@MarkGerstein

#Bioinformatics professor, interested in #DataScience, with photography, triathlons & books as hobbies

 Yale
Gerstein.info
Joined December 2010
  • Tweets6.6K
  • Following895
  • Followers8K
355Media
Posting my talk tomorrow at MoML 2026 at @MIT (organized by @AIHealthMIT lectures.gersteinlab.org/sum… New slides on World Modeling for drug dev. & its integration with @daifengwang's drug repurposing
3
6
685
Interested to learn about Yale’s #PhD program in Computational Biology and Biomedical Informatics (CBB)? Join our virtual information session for interested applicants on Monday, October 19, 2026, 8–9PM ET. 👉Register at: yalesurvey.ca1.qualtrics.com… @YaleCBB @YALEBBS
3
6
542
Mark Gerstein retweeted
The Nobel Prize
@NobelPrizeOct 5
BREAKING NEWS The 2026 #NobelPrize in Physiology or Medicine has been awarded to Karl Deisseroth, Peter Hegemann and Georg Nagel “for their discoveries concerning light-gated ion channels and optogenetics.”
435
9,120
1,616
24,109
3,961,921
Mark Gerstein retweeted
The Nobel Prize
@NobelPrizeOct 7
BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2026 #NobelPrize in Chemistry to Henri B. Kagan and Kenso Soai “for the discovery of non-linear effects and autocatalysis in asymmetric organic synthesis.”
226
7,214
1,014
16,591
2,007,512
Mark Gerstein retweeted
Gerstein Lab | Yale@GersteinLabOct 2
New paper in Protein Science! Meet DreamFold: a World Model that generates protein folding pathways and reveals druggable intermediate states: onlinelibrary.wiley.com/doi/…
2
5
411
Mark Gerstein retweeted
The Nobel Prize
@NobelPrizeOct 6
BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2026 #NobelPrize in Physics to Francis Halzen “for decisive contributions to the IceCube Neutrino Observatory and the discovery of high-energy neutrinos of astrophysical origin.”
300
6,056
990
15,816
1,329,767
We're excited to hear from @YaleMed's @MarkGerstein on Wednesday, Oct. 14 for #MoML2026! <20 tickets left! 🎟️ Register now before tickets are sold out: moml.mit.edu/
1
6
1,026
Mark Gerstein retweeted
Yale MB&B@YaleMBBSep 23
We are excited to announce a tenure-track 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/193444.
1
3
3
8
13,545
Mark Gerstein retweeted
Daifeng Wang@daifengwangSep 23
Our AI framework PASCode w/@panos_roussos @NatureMedicine uses graph neural networks to score phenotypic association of >6M cells #PsychAD and discover unknown cell subtypes & genes in #Alzheimers for pathology, cognitive resilience & psychiatric symptoms nature.com/articles/s41591-0…

AI-based characterization of Alzheimer’s disease phenotypes from population-scale single-cell data

Nature Medicine - Based on single-cell data from a cohort of 584 brain donors including patients with Alzheimer’s disease (AD) and controls, a graph neural network is used to investigate...

nature.com
3
6
18
1,991
Posting a short talk tomorrow for the #QuantumWorldCongress on using Quantum Computing to achieve Biomedical Privacy lectures.gersteinlab.org/sum… #QWC2026 @QWCevent
1
5
708
Did my annual triathlon today. Brisk swim; slow bike; fast walk... Overjoyed just to make it to the finish line without any drama. Lots of pictures of a great "Triathlon Sunrise." (More stuff at linkstream2.gerstein.info/ta…)
9
889
Posting my talk today at Oxford CS on AI in Structural Bioinformatics lectures.gersteinlab.org/sum… Modelling Flexibility, Disorder & Interactions. Lots of new slides on World Models for protein folding
7
979
Posting my talk today at University of Montpellier on the changing challenges in genomics lectures.gersteinlab.org/sum… Lots of slides on variant impact models
4
642
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: medicine.yale.edu/news-artic…

How Many LLMs Does it Take to Reason Through a Decision?

Researchers developed a tool to test different types of AI reasoning models. They found the models have complementary strengths.

medicine.yale.edu
1
5
557
Posting my talk today at @CRGenomica in Barcelona (hosted by @beaborsari & @GuigoLab) lectures.gersteinlab.org/sum… Lots of slides on the AI Scientist from @XiangruTang
1
1
7
1,803
Posting my talk today at @UniBarcelona on the 25th anniversary of the human genome (hosted by @beaborsari) lectures.gersteinlab.org/sum… Lots of new slides on variant impact models & pseudogene epigenetics across tissues
4
18
1,991
Posting my talk today for tutorial IP2 at @iscb's #ISMB2026: Large Language Models & Agentic AI for Biomedical Informatics (organized by @XiangruTang) lectures.gersteinlab.org/sum… Has lots of slides on case studies for LLMs in brain genomics & comparisons with more classic approaches
2
6
1
16
3,236
Thought this "re-imagining" of the declaration goes well with a recent @NewYorker piece on the "committee-style" writing of the piece (newyorker.com/magazine/2026/…). Personally, I always find "(re)writing groups" rather taxing.

Was the Declaration of Independence Better Before the Edits?

Amid contention, criticism, and compromise, a divided nation had to present a unified front. It came at a cost.

newyorker.com
Sundar Pichai
@sundarpichaiJul 2
Love this re-imagining of America’s founding using Docs, Gmail, Calendar and more from @GoogleWorkspace. Really puts the history in version history :)
1
908
(1/n) Ever wonder why scaling up parameters is effective in LLMs or how to make a small model perform better? Our @icmlconf paper on "Dispersion Loss Counteracts Embedding Condensation and Improves Generalization in Small Language Models" @ChenLiu_1996 and @XingzhiSun, may shed some geometric insight Paper: arxiv.org/pdf/2602.00217 Code: github.com/KrishnaswamyLab/L…
1
14
55
3,871
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.
1
4
521
Load more