We have built multiple predictive machine learning models (e.g., random forests, k-nearest neighbors, support vector machines, self-organizing maps, na�ve Bayes) targeting neglected tropical diseases. Each of these models has been collected into (what Gentleman and Temple Lang1 call) a compendium. A compendium is a �container� for all those elements that make up a model and its associated description: the primary data, the annotated computational code, figures, tables and derived data together with textual documentation and conclusions. Compendia are interactive, being purposefully designed to allow researchers to reproduce, modify and extend the compendia's components. We show that, by exploiting their interactive nature, compendia may be constructed to serve as tutorials for the various machine learning methods. In practice, a compendium contains all those components necessary to independently reproduce the results reported in the compendium, and to employ the methods presented with other datasets. As such, a compendium stands as an example of reproducible research. We will describe compendia for the visualization, analysis and mining of antimalarial data deposited in ChEMBL-NTD2. All compendia will be freely available.1 Gentleman, Robert & Duncan Temple Lang, �Statistical Analyses and Reproducible Research� (May 2004) Bioconductor Project Working Papers. Working Paper 2.http://biostats.bepress.com/bioconductor/paper2.2. https://www.ebi.ac.uk/chemblntd

Using compendia as a collaborative tool in neglected diseases drug discovery

245th National Meeting (2013)

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.