Related Experiment Video
Updated: Aug 5, 2026
10:12
Droplet Barcoding-Based Single Cell Transcriptomics of Adult Mammalian Tissues
Published on: January 10, 2019
Protocol for automated optimization of feature selection and clustering parameters in single-cell RNA-seq using
1Department of Neurosurgery, Massachusetts General Hospital, Boston, MA, USA; Department of Neurosurgery, Harvard Medical School, Boston, MA, USA.
STAR Protocols
|August 1, 2026
Summary
scAutoTune automates parameter optimization for single-cell RNA sequencing (RNA-seq) analysis. This protocol enhances feature selection and clustering for more interpretable results.
Area of Science:
- Computational Biology
- Bioinformatics
- Genomics
Background:
- Single-cell RNA sequencing (scRNA-seq) analysis demands precise parameter tuning for feature selection and clustering.
- Suboptimal parameters can lead to inaccurate biological interpretations.
Purpose of the Study:
- To introduce scAutoTune, a protocol for automated optimization of scRNA-seq parameters.
- To provide a reproducible workflow for enhancing scRNA-seq data analysis.
Main Methods:
- Development and implementation of the scAutoTune protocol.
- Utilizing grid-based parameter sweeping with optional Harmony batch correction.
- Employing silhouette metrics and generalized additive model (GAM)-smoothed landscapes for performance evaluation.
Main Results:
- Demonstration of scAutoTune's capability to optimize feature selection and clustering parameters.
- Generation of improved uniform manifold approximation and projection (UMAP) embeddings.
- Facilitation of more interpretable clustering of single-cell data.
Conclusions:
- scAutoTune offers an automated and efficient approach to optimize scRNA-seq analysis.
- The protocol aids researchers in achieving more robust and reproducible single-cell data interpretation.
