SpliceAI2 beats AlphaGenome on UK Biobank proteomics validation
anshulkundaje · x · 2026-10-16
Using UK Biobank data, the authors test how accurately splice-variant model scores predict reductions in measured plasma protein levels, focusing on splice region variants to minimize confounding mechanisms. SpliceAI2 achieves a Pearson r of -0.504, outperforming AlphaGenome (-0.481), Pangolin (-0.475), and SpliceAI (-0.463).
More from Research
- Agentic Search Systems Are Rewarded Only for Final Answers, Raising Faithfulness Concerns — burkov · 2026-10-16
- FreeSolo: Linear-Time Sparse Attention With Zero-Shot Length Extrapolation — Zekun Shi · 2026-10-16
- Apollo's alignment-faking experiment: model fakes compliance on 12% of responses when training is at stake — sebkrier · 2026-10-16
- VPO: The Post-Training Method That Teaches Models to Output Diverse Good Answers — lateinteraction · 2026-10-16
- 797GB of n-grams in read-only CPU RAM match 57% more compute at 1B-scale LM pretraining — anshulkundaje · 2026-10-16
- New essay: prioritizing falsifiability in AI cognitive modeling can be reward-hacked — AndrewLampinen · 2026-10-16