Integrating machine learning and functional genomics to study cross-species gene regulatory evolution
Current Opinion in Genetics & Development · 2026
DOI: 10.1016/j.gde.2025.102415 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Current Opinion in Genetics & Development, 2026. Verfasst von Erin N Gilbertson und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Genetics, Yale School of Medicine, New Haven, CT, USA. Hauptthemen laut MEDLINE: Machine Learning, Evolution, Molecular, Genomics, Gene Expression Regulation. Die Arbeit nennt 81 Literaturangaben.
Abstract (Originalsprache)
Understanding the genetic basis of phenotypic differences across species has been a longstanding goal of evolutionary biology since Darwin. While a recent proliferation of mammalian genomes has provided an unprecedented inventory of sequence differences between species, the vast majority are in noncoding loci, where it remains challenging to link genetic changes to function. Cis-regulatory elements (CREs) control gene expression via combinatorial, redundant, and context-dependent interactions that are both evolutionarily amenable to change but render their gene regulatory logic difficult to decipher. Recent advances in comparative genomics, functional profiling across species, and high-throughput perturbation assays have begun to catalog cross-species differences in gene expression and CRE function. In parallel, machine learning approaches trained on these data are beginning to predict cis-regulatory activity differences from DNA sequences alone. Here, we highlight recent advances in both experimental and computational strategies to study gene regulatory evolution.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Genetics, Yale School of Medicine, New Haven, CT, USA.
- Department of Genetics, Yale School of Medicine, New Haven, CT, USA; Wu Tsai Institute, Yale University, New Haven, CT, USA. Electronic address: Steven.K.Reilly@yale.edu.
Zitieren
APA
Gilbertson, E. N., & Reilly, S. K. (2026). Integrating machine learning and functional genomics to study cross-species gene regulatory evolution. Current Opinion in Genetics & Development. https://doi.org/10.1016/j.gde.2025.102415
Vancouver
Gilbertson EN, Reilly SK. Integrating machine learning and functional genomics to study cross-species gene regulatory evolution. Current Opinion in Genetics & Development. 2026. doi:10.1016/j.gde.2025.102415
BibTeX
@article{Gilbertson2026,
author = {Gilbertson, Erin N and Reilly, Steven K},
title = {Integrating machine learning and functional genomics to study cross-species gene regulatory evolution},
journal = {Current Opinion in Genetics & Development},
year = {2026},
doi = {10.1016/j.gde.2025.102415}
}
EUVIMED