Guiding molecules towards drug-likeness

Abstract

This review discusses computational methods for the prediction of drug-likeness. The coverage of published works include the assessment of historical practices of lead generation and optimization, surveys of the properties of known drugs and their constituent fragments and scaffolds, methods for delineating drug space, optimization techniques for simultaneously enhancing multiple properties and drug-like characteristics, similarity metrics and the application of more advanced pattern recognition algorithms for the prediction of drug-likeness. Areas which could be improved in this field are the scope of the datasets used to build models, the chemical interpretability of models, the use of multivariate optimization methods for drug design and the application of underappreciated statistical methods proven to work in other fields.