fastISM: a grad student tool that sped up in silico mutagenesis is now the default
jmschreiber91 · x · 2026-10-21
A nod to fastISM, written by Surag Nair as a grad student: it speeds up in silico saturation mutagenesis for models with layers lacking a complete receptive field, such as convolutions.
- Published in Bioinformatics (2022) by Stanford researchers
- It is now the default implementation, with an automatic fallback when the speedup doesn't apply
More from Research
- GATOR: generative agentic 3D object reconstruction from casual images — kwangmoo_yi · 2026-10-21
- Claudini: AI autoresearch discovers SOTA jailbreak algorithms with 80% ASR — maksym_andr · 2026-10-21
- Three JEPA variants, one question: how well must a machine predict to plan? — TheTuringPost · 2026-10-21
- COLM 2026 paper shows low-quality training data gives LLMs 'brain rot' — _vztu · 2026-10-21
- Stanford Virtual Embryo Challenge partners with Eigen Labs' open research platform Yukon — anshulkundaje · 2026-10-21
- Laude Institute backs WaggleHaus, an open-source query engine for agentic queries over data lakes — lateinteraction · 2026-10-21