Advancing biomolecular understanding and design following human instructions

Abstract

Understanding and designing biomolecules, such as proteins and small molecules, is central to advancing drug discovery, synthetic biology and enzyme engineering. Recent breakthroughs in artificial intelligence have revolutionized biomolecular research, achieving remarkable accuracy in biomolecular prediction and design. However, a critical gap remains between artificial intelligence's computational capabilities and researchers' intuitive goals, particularly in using natural language to bridge complex tasks with human intentions. Large language models have shown potential to interpret human intentions, yet their application to biomolecular research remains nascent due to challenges including specialized knowledge requirements, multimodal data integration, and semantic alignment between natural language and biomolecules. To address these limitations, we present InstructBioMol, a large language model designed to bridge natural language and biomolecules through a comprehensive any-to-any alignment of natural language, molecules and proteins. This model can integrate multimodal biomolecules as the input, and enable researchers to articulate design goals in natural language, providing biomolecular outputs that meet precise biological needs. Experimental results demonstrate that InstructBioMol can understand and design biomolecules following human instructions. In particular, it can generate drug molecules with a 10% improvement in binding affinity and design enzymes that achieve an enzyme-substrate pair prediction score of 70.4. This highlights its potential to transform real-world biomolecular research. The code is available at https://github.com/HICAI-ZJU/InstructBioMol.

References in corpus (13)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Training language models to follow instructions with human feedback
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• Self-Referencing Embedded Strings (SELFIES): A 100% robust molecular string representation
• 3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction
• Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets
• Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective
• Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models
• Scientific Large Language Models: A Survey on Biological & Chemical Domains
• BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine
• Deep Confident Steps to New Pockets: Strategies for Docking Generalization
• A Text-guided Protein Design Framework
• MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space