A new study shows promising results in helping scientists analyze information.

Can scientists automate research in genomics (the study of what genes do and how they interact)? A new study led by UC San Diego researchers says it’s possible, potentially fasttracking future discoveries.

The study, published Nov 28 in Nature Methods and led by UCSD School of Medicine and Jacobs School of Engineering professor Trey Ideker, demonstrated that artificial intelligence through large language models (LLMs) such as GPT-4 could help automate functional genomics research.

Functional genomics is frequently approached through gene set enrichment, which aims to determine the function of experimentally-identified gene sets by comparing them to existing genomics databases.

As novel biology is often beyond the scope of established databases, using AI to analyze gene sets could save scientists many hours of intensive labor, bringing the field closer to automating one of the most widely used methods for understanding how genes work.

GPT-4 was the most successful tool, the researchers found, achieving a 73 percent accuracy rate in identifying common functions of curated gene sets from a commonly used genomics database, according to a press release.

GPT-4 was also capable of providing detailed narratives to support its naming process.

While further research is needed to fully explore the potential of LLMs in automating functional genomics, the study highlights the need for continued investment in the development of LLMs and their applications in genomics and precision medicine. To support this, the researchers created a web portal to help other researchers incorporate LLMs into their functional genomics workflows.

More broadly, the findings also demonstrate the power of AI to revolutionize the scientific process by synthesizing complex information to generate new, testable hypotheses in a fraction of the time.

© lajolla.ca