This is an exciting opportunity to work at the cutting edge of evidence generation in fast moving field of drug target identification and prioritisation. You will be embedded in a dynamic team working with cloud based technologies, integrating evidence from across EMBL-EBI and other databases to identify and prioritise drug targets.Your roleThe scientific literature is a rich source of evidence for the role of potential drug targets in disease, as well as other relationships between targets, disease, drugs, methods and so on. We are developing a robust pipeline to extract these relationships from the Open Access literature working with Europe PMC and developing machine learning and graph approaches for identifying novel and unexpected relationships.
The post will involve use of natural language processing to develop comprehensive entity recognition, testing and refinement of entity dictionaries, building a knowledge graph combining literature relationships with other evidence from the Open Targets Platform and machine learning to predict novel relationships including disease:target associations and drug repurposing opportunities.
- Participate in building an Open Targets Knowledge Graph
- Develop machine learning approaches to identify novel associations and other opportunities, and publish these.
- Build repertoire of training sets and gold standard for NLP for diverse entities
- Assess and feedback on performance of Europe PMC literature entity tagging including collating user feedback
- Contribute to implementation of graph-based approaches for the next generation Open Targets Platform