Impact of selection bias on the evaluation of clusters of chemical compounds in the drug discovery process

Abstract

Expert opinion plays an important role when selecting promising clusters of chemical compounds in the drug discovery process. Indeed, experts can qualita-tively assess the potential of each cluster and, with appropriate statistical methods, these qualitative assessments can be quanti ed into a success probability for each of them. However, one crucial element often overlooked is the procedure by which the clusters are assigned/selected to/by the experts for evaluation. In the present work, the impact is studied that such a procedure may have on the statistical analysis and the entire evaluation process. It has been shown that some implementations of the selection procedure may seriously compromise the validity of the evaluation and, consequently, the fully random allocation of the clusters to the experts is strongly advocated.