Leveraging Drug-Target Interaction Data for the Translation of Computational Models into Clinically Actionable Interventions
Spencer C. Richmanz, Cole A. Lyman, Matthew C. Morris, Hongbao Caoy, Anastasia Nesterovay, Anton Yuryevy, Chris Cheadley, Gordon Broderick · 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · 2021
Computational modeling is an effective tool for studying complex disease. However, solutions to many models are purely mathematical and cannot immediately provide clinical insights. To overcome this barrier, we propose a series of quantitative scoring metrics that can be used in combination with drug-target interaction data to identify solutions that are readily clinically actionable. Furthermore, we introduce methods for the prediction and ranking of pharmaceutical interventions that closely align with these high-scoring solutions, with an emphasis on robustness across multiple solutions. We demonstrate these methods on a previously-described model of COVID-19 induced cytokine storm. These scoring methods ultimately identify multiple pharmaceutical candidates that have been shown to be effective in reducing mortality rates in COVID-19 patients.