Segway 2.0: Gaussian mixture models and minibatch training

Abstract 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 ab...

Full description

Saved in:
Bibliographic Details
Published inBioinformatics Vol. 34; no. 4; pp. 669 - 671
Main Authors Chan, Rachel C W, Libbrecht, Maxwell W, Roberts, Eric G, Bilmes, Jeffrey A, Noble, William Stafford, Hoffman, Michael M
Format Journal Article
LanguageEnglish
Published England Oxford University Press 15.02.2018
Subjects
Applications Notes
Eukaryota - genetics
Genomics - methods
Molecular Sequence Annotation - methods
Sequence Analysis, DNA - methods
Software
Online AccessGet full text

Cover

More Information
Summary:Abstract 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 http://segway.hoffmanlab.org. We have made available scripts (https://doi.org/10.5281/zenodo.802939) and datasets (https://doi.org/10.5281/zenodo.802906) for this paper's analysis. Supplementary information Supplementary data are available at Bioinformatics online.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Rachel C. W. Chan and Maxwell W. Libbrecht authors wish it to be known that these authors contributed equally.
Present address: School of Computing Science, Simon Fraser University, Burnaby, BC, Canada
ISSN:1367-4803
1460-2059
1367-4811
DOI:10.1093/bioinformatics/btx603