InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929638564954112 |
|---|---|
| author | Cao, He Liu, Zijing Lu, Xingyu Yao, Yuan Li, Yu |
| author_facet | Cao, He Liu, Zijing Lu, Xingyu Yao, Yuan Li, Yu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_16208 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery Cao, He Liu, Zijing Lu, Xingyu Yao, Yuan Li, Yu Biomolecules Artificial Intelligence Machine Learning 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. |
| title | InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery |
| topic | Biomolecules Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2311.16208 |