Dr Tim Beck
University of Leicester
Dr Beck has a track record of developing semantics capabilities to extract meaning from unstructured data, and of connecting health-related research data to enable them to be aligned and compared. These approaches have been applied to various online life sciences databases, most recently to the GWAS Central database of summary-level genome-wide association study (GWAS) findings.
Dr Beck has expertise in using ontologies to harmonise phenotype and disease descriptions to enable human study and disease model information to be integrated, providing a holistic insight into the genetic causes of common diseases.
Dr Beck leads several biomedical text analytics projects, including an ELIXIR collaboration to automatically extract GWAS information from the biomedical literature to support the curation activities of genotype-phenotype association databases.
Focus in CoDiet
Use of natural language processing and text mining to build a novel pipeline for automated literature reviews to identify:
- The risk of unhealthy diets on cardiometabolic diseases
- Evidence for physiological processes involved in the diet-related risk for cardiometabolic diseases
Beck T, Rowlands T, Shorter T, Brookes AJ. 2023. GWAS Central: an expanding resource for finding and visualising genotype and phenotype data from genome-wide association studies. Nucleic Acids Res. 51(D1):D986-D993. DOI: 10.1093/nar/gkac1017.
Yeung CS, Beck T, Posma JM. 2022. MetaboListem and TABoLiSTM: Two Deep Learning Algorithms for Metabolite Named Entity Recognition. Metabolites. 12(4):276. DOI: 10.3390/metabo12040276.
Beck T, Shorter T, Hu Y, Li Z, Sun S, Popovici CM, McQuibban NAR, Makraduli F, Yeung CS, Rowlands T, Posma JM. 2022. Auto-CORPus: A Natural Language Processing Tool for Standardizing and Reusing Biomedical Literature. Front Digit Health. 4:788124. DOI: 10.3389/fdgth.2022.788124.