A Flexible Data-Driven Framework for Correcting Coarsely Annotated scRNA-seq Data

Ruiqing Zheng

doi:10.26599/BDMA.2025.9020009

A Flexible Data-Driven Framework for Correcting Coarsely Annotated scRNA-seq Data

2025-10-01

0

PRE

AI

DOI：10.26599/BDMA.2025.9020009

Original

Original request for help

Save

Abstract

En 中文

Cells are the fundamental units of life and exhibit significant diversity in structure, behavior, and function, known as cell heterogeneity. The advent and development of single-cell RNA sequencing (scRNA-seq) technology have provided a crucial data foundation for studying cellular heterogeneity. Currently, most computational methods based on scRNA-seq involve a sequential process of clustering followed by annotation. However, those clustering-based methods are susceptible to the selection of genes and clustering parameters, resulting in inaccuracies in cell annotation. To address this issue, we develop a flexible data-driven cell correction framework based on partially annotated scRNA-seq data. This framework employs a neighborhood purity strategy and global selection strategies to select the anchor cells. Then, it optimizes a prediction neural network model using a classification loss with a contrastive regularization term to correct the labels of the remaining cells. The validity of this correction framework is demonstrated through various assessments on real scRNA-seq datasets. Based on the correct labels of scRNA-seq data, we further assess the latest unsupervised clustering methods, thereby establishing a more objective benchmark to compare their performance.

Keywords:

Training

Sequential analysis

Annotations

Clustering methods

RNA

Neural networks

Pipelines

Predictive models

Reliability engineering

Web servers

single-cell RNA sequencing (scRNA-seq)

cell heterogeneity

cell annotation

supervised contrastive learning

A Flexible Data-Driven Framework for Correcting Coarsely Annotated scRNA-seq Data

Abstract

Journal

Organization