CryoDRGN ❄️🐉 has officially joined #TeamTomo! In addition to reconstructing conformational heterogeneity, cryoDRGN-ET was surprisingly efficient at classifying subtomograms!

The #MoML conference at MIT is coming back this year!

Check out our cryo-EM simulation-based inference work for amortized template matching: train with simulations, test with experimental images! biorxiv.org/content/10.110… with an amazing team Lars Dingeldein DavidSilva Luke Evans Edoardo D'Imprima Grigorieff Lab Roberto Covino 🎉🎉

Tomorrow (July 31) is the deadline to make a nomination for this year's Rising Stars in Biological Engineering seminar series for Fall 2024 ⬇️ Last year we had terrific talks from Sophia Liu, Bhargav Sanketi and Tetsuhiro Harimoto! Nominate here: bioengineering.princeton.edu/events/rising-…

I'm sharing a public version of my talk slides CGSI-The Computational Genomics Summer Institute two weeks ago - an update from my #LLMs #compbio Primer talk last year - w/ a focus on genomics FMs (DNA, scRNA). As we're exploring related topics, we remain very interested but also skeptical. 1/3 cs.cmu.edu/~jianma/talks/…

De novo protein design is great, but nature has millions of proteins- why not repurpose them? Introducing Raygun, a new approach to protein design. It allows you to miniaturize, magnify or modify any protein. We synthesized miniaturized variants of eGFP and mCherry! 1/

🚀 Excited to share our preprint: CryoBench 🧊🪑: Diverse & Challenging Datasets for the Heterogeneity Problem in Cryo-EM! 🌐cryobench.cs.princeton.edu 🙌 Huge thanks to my amazing co-authors, collaborators, & advisor @zhongingalong! 🎉 #cryoEM #MachineLearning 🧵 Details below!

Cryo-EM heterogeneity analysis needs benchmarks and validation tools. We're very happy to share CryoBench 🧊🪑: cryobench.cs.princeton.edu lead by the amazing EZ team Minkyu Jeon Ellen Zhong with FI miro astore geoff woollard Sonya

Ah yes, forgot to mention, we focus on IgG antibodies in our 🧊🪑 datasets due to their pharmaceutical relevance 🤗 Interestingly, there are very few deposited structures of whole IgG, likely due to conformational heterogeneity (among other reasons)

Our submission portal on CMT is live! 👀 Deadline to submit is Sep 18 11:59pm AoE. See mlsb.io for call for papers and more info. And, mlsb.io/#challenge now hosts a P/L/INDER leaderboard! Show us your models!

Applications for the second cohort of the Brains Research Accelerator are now open! 1/

Introducing PaperQA2, the first AI agent that conducts entire scientific literature reviews on its own. PaperQA2 is also the first agent to beat PhD and Postdoc-level biology researchers on multiple literature research tasks, as measured both by accuracy on objective benchmarks

Our commentary "A renewed call for open artificial intelligence in biomedicine" is now available as a preprint. We call for sharing training data, code, and model weights in biomedical artificial intelligence research. 1/

Really excited to finally share this work from my internship at Microsoft Research in summer 2023! This project began when Judith and Kevin raised a simple question: can we develop better latent mappings of olfactory stimuli, such as molecules to odor perception? Summary (1/12):