Genomic language models could transform medicine but not yet

Recently, a genomic language model (gLM) with 40 billion parameters known as Evo2 has reached the same scale as the most powerful text large language models (LLMs). gLMs have been emerging as powerful tools to decode DNA sequences over the last five years. This article examines the emergence of gLMs...

Full description

Saved in:
Bibliographic Details
Main Authors: Micaela Elisa Consens, Ben Li, Anna R. Poetsch, Stephen Gilbert
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:npj Digital Medicine
Online Access:https://doi.org/10.1038/s41746-025-01603-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850181834835492864
author Micaela Elisa Consens
Ben Li
Anna R. Poetsch
Stephen Gilbert
author_facet Micaela Elisa Consens
Ben Li
Anna R. Poetsch
Stephen Gilbert
author_sort Micaela Elisa Consens
collection DOAJ
description Recently, a genomic language model (gLM) with 40 billion parameters known as Evo2 has reached the same scale as the most powerful text large language models (LLMs). gLMs have been emerging as powerful tools to decode DNA sequences over the last five years. This article examines the emergence of gLMs and highlights Evo2 as a milestone in genomic language modeling, assessing both the scientific promise of gLMs and the practical challenges facing their implementation in medicine.
format Article
id doaj-art-80ce180d1d9e40e89e43b23bf7d7cc1e
institution OA Journals
issn 2398-6352
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series npj Digital Medicine
spelling doaj-art-80ce180d1d9e40e89e43b23bf7d7cc1e2025-08-20T02:17:49ZengNature Portfolionpj Digital Medicine2398-63522025-04-01811410.1038/s41746-025-01603-4Genomic language models could transform medicine but not yetMicaela Elisa Consens0Ben Li1Anna R. Poetsch2Stephen Gilbert3Department of Computer Science, University of TorontoDivision of Vascular Surgery, University of TorontoBiomedical Genomics, Biotechnology Center, Center for Molecular and Cellular Bioengineering, Technische UniversitätCarl Gustav Carus University Hospital Dresden, Dresden University of TechnologyRecently, a genomic language model (gLM) with 40 billion parameters known as Evo2 has reached the same scale as the most powerful text large language models (LLMs). gLMs have been emerging as powerful tools to decode DNA sequences over the last five years. This article examines the emergence of gLMs and highlights Evo2 as a milestone in genomic language modeling, assessing both the scientific promise of gLMs and the practical challenges facing their implementation in medicine.https://doi.org/10.1038/s41746-025-01603-4
spellingShingle Micaela Elisa Consens
Ben Li
Anna R. Poetsch
Stephen Gilbert
Genomic language models could transform medicine but not yet
npj Digital Medicine
title Genomic language models could transform medicine but not yet
title_full Genomic language models could transform medicine but not yet
title_fullStr Genomic language models could transform medicine but not yet
title_full_unstemmed Genomic language models could transform medicine but not yet
title_short Genomic language models could transform medicine but not yet
title_sort genomic language models could transform medicine but not yet
url https://doi.org/10.1038/s41746-025-01603-4
work_keys_str_mv AT micaelaelisaconsens genomiclanguagemodelscouldtransformmedicinebutnotyet
AT benli genomiclanguagemodelscouldtransformmedicinebutnotyet
AT annarpoetsch genomiclanguagemodelscouldtransformmedicinebutnotyet
AT stephengilbert genomiclanguagemodelscouldtransformmedicinebutnotyet