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

Joined December 2010
345 Photos and videos
Mark Gerstein retweeted
Officially Dr. Tang! 🎓 Five years at Yale, and deeply grateful to my advisor @MarkGerstein for everything. 25 first author papers, published across Nature Communications, Nature Biotechnology, ICLR, ACL, ICML, NeurIPS. Best Paper x2. 15k citations. Looking back at the journey: 📝 Started with NLP: LLM factual consistency and grounding 🧬 In parallel, drawn to AI scientists: BioCoder, MolLM, drug design, LatentChem, CellForge, BC-Design, Safety of AI Scientists, Nature Biotech, ... 🤖 And ultimately landed on self-improving agents: MedAgents, ChemAgent, OpenHands, MedAgentsBench, LocAgent, Eigen-Agent, EvoClaw, ... Thank you to every collaborator who made this real. And thank you Mark, for giving me every resource, backing my mission, and always pushing me to think bigger. The throughline was always the same: AI that can actually do real work, improve itself, and accelerate science. That mission continues. Onward. 🙏
32
22
872
64,697
Mark Gerstein retweeted
🤩 spatial panoramic in vivo CRISPR screen via Perturb-DBiT 🤩 Excited to share our collaborative work with @sidichen lab and many outstanding collaborators, now published in Nature Biotechnology! nature.com/articles/s41587-0…
4
57
219
13,847
Posting my talk tomorrow at #FOGBoston (#FOG26) lectures.gersteinlab.org/sum… Lots of slides on single-cell multi-omics integration for brain disorders. New slides on a formalism for model interpretation @FLGenomics @FoGenomics
4
10
2,084
Mark Gerstein retweeted
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 nature.com/articles/s41467-0…
2
5
996
Mark Gerstein retweeted
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: rdcu.be/e9uYh
1
2
7
614
Mark Gerstein retweeted
We are presenting this tutorial at ISMB 2026, together with @XiangruTang (Yale), @WenqiShi0106 (UT Southwestern), and @MarkGerstein (Yale). Looking forward to connecting with friends in DC!
🎟️ SOLD OUT at #ISMB2026 Our tutorial IP2: Large Language Models and Agentic AI for Biomedical Informatics is the only sold-out tutorial on the entire ISMB 2026 program. Huge thanks to everyone who grabbed a seat so early. Organized and taught by @xwang174 (Virginia Tech), @WenqiShi0106 (UT Southwestern), @MarkGerstein (Yale), and me. We did not want this to be yet another "here is what an LLM is" walkthrough. The real question we want to sit with for 4 hours is bigger: What does the future of work in bioinformatics look like in the age of LLMs and agents? On the practical side, the afternoon covers the full stack a working computational biologist actually needs in 2026: The current LLM landscape, open source and commercial, and what each is good for in scientific settings / Prompt design that holds up under biomedical edge cases / Agentic systems that do multi step reasoning, tool use, and workflow orchestration for genuine biomedical tasks / The honest part: hallucination, bias, robustness, reproducibility, and what responsible use looks like in a clinical or scientific context Then we zoom out. Which parts of a computational biologist's day stay deeply human. Which parts get fully automated in the next 2 years. Where the next generation of bioinformaticians should be placing their bets, and what skills compound versus what skills depreciate. If you do any kind of biomedical data science, this is the conversation we think the field needs to have right now, and DC in July 2026 feels like the right room to have it in. 📍 Georgetown room, Washington Hilton 📅 Sunday, July 12, 2026, 14:00 to 18:00 ISMB returns to DC for the first time in over 30 years, to the same city where it started in 1993. Looking forward to seeing everyone there. 🧬
1
3
1,204
Thoughts on @Bob_Wachter's Giant Leap blog.gerstein.info/2026/05/t… Great points about AI's early missteps vs current successes in medicine
1
1
460
Mark Gerstein retweeted
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
1
2
5
477
Mark Gerstein retweeted
A review of my book #OnTheFutureOfSpecies on the convergence of #AI and biology, was published in @science.org magazine today
3
8
1,726
Posting my talk tomorrow at St. Johns U. on brain genomics lectures.gersteinlab.org/sum… Lots of new slides on the challenges of AI model applicability to genomics (@XiangruTang & @danielstupid) & on private federated learning with co-variate matching (@_YunyangLI).
4
8
1,380
Mark Gerstein retweeted
Why π ≈ 3.14 [🎞️ TimBrzezinski] π Day 2026

13
294
1,115
95,947
Posting my talk tomorrow @nygenome (hosted by @gamzeandgursoy). lectures.gersteinlab.org/sum… 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)
15
37
8,847
Mark Gerstein retweeted
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.
10
3
131
8,008
Mark Gerstein retweeted
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/scien… techmeme.com/260128/p39#a260… 📥 Send tips! techmeme.com/contact
1
4
9
2,182
Mark Gerstein retweeted
🔐 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-method…
1
3
533
Mark Gerstein retweeted
🚀 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/bioinformati…
3
7
779
Thoughts on @JSEllenberg's Shape blog.gerstein.info/2025/12/t… Engaging Stories about Hard Stuff, esp. liked the Discussion of Math behind AI
5
533
Mark Gerstein retweeted
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=ls5L…
1
3
6
699
Posting my talk tomorrow at @UMich (hosted by @brendon_watson), on analyzing endophenotypes (expression, biosensors & imaging). lectures.gersteinlab.org/sum… Lots of new slides from @RanMeng_m on using the @GTExPortal images to predict age
3
566
Mark Gerstein retweeted
26 Nov 2025
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.

2
5
1,263