single-popv-annotation

What problem does it solve?

This Skill automates the complex and time-consuming process of annotating cell types in single-cell RNA sequencing data by leveraging multiple algorithms and a consensus voting mechanism.

Core Features & Use Cases

• Multi-Algorithm Annotation: Integrates up to 10 different cell type classification algorithms (e.g., SCVI, SCANVI, CellTypist) for robust predictions.
• Consensus Voting: Aggregates predictions from multiple algorithms to produce a more reliable and robust cell type assignment.
• Ontology-Aware Annotation: Supports hierarchical label resolution using the Cell Ontology (CL) for improved accuracy.
• Pretrained Models: Allows the use of pre-trained models from a hub for faster annotation, especially with large references.
• Use Case: Annotate a new single-cell dataset of immune cells by comparing it against a comprehensive reference atlas, ensuring accurate identification of T-cells, B-cells, and other immune populations.

Quick Start

Use the single-popv-annotation skill to annotate query data against a reference dataset using a majority vote of all available algorithms.