Does this skill support trajectory inference?

Yes, the skill includes patterns for trajectory analysis using PAGA (Partition-based Graph Abstraction) and diffusion pseudotime calculations.

What file formats does the Scanpy skill support?

The skill supports standard single-cell data formats including .h5ad (AnnData), 10X Genomics (MTX and H5), and CSV files.

Can this skill help with cell type annotation?

Yes, it provides automated and manual workflows for identifying marker genes through differential expression and mapping clusters to known biological cell types.

Does it include visualization capabilities?

Absolutely. It includes specialized functions for generating UMAP plots, heatmaps, dot plots, and violin plots designed for both QC and result presentation.

Scanpy Single-Cell Analysis

Name: Scanpy Single-Cell Analysis
Author: ricable

byricable

•

데이터 과학 및 ML

Performs end-to-end single-cell RNA-seq analysis workflows including quality control, clustering, and cell type annotation using the Scanpy toolkit.

소개

This skill provides specialized capabilities for bioinformatics and computational biology, specifically focusing on single-cell RNA sequencing (scRNA-seq) data analysis. It leverages the Scanpy library to manage complex AnnData objects, automate quality control metrics, perform high-dimensional data reduction, and generate publication-quality visualizations. By providing standardized implementation patterns for normalization, feature selection, and clustering, it enables researchers to efficiently transform raw sequencing counts into biological insights through advanced tools like Leiden clustering and trajectory inference.

주요 기능

Advanced Leiden and Louvain clustering for cell population identification
Biological interpretation tools for marker gene ranking and trajectory analysis
High-performance dimensionality reduction using PCA, UMAP, and t-SNE
Comprehensive visualization suite for heatmaps, dot plots, and violin plots
1 GitHub stars
Automated Quality Control (QC) and mitochondrial gene filtering

사용 사례

Conducting trajectory inference and pseudotime analysis for developmental studies
Processing raw 10X Genomics or .h5ad data into annotated cell clusters
Generating publication-ready figures and differential expression reports

소개

주요 기능

Advanced Leiden and Louvain clustering for cell population identification
Biological interpretation tools for marker gene ranking and trajectory analysis
High-performance dimensionality reduction using PCA, UMAP, and t-SNE
Comprehensive visualization suite for heatmaps, dot plots, and violin plots
1 GitHub stars
Automated Quality Control (QC) and mitochondrial gene filtering

사용 사례

Conducting trajectory inference and pseudotime analysis for developmental studies
Processing raw 10X Genomics or .h5ad data into annotated cell clusters
Generating publication-ready figures and differential expression reports