SkillAgentSearch skills...

ScEiaD

Snakefile-based process to turn 1.4 million ocular cells into a unified meta-atlas

Install / Use

/learn @davemcg/ScEiaD
About this skill

Quality Score

0/100

Supported Platforms

Universal

README

scEiaD

Harmonize publicly available scRNA-seq datasets for the eye

The code base that underlies the data for plae.nei.nih.gov

Version 0.92

Selected parameters for integration

  • scANVI (scVI version 0.13)
  • 4000 HVG
  • 5 epochs
  • 15 latent dimensions

Yaml files

  • config.yaml for SnakeQUANT and SnakePOP
  • configSCEIAD.yaml for SnakeSCEIAD

Numbers

  • 44 datasets
  • 4 species (human, mouse, macaque, chicken)
  • 1,136,041 cells
  • ~60 different cell types
<img width="329" alt="image" src="https://user-images.githubusercontent.com/10225430/189389690-13381192-79fa-48df-945f-8a439bcfcb09.png">

Data

Moar data?

Visit plae.nei.nih.gov -> Data for differential gene expression tables, study level counts, and more.

How do I add my own data to scEiaD?

It is possible! Even better, you don't have to ask me! Or tell me!

Interactive colab notebook

View on GitHub
GitHub Stars26
CategoryDevelopment
Updated8mo ago
Forks4

Languages

Jupyter Notebook

Security Score

82/100

Audited on Jul 9, 2025

No findings