Gerstein Lab | Yale

Research in #Biomedical #DataScience & #Bioinformatics #CompBio.
@MarkGerstein AT @YaleMBB @YaleMed

[Gerstein Lab | Yale @GersteinLab]

New study conducted by our lab in collaboration with #PsychENCODE has made significant discoveries linking genetic variants to genes and cell types in human brain. #psychencode24

For more details, refer to our original thread: https://t.co/dz0P7ddEWP

https://t.co/WT4QDUGJl4

[Mark Gerstein @MarkGerstein]

New paper on single-cell genomics & regulatory networks for 388 human brains just out in @ScienceMagazine. Neat stuff on single-cell QTLs, cell-to-cell communication, & DL models simulating drug effects (https://t.co/4paOy63nOu) #PsychENCODE24

[Gerstein Lab | Yale @GersteinLab]

New paper in Protein Science! Meet DreamFold: a World Model that generates protein folding pathways and reveals druggable intermediate states: https://t.co/KYzIMjFMUH

[Gerstein Lab | Yale @GersteinLab]

Excited to see our work featured by @YaleMed! We introduce MedicalAgentsBench, a benchmark for evaluating how multi-agent LLMs compare with reasoning models—and how they can complement each other in clinical decision-making: https://t.co/AF4RrVq3Hn

[Mark Gerstein @MarkGerstein]

Posting my talk today at @UniBarcelona on the 25th anniversary of the human genome (hosted by @beaborsari) https://t.co/IAERDZt6pj Lots of new slides on variant impact models & pseudogene epigenetics across tissues

[Mark Gerstein @MarkGerstein]

Posting my talk today for tutorial IP2 at @iscb's #ISMB2026: Large Language Models & Agentic AI for Biomedical Informatics (organized by @XiangruTang) https://t.co/x7DOidJrPd Has lots of slides on case studies for LLMs in brain genomics & comparisons with more classic approaches

[Gerstein Lab | Yale @GersteinLab]

During our recent lab roster meeting, we asked about everyone's AI chatbot preferences (n=69, multi-select):
🥇 Claude — 49 (71%)
🥈 ChatGPT — 43 (62%)
🥉 Gemini — 14 (20%)
Takeaway: Mostly Claude + ChatGPT co-usage, with Gemini as a distant third and a long tail of niche tools.

[Mark Gerstein @MarkGerstein]

Post term, cleaned up my biomed. data sci. course website. https://t.co/8fw8KqXS28 Now in its 28th year. New thing this year was #AI integration: the students merged (with color coding) the manual & AI summaries of each lecture. Also, lots of new posted videos & PDFs (esp. on DL)

[Gerstein Lab | Yale @GersteinLab]

New @naturecomms paper by @katerbowie @MarkGerstein @jordan_peccia @H2O_Hannah. We study how disinfection shapes microbes in hospital sink drain biofilms. Biofilms regrew in 4 days, enriched for carbapenem-resistant bacteria and multidrug efflux pump genes https://t.co/WvAhxtAHwA

[Gerstein Lab | Yale @GersteinLab]

By Jonathan Warrell, Michael Gancz, Hussein Mohsen, Prashant Emani & @MarkGerstein

[Gerstein Lab | Yale @GersteinLab]

In our @NatMachIntell paper, we introduce a framework to analyse interpretability in deep learning by drawing on a formal notion of model semantics from the philosophy of science. We illustrate our framework with examples from biomedicine. Read here: https://t.co/tOSkNL3Gmz

[Gerstein Lab | Yale @GersteinLab]

Article link: https://t.co/oHdGKof7UG

[Gerstein Lab | Yale @GersteinLab]

Curious how pseudogenes are transcriptionally regulated? Our new @genomeresearch paper shows processed pseudogenes break the rules: they’re transcribed without classic epigenetic marks, linked to enhancers, and enriched for YY1 motifs. Study co-led by @YunzheJ and @beaborsari

[Gerstein Lab | Yale @GersteinLab]

🔐 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.
📄 https://t.co/rwBfwwKcmD

[Gerstein Lab | Yale @GersteinLab]

🚀 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.
🔗 https://t.co/ecr2No1BHv

[Gerstein Lab | Yale @GersteinLab]

@NeurIPSConf @_YunyangLI This work is a close collaboration with colleagues previously at Microsoft Research (@MSFTResearch) and currently at Ubiquant and various other places. Huge thanks to them for the ideas and computational resources.

[Gerstein Lab | Yale @GersteinLab]

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: https://t.co/q8tKBleaF9

[Gerstein Lab | Yale @GersteinLab]

By @RanMeng_m, William Zhu, Christopher Cameron, Pengyu Ni, Xiao Zhou, Tselmeg Ulammandakh, and @MarkGerstein.

[Gerstein Lab | Yale @GersteinLab]

🆕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.
https://t.co/y75uzar2g6

[Gerstein Lab | Yale @GersteinLab]

By @RanMeng_m, William Zhu, Christopher Cameron, Pengyu Ni, Xiao Zhou, Tselmeg Ulammandakh, and @MarkGerstein.

[Gerstein Lab | Yale @GersteinLab]

📚 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)

[Gerstein Lab | Yale @GersteinLab]

New @NatureComms paper led by @beaborsari & Mor Frank. Also thanks to co-authors Eve Wattenberg, @KeXU0828, @Susannaliu99, @XuezhuYu & @MarkGerstein!

[Gerstein Lab | Yale @GersteinLab]

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!
https://t.co/E9Xu5sOqQn