Read more in Genetic Engineering and Biotechnology News: www.genengnews.com/topics/artif...

This perturbation dataset will be the largest of its kind, made up of 120M+ cells across 225,000 drug-patient interactions. The data will be released open source.

Explore the full manuscript + code: www.biorxiv.org/content/10.6...

Learn more about the development of Stack: arcinstitute.org/news/foundat...

The team applied Stack to build Perturb Sapiens: An atlas of ~20,000 predicted cell responses across 28 tissues & 201 perturbations + a subset validated using held-out datasets, confirming that predictions capture real biology.

Just as text prompts guide language models, cells serve as prompts in Stack. It can observe drug-treated immune cells & predict how epithelial cells would respond to the same drug, a task never explicitly trained for.

Stack captures something that most models miss: cellular context. A T cell in inflamed tissue behaves differently, not just because of its own genes, but because of its environment. Stack processes cells together & learns from those relationships.

Megan will oversee our multi-omics, genome engineering, cellular modeling, and mammalian disease modeling Technology Centers—coordinating efforts across our Virtual Cell and Alzheimer's Disease Initiatives.

Learn more: arcinstitute.org/news/megan-v...

Thank you again to our sponsors @nvidia, @10xGenomics and @UltimaGenomics.

The final leaderboards are now posted on the competition website: virtualcellchallenge.org

Virtual Cell Challenge 2026 kicks off mid-year. See you then!

For more details on the winners and our reflections on what we learned—from hybrid models outperforming pure neural networks to the value of multi-modal features—please visit our website: arcinstitute.org/news/virtual...

Congratulations to all of the winners and a huge thank you to the community: Your thoughtful engagement with metric design questions and evaluation frameworks is already shaping next year's Challenge. Together we're building the future of predictive cell biology.

We also introduced a new award for broader evaluation:

🏆 Generalist Prize: Team @altos_labs ranked highest across 7 metrics. They showed the most reliable generalization—robust performance across diverse criteria vs. optimization for a single score.

🥉 Third Place: Team Outlier was a cross-institutional collaboration from U Chicago, Dartmouth, and HKU built TransPert—a statistical framework that predicts perturbations across cell lines using only summary-level data.

🥈 Second Place: Team XLearning Lab from Sichuan University took a streamlined approach: shift from noisy single-cell to pseudo-bulk data, use residual learning to predict perturbation changes, and strategically optimize for the highest-weighted metrics.

🥇 First Place: Team BM_xTVC from BioMap Research built xTrimoSCPerturb, improving upon scFoundation architecture to better capture gene relationships and recover biological signals from technical noise.

Their key insight? Pure AI approaches didn't beat statistical baselines so they integrated both.

By enabling exploration of a combinatorial perturbation space that approaches the diversity accessed by natural evolution, CRISPR All opens new possibilities for both biological discovery and therapeutic design.

Learn more in the preprint: www.biorxiv.org/content/10.1...

The strongest constructs from the pooled CACTUS proliferation screens were then validated independently, showing clear advantages in head-to-head competitive assays across all four major CRISPR All perturbation classes.

Using this framework, the team built CACTUS, a curated library of 600+ proposed CAR and T-cell enhancements.

Evaluating them in matched conditions allowed the team to precisely identify which edits enhance function under chronic stimulation.