Paper 2603.25240
Lingshu-Cell: A generative cellular world model for transcriptome modeling toward virtual cells
- Published
- Mar 2026
- Research lab
- Independent
- Citations
- 3
- GitHub
- Not linked
01 In brief
Summary
Lingshu-Cell is a masked discrete diffusion model (MDDM) for generative modeling of single-cell transcriptomics, introduced by Alibaba DAMO Academy.
It models transcriptomic state distributions across ~18,000 genes without prior gene selection, operating directly in a discrete token space compatible with sparse, non-sequential scRNA-seq data.
The model supports unconditional generation of realistic cell states and conditional generation for perturbation responses.
It accurately reproduces transcriptomic distributions, marker-gene expression, and cell-subtype proportions across nine tissues and five species.
For genetic perturbations, Lingshu-Cell achieved the best average rank on the Virtual Cell Challenge H1 benchmark, with the lowest MAE (0.052) and highest Pearson-Δ correlation (0.306).
It also led in predicting cytokine-induced responses in human PBMCs.
Key design components include classifier-free guidance, embedding-space sequence compression, and biological prior injection.
The model was trained on datasets like PARSE 10M PBMC and CZ CELLxGENE, using a quantization scheme that preserves the first two significant digits of UMI counts.
Limitations include reliance on population-level metrics and lack of causal inference; future work aims to integrate multi-modal data and model temporal dynamics.
02 From the paper
Abstract
Modeling cellular states and predicting their responses to perturbations are central challenges in computational biology and the development of virtual cells. Existing foundation models for single-cell transcriptomics provide powerful static representations, but they do not explicitly model the distribution of cellular states for generative simulation. Here, we introduce Lingshu-Cell, a masked discrete diffusion model that learns transcriptomic state distributions and supports conditional simulation under perturbation. By operating directly in a discrete token space that is compatible with the sparse, non-sequential nature of single-cell transcriptomic data, Lingshu-Cell captures complex transcriptome-wide expression dependencies across approximately 18,000 genes without relying on prior gene selection, such as filtering by high variability or ranking by expression level. Across diverse tissues and species, Lingshu-Cell accurately reproduces transcriptomic distributions, marker-gene expression patterns and cell-subtype proportions, demonstrating its ability to capture complex cellular heterogeneity. Moreover, by jointly embedding cell type or donor identity with perturbation, Lingshu-Cell can predict whole-transcriptome expression changes for novel combinations of identity and perturbation. It achieves leading performance on the Virtual Cell Challenge H1 genetic perturbation benchmark and in predicting cytokine-induced responses in human PBMCs. Together, these results establish Lingshu-Cell as a flexible cellular world model for in silico simulation of cell states and perturbation responses, laying the foundation for a new paradigm in biological discovery and perturbation screening.