# scANMF: Prior Knowledge and Graph-Regularized NMF for Accurate Cell Type Annotation in scRNA-seq

## TL;DR

scANMF is a new method that improves cell type annotation in single-cell RNA sequencing by combining prior knowledge and graph regularization for better accuracy and robustness.

## Contribution

scANMF introduces a unified framework integrating marker genes, label supervision, and graph regularization for robust cell-type annotation.

## Key findings

- scANMF achieved high annotation accuracy across within-dataset, cross-platform, and cross-species evaluations.
- The method remained stable under varying levels of label sparsity and marker-gene noise.
- Ablation analyses showed complementary contributions from marker priors, label supervision, and graph regularization.

## Abstract

Single-cell RNA sequencing (scRNA-seq) provides a high-resolution view of cellular heterogeneity, yet accurate cell-type annotation remains challenging due to data sparsity, technical noise, and variability across tissues, platforms, and species. Many existing annotation tools depend on a single form of prior knowledge, such as marker genes or reference profiles, which can limit performance when these resources are incomplete or inconsistent. Here, we present scANMF, a prior- and graph-regularized non-negative matrix factorization framework that integrates marker-gene information, partial label supervision, and the local manifold structure into a unified annotation model. scANMF factorizes the expression matrix into interpretable gene–factor and cell–factor representations, enabling accurate annotation in settings with limited or noisy prior information. Across multiple real scRNA-seq collections, scANMF achieved a high annotation accuracy in within-dataset, cross-platform, and cross-species evaluations. The method remained stable under varying levels of label sparsity and marker-gene noise and showed a broad robustness to hyperparameter choices. Ablation analyses indicated that marker priors, label supervision, and graph regularization contribute complementary information to the overall performance. These results support scANMF as a practical and robust framework for single-cell annotation, particularly in applications where high-quality prior knowledge is restricted.