One Method Does Not Fit All: A Large-Scale Benchmark of Imputation Methods for Single-Cell RNA Sequencing Data

Read full text Summarise with VIRAT
Authors: Yuichiro Iwashita, Ahtisham Fazeel Abbasi, Koichi Kise, Andreas R. Dengel, Muhammad Nabeel Asim
Cited by: 0
References: 117

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Single-cell RNA sequencing (scRNA-seq) enables gene expression profiling at cellular resolution but is inherently affected by sparsity caused by dropout events, where expressed genes are recorded as zeros due to technical limitations. These dropout events distort gene expression distributions and compromise downstream analyses. To address this challenge, numerous traditional and deep learning (DL)-based imputation methods have been developed to detect dropout events and impute their true expression values. However, evaluations of these methods have largely been restricted to specific downstream tasks and limited datasets, and large-scale systematic comparisons under standardized benchmarking conditions are lacking. To fill this gap, we present a comprehensive framework that evaluates 16 imputation methods across 10 experimental protocols, 6 downstream tasks, and 30 benchmark datasets. Through extensive experimentation, we systematically investigate the strengths, limitations, and task-specific performance of these methods under consistent evaluation settings. Our results show that traditional methods perform relatively better across a wide range of downstream tasks, whereas DL-based methods are more variable. In addition, strong performance in numerical gene expression recovery does not necessarily translate into improved biological interpretability in downstream analyses, including cell clustering, differential expression analysis, marker gene analysis, trajectory analysis, and cell type annotation. Furthermore, performance varies substantially across datasets, protocols, and downstream analyses, with no single method consistently outperforming the others. Our findings provide practical guidance for selecting imputation methods tailored to specific analytical objectives and underscore the importance of task-specific evaluation in scRNA-seq data analysis.

Fields of Study & Subjects

Single-cell and spatial transcriptomics Gene expression and cancer classification Genomics and Phylogenetic Studies

Publication details

Journal / source
arXiv (Cornell University)
Publication date
25 March 2026
Language
EN
Document type
Preprint