Assessing the Effect of 2D Fingerprint Filtering on ILP-Based Structure-Activity Relationships Toxicity Studies in Drug Design

The rational development of new drugs is a complex and expensive process. A myriad of factors affect the activity of putative candidate molecules in vivo and the propensity for causing adverse and toxic effects is recognised as the major hurdle behind the current "target-rich, lead-poor" scenario. Structure-Activity Relationship studies, using relational Machine Learning algorithms, proved already to be very useful in the complex process of rational drug design. However, a typical problem with those studies concerns the use of available repositories of previously studied molecules. It is quite often the case that those repositories are highly biased since they contain lots of molecules that are similar to each other. This results from the common practice where an expert chemist starts off with a lead molecule, presumed to have some potential, and then introduces small modifications to produce a set of similar molecules. Thus, the resulting sets have a kind of similarity bias. In this paper we assess the advantages of filtering out similar molecules in order to improve the application of relational learners in Structure-Activity Relationship (SAR) problems to predict toxicity. Furthermore, we also assess the advantage of using a relational learner to construct comprehensible models that may be quite valuable to bring insights into the workings of toxicity.