Daniela Oliveira

I’m an Invited Assistant Professor in the Department of Informatics of the Faculty of Sciences in the University of Lisbon. I am also a researcher at LASIGE in the research line of Health and Biomedical Informatics. My current research broadly focuses on data integration to enable the publication of meaningful knowledge on the Web, with a special interest in the publication of health data to help find and access currently available knowledge that can enable the generation new knowledge in the domain.​

I hold a BSc degree in Health Sciences from the University of Lisbon (2010-2013). This BSc degree provided me with the necessary knowledge to understand the complexity of biomedical data and, therefore, have a deeper understanding of the challenges involved in finding, accessing, integrating, and publishing research findings in this area. In my MSc in Bioinformatics and Computational Biology from the Faculty of Sciences, University of Lisbon (2013-2015), I was introduced to a plethora of bioinformatics tools and resources. In my dissertation, supervised by Dr Catia Pesquita, I focused on researching methods for providing complex matches between biomedical ontologies and produced a thesis entitled Compound Matching of Biomedical Ontologies.

I completed my PhD in Computer Science at the Data Science Institute in the National University of Ireland, Galway, under the supervision of Dr Mathieu d’Aquin. My thesis, entitled Generating and Ranking Candidate Data Models from Background Knowledge, I investigated a solution to provide complete data model recommendations for knowledge graphs based on published knowledge. Besides a life sciences integration use-case, my thesis mainly features the use-case of integrating library data domain datasets considering that several data models have been published by different libraries and no clear agreements exists in the domain as to which data model should be the main standard. Therefore, the work on my thesis is a first step into lowering the entry level barrier for publishing interoperable knowledge graphs in domains where a rich knowledge lake exists.

Currently, as a researcher in LASIGE I’m focusing on further enabling the semantic integration of heterogeneous data sources, now with a special focus on health-related data. This field poses interesting challenges due to the complexity associated with the data in the domain and the sheer volume of data that is constantly being produced. This high rate of publication demands methods that can swiftly integrate new research contributions with existing data so that knowledge is more easily interoperable and new conclusions can be drawn with a hollistic view of the subject. I aim to focus my main contributions in the fields of biomedical ontologies, ontology matching, data integration, knowledge management and data mining.