adadmire

Functions for detecting anomalies in molecular data sets using Mixed Graphical Models.

Installation

Enter the following commands in a shell like bash, zsh or powershell:

pip install -U adadmire

Usage

The usage example in this section requires that you first download the data files from the data folder. For a description of the contents of this folder, see section Data of the adadmire documentation site.

from adadmire import admire, penalty
import numpy as np

# Load example data
X = np.load('data/Feist_et_al/scaled_data_raw.npy') # continuous data
D = np.load('data/Feist_et_al/pheno.npy') # discrete data
levels = np.load('data/Feist_et_al/levels.npy') # levels of discrete variables

# Define lambda sequence of penalty values
lam = penalty(X, D, min= -2.25, max = -1.5, step =0.25)

# Get anomalies in continuous and discrete data
X_cor, n_cont, position_cont, D_cor, n_disc, position_disc = admire(X, D, levels, lam)
print(X_cor) # corrected X
print(n_cont) # number of continuous anomalies
print(position_cont) # position in X
print(D_cor) # corrected D
print(n_disc) # number of discrete anomalies
print(position_disc) # position in D

You can find more usage examples in the Usage section of adadmire's documentation site.

Documentation

You can find the full documentation for adadmire at spang-lab.github.io/adadmire. Amongst others, it includes chapters about:

• Installation
• Usage
• Modules
• Contributing
• Testing
• Documentation

Citation

If you use adadmire in your research, please cite:

Buck L, Schmidt T, Feist M, Schwarzfischer P, Kube D, Oefner PJ, Zacharias HU, Altenbuchinger M, Dettmer K, Gronwald W, Spang R. Anomaly detection in mixed high-dimensional molecular data. Bioinformatics. 2023;39(8):btad501. doi:10.1093/bioinformatics/btad501