EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Boosting GPT models for genomics analysis: generating trusted genetic variant annotations and interpretations through RAG and Fine-tuning

Shuangjia Lu iD, Erdal Cosgun iD

Bioinformatics Advances · 26.12.2024 · 5 (1)

DOI: 10.1093/bioadv/vbaf019 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics Advances, online erschienen am 05.02.2025. Verfasst von Shuangjia Lu und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Genetics, Yale University School of Medicine, New Haven, CT 06511, United States. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Microsoft’s Health Future Genomics Team.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Large language models (LLMs) have acquired a remarkable level of knowledge through their initial training. However, they lack expertise in particular domains such as genomics. Variant annotation data, an important component of genomics, is crucial for interpreting and prioritizing disease-related variants among millions of variants identified by genetic sequencing. In our project, we aimed to improve LLM performance in genomics by adding variant annotation data to LLMs by retrieval-augmented generation (RAG) and fine-tuning techniques. Results Using RAG, we successfully integrated 190 million highly accurate variant annotations, curated from five major annotation datasets and tools, into GPT-4o. This integration empowers users to query specific variants and receive accurate variant annotations and interpretations supported by advanced reasoning and language understanding capabilities of LLMs. Additionally, fine-tuning GPT-4 on variant annotation data also improved model performance in some annotation fields, although the accuracy across more fields remains suboptimal. Our model significantly improved the accessibility and efficiency of the variant interpretation process by leveraging LLM capabilities. Our project also revealed that RAG outperforms fine-tuning in factual knowledge injection in terms of data volume, accuracy, and cost-effectiveness. As a pioneering study for adding genomics knowledge to LLMs, our work paves the way for developing more comprehensive and informative genomics AI systems to support clinical diagnosis and research projects, and it demonstrates the potential of LLMs in specialized domains. Availability and implementation We used publicly available datasets as detailed in the paper, which can be provided upon request.

Autor:innen und Institutionen

  • Department of Genetics, Yale University School of Medicine, New Haven, CT 06511, United States.
  • Genomics Team, Health Futures, Microsoft Research, Redmond, WA 98052, United States.

ORCID-Profile: Shuangjia Lu, Erdal Cosgun

Förderung

  • Microsoft’s Health Future Genomics Team

Zitieren

APA

Lu, S., & Cosgun, E. (2024). Boosting GPT models for genomics analysis: generating trusted genetic variant annotations and interpretations through RAG and Fine-tuning. Bioinformatics Advances, 5(1). https://doi.org/10.1093/bioadv/vbaf019

Vancouver

Lu S, Cosgun E. Boosting GPT models for genomics analysis: generating trusted genetic variant annotations and interpretations through RAG and Fine-tuning. Bioinformatics Advances. 2024;5(1). doi:10.1093/bioadv/vbaf019

BibTeX
@article{Lu2024,
  author = {Lu, Shuangjia and Cosgun, Erdal},
  title = {Boosting GPT models for genomics analysis: generating trusted genetic variant annotations and interpretations through RAG and Fine-tuning},
  journal = {Bioinformatics Advances},
  year = {2024},
  volume = {5},
  number = {1},
  doi = {10.1093/bioadv/vbaf019}
}
Kostenlos starten →