How can we improve identification of toxicology-related risks in drug discovery?

Incorporating best practices and artificial intelligence into workflows improves success rates

Two factors largely drive the discontinuation of a drug development program, contributing to the low success rate for clinical trials: poor efficacy in humans and adverse events. Although a variety of factors contribute to adverse outcomes for a given therapy, there is also a growing appreciation for the nuanced role of genetics in determining the extent of an adverse outcome for a given individual. Findings related to this role as well as the inherent properties of the drug itself can be used to improve the overall success rates of a drug development program. In this report, we discuss how each step in the drug discovery phase is crucial to improving success rates and some of the best practices that could be incorporated into the workflow. Download the report now, then contact us to learn how Cortellis can help you improve your toxicology processes.

Report highlights:

  • The discovery stage
  • For successful drug development, we need to start as early as possible. Learn about what needs to be considered during the discovery stage that could impact safety, such as target liability; analysis; drug design, triage and hit; and drug repurposing

  • Personalized approaches
  • Because safety can vary by person and organ, we also need to identify how we can determine a drug’s potential toxic effects on specific organs and specific patients via toxicogenomics, pharmacogenomics and pharmacoepigenomics.

  • Artificial intelligence
  • To reach a deeper understanding of toxicity-related mechanisms and the effect of genetic differences, we need to access and process large quantities of experimental data. Learn how this can be achieved with AI and machine learning algorithms.

  • Future outlook
  • The future of economically viable drug development programs that deliver safe and efficacious therapies relies on changing our approach towards toxicology, including a move toward big data and artificial intelligence.