities (e.g., 3D molecules/proteins) |
Training Details
Base Architecture: InstructBioMol-instruct-stage1
Training Data:
1. Molecule - Natural Language Alignment:
- 52K data from chebi
2. Protein - Natural Langauge Alignment:
- 2 million data from UniProt (Swiss-Prot)
3. Molecule - Protein Alignment:
- 1 million data from BindingDB and Rhea
Training Objective: Instruction tuning
Citation
@article{zhuang2025advancing,
author = {Xiang Zhuang and
Keyan Ding and
Tianwen Lyu and
Yinuo Jiang and
Xiaotong Li and
Zhuoyi Xiang and
Zeyuan Wang and
Ming Qin and
Kehua Feng and
Jike Wang and
Qiang Zhang and
Huajun Chen},
title={Advancing biomolecular understanding and design following human instructions},
journal={Nature Machine Intelligence},
pages={1--14},
year={2025},
publisher={Nature Publishing Group UK London}
}