IDPEnsembleTools

---

IDPEnsembleTools: An Open-Source Library for Analysis of Conformational Ensembles of Disordered Proteins

IDPEnsembleTools is a Python package designed to facilitate the loading, analysis, and comparison of multiple conformational ensembles of intrinsically disordered proteins (IDPs).

It supports various input formats such as .pdb, .xtc, and .dcd, and enables users to extract both global and local structural features, perform dimensionality reduction, and compute similarity scores between ensembles.

---

Documentation

Full documentation is available at:
https://bioComputingUP.github.io/EnsembleTools

---

Features

With IDPEnsembleTools, you can:

• Extract global features of structural ensembles:

  • Radius of gyration (Rg)
  • Asphericity
  • Prolateness
  • End-to-end distance

• Extract local features:

  • Interatomic distances
  • Phi–psi angles
  • Alpha-helix content

• Perform dimensionality reduction on ensemble features:

  • PCA
  • UMAP
  • t-SNE

• Compare structural ensembles using:

  • Jensen-Shannon (JS) divergence
  • Visualize similarity matrices

---

Example Notebooks

The notebooks/ directory contains a collection of Jupyter notebooks that demonstrate how to use the EnsembleTools package. These examples cover key functionalities such as ensemble comparison, dimensionality reduction (PCA, t-SNE, UMAP), feature extraction, and visualization customization. They serve both as tutorials and reproducible workflows for analyzing disordered protein ensembles.

Notebook	Description	Link
comparing_ensembles.ipynb	Compare multiple conformational ensembles using selected metrics and visualizations.	View
featurization.ipynb	Generate numerical features from protein ensembles for downstream analysis.	View
kpca_analysis.ipynb	Perform Kernel PCA to capture non-linear variance in ensemble structures.	View
loading_data.ipynb	Load and preprocess ensemble data from various formats.	View
pca_analysis.ipynb	Principal Component Analysis (PCA) for dimensionality reduction and visualization.	View
plot_customization.ipynb	Customize plots for clarity and publication-quality visualizations.	View
sh3_example.ipynb	Case study: global and local analysis of the SH3 domain of the Drk protein.	View
tsne_analysis.ipynb	t-SNE embedding of ensemble features to explore local structure.	View
umap_analysis.ipynb	UMAP embedding of ensemble features and visualization.	View

---

Installation

It is recommended to install idpet in a clean virtual environment to avoid conflicts with existing packages.

🔹 Option 1: Using conda (if you use Anaconda/Miniconda)

# Create and activate a new conda environment
conda create -n idpet-env python=3.9
conda activate idpet-env

# Install the package from PyPI
pip install idpet

🔹 Option 2: Using venv (standard Python)

# Create a new virtual environment (Python 3.7+)
python -m venv idpet-env

# Activate the environment
# On Linux/macOS:
source idpet-env/bin/activate
# On Windows:
idpet-env\Scripts\activate

# Upgrade pip and install the package
pip install --upgrade pip
pip install idpet 

Developer Installation (from source)

git clone https://github.com/BioComputingUP/EnsembleTools.git
cd idpet
pip install -e .

License

This project is licensed under the MIT License.