Posting my talk tomorrow at St. Johns U. on brain genomics lectures.gersteinlab.org/summary/Clas... Lots of new slides on the challenges of AI model applicability to genomics & on private federated learning with co-variate matching.
Posting my talk tomorrow @nygenome.org (hosted by @gamzeandgursoy.bsky.social). lectures.gersteinlab.org/summary/AI-A... Doing genomics with AI & then seeing if AI can take over the whole thing (spoiler: not yet!). New slides on assessing agent models with externalized reasoning (vs. baselines)
Google DeepMind researchers unveil AlphaGenome, an AI model trained on molecular data to predict 11 different genomic processes, such as gene splicing (Carl Zimmer/New York Times)
Main Link | Techmeme Permalink
Our @neuripsconf.bsky.social work led by YunyangLI “E2Former: An Efficient and Equivariant Transformer with Linear-Scaling Tensor Products” was selected as a spotlight (with score ranked ~17 / 21k submissions).
Poster: Thur Dec 4, Exhibit Hall CDE #5512
Online: openreview.net/forum?id=ls5...
Thoughts on @jsellenberg.bsky.social's Shape blog.gerstein.info/2025/12/thou... Engaging Stories about Hard Stuff, esp. liked the Discussion of Math behind AI
Posting my talk tomorrow @umich.edu, on analyzing endophenotypes (expression, biosensors & imaging). lectures.gersteinlab.org/summary/Geno... Lots of new slides on using the @gtexportal.bsky.social images to predict age
We are excited to announce a tenure-track or tenured faculty position in Computational Biophysics and Biochemistry, exploring the intricate molecular and cellular processes and the complex interactions of their macromolecular components!
apply.interfolio.com/177120
Our new PNAS study bridges histology and genomics. Using deep learning and imageQTL analysis, we show how tissue images reflect gene expression and aging — making histology more interpretable with AI. By RanMeng, W. Zhu, C. Cameron, P. Ni, X. Zhou, T. Ulammandakh, and @markgerstein.bsky.social
Posting my talk at UW Madison (the DeMets lecture, hosted by
@daifengwang.bsky.social). Lots on bioinformatics methods for studying the brain: classic, present (DL) & future (quantum) lectures.gersteinlab.org/summary/Clas... New slides on AI agents & homomorphic encryption for privacy
Can AI developers avoid Frankenstein’s fateful mistake? www.latimes.com/opinion/stor... #AI #Frankenstein
Posting my talk tomorrow at the Computational Molecular Sciences & Engineering (CMSE) Symposium @Yale lectures.gersteinlab.org/summary/Enha... Lots of new slides on the discard-and-restart approach for enhanced structural sampling
Posting my talk today for the AI in Health Series lectures.gersteinlab.org/summary/AI-M... Goes over an evolution of computational methods for biomedicine: Classical, DL & Quantum.
Posting my talk tomorrow on Biomed AI @mila-quebec.bsky.social lectures.gersteinlab.org/summary/Biom...
Some new slides from Yunzhe Jiang on ENTEx & variant impact prediction and W Lee on ensembling ML models for drug screening
Posting my talk tomorrow on AI in Biomedicine at
Einstein Med (hosted by @zhengdy.bsky.social)
lectures.gersteinlab.org/summary/AI-t... Using AI for brain genomics & thinking about how it can do this research autonomously. Lots of new slides on AI coding & risks
John Clarke, UC Berkeley Emeritus professor, Michel Devoret, Yale Emeritus Professor, and John Martinis, UC Santa Barbara Emeritus Professor, winners of the 2025 Nobel Prize in Physics.
🧵The Nobel Prize in Physics today went to John Clarke (UK), Michel Devoret (France), & John Martinis (USA) today for work conducted in Clarke's UC Berkeley lab in the mid 80s showing that alternation of a quantum state could proceed from one side to the other of a device you can see with your eye.
📚 Yale students have returned to campus, so time for a roster meeting!
We again made our Nobel Prize predictions (given how accurate we were last year 😉)
🥇Our top prediction is Habener & Knudsen (GLP-1) with 28.5% of the vote!
🥈 In second is Rothberg & David Klenerman (NGS)
Did my annual triathlon today in Madison. Good swim. Steady bike. Walk-skip-walk to the finish line. Made it! And, unlike last year, did an extensive stretch afterwards & drove myself home. Before & after race pics. (More at flickr.com/photos/mbgmb...)
Curious how your favorite gene changes when and how during a biological process?
Want to dive into the kinetics of chromatin + gene expression?
Meet chronODE, our new tool to model multi-omic time-series with logistic equations + ML!
doi.org/10.1038/s414...
Posting my talk on AI & Brain Disorders at Princeton CHDI on Tuesday lectures.gersteinlab.org/summary/Ext-... Lots of new slides on drug repurposing and predicting age from histology images
🧠 At our recent Gerstein Lab roster meeting, we took a detour into… personality science!
Turns out we’re INT Central 🧪
📌 70% Introverts
📌 83% Intuitives
📌 57% Thinkers
Analysts (INTP, INTJ) dominate, far more than the U.S. baseline.
#MBTI #INTP #INTJ
Thoughts on Pearl's Book of Why blog.gerstein.info/2025/08/thou... Lots of Good Intuition on Bayesian Networks, Sometimes with Strong Opinions
"The microplastic (MP) 1–10 μm exposure estimates are 100-fold higher than previous estimates that were extrapolated from larger MP sizes, and suggest that the health impacts of MP inhalation may be more substantial than we realize."
journals.plos.org/plosone/arti...
Posting my talk tomorrow at @emblebi.bsky.social (for the @ensembl.bsky.social group) lectures.gersteinlab.org/summary/Expl... AI Approaches for Understanding Brain Disorders: Exploring Intermediate Endophenotypes connecting Genotype to Diseases
Posting my talk tomorrow at @geneticscam.bsky.social on AI for Brain Disorders lectures.gersteinlab.org/summary/Mode... Lots of new slides on characterizing brain developmental time series with sigmoids
Posting my talk on Mon. on Cancer Genomics at the Institut Curie lectures.gersteinlab.org/summary/Char... Lots of new slides on using LLMs for "tumor boards" & for generating genomics workflows
Posting my talk tomorrow at the AI4Chemistry Summit at NYU lectures.gersteinlab.org/summary/AI-f... Lots of new slides on computing small molecule Hamiltonians & predicting macromolecular misfolding
Posting my talk tomorrow at the SCORCH consortium meeting lectures.gersteinlab.org/summary/Chro... Tools for brain single-cell analysis: ChronODE for series data and ASTRO for spatial data.
Join us next week for MB&B's Computational Biophysics & Biochemistry Symposium on 6/17 in Bass 305!
Posting my talk tomorrow for the IMPACT-MH Consortium lectures.gersteinlab.org/summary/Digi... Digital Phenotyping from Wearables Using AI. Some new slides on using wearables to predict exercise lapses
Also, we've summarized our analysis of @carlzimmer.com's genome out to Chr22. And we have synced the lectures more closely with readings, now trying to reference the great ISL book as much as possible (statlearning.com)