Article: The original manuscript Prediction of drug combination effects with a minimal set of experiments is published in Nature Machine Intelligence journal, DOI: 10.1038/s42256-019-0122-4
DECREASE an efficient machine learning-based method that requires only a limited set of pairwise dose-response measurements to enable accurate synergy predictions, hence drastically reducing the time and resources needed in high-throughput combinatorial screening. The public version of web application (https://decrease.fimm.fi) is hosted by Open Source Shiny Server and its implementation is available here. The source code of DECREASE model with an example can be found here.
For any questions please contact Aleksandr Ianevski @IanevskiAleksandr
Code copyright 2019 DECREASE
Licence [https://github.com/IanevskiAleksandr/DECREASE/blob/master/LICENSE]