Using computational models to overcome the blood brain barrier

Log in to watch this webinar

Not registered yet? Create an account

A key challenge when designing compounds that target the central nervous system (CNS) is the prediction of blood-brain barrier (BBB) penetration. The BBB can hinder paracellular transport, so CNS drugs typically pass into the brain via transcellular permeation. However, this route can be challenged by issues with the efflux of the drug from within the cells, which can drive higher dosage requirements to ensure the correct concentration in brain tissues. Higher exposure of a compound in the brain generally translates into better (neuro-) pharmacokinetics and ultimately lower dosage requirements. Pre-screening of potential compounds ahead of analysis in vivo is desirable for the identification of the best performers, and computational and chemoinformatic methods are routinely applied to design and screen compound libraries. Multi-parameter optimization (MPO) of physicochemical properties along with machine learning driven predictive modeling has been reported in the literature for these designs. Recent work using MPO techniques has shown that it is possible to push the physicochemical property landscape boundaries to design and optimize CNS drugs.

What you will learn:

In this webinar, Dr Sandeep Pal will show you the approach CRO service provider Concept Life Sciences (CLS) uses to design CNS-penetrant compound libraries, covering techniques such as:

  • CNS-MPO 
  • Sparse array design 
  • Machine learning/AI


  • Dr. Sandeep Pal - Research Leader - Concept Life Sciences

Pour en savoir plus

Who should attend? 

  • Scientists or Academics with an interest in neuroscience drug discovery, medicinal and computational chemistry. 

What will you learn? 

  • Learn about CLS’s computational chemistry library design approach to predict brain exposure
  • See how MPO of physicochemical properties can improve the performance of CNS drugs
  • Understand the application of other techniques including Sparse Array Design and Machine Learning on the development and optimization of CNS drugs