Discrete Diffusion for Single-Cell Gene Expression Modeling
Bhattacharya, S.; Gensbigler, C.; Karim, S.; Lees, J.
Show abstract
AO_SCPLOWBSTRACTC_SCPLOWCurrent generative modeling of single-cell transcriptomics relies on continuous latent representations, transforming inherently discrete and sparse gene counts into continuous space. We propose Discrete Cell Models (DCM), a diffusion-based framework that learns cellular representations directly in the discrete domain. Our framework supports both unconditional and conditional generation, allowing for precise modeling of complex biological scenarios such as cell-type-specific transcriptional responses to genetic perturbations. We demonstrate that DCM scales effectively and achieves strong performance against current state-of-the-art methods, including scVI, CPA, STATE, scGPT, and scLDM. On the Dentate Gyrus benchmark, DCM achieves a 5-fold improvement in MMD2RBF and a nearly 2-fold improvement in W2 distance, over the leading continuous diffusion baseline (scLDM). On the conditional Replogle perturbation benchmark, DCM sets a new state of the art on W2 distance while remaining competitive on MMD2RBF. Together, these results establish discrete diffusion as a promising direction for foundational models of cellular biology.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Single-Cell Multi-Modal GAN (scMMGAN) reveals spatial patterns in single-cell data from triple negative breast cancer 96%
- Generating hard-to-obtain information from easy-to-obtain information: applications in drug discovery and clinical inference 95%
- Hierarchical confounder discovery in the experiment-machine learning cycle 95%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.