Tabula: Privacy-Preserving Single-Cell Foundation Model for Genomics

Jiayuan Ding, Jianhui Lin, Ziyang Miao, Nils Mechtel, Shiyu Jiang, Yixin Wang, Zhaoyu Fang, Jorge D. Martin-Rufino, Chen Weng, Reuben Saunders, Weize Xu, Jonathan S. Weissman, Min Li, Jiliang Tang, Wei Ouyang, Yuancheng Ryan Lu, Xiaojie Qiu· July 23, 2026 View original

Summary

Researchers introduce Tabula, a privacy-preserving foundation model for single-cell genomics that explicitly models tabular data structure using federated learning. Deployed via the Chiron platform, Tabula reveals combinatorial regulatory logic and nominates rejuvenation factors, outperforming conventional approaches while addressing privacy concerns in collaborative training.

A new foundation model named Tabula has been developed for single-cell genomics, specifically designed to address both the unique tabular structure of single-cell data and critical privacy concerns. Unlike existing models, Tabula integrates federated learning (FL) to enable collaborative training across multiple institutions without requiring the sharing of raw, sensitive patient data. To facilitate its deployment, the researchers also created Chiron, a decentralized AI agent-enabled platform. Tabula demonstrates strong predictive performance across various benchmarks and offers insights into combinatorial regulatory logic in diverse biological systems, including hematopoiesis and neurogenesis. Furthermore, using a novel dataset of paired young and aged human fibroblasts, Tabula successfully identifies potential rejuvenation factors through an age- and identity score-guided prioritization method, surpassing the capabilities of traditional approaches. This work represents a significant step towards creating privacy-preserving "virtual cells" for advancing human health research.

Why it matters

For professionals in biotech, pharma, and healthcare, Tabula offers a powerful new tool for genomic research that respects data privacy, enabling collaborative studies on sensitive patient data to accelerate drug discovery, disease understanding, and anti-aging research.

How to implement this in your domain

  1. 1Explore integrating federated learning approaches like Tabula into multi-institutional genomic research collaborations.
  2. 2Investigate the use of single-cell foundation models for identifying novel therapeutic targets or biomarkers.
  3. 3Implement privacy-preserving AI frameworks for handling sensitive biological datasets.
  4. 4Collaborate with research institutions to leverage decentralized AI platforms for genomic data analysis.

Who benefits

BiotechnologyPharmaceuticalsHealthcareLife SciencesResearch & Development

Key takeaways

  • Tabula is a privacy-preserving foundation model for single-cell genomics using federated learning.
  • It explicitly models the tabular structure of single-cell data, a unique feature.
  • The model reveals combinatorial regulatory logic and identifies rejuvenation factors.
  • Tabula enables collaborative research across institutions while protecting data privacy.

Original post by Jiayuan Ding, Jianhui Lin, Ziyang Miao, Nils Mechtel, Shiyu Jiang, Yixin Wang, Zhaoyu Fang, Jorge D. Martin-Rufino, Chen Weng, Reuben Saunders, Weize Xu, Jonathan S. Weissman, Min Li, Jiliang Tang, Wei Ouyang, Yuancheng Ryan Lu, Xiaojie Qiu

"arXiv:2607.19400v1 Announce Type: new Abstract: Pre-trained foundation models (FMs) have begun transforming single-cell genomics, but scaling them raises privacy concerns. Moreover, unlike text data, single-cell data is unordered and exhibits a unique tabular structure that curre…"

View on X

Originally posted by Jiayuan Ding, Jianhui Lin, Ziyang Miao, Nils Mechtel, Shiyu Jiang, Yixin Wang, Zhaoyu Fang, Jorge D. Martin-Rufino, Chen Weng, Reuben Saunders, Weize Xu, Jonathan S. Weissman, Min Li, Jiliang Tang, Wei Ouyang, Yuancheng Ryan Lu, Xiaojie Qiu on X · view source

Want to go deeper?

Turn these trends into skills with Learnijoy's hands-on AI & tech courses.

Explore courses