Getting SMARt in drug discovery: chemoinformatics approaches for mining structure-multiple activity relationships

In light of the high relevance of polypharmacology, multi-target screening is a major trend in drug discovery. As such, the increasing amount of available structure-activity data requires the application of chemoinformatic approaches to mine structure-multiple activity relationships. To this end, activity landscape methods, initially developed to explore the structure-activity relationships for compounds screened against one target, have been adapted to mine Structure-Multiple Activity Relationships (SMARt). Herein, we survey advances in the chemoinformatic approaches to retrieve SMARt from screening data sets. Case studies relevant to modern drug discovery are discussed. The methods covered in this survey are general and can be implemented to explore the SMARt of other data sets screened across multiple biologically endpoints.