Welcome to proteovae’s documentation!

This package aims at providing a consistent set of tools for implementing multi-task objective variational autoencoders. It was originally developed for uses in genomics data (hence the name proteo[mics]-vae).

News 📢

The first version of this package is now live ❤️🇮🇹🧑‍🔬! in subsequent realeases options for specifying different losses in the reconstruction objective will be available, as well as a cleaner embedding method for VAE objects.

proteovae:

• Models
• Trainers
• Disentanglement

Setup

To install the latest stable release of this library run the following using pip

$ pip install proteovae

For local installations try git cloning and installing the project repo

$ git clone git@github.com:nnethercott/proteovae.git
$ cd proteovae
$ pip install -e .

If you clone the proteovae repository you will access to the following:

• docs: The folder in which the documentation can be retrieved.

• examples: A list of ipynb tutorials and script describing some use cases for proteovae.

• src/proteovae: The main library which can be installed with pip.