University of Birmingham > Talks@bham > CCB seminars > Explainable Multiview Learning for Environmental Multiomics Modelling

Explainable Multiview Learning for Environmental Multiomics Modelling

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Jordan McCormick.

The non-targeted multiomics approaches provide data-rich and unbiased profiling of the gene composition (genome), gene expression (transcriptome), protein composition (proteome), and metabolic activity (metabolome) etc. The multiomics data assists a systematic and holistic understanding of the biological responses and their interactions at multiple molecular levels, facilitating the discovery of underlying bio-mechanisms, critical molecular events, and biomarkers. It has fuelled significant advancements in fields like system biology, toxicogenomic, and ecogenomics. Multiview learning employs consensus and complementary principles to extract robust information while suppressing heterogeneous noises, leading to superior predictability. The explainable machine learning models obtain human-understandable insight into the cause of a prediction, enabling biological interpretations to contribute to new knowledge.

In this seminar, I will discuss 1). the general scenario, opportunities, and challenges of multiomics data integration analysis; 2). explainable multiview learning as a new machine learning paradigm for environmental multiomics modelling; 3). the Multi-Omics Co-responsive Analysis (MOCA) algorithm we proposed to implement the paradigm, and 4). the application in our latest EU research project – PrecisionTox, focusing on identifying molecular key event (mKE) biomarkers in the adverse outcome pathway (AOP) model.

This talk is part of the CCB seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


Talks@bham, University of Birmingham. Contact Us | Help and Documentation | Privacy and Publicity.
talks@bham is based on from the University of Cambridge.