UNIFAN: A Tool for Unsupervised Single-Cell Clustering and Annotation.

Area of Science:

• Bioinformatics
• Computational Biology
• Genomics

Background:

• Single-cell RNA sequencing (scRNA-seq) generates high-dimensional data requiring robust analytical tools.
• Accurate cell type annotation is crucial for interpreting scRNA-seq experiments.
• Existing methods may lack efficiency or comprehensive utilization of biological context.

Purpose of the Study:

• To introduce UNIFAN, an unsupervised tool for cell type annotation of scRNA-seq data.
• To describe the installation and primary usage of UNIFAN for biological data analysis.
• To highlight the integration of pathway and biological process information in the annotation pipeline.

Main Methods:

• UNIFAN employs an unsupervised clustering approach for scRNA-seq data.
• The algorithm integrates pathway and biological process information into the clustering process.
• The software provides direct cell type annotations for identified clusters.

Main Results:

• UNIFAN successfully clusters and annotates cell types from scRNA-seq data.
• The tool's methodology effectively utilizes biological pathway information for improved annotation.
• The article details the practical steps for installing and implementing UNIFAN.

Conclusions:

• UNIFAN offers a valuable unsupervised approach for scRNA-seq cell type annotation.
• The integration of biological pathways enhances the accuracy and interpretability of annotations.
• This software provides a user-friendly solution for researchers analyzing single-cell expression data.