報告題目: Leveraging the power of data-driven machine learning techniques to address significant biomedical classification problems
主講人: 宋江寧 (Jiangning Song), Monash University, Australia
線上講座: 騰訊會議，會議ID: 116 499 643, 會議密碼: 0521
Recent advances in high-throughput sequencing have significantly contributed to an ever-increasing gap between the number of gene products (‘proteins’) whose function is well characterized and those for which there is no functional annotation at all. Experimental techniques to determine the protein function are often expensive and time-consuming. Improving our ability to predict the functional phenotype from genotype is fundamental for understanding the underlying mechanisms of many genetic diseases. Machine-learning (ML) techniques based on statistical learning have recently emerged as efficient solutions to challenging problems of sequence classification, functional annotation or other biomedical classification tasks that were previously regarded difficult to address. In this talk, by combining our recent research works, I will present some important developments in computational algorithms and resources to functionally interpret massive heterogeneous biomedical datasets. In particular, I will highlight three representative research projects to illustrate how biomedical discovery can be alternatively catalysed by data-driven techniques. I will also discuss how ML methods can extract the predictive power from a variety of features that are derived from different aspects of the data and useful strategies that help to contribute to the performance of ML approaches.
Dr Song is an Associate Professor and group leader in the Monash Biomedicine Discovery Institute and Monash Data Futures Institute, Monash University, Australia. Trained as a bioinformatician and data-savvy scientist, he has a strong specialty in Artificial Intelligence, Bioinformatics, Comparative Genomics, Cancer Genomics, Computational Biomedicine, Data Mining, Infection and Immunity, Machine Learning, Proteomics, and 'Biomedical Big Data', which are sought-after expertise and skill sets in the data-driven biomedical sciences. He is a member of the Monash Centre for Data Science and also Associate Investigator of the ARC Centre of Excellence in Advanced Molecular Imaging at Monash University. He is an Associate Editor of BMC Bioinformatics, Frontiers in Bioinformatics, Genomics, Proteomics and Bioinformatics, an Editorial board member of BMC Genomic Data, Biomolecules and an Advisory Board member of Current Protein & Peptide Science. He is the founding member of Monash University's Centre to Impact AMR and is responsible for developing the Centre’s AMR Big Data and AI-Driven research capacity. His data-driven bioinformatics research has been well funded by the US NIH and Australian MRFF, NHMRC, ARC and Monash Major Inter-Disciplinary research funding schemes.