scverse/scanpy

Features

• Single-Cell Analysis - Provides a comprehensive toolkit for preprocessing, visualizing, and analyzing large-scale single-cell gene expression datasets.
• Cellular State Trajectories - Models transitions between cell states over time to reconstruct biological development and differentiation processes.
• Biological Data Visualization - Generates graphical representations of cell populations and gene expression patterns to identify biological trends.
• Genomic Preprocessing Pipelines - Provides memory-efficient pipelines for cleaning and preparing large-scale single-cell datasets.
• Genome Visualization - Provides a suite of tools for rendering and exploring genomic data and sequence diagrams.
• Leiden Community Detection - Implements the Leiden algorithm to identify distinct cell clusters within gene expression graphs.
• Cellular State Projections - Implements graph-based manifold learning to project high-dimensional cell states into low-dimensional visual spaces.
• Genomic Data Cleaning - Provides vectorized preprocessing pipelines using NumPy and SciPy for high-throughput normalization and scaling of cell data.
• Genomic Expression Arrays - Provides memory-efficient storage of high-dimensional gene expression matrices and cell metadata using sparse arrays.
• Biological Trajectory Inferences - Models developmental transitions between cell clusters to reconstruct biological differentiation and development paths.
• Cellular Trajectory Inference Tools - Models transitions between cell states to reconstruct biological development and differentiation processes.
• Differential Gene Expression Tests - Provides statistical testing to compare gene expression levels between cell groups to identify characteristic biological markers.
• Sparse Linear Algebra Routines - Performs large-scale linear algebra using compressed sparse row formats for high-dimensional genomic data.
• Python Bioinformatics Modules - Toolkit for single-cell gene expression analysis.

Star history