A full workflow for fine-tuning AlphaGenome splicing heads on RNA-seq data
anshulkundaje · x · 2026-07-29
This is the full linked post for the same AlphaGenome fine-tuning write-up. It details a workflow for preprocessing, loading, debugging, and evaluating splicing-head training across RNA-seq modalities.
The case study uses SF3B1 K700E and wild-type samples to show how the model can be adapted to new transcriptomic inputs and evaluated on held-out genomic intervals.
Related event: New Fine-Tuning Framework Adapts AlphaGenome to Diverse RNA-seq Modalities(2 posts)→
More from Research
- Stanford trial says GPT-4 beat doctors when used alone, but hurt non-experts — jonc101x · 2026-07-29
- New Platform Enables Multi-Agent Task-Level Reinforcement Learning Training — ypatil125 · 2026-07-29
- ICLR 2025: Articulate-Anything Uses VLMs to Automate Object Modeling for Robot Training — CSProfKGD · 2026-07-29
- CIMC and Apart Research launch a San Francisco sprint on AI sentience and alignment — matiroy · 2026-07-29
- OpenAI Foundation is urged to fund AI research hubs in the Global South — ShakeelHashim · 2026-07-29
- Annals of Mathematics paper proves a 1853 design conjecture — MarioKrenn6240 · 2026-07-29