Antigen encoding theory: Publication-ready version with documentation

Code to reproduce the theoretical results of

Sooraj R. Achar^#, François X. P. Bourassa^#, Thomas J. Rademaker^#, Angela Lee, Taisuke Kondo, Emanuel Salazar-Cavazos, John S. Davies, Naomi Taylor, Paul François, and Grégoire Altan-Bonnet. "Universal antigen encoding of T cell activation from high dimensional cytokine data", submitted, 2021. (^#: these authors contributed equally)

The following main theoretical analyses are included in this repository:

• Modelling cytokine dynamics in latent space
• Generating cytokine data with reconstruction from the latent space
• Computing the channel capacity of cytokine dynamics for antigen quality.

All cytokine data necessary to run the code is included in the Github repository. Also included are neural network weights that produce the latent space used throughout the paper, and a few other parameters (e.g., antigen functional EC₅₀s).

More details on the Github where the code is hosted: https://github.com/frbourassa/antigen_encoding_theory

More neural networks can be trained and more cytokine data processing and fitting can be done using the antigen-encoding-pipeline user interface, also hosted on Github.