Pairwise comparison of data vectors represents a large part of computational biology, especially with the continuous increase in genome-wide approaches yielding more information from more biological samples simultaneously. Gene clustering for function prediction as well as analyses of signalling pathways and the time-dependent dynamics of a system are common biological approaches that often rely on large dataset comparison. Different metrics can be used to evaluate the similarity between entities to be compared, such as correlation coefficients and distances. While the latter offers a more flexible way of measuring potential biological relationships between datasets, the significance of any given distance is highly dependent on the dataset and cannot be easily determined. Monte Carlo methods are robust approaches for evaluating the significance of distance values by multiple random permutations of the dataset followed by distance calculation. We have developed R. S. WebTool (http://rswebtool.kwaklab.org), a user-friendly online server for random sampling-based evaluation of distance significances that features an array of visualization and analysis tools to help non-bioinformaticist users extract significant relationships from random noise in distance-based dataset analyses.