Example PhD

Facilitating ontology development in metabolomics with text mining

Supervisor: Dr I. Spasić

Keywords: Natural language processing, Semantics, Ontologies, Metabolomics.

Metabolomics as the 'systematic study of the unique chemical fingerprints that specific cellular processes leave behind', together with proteomics and transcriptomics, can provide a more complete picture of living organisms. Data integration is crucial in systems biology research, which aims to understand how the heterogeneous parts, represented through omics data, combine to form the whole. Effective data integration depends on the availability of ontologies as formal representation of domain-specific concepts and their relationships. Ontologies offer support for consistent annotation of metabolomics experiments, which in turn allows for such data to be properly interpreted and integrated. Text mining can greatly facilitate the process of ontology development though detection of relevant concepts in the literature through named entity recognition, as well as their relationships by using more advanced information extraction techniques, often based on machine learning. The aim of the current project would be to demonstrate how text mining can be used to automatise ontology development using metabolomics as a case study.

Key Skills/Background: Open to Computing Graduates and postgraduates.

Contact: Dr I. Spasić to discuss this research topic.