AutoEncoders for Anomaly Detection tutorial using BioExcel Building Blocks (biobb)

This tutorial involves the use of a multilayer AutoEncoder (AE) for feature extraction and pattern recognition by analyzing Molecular Dynamic Simulations, step by step, using the BioExcel Building Blocks library (biobb).

Settings

Biobb modules used

biobb_pytorch: module collection to create and train ML & DL models using the popular PyTorch Python library.

Auxiliary libraries used

jupyter: Free software, open standards, and web services for interactive computing across all programming languages.
nglview: Jupyter/IPython widget to interactively view molecular structures and trajectories in notebooks.
numpy: The fundamental package for scientific computing with Python.
mdtraj: Read, write and analyze MD trajectories with only a few lines of Python code.
requests: Requests is an elegant and simple HTTP library for Python, built for human beings.
matplotlib: Matplotlib is a comprehensive library for creating static, animated, and interactive visualizations in Python.

IMPORTANT: if your computer is a mac ARM, please be sure that the chosen architecture in conda is ARM. If not sure, type the following instruction in your terminal before starting the creation of the environment:
conda config --env --set subdir osx-arm64
This instruction ensures that the installed torch dependency will match your architecture.

Conda Installation and Launch

git clone https://github.com/bioexcel/biobb_wf_autoencoder.git
cd biobb_wf_autoencoder
conda env create -f conda_env/environment.yml
conda activate biobb_wf_autoencoder
jupyter-notebook biobb_wf_autoencoder/notebooks/biobb_wf_autoencoder.ipynb

Tutorial

Click here to view tutorial in Read the Docs

Click here to execute tutorial in Binder

Click here to open tutorial in Google Colab

Version

2024.1 Release

Copyright & Licensing

This software has been developed in the MMB group at the BSC & IRB for the European BioExcel, funded by the European Commission (EU Horizon Europe 101093290, EU H2020 823830, EU H2020 675728).

(c) 2015-2024 Barcelona Supercomputing Center
(c) 2015-2024 Institute for Research in Biomedicine

Licensed under the Apache License 2.0, see the file LICENSE for details.