Monday, March 26^th–Wednesday, March 28^th

Tuesday March 27^th, 1:30–4:50pm
McCormick Place Lakeside-Room E353 A/B, Level 3.
 

For many years there has been continuing debate about the definition of "drug-like" molecules. Although Lipinski's 'rule-of-five' is probably the most widely used paradigm in the medicinal chemistry community today, many others, including Hansch and Veber, have contributed to our understanding of how the physical properties of molecules influence physiological endpoints. Quite often, however, our understanding of the effect of individual properties and the relationship between property values and molecular structure is limited. In this presentation we will discuss the frequently overlooked impact of molecular physical properties (such as logP, logD, solubility, and pK_a) of compounds investigated in medicinal chemistry, with relevant pharmaceutical examples.

Is there a price to be paid for the use of inaccurate predictions? As a result of the additive-constitutive fragmental approach taken by ACD/Labs for physicochemical property prediction, the software offers algorithm training tools for pK_a, logP, logD, and, most recently, solubility. Accuracy Extender and System Training allow chemists to utilize in-house knowledge from experimental measurements to improve predictions for proprietary/novel compounds. In turn, improved accuracy of prediction can have a major impact on the use of these values and training is much easier than you may think. In this presentation, we shall be discussing the details of algorithm training and providing case studies of how improved prediction accuracy can have a positive impact on discovery projects.