A platform for the biomedical application of large language models (2025, Nat. Biotech.)

https://www.nature.com/articles/s41587-024-02534-3  

쉽게 LLM을 이용해 나만의 생명의료 소프트웨어를 만들 수 있는 플랫폼.

 

LLM을 이용한 바이오인포 연구에 관심이 있어, 이 플랫폼을 활용할 수 있을지, 플랫폼을 통하지 않고 개발하는 것에 비해 어떤 장단점이 있는지 알아봐야 겠다는 생각이 들었다.

LLM을 활용한 연구 장벽을 낮추려는 시도 자체도 흥미로움. 앞으로 이 쪽으로 더 많은 시도가 있을 것 같다.     

 

 

 

To bridge the gap between complex custom solutions and closed-source commercial platforms, we present BioChatter (https://biochatter.org), an open-source Python framework designed to develop custom biomedical research software in line with open science principles5. 

<The two main avenues for using large language models (LLMs) & Limitations>

1. End-user-ready platforms - provided by large corporations

• do not meet the transparency standards required for reproducible research
• privacy concerns
• considerable commercial pressures
• not fully customizable to accommodate a specific research domain or workflow.

2. Custom solutions - developed by individual researchers with programming knowledge. 

• not accessible to most biomedical researchers.  require many specialized skills

-> Applications of LLMs in biomedical research are still at the level of individual case studies2,4, in contrast to the imaging domain, which boasts several open-source AI frameworks and approved medical devices1.

 

 

Our ultimate aim is to harmonize APIs not only for LLMs but across the entire scientific knowledge management ecosystem. This includes everything from extraction of information from text and images, through knowledge representation, to the application of this knowledge in decision-making, data analysis, hypothesis generation and scientific communication. We focus on facilitating research tasks that are manual and repetitive, freeing up more time for creative thinking and complex reasoning4. 

 

We have initiated projects to tackle challenges in research software support, knowledge management, publishing and large-scale drug discovery through the BioChatter consortium (Supplementary Note: The BioChatter Consortium).

 

Supplementary Note: The BioChatter Consortium 

아래 LLM을 활용한 생명의학 연구 방향들 참고 

A Conversational Platform for Drug Discovery

 We are working with Open Targets and the Chemical and Literature services at EMBL-EBI (coordinating author: EMM, collaborating authors: BZ, MeHa) to develop a conversational platform that can answer user questions about the Open Targets Platform, data, and tools.

A Conversational Platform for Experimental Design and Analysis

We are working with two of the Crick’s core facilities (for Bioinformatics and Biostatistics and for Software Engineering and AI) to develop a conversational platform that can help researchers design experiments, analyse data, and interpret results (coordinating authors AS and StBo). 

A Platform for Publishing and Peer Review (생략)

 

아래 두개. 시간 될 때 확인해보면 좋을 것 같음. 이 플랫폼을 연구에 구체적으로 어떻게 활용할 수 있을지.  

Supplementary Note: Use Case - Cancer Genetics

Supplementary Note: Use Case - Project Management