Наредни састанак Семинара биће одржан онлајн у среду, 2.марта 2022. са почетком у 18.15.

Предавач: проф. др Маринка Житник, Универзитет Харвард

Наслов предавања: INFUSING STRUCTURE AND KNOWLEDGE INTO BIOMEDICAL AI

Апстракт: Grand biomedical challenges require AI/ML models to generalize to entirely new scenarios not seen during training. However, standard supervised learning is incredibly limited in scenarios, such as designing novel therapeutics, modeling emerging pathogens, and treating rare diseases. In this talk, I present our efforts to overcome these obstacles by infusing structure and knowledge into AI/ML algorithms. First, I will outline general-purpose and scalable algorithms for few-shot learning on graphs. At the core is the notion of local subgraphs that transfer knowledge from one task to another, even when only a handful of labeled examples are available. This principle is theoretically justified as we show the evidence for predictions can be found in subgraphs surrounding the targets. Finally, I will conclude with applications in drug discovery and precision medicine. The algorithmic predictions were validated in human cells and led to discovering a new class of drugs.

Биографија предавача и Webex линк су доступни на: http://bioinfo.matf.bg.ac.rs/.

Организатори семинара Биоинформатика су Српско друштво за биоинформатику и рачунарску биологију ( http://www.birbi.matf.bg.ac.rs/ ) и Математички факултет.