🛰️ Daily AI Frontier
‹ back to 2026-09-10

Predicting genome-wide functional constraints with GPN-Star

Nature Bioinformatics AI Chengzhong Ye, Gonzalo Benegas, Carlos Albors, Jianan Canal Li, Sebastian Prillo, Peter D. Fields, Brian Clarke, Yun S. Song 2026-09-09

TL;DR - GPN-Star is a genomic language model designed to predict genome-wide functional constraints and genetic variant effects across species. Its phylogeny-aware architecture processes whole-genome alignment data with an emphasis on scalability and flexibility.

  • Uses evolutionary relationships encoded in whole-genome alignments.
  • Supports cross-species genetic variant effect prediction.
  • Targets scalable analysis of functional constraints across entire genomes.
  • The provided abstract does not include quantitative performance results.

view merged work →