Welcome to scGEAToolbox’s documentation!
Single-cell RNA sequencing (scRNA-seq) technology has revolutionized the way research is done in biomedical sciences. It provides an unprecedented level of resolution across individual cells for studying cell heterogeneity and gene expression variability. Analyzing scRNA-seq data is challenging though, due to the sparsity and high dimensionality of the data. scGEAToolbox is a MATLAB toolbox for scRNA-seq data analysis. It contains a comprehensive set of functions for quality control, normalization, feature selection, batch correction, imputation, cell clustering, trajectory/pseudotime analysis, cell type annotation, differential expression and variability testing, gene set scoring, and gene regulatory network construction, which can be combined into custom workflows. Most functions are implemented in native MATLAB; wrapper functions let you call third-party tools written in MATLAB, Python or R from the same session. scGEAToolbox is equipped with sophisticated graphical user interfaces (GUIs), making it an easy-to-use application for quick data processing.
Three ways to use it
SCGEATOOL, the App Designer GUI: run
scgeatoolin MATLAB. See SCGEATOOL.The function API, at the matrix level or through the
SingleCellExperimentclass. See Getting Started and Function Reference.The
scgeacommand line, for batch and pipeline work without opening MATLAB. See Command-Line Interface.
Official Websites and Social Networks
Please, visit the official website 
of scGEAToolbox for further information.
Main Documents
- Installation
- Getting Started
- SCGEATOOL
- Command-Line Interface
- Code Formulas
- Import 10x Genomics files
- Process expression matrix, X and gene list, g
- t-SNE embedding of cells using highly variable genes (HVGs)
- An example pipeline for raw data processing
- An example pipeline for processing 10x data folder
- Merge two data sets (WT and KO)
- Import other file formats
- Export an SCE for other tools
- Variance-stabilizing transformation
- Doublet detection
- Subsample a large data set
- Score cells against a gene signature
- Build and inspect a gene regulatory network
- Run a step from the shell
- Case Studies and Tutorials
- Demo 1: Filter, Normalization and Batch Correction of Data
- Demo 2: Feature Selection Functions
- Demo 3: Visualization Functions
- Demo 4: Clustering Functions
- Demo 5: Pseudotime Analysis and Gene Network Functions
- Demo 6: DE Analysis and Marker Gene Identification Functions
- Demo 7: Object-Level Workflow with
SingleCellExperiment - Demo 8: Differential Expression, Variability and Signature Scoring
- Function Reference
- Data import
- Data export
- Quality control and filtering
- Normalization and transformation
- Feature selection
- Dimensionality reduction
- Clustering
- Differential analysis
- Gene sets, pathways and scoring
- Cell type annotation
- Trajectory and dynamics
- Gene regulatory networks
- Copy number and malignancy
- Glycobiology
- Visualization
- The
SingleCellExperimentclass - Wrappers for external tools
- Packages
Social Networks