Viribus Unitis: Drug Combinations as a Treatment Against COVID-19
Preprints are manuscripts made publicly available before they have been submitted for formal peer review and publication. They might contain new research findings or data. Preprints can be a draft or final version of an author's research but must not have been accepted for publication at the time of submission.
The opportunities that may be provided by synergistic antiviral action of drugs for battling SARS-CoV2 are currently underestimated. Modern AI technologies realized as text, data, and knowledge mining and analytics tools provide the researchers with unprecedented opportunities for “smart” design of drug combinations with synergistic antiviral activities. The goal of this study is to emphasize the combination therapy as a potential treatment against COVID-19 and to utilize the combination of modern machine learning and AI technologies with our expertise to select the most promising drug combinations with further experimental validation. To the best of our knowledge, we are the first who applied the combination of data, text, and knowledge mining and modeling towards identification of drug combinations against SARS-CoV2. As a result, we have identified 281 combinations of 38 drugs that may serve as potential treatment for COVID-19. Among them, we selected twenty binary combinations that were submitted to experimental testing and twenty treble drug combinations that will be submitted for experimental testing as soon as necessary infrastructure will be developed. We hope that this study will promote the combination therapy as an efficient treatment for COVID-19.