ISCB Innovator Award Keynote
William Stafford Noble
Department of Genome Sciences; Department of Computer Science and Engineering
University of Washington, Seattle, United States
Time: Monday, July 22, 8:30 am - 9:30 am
Room: San Francisco
The ISCB Innovator Award, which is given to a leading scientist who is within a decade and half of receiving her or his PhD degree, and has consistently made outstanding contributions to the field and continues to forge new directions. William Stafford Noble the 2019 winner of the ISCB Innovator Award.
Many machine learning methods work by translating data points from the space in which they reside to a new, latent space of either higher or lower dimension. In this talk, I will describe three settings in which a latent representation can help us make sense of complex genomic or proteomic data. In one case, we train a deep tensor factorization model to learn latent representations of genomics assay types, cell types and genomic positions. These learned embeddings then turn out to be useful not only for imputing new genomics experiments, but also for a variety of other downstream machine learning tasks. In a second setting, we train a siamese deep neural network to embed tandem mass spectra into a latent space, such that spectra generated by the same peptide are close together. This learned embedding then provides a flexible framework for jointly analyzing hundreds of mass spectrometry experiments. Finally, I will describe how an unsupervised embedding approach can map diverse types of single-cell measurements into a latent space, effectively providing an in silico co-assay for experiments performed on similar sets of cells but using different experimental techniques.
William Stafford Noble received the Ph.D. in computer science and cognitive science from UC San Diego in 1998. After a one-year postdoc with David Haussler at UC Santa Cruz, he became an Assistant Professor in the Department of Computer Science at Columbia University. In 2002, he joined the faculty of the Department of Genome Sciences at the University of Washington. His research group develops and applies statistical and machine learning techniques for modeling and understanding biological processes at the molecular level. Noble is a Fellow of the International Society for Computational Biology and currently chairs the NIH Biodata Management and Analysis Study section. He is the author of >230 peer reviewed publications and has advised 21 postdoctoral fellows and 15 graduate students, including current faculty members at Columbia, UCLA, UC Irvine, University of Delaware, Colorado State University, University of Toronto, University of British Columbia, and others.