The BioHIT group of SKEL | The AI Lab, organises an online presentation on Tuesday 29 June at 17.00 with invited speaker Dr Eleni Litsa, entitled Deciphering metabolism through Machine Learning.
Metabolism consists of all chemical reactions that take place within an organism to sustain life. Metabolic studies have the potential to advance chemical synthesis and drug development, discovery of biomarkers and therapeutic targets, as well as, environmental management. Computational tools can greatly benefit metabolic studies as the standard experimental practices are often laborious and resource demanding. Existing computational approaches often rely on expert knowledge limiting scalability and generalizability. As the volume of the available metabolic data grows, Machine Learning (ML) is emerging as a promising tool to assist metabolic studies.
The latest advancements in the field of Deep Learning (DL), especially regarding applications on structured data including chemical molecules, are also pointing to the same direction. Metabolic data though are very scarce, as opposed to general chemical data, making the application of ML in this field especially challenging. In addition to that, chemical molecules, which are the core element of metabolic datasets, do not have a straightforward representation within an ML framework. In this talk, I will present three ML-based approaches which demonstrate the potential of ML and DL to assist metabolic studies despite those challenges. The approaches range from statistical ML models to DL models along with techniques such as ensembling and transfer learning.
Eleni Litsa has recently completed a PhD programme in Computer Science at Rice University. She also holds a Diploma in Electrical & Computer Engineering from the National Technical University of Athens. Her current research is focused on applications of Machine Learning for accelerating drug discovery and development of therapeutics. Eleni Litsa has been an NCSR Demokritos fellow for a joint PhD program between Rice University and NCSR Demokritos.
ePresentation Log in Details
Meeting ID: 826 2368 2981