GPN-Star: evolution-aware genome model hits SOTA, published in Nature
EricTopol · x · 2026-09-09
UC Berkeley researchers published GPN-Star in Nature: a phylogeny-aware genomic language model that explicitly uses whole-genome alignments and species trees to model evolution. Trained across vertebrate, mammal and primate timescales, it achieves state-of-the-art variant effect prediction in both coding and non-coding regions — outperforming larger NLP-style genomic models and classical evolutionary methods — moving toward predicting the molecular impact of all 9 billion human genome variants.
Related event: GPN-Star hits Nature, beating 40B Evo 2 with 200M parameters(3 posts)→
More from Research
- Scaling-fit discrepancy: output-head FLOPs are ~65% of compute at the smallest rung, ~3% at 535B — dlwh · 2026-10-27
- Marin's dlwh Explains the Scaling Law Fit: Estimating the Loss Floor Early — dlwh · 2026-10-27
- Marin's Open Scaling Law Extrapolates 300× and Predicts Loss Within 0.2% — dlwh · 2026-10-27
- Marin Shares Forecast-vs-Measured Plots: Paloma Hits 0.4% RMS Error — dlwh · 2026-10-27
- AW-0 hits 80.8% on RoboTwin tasks, beating strongest baseline by 16 points — trevordarrell · 2026-10-27
- AW-0's code stream fixes world model prediction: picks mango where baseline grabs apple — trevordarrell · 2026-10-27