Why AI genomic models still struggle with gene regulation complexity
Overview
Wired reports that genomic foundation models such as Evo 2, Genos and Google DeepMind's AlphaGenome, which are trained on large genomic datasets to predict how DNA sequence differences affect biological processes, still cannot fully explain the genome's gene regulation.
The article argues that the regulation is too complex for these black-box models, and that researchers have only scratched the surface of the three-dimensional DNA structures that influence genome function.
Written by AI from the articles below · updated Oct 17, 5:47 AM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- Wired · AINewsWhy AI still struggles to decode the genome's regulatory complexity
AIGenomic foundation models such as Evo 2, Genos, and Google DeepMind's AlphaGenome are trained on large genomic datasets to predict how DNA sequence differences affect biological processes. The article argues that the genome's gene regulation is too complex for such black-box models to fully explain. Researchers have only scratched the surface of the three-dimensional knots that influence genome function.
Heat trend
Not enough continuous observations to show a trend yet.