
Mitch Guttman
324 posts

Mitch Guttman
@mitchguttman
Molecular biologist interested in non-coding RNAs, nuclear organization, and gene regulation. Professor at Caltech


Our paper is finally out in Cell! Years of work on one of biology's most beautiful tissue clocks, and finding an intrinsic oscillator that helps organize tissue dynamics. From my PhD work at @LongCai_Lab, with Shosei Yoshida and Ben Simons! 🧵(1/10) cell.com/cell/fulltext/…


Now out in @NatureBiotech ! Do lncRNAs commonly bind 1000s of genomic sites? Maybe they do, but the dozens of studies that report genomic binding maps of lncRNAs are deeply flawed, with probes binding suprious DNA sites rather than RNA-bound ones. nature.com/articles/s4158…


A preprint‼️that's bound to ruffle some 🪶 "Widespread DNA off-targeting confounds studies of RNA chromatin occupancy" led by our @MicahGoldrich and Louis Delhaye from @pieter_mestdagh. TL;DR we show that many of lncRNA chromatin occupancy maps are flawed🧵biorxiv.org/content/10.110…







A lot of scientific know-how already exists in Gtihub repos, APIs, notebooks, docs, and research papers. But agents still cannot really make use of it out of the box because it is scattered everywhere, We built SkillFoundry to bridge that gap. It turns fragmented scientific resources into reusable #skills that agents can actually use. The basic idea is to use a Domain Knowledge Tree to guide the search, mine candidate skills from heterogeneous resources, package them into executable skills, test them automatically, and then keep refining the library based on what works, what fails, and what overlaps. With the agent skills automatically designed by SkillFoundry, we see gains on 5/6 MoSciBench datasets, and Codex + SkillFoundry does much better on cell annotation than Codex alone, while staying competitive with systems like SpatialAgent. We also gave Biomni automatically designed skills from SkillFoundry for the scDRS workflow, and it outperformed Biomni running on its own. Project: #paper" target="_blank" rel="nofollow noopener">ma-compbio-lab.github.io/SkillFoundry/#…
Paper: arxiv.org/abs/2604.03964 Thanks to my co-authors @WenduoC @mishamamq @TurcanAlistair @martinjzhang and @jmuiuc for guidance and support throughout this work.

















