datasets-loading

Load curated bioinformatics datasets and generate configurable mock datasets.

32|5|Updated Mar 12, 2026

Search Tags:#bioinformatics #omicverse #mock data #data loading #datasets #gene sets

Ready to run

npx skills add https://github.com/Starlitnightly/omicclaw --skill datasets-loading

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: datasets-loading
Source: https://github.com/Starlitnightly/omicclaw/tree/main/src/omicverse_skills/skills/datasets-loading
Command: npx skills add https://github.com/Starlitnightly/omicclaw --skill datasets-loading

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires omicverse, scanpy, anndata, numpy, pandas, tqdm, requests, muon, importlib.resources, and includes references (resource) components.

What problem does it solve?

This Skill simplifies the process of accessing and using standard bioinformatics datasets and generating synthetic data for testing and development, eliminating the need for manual downloads and complex setup.

Core Features & Use Cases

Access to 30+ built-in datasets: Includes single-cell, RNA velocity, spatial, multiome, and bulk RNA-seq data.
Mock data generation: Create synthetic datasets for pipeline testing without network access.
Predefined gene set signatures: Load curated gene sets for scoring tasks.
Use Case: Load the PBMC3k dataset to quickly test a new clustering algorithm or generate a mock dataset to demonstrate a visualization function.

Quick Start

Load the pbmc3k dataset using the datasets loading skill.

Frequently Asked Questions about datasets-loading

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I load standard bioinformatics datasets for single-cell RNA-seq analysis?▼

You can load single-cell RNA-seq datasets by accessing over 30 built-in bioinformatics datasets, including single-cell, spatial, and bulk RNA-seq data. The Skill provides automatic download and caching to simplify reproducible research.

Can I generate mock single-cell data for pipeline testing without network access?▼

Yes, you can generate configurable mock datasets for pipeline testing and development without network access. This allows you to demonstrate visualization functions or test clustering algorithms offline.

Does the data loader work with scanpy and anndata workflows?▼

The data loader integrates seamlessly with scanpy and anndata workflows. It supports single-cell, RNA velocity, spatial, multiome, and bulk RNA-seq data formats directly compatible with these frameworks.

How do I load predefined gene set signatures for scoring tasks?▼

You can load predefined gene set signatures for scoring tasks by using the built-in curated gene sets provided. These signatures are ready for integration into your bioinformatics analysis pipelines.

What are the limitations when downloading bulk RNA-seq datasets?▼

The system includes fallback mechanisms for downloading bulk RNA-seq datasets, but limitations include dependence on external hosting for the 30+ built-in datasets. Mock data generation is available as an offline alternative.