Guest Talk
Prof. Hiroshi Mamitsuka
Bio-Knowledge Engineering Research Laboratory
Hiroshi Mamitsuka is a Professor at the Bioinformatics Center at Kyoto University in Japan.
The Bio-Knowledge Engineering Research Laboratory is interested in graphs and networks in biology, chemistry and medical sciences, which include metabolic networks, protein-protein interactions and chemical compounds. They have developed original techniques in machine learning and data mining for analyzing these graphs and networks, occasionally combining with table-format datasets, such as gene expression and chemical properties. Furthermore, they have applied the developed techniques to real data to demonstrate the performance of the methods and further to find new scientific insights.
In his talk 'Machine learning for multiomics data: realizing precise drug response prediction' Hiroshi Mamitsuka explained how Bayesian Data IntegratiVE Learning for Precise Drug ResponSE Prediction (DIVERSE) can be used to predict biomarkers from multiomics data. Biomarkers serve as essential tools for the diagnostics of complex diseases and improve the treatment of patients.
Abstract
Detecting predictive biomarkers from multiomics data is important for precision medicine, to improve diagnostics of complex diseases and for better treatments. This needs substantial experimental efforts that are made difficult by the heterogeneity of cell lines and huge cost. An effective solution is to build a computational model over the diverse omics data, including genomic, molecular, and environmental information. However, choosing informative and reliable data sources from among the different types of data is a challenging problem.
We propose DIVERSE, a framework of Bayesian importance-weighted tri- and bi-matrix factorization (DIVERSE3 or DIVERSE2) to predict drug responses from data of cell lines, drugs, and gene interactions. DIVERSE integrates the data sources systematically, in a step-wise manner, examining the importance of each added data set in turn. More concretelly, we sequentially integrate five different data sets, which have not all been combined in earlier bioinformatic methods for predicting drug responses. Empirical experiments show that DIVERSE clearly outperformed five other methods including three state-of-the-art approaches, under cross-validation, particularly in out-of-matrix prediction, which is closer to the setting of real use cases and more challenging than simpler in-matrix prediction. Additionally, case studies for discovering new drugs further confirmed the performance advantage of DIVERSE.