PuSH - Publikationsserver des Helmholtz Zentrums München

Export: TXT Text RIS Endnote (RIS) BIB BibTeX
Tomaz da Silva, P.* ; Karollus, A.* ; Hingerl, J.* ; Galindez, G.S.T.* ; Wagner, N.* ; Hernandez-Alias, X.* ; Incarnato, D.* ; Gagneur, J.

Nucleotide dependency analysis of genomic language models detects functional elements.

Nat. Genet. 57, 2589-2602 (2025)
Verlagsversion Forschungsdaten DOI PMC
Open Access Hybrid
Creative Commons Lizenzvertrag
Deciphering how nucleotides in genomes encode regulatory instructions and molecular machines is a long-standing goal. Genomic language models (gLMs) implicitly capture functional elements and their organization from genomic sequences alone by modeling probabilities of each nucleotide given its sequence context. However, discovering functional genomic elements from gLMs has been challenging due to the lack of interpretable methods. Here we introduce nucleotide dependencies, which quantify how nucleotide substitutions at one genomic position affect the probabilities of nucleotides at other positions. We demonstrate that nucleotide dependencies are more effective at indicating the deleteriousness of genetic variants than alignment-based conservation and gLM reconstruction. Dependency analysis accurately detects regulatory motifs and highlights bases in contact within RNAs, including pseudoknots and tertiary structure contacts, revealing new, experimentally validated RNA structures. Finally, we leverage dependency maps to reveal critical limitations of several gLM architectures and training strategies. Altogether, nucleotide dependency analysis opens a new avenue for discovering and studying functional elements and their interactions in genomes.
Impact Factor
Scopus SNIP
Altmetric
29.000
0.000
Tags
Anmerkungen
Besondere Publikation
Auf Hompepage verbergern

Zusatzinfos bearbeiten
Eigene Tags bearbeiten
Privat
Eigene Anmerkung bearbeiten
Privat
Auf Publikationslisten für
Homepage nicht anzeigen
Als besondere Publikation
markieren
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
Schlagwörter Rna; Identification; Classification; Prediction; Alignment; Database; Genes
Sprache englisch
Veröffentlichungsjahr 2025
HGF-Berichtsjahr 2025
ISSN (print) / ISBN 1061-4036
e-ISSN 1546-1718
Zeitschrift Nature Genetics
Quellenangaben Band: 57, Heft: 10, Seiten: 2589-2602 Artikelnummer: , Supplement: ,
Verlag Nature Publishing Group
Verlagsort New York, NY
Begutachtungsstatus Peer reviewed
Institut(e) Institute of Computational Biology (ICB)
POF Topic(s) 30205 - Bioengineering and Digital Health
Forschungsfeld(er) Enabling and Novel Technologies
PSP-Element(e) G-503800-001
Förderungen European Union
Helmholtz Association under the joint research school 'Munich School for Data Science-MUDS'
Dutch Research Council (NWO)
NWO Open Competitie ENW-XS
European Research Council (ERC), European Union's Horizon Europe research and innovation program
EMBO Postdoctoral Fellowship
German Bundesministerium fur Bildung und Forschung (BMBF) through the Model Exchange for Regulatory Genomics project MERGE
Deutsche Forschungsgemeinschaft (DFG
German Research Foundation)
EVUK program ('Next-generation AI for Integrated Diagnostics') of the Free State of Bavaria
DFG (German Research Foundation)
DFG (German Research Foundation) through the IT Infrastructure for Computational Molecular Medicine
ERC (EPIC)
Munich Center for Machine Learning
DOI 10.1038/s41588-025-02347-3
WOS ID 001591900700032
Scopus ID 105018398113
PubMed ID 41073788
Erfassungsdatum 2025-10-14
[➜Korrektur melden]