With the rapidly evolving SARS-CoV-2 variants of concern, there is an urgent need for the discovery of further treatments for the coronavirus disease . Drug repurposing is one of the most rapid strategies for addressing this need, and numerous compounds have already been selected for in vitro testing by several groups. These have led to a growing database of molecules with in vitro activity against the virus. Machine learning models can assist drug discovery through prediction of the best compounds based on previously published data. Herein, we have implemented several machine learning methods to develop predictive models from recent SARS-CoV-2 in vitro inhibition data and used them to prioritize additional FDA-approved compounds for in vitro testing selected from our in-house compound library. From the compounds predicted with a Bayesian machine learning model, lumefantrine, an antimalarial was selected for testing and showed limited antiviral activity in cell-based assays while demonstrating binding (K d 259 nM) to the spike protein using microscale thermophoresis. Several other compounds which we prioritized have since been tested by others and were also found to be active in vitro. This combined machine learning and in vitro testing approach can be expanded to virtually screen available molecules with predicted activity against SARS-CoV-2 reference WIV04 strain and circulating variants of concern. In the process of this work, we have created multiple iterations of machine learning models that can be used as a prioritization tool for SARS-CoV-2 antiviral drug discovery programs. The very latest model for SARS-CoV-2 with over 500 compounds is now freely available at www.assaycentral.org.

27With the ongoing SARS-CoV-2 pandemic there is an urgent need for the 28 discovery of a treatment for the coronavirus disease . Drug repurposing is 29 one of the most rapid strategies for addressing this need and numerous compounds 30 have been selected for in vitro testing by several groups already. These have led to a 31 growing database of molecules with in vitro activity against the virus. Machine learning 32 models can assist drug discovery through prediction of the best compounds based on 33 previously published data. Herein we have implemented several machine learning 34 methods to develop predictive models from recent SARS-CoV-2 in vitro inhibition data 35and used them to prioritize additional FDA approved compounds for in vitro testing 36 selected from our in-house compound library. From the compounds predicted with a 37 Bayesian machine learning model, CPI1062 and CPI1155 showed antiviral activity in 38HeLa-ACE2 cell-based assays and represent potential repurposing opportunities for 39 COVID-19. This approach can be greatly expanded to exhaustively virtually screen 40 available molecules with predicted activity against this virus as well as a prioritization 41 tool for SARS-CoV-2 antiviral drug discovery programs. The very latest model for 42 SARS-CoV-2 is available at www.assaycentral.org. 43 44 45 46 47 129 Applicability and Reliability Domain Assessment 130In order to check if it is valid to apply the model for compounds being predicted 131 and how reliable the predictions are, an applicability and reliability domain assessment 132 was performed. First, the compound applicability within the model is assessed 133 comparing its similarity with the model's data using both molecular and fingerprint 134 descriptors. If the molecule satisfies both criteria it is considered within the applicability 135 domain and goes to the reliability domain assessment. 136

No abstract