Supervised and self-supervised autoencoders to identify the mechanistic basis for biochemical differences between protein variants.
If you use 'DiffNets' for published research, please cite us:
M.D. Ward, M.I. Zimmerman, S. Swamidass, G.R. Bowman. DiffNets: Self-supervised deep learning to identify the mechanistic basis for biochemical differences between protein variants. bioRxiv. DOI: 10.1101/2020.07.01.182725, 2020.
-python 3.6
-scipy, sklearn
-enspara -> which requires (MDTraj=1.8,numpy=1.14,cython, mpi4py)
-pytorch
Follow line-by-line instructions here.
While the above install should be simple to follow, a more concise install is in the works.
DiffNets uses sphinx for documentation. They are a work in progress, but can be found here.
Testing is in early stages. We use pytest.
cd tests
pytestFor a brief tutorial on how to use DiffNets as a command line interface (cli) please visit our documnetation page here. We recommend using the CLI to get started with diffnets.
For examples on how to use the API, view docs/example_api_scripts
Copyright (c) 2020, Michael D. Ward, Bowman Lab
Project based on the Computational Molecular Science Python Cookiecutter version 1.3.