Unsupervised pattern discovery in human chromatin structure through genomic segmentation.
Nature methods. 2012 May;9(5):473-6.
- Abstract
- We trained Segway, a dynamic Bayesian network method, simultaneously on chromatin data from multiple experiments, including positions of histone modifications, transcription-factor binding and open chromatin, all derived from a human chronic myeloid leukemia cell line. In an unsupervised fashion, we identified patterns associated with transcription start sites, gene ends, enhancers, transcriptional regulator CTCF-binding regions and repressed regions. Software and genome browser tracks are at http://noble.gs.washington.edu/proj/segway/.
- References
Related data
- Available data
- genomic annotations
- File format
- BED
- Data summary
- Segway uses a dynamic Bayesian network model to automatically annotate the genome with labels corresponding to enhancers, promoters, transcribed regions, etc. The model is trained on histone modification and TF binding ChIP-seq data as well as chromatin accessibility data.