Bayesian versus Frequentist statistical modeling: A debate for hit selection from HTS campaigns.

摘要

The existing literature suggests the Bayesian-Frequentist debate could soon be involved in the prioritization of hits from HTS campaigns. The Bayesian-Frequentist debate reflects two archetypical attitudes regarding the process of conducting scientific and technological research. This review article covers recent advances in statistical analyses, currently in use, for hit selection in the drug discovery process. The impact of decisions (e.g. attrition) executed at early stages in the drug discovery process influences HTS performance in later development stages. It shows that, as the high content value of the information from HTS campaigns increases over time, the two statistical approaches aim to provide similar answers, but they might not succeed.