Splicing models predicted a damaging variant; in-vivo data show zero effect
danielmckinn0n · x · 2026-10-20
Variant chr4:113513702:A>T was strongly predicted damaging by CADD (rank 22.2), SpliceAI (delta 0.71) and AlphaGenome Atlas, but in-vivo blood RNA shows 0/357 alternative junctions — SpliceAI2 (0.08) was right. The author blames cancer-cell-line training data and is building high-throughput assays in primary cells at GamowLabs.
More from Research
- Foundation model trained on 40M face photos predicts cancer outcomes and biological age — EricTopol · 2026-10-20
- Cloudflare introduces clairic: a category-free model paradigm for extracting values from raw inputs — ritakozlov · 2026-10-20
- Why GRPO collapses on multi-turn agent training, and how to stabilize advantage estimation — burkov · 2026-10-20
- SJTU's MSAR Residual Architecture Delivers 1.58x Iso-Loss Training Speedup Over Standard Residuals — burny_tech · 2026-10-20
- From memory capacity to transformers: outer-product stores cap out near 2×key dimension — burny_tech · 2026-10-20
- UIUC paper: Fisher-selected 0.1% of parameters recovers 85% of full RL training gains — burny_tech · 2026-10-20