Demo
We designed the IDPET Python package to facilitate the study and analysis of conformational ensembles of intrinsically disordered proteins. These proteins, known for their dynamic and highly variable structures, play a fundamental role in various biological processes.
Here, we highlight four different types of analyses that can be performed using IDPET. For more details you can also check the jupyter notebooks provided in the github repository.
Notebooks Overview
Here’s a summary of the example notebooks available in the github repository:
comparing_ensembles
Compare multiple conformational ensembles using selected metrics and visualizations.
featurization
Generate numerical features from protein ensembles for downstream analysis.
kpca_analysis
Perform Kernel PCA to capture non-linear variance in ensemble structures.
loading_data
Load and preprocess ensemble data from various formats.
pca_analysis
Principal Component Analysis (PCA) for dimensionality reduction and visualization.
plot_customization
Customize plots for clarity and publication-quality visualizations.
sh3_example
Case study: global and local analysis of the SH3 domain of the Drkn protein.
tsne_analysis
t-SNE embedding of ensemble features to explore local structure.
umap_analysis
UMAP embedding for global manifold learning and visualization.



