Skip to content

README.md

Latest commit

 

History

History
28 lines (21 loc) · 1.37 KB

README.md

File metadata and controls

28 lines (21 loc) · 1.37 KB

Graph Structured Neural Networks (GSNN)

DOI RTD

Overview

The GSNN method is a algorithm that integrates prior knowledge of latent variable interactions directly into neural architecture. See the read-the-docs for documentation.

Citation

Please cite the DOI listed above or the pre-print below:

@article {Evans2024.02.28.582164,
	author = {Nathaniel J. Evans and Gordon B. Mills and Guanming Wu and Xubo Song and Shannon McWeeney},
	title = {Graph Structured Neural Networks for Perturbation Biology},
	elocation-id = {2024.02.28.582164},
	year = {2024},
	doi = {10.1101/2024.02.28.582164},
	publisher = {Cold Spring Harbor Laboratory},
	URL = {https://www.biorxiv.org/content/early/2024/02/29/2024.02.28.582164},
	eprint = {https://www.biorxiv.org/content/early/2024/02/29/2024.02.28.582164.full.pdf},
	journal = {bioRxiv}
}

Please note that the figures and analysis presented in the preprint can be run using the code available from this release v1.0.0. We have since migrated much of the bio-specific analysis for the GSNN pre-print paper to this auxillary library.