Mark Gerstein

Posting my talk tomorrow at St. Johns U. on brain genomics lectures.gersteinlab.org/summary/Classi… Lots of new slides on the challenges of AI model applicability to genomics (@XiangruTang & @danielstupid) & on private federated learning with co-variate matching (@_YunyangLI).

Why π ≈ 3.14 [🎞️ TimBrzezinski] π Day 2026

Posting my talk tomorrow @nygenome (hosted by @gamzeandgursoy). lectures.gersteinlab.org/summary/AI-Ass… Doing genomics with AI & then seeing if AI can take over the whole thing (spoiler: not yet!). New slides from @XiangruTang on assessing agent models with externalized reasoning (vs. baselines)

PhD defended at Yale. I feel very fortunate to have worked with so many brilliant collaborators and to have had such a supportive committee. Thank you all for supporting my work. 🥺 Special thanks to my advisor Mark for his mentorship, support for my research, and the many lessons that shaped how I think, communicate, and do science. 🙏 On to the next chapter.

Google DeepMind researchers unveil AlphaGenome, an AI model trained on molecular data to predict 11 different genomic processes, such as gene splicing (@carlzimmer / New York Times) nytimes.com/2026/01/28/sci… #a260128p39" target="_blank" rel="nofollow noopener">techmeme.com/260128/p39#a26… 📥 Send tips! techmeme.com/contact

🔐 New open-access paper in Cell Reports Methods! We show that fully homomorphic encryption enables privacy-preserving polygenic risk scores (PRS), allowing secure computation directly on encrypted genomes with near-zero accuracy loss. 📄 cell.com/cell-reports-m…

🚀 New paper in Bioinformatics! Our #ASTRO work led by @dingyao_zhang introduces "ASTRO: Automated Spatial-Transcriptome whole RNA Output", an automated pipeline optimized for whole-transcriptome spatial analysis, especially in challenging FFPE samples. 🔗 doi.org/10.1093/bioinf…

Thoughts on @JSEllenberg's Shape blog.gerstein.info/2025/12/though… Engaging Stories about Hard Stuff, esp. liked the Discussion of Math behind AI

Our @NeurIPSConf 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=ls5L4…

Posting my talk tomorrow at @UMich (hosted by @brendon_watson), on analyzing endophenotypes (expression, biosensors & imaging). lectures.gersteinlab.org/summary/Genoty… Lots of new slides from @RanMeng_m on using the @GTExPortal 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 now at apply.interfolio.com/177120.

Honored to host my postdoc advisor, Dr. Mark Gerstein @MarkGerstein from Yale, for annual DeMets Lecture today @uwcdis @UWMadison. Inspiring talk & fantastic overview on AI in biomedicine: single-cell genomics, drug discovery, genomic privacy, LLM & agents, and quantum computing.

Posting my talk at @UWMadison (the DeMets lecture, hosted by @daifengwang). Lots on bioinformatics methods for studying the brain: classic, present (DL) & future (quantum) lectures.gersteinlab.org/summary/Classi… New slides on AI agents (from @XiangruTang) & homomorphic encryption for privacy

AI & Frankenstein comparison, seems about right. Can AI developers avoid Frankenstein’s fateful mistake? latimes.com/opinion/story/…

The 2025 Yale Faculty Innovation Awards honor academic founders whose startups—rooted in Yale research—are advancing breakthroughs in health, sustainability, and engineering. Meet the awardees: ventures.yale.edu/news/lab-launc…

Posting my talk tomorrow at the Computational Molecular Sciences & Engineering (CMSE) Symposium @Yale lectures.gersteinlab.org/summary/Enhanc… Lots of new slides on the discard-and-restart approach for enhanced structural sampling

Posting my talk tomorrow for the AI in Health Series lectures.gersteinlab.org/summary/AI-Met… Goes over an evolution of computational methods for biomedicine: Classical, DL & Quantum. Slides from @XiangruTang & @hypahub

An illusion in motion: the circles stay still, your brain doesn’t.

Posting my talk tomorrow on Biomed AI @Mila_Quebec lectures.gersteinlab.org/summary/Biomed… Some new slides from @YunzheJ on ENTEx & variant impact prediction and W Lee on ensembling ML models for drug screening

AI meets biology: a collaboration between @Yale’s @david_van_dijk and @Google has led to a powerful new model that discovered a previously unknown cancer therapy pathway. Another step toward AI-driven scientific discovery.