scFLAME: a unified generative model for interpretable clustering, hierarchical structure discovery and marker-gene identification in single-cell RNA-seq data
- 1MRC Biostatistics Unit
Abstract
Identifying cell types from single-cell RNA sequencing (scRNA-seq) data typically requires several separate and often uninterpretable steps: dimensionality reduction, batch-correction, clustering, marker-gene identification and the discovery of finer-grained structure. Here we introduce scFLAME (single-cell Factor Latent Analysis with Mixture Embeddings), a probabilistic generative model that unifies these tasks: a negative binomial factor analysis of the raw counts - which can be adjusted for batch - is coupled to a Gaussian mixture prior over the latent space, learning the embedding and clustering jointly, while a shared linear decoder provides cluster-specific marker genes directly from the fitted model, and a merging procedure recovers a probabilistic hierarchy of finer-grained partitions. On simulated and real data, scFLAME matches or exceeds state-of-the-art clustering accuracy, is robust across sequencing platforms, and scales near-linearly to hundreds of thousands of cells. scFLAME thus replaces a chain of separate tools with a single, interpretable model for single-cell analysis.
Related
- Ourotide: decoding the hierarchical peptide recognition for generative design
- A generative network model reveals hierarchical structural memory guiding post-mitotic 3D genome inheritance
- Classifying tumors from broad category to hierarchical molecular subtype: an interpretable hierarchical framework for precision oncology
- A Novel Open-Source CellProfiler Pipeline for Automated, User-Friendly Hierarchical and K-Means Clustering of Microglial Morphology
- BiHC: Protein domain segmentation by bidirectional hierarchical clustering using Voronoi tessellation and physical self-containment
BibTeX
@misc{rao2026scflame,
title = {{scFLAME: a unified generative model for interpretable clustering, hierarchical structure discovery and marker-gene identification in single-cell RNA-seq data}},
author = {J. Rao and M. Jihad and G. Biffi and P. D. Kirk},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.04.749363},
url = {https://www.biorxiv.org/content/10.64898/2026.09.04.749363v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - scFLAME: a unified generative model for interpretable clustering, hierarchical structure discovery and marker-gene identification in single-cell RNA-seq data
AU - J. Rao
AU - M. Jihad
AU - G. Biffi
AU - P. D. Kirk
PY - 2026
DA - 2026/09/04
PB - bioRxiv
DO - 10.64898/2026.09.04.749363
UR - https://www.biorxiv.org/content/10.64898/2026.09.04.749363v1
AB - Identifying cell types from single-cell RNA sequencing (scRNA-seq) data typically requires several separate and often uninterpretable steps: dimensionality reduction, batch-correction, clustering, marker-gene identification and the discovery of finer-grained structure. Here we introduce scFLAME (single-cell Factor Latent Analysis with Mixture Embeddings), a probabilistic generative model that unifies these tasks: a negative binomial factor analysis of the raw counts - which can be adjusted for batch - is coupled to a Gaussian mixture prior over the latent space, learning the embedding and clustering jointly, while a shared linear decoder provides cluster-specific marker genes directly from the fitted model, and a merging procedure recovers a probabilistic hierarchy of finer-grained partitions. On simulated and real data, scFLAME matches or exceeds state-of-the-art clustering accuracy, is robust across sequencing platforms, and scales near-linearly to hundreds of thousands of cells. scFLAME thus replaces a chain of separate tools with a single, interpretable model for single-cell analysis.
ER -