Andrey Ustyuzhanin: Innovating in the Generation of Scientific Hypotheses

Last Tuesday, April 16, in the Aula Magna, an interesting talk by Andrey Ustyuzhanin took place. Andrey is a data scientist and software developer at Constructor University in Bremen and the Institute for Functional Intelligent Materials at the National University of Singapore.

During his presentation, Andrey explored two advanced methodologies: THiGER and HypoFinder. THiGER uses temporal graphs to analyze the dynamics of relationships between entities in the field of nutrition, while HypoFinder leverages language models to automate the initial stages of research and analysis of scientific literature. Both methods highlight the importance of integrating temporal graphs and language models in the generation of scientific hypotheses.

Thus, his talk inspired us to think about new ways to approach current challenges in scientific research.