Cátia Pesquita was the keynote speaker at the 5th Workshop on Semantic Web solutions for large-scale biomedical data analytics (SeWeBMeDA) co-located with ESWC 2022. The talk, titled “Powering Biomedical Artificial Intelligence with a Holistic Knowledge Graph”, addressed the challenges in building the knowledge graph from public resources and the methodology we are using and discussed the road-ahead in biomedical ontology and knowledge graph alignment as AI becomes an integral part of biomedical research.
LASIGE’s PhD Student Rita Sousa also had the opportunity the present the research she’s developing with LASIGE’s integrated members Sara Silva and Catia Pesquita on the event. The student presented the paper “Towards Supervised Biomedical Semantic Similarity”, which describes a novel approach that uses supervised machine learning methods to tailor semantic similarity measures to fit a particular view on biological similarity. The results demonstrated that the novel approach outperforms non-supervised methods, producing semantic similarity models that fit different biological perspectives significantly better.