CoGAPS Software
Coordinated Gene Activity in Pattern Sets (CoGAPS) identifies overlapping coregulation between genes and improves inference of biological process activity. CoGAPS achieves this improvement by combining an MCMC matrix factorization algorithm (GAPS) with a threshold-independent statistic inferring activity on gene sets.
The files provided here include an open source implementation of the GAPS algorithm in C++, using the infrastructure of JAGS version 2.1.0 called GAPS-JAGS and an R package called CoGAPS which serves as an interface the GAPS and CoGAPS algorithms.
Please read the Users Manual for installation and running instructions of CoGAPS. For any questions, please contact Elana Fertig or Michael Ochs.