Discovering drugs that show therapeutic potential is difficult, time-consuming, and expensive. But of those found, it is harder still to find those drugs which do not also have severe side effects and can pass through clinical trials.
We look at historically failed clinical trials to identify the most promising targets as well as internal projects that were abandoned.
By focusing on safety problems that occur in Preclinical, Phase 1, or Phase 2 trials, we are able to identify the most promising drugs, turn them around quickly, and get them to patients faster than starting drug discovery from scratch.
Our proprietary AI model, SAFEPATH, applies deep learning to our combined bioinformatics and cheminformatics datasets to solve drug safety issues.
In preclinical and clinical studies, safety assessments typically reveal what went wrong—such as liver damage or heart issues—but fail to explain why these issues occurred, or how they might be mitigated.
SAFEPATH is a first-of-its-kind AI platform that combines advanced machine learning models with a multimodal data approach to enable a deep understanding of toxicity mechanisms, and offers actionable insights to facilitate drug turnaround.