Fuzzy Clustering: Identification of Similar Compounds for Virtual Screening in Rational Drug Design

CRAVERO, FIORELLA; MARTÍNEZ, MARÍA JIMENA; DIAZ, MÓNICA FÁTIMA; PONZONI, IGNACIO

Conferencia; Fourth International Society for Computational Biology Latin America Bioinformatics Conference (ISCB-LA); 2016

Given a new compound, identify compounds of the training set that are structurally similar tothis one it is the first step of a possible strategy to define the Applicability Domain (AD) of a model. Todetermine this similarity, the data should be grouped. We are interested in fuzzy clustering algorithms whosenovelty resides in allowing an element belonging to more than one group using a degree of membership.As a next and last step of the process, using a series of statistical tests, the capacity of the predictor should beevaluated on the new compound. Determine the applicability domain of a model allows establishing the limitsinside which the prediction of a compound will be reliable. The definition of the chemical domain of a predictivemodel allows a more practical use of it, as it will prevent spending time with compounds that will not beapplicable. More specifically, in QSAR/QSPR (Quantitative Structure-Activity Relationship) modeling estimatethe level of certainty to predict a new compound based on how similar it is with respect to the compounds usedto build the model, is a crucial step.