Skip to content

An anomaly detection method specifically designed for microbiome data.

Notifications You must be signed in to change notification settings

borenstein-lab/KADAIF

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

KADAIF

An anomaly detection method specifically designed for microbiome data.

This Github repository contains three folder:

  1. src - Contains the implementation of KADAIF (MicrobiomeIsolationForest.py and KADAIF.py), an implementation of CLOUD (published by Montassier et al.), and scripts for contamination and mislabeling tests as described in the manuscript.
  2. run_on_datasets - Bash and Python scripts for running and reproducing the specific mislabeling and contamination tests outlined in the manuscript. Due to GitHub file size limitations, raw data and results are not included.
  3. analysis - Jupyter notebooks with the analysis results from the manuscript.

For details on KADAIF's implementation, attributes and functions, see here:

Schematic illustration of KADAIF

About

An anomaly detection method specifically designed for microbiome data.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published