InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery
This work addresses the problem of building a versatile and reliable AI assistant for drug discovery researchers, though it appears incremental as it builds on existing LLM and multi-modal approaches.
The authors tackled the challenge of generalization and extensive training in AI for drug discovery by developing InstructMol, a multi-modal LLM that aligns molecular structures with natural language, resulting in substantial performance improvements in molecular tasks and reducing the gap with specialized models.
The rapid evolution of artificial intelligence in drug discovery encounters challenges with generalization and extensive training, yet Large Language Models (LLMs) offer promise in reshaping interactions with complex molecular data. Our novel contribution, InstructMol, a multi-modal LLM, effectively aligns molecular structures with natural language via an instruction-tuning approach, utilizing a two-stage training strategy that adeptly combines limited domain-specific data with molecular and textual information. InstructMol showcases substantial performance improvements in drug discovery-related molecular tasks, surpassing leading LLMs and significantly reducing the gap with specialized models, thereby establishing a robust foundation for a versatile and dependable drug discovery assistant.