Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2411.15692 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912259481010176 |
|---|---|
| author | Liu, Sizhe Lu, Yizhou Chen, Siyu Hu, Xiyang Zhao, Jieyu Lu, Yingzhou Zhao, Yue |
| author_facet | Liu, Sizhe Lu, Yizhou Chen, Siyu Hu, Xiyang Zhao, Jieyu Lu, Yingzhou Zhao, Yue |
| contents | Recent progress in Large Language Models (LLMs) has drawn attention to their potential for accelerating drug discovery. However, a central problem remains: translating theoretical ideas into robust implementations in the highly specialized context of pharmaceutical research. This limitation prevents practitioners from making full use of the latest AI developments in drug discovery. To address this challenge, we introduce DrugAgent, a multi-agent framework that automates machine learning (ML) programming for drug discovery tasks. DrugAgent employs an LLM Planner that formulates high-level ideas and an LLM Instructor that identifies and integrates domain knowledge when implementing those ideas. We present case studies on three representative drug discovery tasks. Our results show that DrugAgent consistently outperforms leading baselines, including a relative improvement of 4.92% in ROC-AUC compared to ReAct for drug-target interaction (DTI). DrugAgent is publicly available at https://anonymous.4open.science/r/drugagent-5C42/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_15692 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaboration Liu, Sizhe Lu, Yizhou Chen, Siyu Hu, Xiyang Zhao, Jieyu Lu, Yingzhou Zhao, Yue Machine Learning Recent progress in Large Language Models (LLMs) has drawn attention to their potential for accelerating drug discovery. However, a central problem remains: translating theoretical ideas into robust implementations in the highly specialized context of pharmaceutical research. This limitation prevents practitioners from making full use of the latest AI developments in drug discovery. To address this challenge, we introduce DrugAgent, a multi-agent framework that automates machine learning (ML) programming for drug discovery tasks. DrugAgent employs an LLM Planner that formulates high-level ideas and an LLM Instructor that identifies and integrates domain knowledge when implementing those ideas. We present case studies on three representative drug discovery tasks. Our results show that DrugAgent consistently outperforms leading baselines, including a relative improvement of 4.92% in ROC-AUC compared to ReAct for drug-target interaction (DTI). DrugAgent is publicly available at https://anonymous.4open.science/r/drugagent-5C42/. |
| title | DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaboration |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2411.15692 |