A Hybrid Computational Intelligence Framework for scRNA-seq Imputation: Integrating scRecover and Random Forests

TL;DR

This paper introduces SCR-MF, a hybrid framework combining dropout detection and non-parametric imputation for scRNA-seq data, achieving high accuracy and efficiency while preserving biological signals.

Contribution

The study presents a novel two-stage workflow integrating scRecover and missForest for improved scRNA-seq data imputation.

Findings

SCR-MF outperforms existing methods in accuracy.

It maintains biological fidelity and interpretability.

The method is computationally efficient for mid-scale datasets.

Abstract

Single-cell RNA sequencing (scRNA-seq) enables transcriptomic profiling at cellular resolution but suffers from pervasive dropout events that obscure biological signals. We present SCR-MF, a modular two-stage workflow that combines principled dropout detection using scRecover with robust non-parametric imputation via missForest. Across public and simulated datasets, SCR-MF achieves robust and interpretable performance comparable to or exceeding existing imputation methods in most cases, while preserving biological fidelity and transparency. Runtime analysis demonstrates that SCR-MF provides a competitive balance between accuracy and computational efficiency, making it suitable for mid-scale single-cell datasets.