Artificial Intelligence to Predict Clinical Trial Readiness of Drug Candidates challenge
What is this challenge all about?
In the drug discovery field, clinical testing in human patients is the most expensive and difficult step.
Advances in biological technology allow us to generate massive pre-clinical data in cells and animal, learn from a huge amount of literature on genes, pathways and diseases and learn from our previous experience in translational medicine. However, we still fail 25% of the time on toxicity in humans and about 50% of the time on efficacy (source: https://www.nature.com/articles/nrd.2016.184).
In this challenge, we are looking for a system that will ingest all the pre-clinical data that exists on a drug of interest and deliver potential safety liabilities that were overlooked and predict the likelihood of potential desired effects in humans. In addition, given everything the system has seen before, we expect the system to provide suggestions for experiments that could address the identified gaps.