Predictive single cell foundation model for gene regulation and aging with privacy-preserving tabular learning
This work addresses the need for privacy-preserving and structurally-aware foundation models in single-cell genomics, enabling collaborative training across institutions without sharing raw data.
Tabula is a privacy-preserving single-cell foundation model using federated learning that explicitly models tabular data structure, achieving strong downstream benchmarks and outperforming conventional methods in nominating rejuvenation factors from a new scRNA-seq dataset of young and aged human fibroblasts.
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 current single-cell FMs overlook. We introduce Tabula, a privacy-preserving FM designed with federated learning (FL) that explicitly models the tabular structure of single-cell data. To deploy Tabula, we further developed Chiron, a decentralized AI agent-enabled platform for collaborative training across institutions without sharing raw data. Beyond strong performance across downstream benchmarks, Tabula reveals combinatorial regulatory logic across diverse biological systems, including hematopoiesis, pancreatic endogenesis, neurogenesis, and cardiogenesis. Using a new scRNA-seq dataset of paired young and aged human fibroblasts, Tabula nominates rejuvenation factors through age- and identity score-guided in silico prioritization, outperforming conventional approaches. Thus, Tabula represents an important advance in single-cell foundation modeling by integrating tabular learning with FL, paving the way toward privacy-preserving virtual cells for human health.