Summary


In this drug optimisation article, co-authored with Pfizer we discuss new ‘rule induction’ methods. These explore complex data to find interpretable, multi-parameter rules, tailored to any drug discovery objective, and are useful in identifying compounds with a higher chance of success. We illustrate this with applications to simple ‘drug like’ properties for oral drugs and to the exploration of experimental target inhibition data to find rules for selecting compounds with a low risk of cardio- and hepatotoxicity.

Rule induction methods enable us to explore complex data and identify the compounds with the right balance of properties.

Citation details

I. Yusof, F. Shah, T. Hashimoto, M. D. Segall, N. Greene, Drug Discovery Today (2014) 19(5) pp. 680-687
DOI: 10.1016/j.drudis.2014.01.005

Find out more


f you’d like to see a worked example of ‘rule induction’ for multi-parameter optimisation in action, take a look at our tutorial video.