EVENTO
Novel, interpretable, machine learning approaches for discovery in genome-scale datasets
Tipo de evento: Seminário LNCC
Most computational approaches used for the genome-scale discovery of new links between molecular data and clinical observations areclassical, based on single measurements, or linear combinations thereof. A lot of biology is certain to be more complex than this, butlimited available data and limited computational resources make it difficult to go beyond these simple models, while preserving theinterpretability of the results. In my talk, I will discuss two cases in which our group created new and carefully calibrated computational approaches that do go beyond classical models. Both allowed us to discover and validate previously unknown associations between transcriptomic data and medically relevant phenotypes. And both models are highly interpretable and generic enough to be applied to a wide range of transcriptome analysis scenarios.References: Gwinner et al. (2017),https://doi.org/10.1093/bioinformatics/btw676, and Nikolayeva et al. (2018), https://doi.org/10.1093/infdis/jiy086
Data Início: 04/07/2019 Hora: 10:00 Data Fim: Hora: 11:00
Local: LNCC - Laboratório Nacional de Computação Ciêntifica - Auditorio A
Comitê Organizador: Benno Schwikowski - Institut Pasteur, França - -