Extracting and Using Knowledge about Biomarkers from Structured and Unstructured Data

OntoChem is extracting knowledge about biomarkers from text documents such as scientific articles, patents, news flows and websites using frame based natural language processing technologies. The resulting explicit and complex relationships between drugs, diseases, clinical trials, biological targets and their mutations and haplotypes are normalized using large background ontologies. Normalized data from structured databases is integrated as well - such as ClinicalTrials.gov, GWAS, OMIM, COSMIC or ClinVar and others. An easy-to-use search interface uses Google's BigQuery technology as a backend server engine.