Making sense of biological sequences: biomedical text mining and microbial genome recovery
In this talk, I will cover my research work in the area of bioinformatics, more specifically using machine learning for biomedical sequential data in two subdomains. Scientific literature is one of the major sources of knowledge for systems biology, in the form of papers, patents, and other types of written reports. Text mining methods aim at automatically extracting relevant information from the literature. I will discuss different approaches that demonstrate the usefulness of text mining methods to the biomedical domain, by extracting domain-specific information from the literature and integrating it with knowledge bases. I will also present my work in metagenomic binning, where the objective is to cluster DNA sequences obtained from environmental samples, according to their original microbial genome. This is necessary to identify the different species in a certain environment, such as wastewater treatment plants, residual waters, or the human gut.
Andre Lamurias is an Assistant Professor in the Department of Computer Science at FCT, NOVA University of Lisbon. He completed his PhD as part of the BioSYS PhD programme in the University of Lisbon. He holds a master's degree in Bioinformatics and Computational Biology from the same institution. Previously, he worked at Priberam Labs as a research scientist and as a postdoctoral researcher at Aalborg University.