Registration is now open for our 5-day Simons workshop taking place in two months (June 10th-14th) in Berkeley (w Aditi Krishnapriyan ).

AI≡Science: Strengthening the Bond Between the Sciences and Artificial Intelligence simons.berkeley.edu/workshops/aisc…

Our primer 'Generative models for protein structures and sequences' is now live nature.com/articles/s4158… Chloe Hsu @seafann (free version: nature.com/articles/s4158…)

Hunter and Yixin's paper on blending biophysics based information with neural network models for molecule/protein property prediction has come out, and with an Editor's Choice award (Hunter Nisonoff, Yixin Wang) pubs.acs.org/doi/full/10.10…

It's been a long saga, but our ML for AAV library design work has finally been published! science.org/doi/10.1126/sc…

The commentary I wrote is now live at Nature Biotech: nature.com/articles/s4158… (free version rdcu.be/dwSSy).

Since we just wrapped up an AI megaconference, it felt like a good day to plead for fewer papers. argmin.net/p/too-much-inf…

Clara's and my piece, 'Is Novelty Predictable', on machine learning based design/engineering is now officially out in Cold Spring Harbor Perspectives in Biology @seafann doi.org/10.1101/cshper…….

A commentary I wrote on AI + Science: The perpetual motion machine of AI-generated data and the distraction of “ChatGPT as scientist” (on hold at arXiv so published as TR for now) www2.eecs.berkeley.edu/Pubs/TechRpts/…

Congratulations to Hunter Nisonoff for his work on combining function valued priors with neural network predictions for problems in biology and chemistry. pubs.acs.org/doi/10.1021/ac…

Come join us in EECS at UC Berkeley! aprecruit.berkeley.edu/JPF04168

Do you estimate/predict log enrichment scores from sequencing data? Do you want greater statistical power? Or do you want an easy way to combine all kinds of short and long reads? Akosua Busia’s paper is officially out now. genomebiology.biomedcentral.com/articles/10.11…

Come join our AI-Science community at UC Berkeley, open to any rank faculty!
aprecruit.berkeley.edu/JPF04118?fbcli…

Musings on machine learning-based design from me and @seafann: arxiv.org/abs/2306.00872

Do you estimate/predict log enrichment scores from sequencing data? Do you want greater statistical power? Or do you want an easy way to combine all kinds of short and long reads? Check out our pre-print, led by Akosua Busia, now on the job market. biorxiv.org/content/10.110…

Come join us! aprecruit.berkeley.edu/JPF03615?fbcli…

Come join us! Applications close November 15th. aprecruit.berkeley.edu/JPF03606

The deadline for this summer undergraduate program is extended till 2/28!! Still have time to submit your applications!

pumped to share our latest work! if *any* trained model decides what data to test—for example, NNs designing novel proteins—we can quantify its uncertainty w/ finite-sample guarantees.
arxiv.org/abs/2202.03613
w/ ​​Stephen Bates, Anastasios Nikolas Angelopoulos, Jennifer Listgarten, M.I. Jordan 1/5

Hunter's work on how to use (eg) a biophysics-based fitness prior to train neural networks arxiv.org/abs/2202.04798. Hunter Nisonoff,
Yixin Wang

This is officially out now: nature.com/articles/s4158…