Skip to content


Repository files navigation

RECOVER: sequential model optimization platform for combination drug repurposing identifies novel synergistic compounds in vitro


RECOVER is a platform that can guide wet lab experiments to quickly discover synergistic drug combinations active against a cancer cell line, requiring substantially less screening than an exhaustive evaluation (preprint).


Environment setup

Requirements: Anaconda ( and Git LFS ( Please make sure both are installed on the system prior to running installation.

Installation: enter the command source and follow the instructions. This will create a conda environment named recover and install all the required packages including the reservoir package that stores the primary data acquisition scripts.

In case you have any issue with the installation procedure of the reservoir, you can access and download all files directly from this google drive.

Running the pipeline

Configuration files for our experiments are provided in the following directory: Recover/recover/config

To run the pipeline with a custom configuration:

  • Create your configuration file and move it to Recover/recover/config/
  • Run python --config <my_configuration_file>

For example, to run the pipeline with configuration from the file, run python --config model_evaluation.

Log files will automatically be created to save the results of the experiments.


This Recover repository is based on research funded by (or in part by) the Bill & Melinda Gates Foundation. The findings and conclusions contained within are those of the authors and do not necessarily reflect positions or policies of the Bill & Melinda Gates Foundation.


Exploring the space of drug combinations to discover synergistic drugs using Active Learning







No packages published

Contributors 4