Date(s) - 06 Jun 2019
4:00 pm - 5:00 pm
Prof. John Overington, the CIO of the Medicines Discovery Catapult will describe the AssayNet project and its very far reaching implications.
The historical physical publication of scientific results, paid little attention to aggregation and reuse of data, historically, the extraction from the literature of data was an intensely manual and expert curation led approach, more recently there has been significant interest and developments in information extraction and curation to scale the extraction of facts and numerical data using NLP approaches. The thirst for data though is especially acute now for AI/deep learning approaches, and also for data with lower latency with respect to publication date.
The work presented will outline our historical experience and efforts in over twenty years of building drug discovery information systems, both in the private and public sectors, from the scientific literature and patents. Some of our future plans will be presented, building links between data points, from target through to clinical trials. Specifically, the organisation and indexing of data from a bioassay viewpoint, offers a natural view of how drug discovery science is performed.
After registering, you will receive a confirmation email containing information about joining the webinar.
Image credit: Joshua Sortino, Unsplash