Our research focuses on the development of machine learning techniques for application to problems in molecular biology. We approach these problems using Bayesian techniques such as hidden Markov models, as well as support vector machines and related, non-Bayesian methods. Much of our work addresses two core problems in machine learning: incorporating domain-specific prior knowledge and learning from heterogeneous data. We apply our techniques to problems such as automatic gene finding, microarray expression analysis, gene functional classification, and protein remote homology detection.
J Liu, JT Halloran, JA Bilmes, RM Daza, C Lee, EM Mahen, D Prunkard, C Song, S Blau, MO Dorschner, VK Gadi, J Shendure, CA Blau, and WS Noble. “Comprehensive statistical inference of the clonal structure of cancer from multiple biopsies.” Scientific Reports. 7(1):16943, 2017.
MW Libbrecht, JA Bilmes and WS Noble. “Choosing non-redundant representative subsets of protein sequence data sets using submodular optimization.” Proteins. 86(4):454–466, 2018.
J Liu, D Lin, G Yardımcı, and WS Noble. “Unsupervised embedding of single-cell Hi-C data.” Bioinformatics (Proceedings of the ISMB). 34(13):i96–i104, 2018.
W Bai, J Bilmes and WS Noble. “Submodular generalized matching for peptide identification in tandem mass spectrometry.” IEEE Transactions in Computational Biology and Bioinformatics. 16(4):1168–1181, 2019.
A Bertero, PA Fields, V Ramani, G Bonora, G Yardımcı, H Reinecke, L Pabon, WS Noble, J Shendure, CE Murry. “Dynamics of genome reorganization during human cardiogenesis reveal an RBM20- dependent splicing factory.” Nature Communications. 10(1):1538, 2019.
DF Read, K Cook, YY Lu, K Le Roch, and WS Noble. “Predicting gene expression in the human malaria parasite Plasmodium falciparum.” PLOS Computational Biology. 15(9):e1007329, 2019.
J Schreiber, TJ Durham, J Bilmes, WS Noble. “Multi-scale deep tensor factorization learns a latent representation of the human epigenome.” Genome Biology. 21:81, 2020.