Screening Explorer is a web-based application that allows
for an intuitive evaluation o
f the results o
f screening experiments using complementary metrics in the
field. The usual evaluation o
f screening results implies the separate generation and apprehension o
f the ROC, predictiveness, and enrichment curves and their global metrics. Similarly, partial metrics need to be calculated repeatedly
for di
fferent
fractions o
f a data set and there exists no handy tool that allows reading partial metrics simultaneously on di
fferent
charts. For a deeper understanding o
f the results o
f screening experiments, we rendered their analysis straight
forward by linking these metrics interactively in an interactive usable web-based application. We also implemented simple consensus scoring methods based on scores normalization, standardization (
z-scores), and compounds ranking to evaluate the enrichments that can be expected through methods combination. Two demonstration data sets allow the users to easily apprehend the
functions o
f this tool that can be applied to the analysis o
f virtual and experimental screening results. Screening Explorer is
freely accessible at
f="http://stats.drugdesign.fr" class="extLink">http://stats.drugdesign.fr.