Our article "Learning antibody sequence constraints from allelic inclusion" is now published in Cell Systems and freely available from this link until Oct 2, 2025: https://t.co/qCZERPUMPF Previous post on the article: https://t.co/ZEiKBWiWKi

Thanks for posting. I wasn't aware of this beautiful exposition by @rlmcelreath, which I highly recommend for curious statisticians. Primer is now available free of charge: https://t.co/pozbfdiOQW Including Homework and Solution Manual, which we have released for enlightened

Try Cosmos in Python now! See vignettes to get started 🔗 Code:

We apply Cosmos to 3 DMS datasets: Kir2.1: abundance → surface expression PDZ3: abundance → CRIPT binding KRAS: abundance → RAF1_RBD binding Cosmos clearly separates direct binding residues from those with indirect effects.

How does it work? Cosmos aggregates mutation effects by position, learns interpretable causal graphs via Bayesian model selection, and outputs residue-level direct vs indirect effects. [5/n]

Cosmos answers three key questions: 1️⃣ Is there a causal link between the phenotypes? 2️⃣ How strong is it? 3️⃣ What would the downstream phenotype look like if we “normalized” the upstream one (i.e., counterfactual inference)? [4/n]

Cosmos is a Bayesian framework that performs residue-level causal inference to decouple how mutations influence upstream vs downstream functions. No need for detailed biophysical models—just stats and data. [3/n]

Multi-phenotype DMS experiments are revealing how mutations impact different protein functions. But these phenotypes are often causally linked—e.g., when measuring activity, we may also capture effects propagated from abundance. So how do we tell what’s direct vs indirect? [2/n]

How do we decouple the effects of two functional phenotypes in protein deep mutational scanning (DMS)? Meet Cosmos, our new statistical framework for causal inference in multi-phenotype DMS. https://t.co/ZOy32xLJ5T [1/n]

🧬 BREAKING: Our CRISPR-GPT paper is out TODAY in Nature Biomedical Engineering @natBME ! 🤯 We built an AI agent that turns ANYONE into a gene-editing expert in 1 DAY instead of months. An undergrad with ZERO experience achieved 90%+ editing efficiency on their FIRST attempt. 🧵

Presenting at #ISMBECCB2025 tomorrow! GASTON-Mix, a unified model of spatial gradients and domains in spatial 'omics data. 11:20am UK time at RegSys Also recruiting students for my new lab at @JHUCompSci, feel free to reach out if you want to chat

Check out our latest foundation model for wearable sensor data (LSM-2)!

🚀 Join CongLab @Stanford! We’re hiring postdocs to create lab-in-the-loop self-evolving AI agents, open benchmarks, to design, test & learn—advancing safer gene & cell therapies. Build on CRISPR-GPT, RNAGenesis model, Genome-Bench, for innovative medicines. #PostdocJobs

Thrilled to share that I just successfully defended my PhD! Thanks to my committee, collaborators, and everyone who’d supported me throughout my seven years at UCLA. A special thank you to my PI Harold for his incredible mentorship! @hjpimentel

Happy to share that our work from the @nmancuso_ lab is out in @NatureGenet! We developed SuShiE, a multiancestry fine-mapping method for molecular traits.

I’m honored to join Fred Hutch as Professor and Program Head of Biostatistics, and as the Donald and Janet K. Guthrie Endowed Chair in Statistics. Excited to be part of a deeply collaborative and scientifically vibrant community with a rich legacy of impact.

Introducing Arc Institute’s first virtual cell model: STATE

In the nucleus, many intrinsically disordered proteins (IDPs) form condensates. What IDP sequence features drive this behavior? We developed CondenSeq, a high-throughput method to measure nuclear condensate formation & applied it to ~14000 IDPs to find out https://t.co/qfa8jtvFOp

University budgets everywhere are getting slashed, and we hear many PhD students with accepted ICML papers can no longer afford to attend. We are stepping in to offer travel grants for researchers who lost funding. Sponsored by Pillar VC, Ormoni Bio, Latent Labs, and Cimulate

I’ll speak on July 16 (2:30pm ET) at NSF@75: Advancing Statistical Science for a Data‑Driven World @InStatsOrg conference. My talk is about an info-theoretic criterion (ITCA) for combining ambiguous class labels: https://t.co/18yDuDAKwa Free registration: