GPN-Star: phylogeny-aware genomic language model hits SOTA on variant effect prediction
pastramimachine · x · 2026-09-10
Yun S. Song's team published GPN-Star in Nature (open access), a genomic language model with a phylogeny-aware architecture that explicitly leverages whole-genome alignments and species trees.
- Motivation: NLP-adapted genomic LMs need large sizes and compute yet still trail classical evolutionary models on prediction tasks.
- Method: species-tree and alignment representations trained across vertebrate, mammal and primate timescales.
- Results: state-of-the-art variant effect prediction in both coding and non-coding regions, with a biologically grounded, smaller model.
A notable AI-for-Science result blending evolutionary priors with language modeling.
Related event: Berkeley's GPN-Star Genomic Model Published in Nature(2 posts)→
More from Research
- At ECCV, every speaker got asked "is 3D dead?" — ftm_guney · 2026-09-10
- Terminal Bench 4.0: one of the few evals whose ranking actually reflects capability — JJitsev · 2026-09-10
- UCLA releases VDiff-Bench, exposing multimodal models' weakness at fine-grained image differences — UCLA · 2026-09-10
- Study: ChatGPT dating advice beats humans blind, but AI label flips ratings — ipeirotis · 2026-09-10
- Quanquan Gu launches Geodesic Intelligence to build AGI for drug discovery — DeryaTR_ · 2026-09-10
- People prefer AI writing in blind tests—until they're told it's AI — ipeirotis · 2026-09-10