SingleCellNet

SingleCellNet classifies single-cell RNA sequencing (RNA-seq) data by comparing query datasets to reference datasets to assign cell identities across sequencing platforms and species.

Key Features:

• Quantitative Analysis: Employs a quantitative approach to classify cells using single-cell RNA-seq gene expression profiles.
• Cross-Platform and Cross-Species Classification: Performs classification across different sequencing platforms and across species.
• Reference-Based Comparison: Compares query single-cell RNA-seq datasets against reference datasets for cell identity assignment.
• Integration of Multiple Studies: Integrates reference data from multiple studies to leverage comprehensive training sets.
• Sensitivity and Specificity: Produces classification results with favorable sensitivity and specificity metrics.

Scientific Applications:

• Cell-Type Identification: Identifies unknown or ambiguous cell types within complex tissues using reference-based classification.
• Tissue Composition Analysis: Determines tissue cell-type composition from single-cell RNA-seq datasets.
• Cell Fate Engineering Evaluation: Evaluates outcomes of cell fate engineering experiments by comparing engineered cells to reference cell types.
• Developmental Program and Diversity Studies: Supports investigation of developmental programs and cellular diversity through cross-study comparisons.

Methodology:

SingleCellNet performs quantitative classification by comparing query single-cell RNA-seq gene expression profiles against reference datasets and integrating data from multiple studies.