Preprint Paper.

Abstract

Contemporary deep learning approaches still struggle to bring a useful improvement in the field of drug discovery due to the challenges of sparse, noisy and heterogeneous data that are typically encountered in this context. We use a state-of-the-art deep learning method, Alchemite™, to impute data from drug discovery projects, including multi-target biochemical activities, phenotypic activities in cell-based assays, and a variety of absorption, distribution, metabolism, and excretion (ADME) endpoints. The resulting model gives excellent predictions for activity and ADME endpoints, offering an average increase in R² of 0.22 versus quantitative structure-activity relationship methods. The model accuracy is robust to combining data across uncorrelated endpoints and projects with different chemical spaces, enabling a single model to be trained for all compounds and endpoints. We demonstrate improvements in accuracy on the latest chemistry and data when updating models with new data as an ongoing medicinal chemistry project progresses.

You can download this paper as a PDF
You can download the supplementary material as a PDF

Held on 8 September 2020.

Multi-parameter Optimisation in Practice

This webinar was presented by Ed Champness, Tim Hohm and John Norman.

In this webinar you can hear how you can quickly find high-quality compounds for your projects.

We described how a safe and efficacious drug must possess a balance of potency with appropriate ADME and toxicity properties. The ideal property profile will be different for every project, depending on the therapeutic indication, intended route of administration and commercial factors; the goal of a drug discovery project is to target compounds that are likely to achieve this delicate balance as quickly as possible. We will discuss how you can achieve this in practice, illustrated with case studies and interactive examples.

_{To hear the narration, please increase your speaker volume.}