RT Journal Article
SR Electronic
T1 Segway 2.0: Gaussian mixture models and minibatch training
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 147470
DO 10.1101/147470
A1 Rachel C.W. Chan
A1 Maxwell W. Libbrecht
A1 Eric G. Roberts
A1 William Stafford Noble
A1 Michael M. Hoffman
YR 2017
UL http://biorxiv.org/content/early/2017/06/08/147470.abstract
AB Summary Segway performs semi-automated genome annotation, discovering joint patterns across multiple genomic signal datasets. We discuss a major new version of Segway and highlight its ability to model data with substantially greater accuracy. Major enhancements in Segway 2.0 include the ability to model data with a mixture of Gaussians, enabling capture of arbitrarily complex signal distributions, and minibatch training, leading to better learned parameters.Availability and Implementation Segway and its source code are freely available for download at https://segway.hoffmanlab.org. We have made available scripts (https://doi.org/10.5281/zenodo.802940) and datasets (https://doi.org/10.5281/zenodo.802907) for this paper’s analysis.Contact michael.hoffman{at}utoronto.ca