Local Edge Machine (LEM)
Beginning with time-series gene expression data, the Local Edge Machine (LEM) seeks to find functional
network models capable of exhibiting the dynamic behavior of the data. It combines nonlinear kinetic
equations, a Bayesian framework, and a local approximation to the system of differential equations that
relies on sparse priors.

This file package servers as an image of the source code used in our recent paper only. For all the
programme output, please send email to Xin Guo. For latest version of LEM, see:
https://gitlab.com/biochron_open/lem

For information on running, see:
https://gitlab.com/biochron_open/lem

For mathematical details, see:
https://gitlab.com/biochron_open/lem

Copyright and License, see:
COPYRIGHT.txt
LICENSE.txt

Authors:
Xin Guo x<dot>guo<at>polyu<dot>edu<dot>hk
Kevin McGoff kmcgoff1<at>uncc<dot>edu
Anastasia Deckard anastasia<dot>deckard<at>duke<dot>edu
John Harer john<dot>harer<at>duke<dot>edu
