ICML 2015poster26 citations

PeakSeg: constrained optimal segmentation and supervised penalty learning for peak detection in count data

Toby Hocking, Guillem Rigaill, Guillaume Bourque

Abstract

Peak detection is a central problem in genomic data analysis, and current algorithms for this task are unsupervised and mostly effective for a single data type and pattern (e.g. H3K4me3 data with a sharp peak pattern). We propose PeakSeg, a new constrained maximum likelihood segmentation model for peak detection with an efficient inference algorithm: constrained dynamic programming. We investigate unsupervised and supervised learning of penalties for the critical model selection problem. We show that the supervised method has state-of-the-art peak detection across all data sets in a benchmark that includes both sharp H3K4me3 and broad H3K36me3 patterns.

BibTeX
@InProceedings{pmlr-v37-hocking15,
  title = 	 {PeakSeg: constrained optimal segmentation and supervised penalty learning for peak detection in count data},
  author = 	 {Hocking, Toby and Rigaill, Guillem and Bourque, Guillaume},
  booktitle = 	 {Proceedings of the 32nd International Conference on Machine Learning},
  pages = 	 {324--332},
  year = 	 {2015},
  editor = 	 {Bach, Francis and Blei, David},
  volume = 	 {37},
  series = 	 {Proceedings of Machine Learning Research},
  address = 	 {Lille, France},
  month = 	 {07--09 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v37/hocking15.pdf},
  url = 	 {https://proceedings.mlr.press/v37/hocking15.html},
  abstract = 	 {Peak detection is a central problem in genomic data analysis, and current algorithms for this task are unsupervised and mostly effective for a single data type and pattern (e.g. H3K4me3 data with a sharp peak pattern). We propose PeakSeg, a new constrained maximum likelihood segmentation model for peak detection with an efficient inference algorithm: constrained dynamic programming. We investigate unsupervised and supervised learning of penalties for the critical model selection problem. We show that the supervised method has state-of-the-art peak detection across all data sets in a benchmark that includes both sharp H3K4me3 and broad H3K36me3 patterns.}
}