In this webinar, we explore how the limitations of pharmaceutical data can impact conventional predictive model building. Our speakers, Julian Levell (Constellation pharmaceuticals), Ben Irwin and matt Segall (Optibrium) demonstrate how the deep learning imputation algorithm underlying our Cerella platform, overcomes these challenges.
Walking through case studies from a collaboration between Constellation Pharmaceuticals and Optibrium on applying deep learning imputation to project data, we see the impact our methods can bring at all stages from early screening of datasets over temporal validation to later stage models, larger applications and the potential of this cutting-edge technology for future projects.
More webinars you might like
Finding balance in drug discovery through multi-parameter optimisation
Successful drugs require a delicate balance of many properties, such as potency, ADME and toxicity, to meet a project’s therapeutic objective. To make decisions about compound progression and assay selection, the available data must be assessed against project-specific criteria. However, the data on which we base our decisions often come from different sources and can vary in quality, so how can we use this information to make confident decisions? In addition, how can we be sure that the criteria we’re using are the most appropriate?
