PARNET: A CLIP-seq-based foundation model for RNA sequence representation
anshulkundaje · x · 2026-09-17
A multi-institution team from Helmholtz Munich's Computational Health Center, King's College London, the Francis Crick Institute, TU Munich and Slovenia's National Institute of Chemistry (including Gagneur, Ule and Marsico as senior authors) released the bioRxiv preprint PARNET, a foundation model for RNA sequence representation learning trained on CLIP-seq data, aiming to learn general-purpose RNA sequence embeddings for downstream genomics studies.
More from Research
- ModAR: a 30.1M robot world model trained from scratch beats a 6B video-model baseline — CSProfKGD · 2026-09-17
- Polymarket bets put 35% odds on AI solving the Hodge Conjecture by end of 2026 — Polymarket · 2026-09-17
- FlashAttention explained on an actual napkin by its author — vtabbott_ · 2026-09-17
- MessyMem (CoRL 2026): persistent memory for robots via 3D scene graphs and VLM analysis — leto__jean · 2026-09-17
- Kingston AI Group report says Australia punches above its weight in AI research — TobyWalsh · 2026-09-17
- Suspected AI-generated code gets GitHub PRs rejected with shallow feedback, study finds — soumitrashukla9 · 2026-09-17