@inproceedings{schein2021doubly,
author = {Schein, Aaron and Nagulpally, Anjali and Wallach, Hanna and Flaherty, Patrick},
title = {Doubly Non-Central Beta Matrix Factorization for DNA Methylation Data},
booktitle = {Conference on Uncertainty in Artificial Intelligence (UAI) 2021},
year = {2021},
month = {June},
abstract = {We present a new non-negative matrix factorization model for (0,1) bounded-support data based on the doubly non-central beta (DNCB) distribution, a generalization of the beta distribution. The expressiveness of the DNCB distribution is particularly useful for modeling DNA methylation datasets, which are typically highly dispersed and multi-modal; however, the model structure is sufficiently general that it can be adapted to many other domains where latent representations of (0,1) bounded-support data are of interest. Although the DNCB distribution lacks a closed-form conjugate prior, several augmentations let us derive an efficient posterior inference algorithm composed entirely of analytic updates. Our model improves out-of-sample predictive performance on both real and synthetic DNA methylation datasets over state-of-the-art methods in bioinformatics. In addition, our model yields meaningful latent representations that accord with existing biological knowledge.},
url = {http://approjects.co.za/?big=en-us/research/publication/doubly-non-central-beta-matrix-factorization-for-dna-methylation-data/},
}