Count Bridges enable Modeling and Deconvolving Transcriptomic Data

TL;DR

Count Bridges introduces a novel stochastic process for modeling and deconvolving integer-valued biological count data, enabling accurate single-cell resolution analysis from aggregated measurements with state-of-the-art performance.

Contribution

The paper presents Count Bridges, a new tractable stochastic bridge process for count data, extending diffusion models to integer-valued data and enabling direct training from aggregated measurements.

Findings

State-of-the-art performance on integer distribution benchmarks

Effective deconvolution of bulk RNA-seq data

Successful resolution of spatial transcriptomic spots into single-cell profiles

Abstract

Many modern biological assays, including RNA sequencing, yield integer-valued counts that reflect the number of molecules detected. These measurements are often not at the desired resolution: while the unit of interest is typically a single cell, many measurement technologies produce counts aggregated over sets of cells. Although recent generative frameworks such as diffusion and flow matching have been extended to non-Euclidean and discrete settings, it remains unclear how best to model integer-valued data or how to systematically deconvolve aggregated observations. We introduce Count Bridges, a stochastic bridge process on the integers that provides an exact, tractable analogue of diffusion-style models for count data, with closed-form conditionals for efficient training and sampling. We extend this framework to enable direct training from aggregated measurements via an Expectation-Maximization-style approach that treats unit-level counts as latent variables. We demonstrate state-of-the-art performance on integer distribution matching benchmarks, comparing against flow matching and discrete flow matching baselines across various metrics. We then apply Count Bridges to two large-scale problems in biology: modeling single-cell gene expression data at the nucleotide resolution, with applications to deconvolving bulk RNA-seq, and resolving multicellular spatial transcriptomic spots into single-cell count profiles. Our methods offer a principled foundation for generative modeling and deconvolution of biological count data across scales and modalities.