BioAgents: Democratizing Bioinformatics Analysis with Multi-Agent Systems
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910780652257280 |
|---|---|
| author | Mehandru, Nikita Hall, Amanda K. Melnichenko, Olesya Dubinina, Yulia Tsirulnikov, Daniel Bamman, David Alaa, Ahmed Saponas, Scott Malladi, Venkat S. |
| author_facet | Mehandru, Nikita Hall, Amanda K. Melnichenko, Olesya Dubinina, Yulia Tsirulnikov, Daniel Bamman, David Alaa, Ahmed Saponas, Scott Malladi, Venkat S. |
| contents | Creating end-to-end bioinformatics workflows requires diverse domain expertise, which poses challenges for both junior and senior researchers as it demands a deep understanding of both genomics concepts and computational techniques. While large language models (LLMs) provide some assistance, they often fall short in providing the nuanced guidance needed to execute complex bioinformatics tasks, and require expensive computing resources to achieve high performance. We thus propose a multi-agent system built on small language models, fine-tuned on bioinformatics data, and enhanced with retrieval augmented generation (RAG). Our system, BioAgents, enables local operation and personalization using proprietary data. We observe performance comparable to human experts on conceptual genomics tasks, and suggest next steps to enhance code generation capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_06314 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | BioAgents: Democratizing Bioinformatics Analysis with Multi-Agent Systems Mehandru, Nikita Hall, Amanda K. Melnichenko, Olesya Dubinina, Yulia Tsirulnikov, Daniel Bamman, David Alaa, Ahmed Saponas, Scott Malladi, Venkat S. Artificial Intelligence Multiagent Systems Creating end-to-end bioinformatics workflows requires diverse domain expertise, which poses challenges for both junior and senior researchers as it demands a deep understanding of both genomics concepts and computational techniques. While large language models (LLMs) provide some assistance, they often fall short in providing the nuanced guidance needed to execute complex bioinformatics tasks, and require expensive computing resources to achieve high performance. We thus propose a multi-agent system built on small language models, fine-tuned on bioinformatics data, and enhanced with retrieval augmented generation (RAG). Our system, BioAgents, enables local operation and personalization using proprietary data. We observe performance comparable to human experts on conceptual genomics tasks, and suggest next steps to enhance code generation capabilities. |
| title | BioAgents: Democratizing Bioinformatics Analysis with Multi-Agent Systems |
| topic | Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2501.06314 |