Computational biologist working on gene editing and cancer biology. Associate Professor, University of Maryland School of Medicine. Views are my own.
Rockville, MD
Joined June 2009
- Tweets322
- Following658
- Followers953
- Likes879
Pinned Tweet
Our most recent Nature Cell Biology paper describes an innovative Perturbation-response Score (PS) method to decode heterogeneous responses of cells to perturbations at single-cell level. Particularly helpful for analyzing Perturb-seq data. nature.com/articles/s41556-0…
Wei Li retweeted
One of the puzzles in perturbation prediction, and the cause of many food fights, is that deep learning models often lose to the simplest possible baseline-- just predict the average response across all perturbations.
This summer, multiple labs converged on an answer to this.
Perturbation-prediction AI models are critical for building virtual cells. Many models exist, but what is next? What is the critical gap to application? Our pertTF preprint shows the next step: cross-system prediction, and beyond gene expression. biorxiv.org/content/10.64898…
A great collaboration with many labs including @DanweiHuangfu @hon_lab @YaruiDiao @hanrui_zhang and many others. It's also great timing as we see many exciting new datasets/models released this month: X-Cell/X-Atlas @Xaira_Thera, in vivo Perturb-seq @perturbai_tx etc.
Wei Li retweeted
Happy to share scHiCAR, an ultra-high throughout (millions of cells), low cost (5 cents/cell including NGS), and trimodal platform for integrated single-cell level analysis of mRNA, open chromatin, and 5-kb resolution looping with ground-truth data the same individual cell.
Trimodal single-cell profiling of transcriptome, epigenome and 3D genome in complex tissues with scHiCAR go.nature.com/4rZqimf
Perturb2026 is an exciting conference about generating perturbation data, building AI models, and interacting with academic and industry attendees. Great lineup of speakers. Come and join us on March 18-19, Vienna, Austria! perturb2026.bio/
Wei Li retweeted
🧬 Building the Virtual Cell starts with data.
Today, we’re making the X-Atlas/Orion Perturb-seq dataset even more accessible — now live on Hugging Face @huggingface 🤗
📊 One of the largest & highest-quality perturbation datasets ever released, it provides the foundation for training AI models that can simulate and reason about cellular behavior.
👉 Explore here: huggingface.co/datasets/Xair…
Fewer barriers. More models. A step closer to the virtual cell. 🌌
#VirtualCell #FoundationModels #AIinBiology #HuggingFace
🚀 Xaira Therapeutics has just dropped a game-changer for AI-driven biology.
Today, we unveiled X-Atlas/Orion, the largest publicly available genome-wide Perturb-seq dataset to date—spanning 8.4 million single cells with perturbations across all ~20,000 human protein-coding genes.
This release is not just about scale—it’s about enabling a new era of causal, mechanistic foundation models for biology.
📝 Preprint on bioRxiv: biorxiv.org/content/10.1101/…
📂 Dataset on Figshare:
doi.org/10.25452/figshare.pl…
🔍 What makes X-Atlas/Orion special:
📈 Unprecedented scale & quality: Each cell profiled with deep (~16k UMIs) transcriptomics and rich metadata
🧪 Quantitative dose-response modeling: Thanks to high-fidelity sgRNA detection and ~4 guides per gene, allowing continuous modeling of genetic effects
🧬 FiCS platform: A fully industrialized single-cell perturbation system enabling rapid, reproducible experiments at massive throughput
🧠 This isn’t just “data.” It’s the biological substrate for building virtual cell models that can generalize, predict, and ultimately power AI-native drug discovery.
💬 My final take:
This is a foundational moment for the field. The ability to model how genes affect cell state—quantitatively, causally, and at scale—is what we need to unlock predictive biology.
Kudos to the incredible team at Xaira for open-sourcing this resource so the entire community can build on it.
#PerturbSeq #SingleCell #Genomics #VirtualCell #FoundationModels #AIForBiology #Xaira #DrugDiscovery #SyntheticBiology #CausalAI
More press release: Press release :
🔗 GEN article : genengnews.com/topics/artifi…
🔗 BusinessWire: businesswire.com/news/home/2…
Wei Li retweeted
Following 2023 paper, our new study on TE regulation is out today @NatureCellBio! nature.com/articles/s41556-0…
Out now @NatureGenet!!! Dive into the interplay of RNA m6A/DNA 5mC that controls transposable elements (TEs) chromatin activation and hESC fate! Kudos to our brilliant postdoc, Tongyu Sun, who developed CARGO-BioID for TE-centered proteome analysis to unearth all these findings!
Application is still open until Aug 25. Great for trainees of all levels. Come and join us!
Wei Li retweeted
Our Cell paper is online (doi.org/10.1016/j.cell.2025.…)! We present the CIDE framework, broadly applicable to cancer research and oncology. Also, we highlight AOAH as a promising new immunotherapy.
I am thrilled to join UMSOM and work with many great scientists here!
🎉 Join us in welcoming Dr. Wei Li as Associate Professor in Pharmacology & Physiology at UMSOM!
His groundbreaking work in AI, CRISPR, and cancer biology is driving the future of precision medicine. Welcome aboard, Dr. Li! 👏🔗 shorturl.at/0M4UC
2
17
1,330
Wei Li retweeted
Today @arcinstitute releases State, our first perturbation prediction AI model and an important step towards our goal of a virtual cell
State is designed to learn how to shift cells between states (e.g. “diseased” to “healthy”) using drugs, cytokines, or genetic perturbations
Wei Li retweeted
Yesterday, the NIH R35 “Outstanding Investigator” grant to fund scientists in my lab studying antibiotic resistance was terminated for reasons not related to the content of the science, or any actions taken by me or members of my lab
ALT A screenshot showing "Outstanding Investigator Grants"
ALT A screenshot of the termination notice with "This award is terminated effective the date of this award, due to unsafe antisemitic actions that suggest the institution lacks concern for the safety and wellbeing of Jewish students." highlighted