Can I use this skill for large datasets that don't fit in RAM?

Yes, this skill provides specific guidance on using 'backed mode' and sparse matrices to process massive datasets efficiently without crashing your system.

Does it support multimodal data?

While AnnData is primarily for unimodal data, this skill includes patterns for integrating with MuData and AnnCollection for multimodal and multi-sample biological analysis.

What is an AnnData object?

An AnnData object is a Python data structure that stores a primary data matrix (X) alongside rich metadata for observations (rows) and variables (columns) in a single, unified object.

How does AnnData relate to Scanpy?

AnnData is the foundational data structure used by Scanpy; this skill helps you prepare and manage data specifically for Scanpy analysis pipelines and visualizations.

Which file formats are supported for input and output?

It supports a wide range of formats including h5ad (native), Zarr, MTX, Loom, CSV, and 10X Genomics HDF5 files.

AnnData Genomics & Data Science

Name: AnnData Genomics & Data Science
Author: ricable

byricable

•

数据科学与机器学习

Manages annotated data matrices and metadata for single-cell genomics and large-scale biological datasets in Python.

AnnData is a specialized skill for handling annotated data matrices (X) alongside observation (obs) and variable (var) metadata. It serves as the foundational framework for the scverse ecosystem, enabling efficient storage, manipulation, and analysis of single-cell RNA-seq and other high-dimensional biological data. This skill helps users perform complex data operations like reading h5ad files, subsetting large datasets, and integrating with tools like Scanpy while following best practices for memory management and sparse matrix handling.

主要功能

01Advanced concatenation strategies for merging multiple experimental batches.

02Efficient data subsetting and filtering using metadata-driven conditions.

03Read and write multiple formats including h5ad, Zarr, CSV, and 10X Genomics h5.

04Memory-optimized operations using sparse matrices and on-disk backed mode.

051 GitHub stars

06Seamless integration with the scverse ecosystem including Scanpy and scvi-tools.

使用场景

01Processing and quality control of single-cell RNA-sequencing (scRNA-seq) datasets.

02Building memory-efficient data loaders for deep learning models in genomics.

03Integrating multiple biological datasets with complex observation and variable metadata.

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add ricable/ultimate-ai-agent anndata

For use in Claude.ai and ChatGPT

Download Skill