emisbrooke / GENERALIST

GENERALIST: An efficient generative model for protein sequence families

Authors: Hoda Akl, Brooke Emison, Xiaochuan Zhao , Arup Mondal, Alberto Perez, Purushottam Dixit

Generative Model for protein sequences and generally for categorical data.

What's in this repo?

• src/

  Contains the source code for GENERALIST , and functions that allow performance assessment.

• jupyter/

  Contains jupyter notebooks that run the inference, generate new data and run tests on the model.

• benchmark/

  Contains implementation of published code and other developed code to compare other models (bmdca, ardca, VAE) to GENERALIST.

• todo.txt

  Contains list of to do items and ideas for this repo.

University of Florida

Physics Department

Laboratory of Computational Biophysics

2022

contact:

Hoda Akl : [e-mail]

Brooke Emison : [e-mail]

Purushottam Dixit: [e-mail]