EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY-NC 4.0

Large language model agents for biological intelligence across genomics, proteomics, spatial biology, and biomedicine

Sajib Acharjee Dip iD, Dipanwita Mallick, Uddip Acharjee Shuvo, Shovito Barua Soumma iD, Fazle Rafsani iD, Bikash Kumar Paul, Nazifa Ahmed Moumi, Shafayat Ahmed, Liqing Zhang iD

Briefings in Bioinformatics · 01.03.2026 · 27 (2)

DOI: 10.1093/bib/bbag110 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Briefings in Bioinformatics, online erschienen am 25.03.2026. Verfasst von Sajib Acharjee Dip und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Virginia Tech, 225 Stanger Street, Blacksburg, VA 24061, United States. Hauptthemen laut MEDLINE: Large Language Models, Genomics, Proteomics, Computational Biology. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 117 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Virginia Tech, the Department of Computer Science, and the U.S. National Science Foundation (NSF).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language models (LLMs) are evolving from passive predictors into agentic systems capable of planning, tool-use, and multimodal reasoning. This shift is especially consequential for biology, where complex, noisy, and multi-scale data require adaptive and integrative computational strategies. In this review, we provide the first systematic synthesis of LLM-based agents across genomics, molecular biology, imaging, biomedical analysis, and automated bioinformatics workflows. We analyze >60 emerging systems and organize them within a unifying framework that characterizes agentic traits, such as autonomous decision-making, external tool invocation, memory, and self-correction. Across domains, agentic LLMs show early promise in enabling multi-step analysis, linking heterogeneous evidence, and supporting exploratory scientific tasks. At the same time, our comparative assessment highlights consistent challenges, including unstable reasoning, limited biological grounding, retrieval misalignment, and barriers to reproducibility and biosafety. We conclude by outlining opportunities for trustworthy and collaborative biological agents, including multimodal integration, closed-loop experimental design, and robust evaluation practices. This survey aims to clarify the emerging landscape and chart a path toward reliable agentic systems for biological discovery.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Large Language ModelsGenomicsProteomicsComputational BiologyHumans

Stichwörter der Autor:innen

LLM agentsagentic AIartificial intelligence in biologybioinformaticsbiological sequence analysisbiomedical AIdrug discoverygenomicslarge language modelsmetagenomicsmulti-omicsproteomicstransformer models

Autor:innen und Institutionen

  • Department of Computer Science, Virginia Tech, 225 Stanger Street, Blacksburg, VA 24061, United States.
  • Department of Computer Science, North South University, Bashundhara, Dhaka 1229, Bangladesh.
  • Institute of Information Technology, University of Dhaka, Nilkhet Road, Dhaka 1000, Bangladesh.
  • School of Computing and Augmented Intelligence, Arizona State University, 699 S Mill Ave, Tempe, AZ 85281, United States.
  • College of Health Solutions, Arizona State University, 550 N 3rd Street, Phoenix, AZ 85004, United States.
  • Fralin Biomedical Research Institute at VTC, Virginia Tech, 2 Riverside Circle, Roanoke, VA 24016, United States.

ORCID-Profile: Sajib Acharjee Dip, Shovito Barua Soumma, Fazle Rafsani, Liqing Zhang

Förderung

  • Virginia Tech, the Department of Computer Science, and the U.S. National Science Foundation (NSF)

Zitieren

APA

Dip, S. A., Mallick, D., Acharjee Shuvo, U., Barua Soumma, S., Rafsani, F., Kumar Paul, B., Ahmed Moumi, N., Ahmed, S., & Zhang, L. (2026). Large language model agents for biological intelligence across genomics, proteomics, spatial biology, and biomedicine. Briefings in Bioinformatics, 27(2). https://doi.org/10.1093/bib/bbag110

Vancouver

Dip SA, Mallick D, Acharjee Shuvo U, Barua Soumma S, Rafsani F, Kumar Paul B, et al. Large language model agents for biological intelligence across genomics, proteomics, spatial biology, and biomedicine. Briefings in Bioinformatics. 2026;27(2). doi:10.1093/bib/bbag110

BibTeX
@article{Dip2026,
  author = {Dip, Sajib Acharjee and Mallick, Dipanwita and Acharjee Shuvo, Uddip and Barua Soumma, Shovito and Rafsani, Fazle and Kumar Paul, Bikash and Ahmed Moumi, Nazifa and Ahmed, Shafayat and Zhang, Liqing},
  title = {Large language model agents for biological intelligence across genomics, proteomics, spatial biology, and biomedicine},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  volume = {27},
  number = {2},
  doi = {10.1093/bib/bbag110}
}
Kostenlos starten →