A Second-Generation Oral SARS-CoV-2 Main Protease Inhibitor Clinical Candidate for the Treatment of COVID-19.

Despite the record-breaking discovery, development and approval of vaccines and antiviral therapeutics such as Paxlovid, coronavirus disease 2019 (COVID-19) remained the fourth leading cause of death in the world and third highest in the United States in 2022. Here, we report the discovery and characterization of PF-07817883, a second-generation, orally bioavailable, SARS-CoV-2 main protease inhibitor with improved metabolic stability versus nirmatrelvir, the antiviral component of the ritonavir-boosted therapy Paxlovid. We demonstrate the in vitro pan-human coronavirus antiviral activity and off-target selectivity profile of PF-07817883. PF-07817883 also demonstrated oral efficacy in a mouse-adapted SARS-CoV-2 model at plasma concentrations equivalent to nirmatrelvir. The preclinical in vivo pharmacokinetics and metabolism studies in human matrices are suggestive of improved oral pharmacokinetics for PF-07817883 in humans, relative to nirmatrelvir. In vitro inhibition/induction studies against major human drug metabolizing enzymes/transporters suggest a low potential for perpetrator drug-drug interactions upon single-agent use of PF-07817883.

An Advax-CpG55.2 adjuvanted recombinant hemagglutinin vaccine provides immunity against H7N9 influenza in adult and neonatal mice.

There is a major unmet need for strategies to improve the immunogenicity and effectiveness of pandemic influenza vaccines, particularly in poor responder populations such as neonates. Recombinant protein approaches to pandemic influenza offer advantages over more traditional inactivated virus approaches, as they are free of problems such as egg adaptation or need for high level biosecurity containment for manufacture. However, a weakness of recombinant proteins is their low immunogenicity. We asked whether the use of an inulin polysaccharide adjuvant (Advax) alone or combined with a TLR9 agonist (CpG55.2) would enhance the immunogenicity and protection of a recombinant hemagglutinin vaccine against H7N9 influenza (rH7HA), including in neonatal mice. Advax adjuvant induced predominantly IgG1 responses against H7HA, whereas Advax-CpG55.2 adjuvant also induced IgG2a, IgG2b and IgG3 responses, consistent with the TLR9 agonist component inducing a Th1 bias. Advax-CpG55.2 adjuvanted rH7HA induced high serum neutralizing antibody titers in adult mice. In newborns it similarly overcame immune hypo-responsiveness and enhanced serum anti-rH7HA IgG levels in 7-day-old BALB/C and C57BL/6 mice. Immunized adult mice were protected against a lethal H7N9 virus challenge. When formulated with Advax-CpG55.2 adjuvant, greater protection was seen with rH7HA than with inactivated H7 whole virus antigen. Advax-CpG55.2 adjuvanted rH7HA represents a promising influenza vaccine platform for further development.

An Advax-CpG adjuvanted recombinant H5 hemagglutinin vaccine protects mice against lethal influenza infection.

There is a major unmet need for strategies to improve the immunogenicity of vaccines to protect against highly pathogenic avian influenza strains with pandemic potential. This study tested the ability of adjuvants based on delta inulin (Advax™) alone or combined with a TLR9 agonist (Advax-CpG™) to enhance the immunogenicity of recombinant H5 hemagglutinin antigen expressed in insect cells (rH5HA) to protect mice against lethal influenza infection. The Advax-adjuvanted rH5HA induced high serum hemagglutination inhibition activity, as well as Th1 and Th2 cytokine secreting CD4 and CD8 T cells. Immunization protected mice against a lethal heterosubtypic H5N1 virus challenge. Mice immunized with an Advax-adjuvanted rHA2 stem antigen prepared by enzymatic cleavage of rH5HA produced serum antibodies devoid of hemagglutination inhibition activity, but these anti-HA2 antibodies were nevertheless able to transfer protection against lethal H1N1 or H3N2 infections to naïve mice. We hypothesize that the enhanced protection afforded by Advax-adjuvanted rH5HA may be mediated by the combination of neutralizing antibodies directed at the HA head, anti-HA2 stem antibodies plus memory CD4 + and CD8 + T cells. This outcome supports further development of the Advax-adjuvanted rH5 pandemic influenza vaccine platform.

Meeting report: 36th International Conference on Antiviral Research in Lyon, France - March 13-17, 2023.

The 36th International Conference on Antiviral Research (ICAR), sponsored by the International Society for Antiviral Research (ISAR), was held March 13-17, 2023, in Lyon, France, and concurrently through an interactive remote meeting platform. Here we provide a report summarizing the presentations at the 36th ICAR, including the ISAR speaker awards. We also detail special events, sessions, and additional awards conferred at the meeting. ICAR returned to in-person meetings in 2022, convening in Seattle, WA, USA. The 36th ICAR is the first in-person meeting of the society in Europe since the beginning of the COVID-19 pandemic, which restricted most events to virtual attendance to help mitigate the spread and subsequent public health impact of SARS-CoV-2. An exceptionally high number of registrants and record attendance at this year's ICAR, along with a vast array of demonstrable expertise in a variety of antiviral research-related fields, reflected a strong and growing antiviral research community committed to improving health outcomes from viral diseases, including SARS-CoV-2, and to future pandemic preparedness. This report highlights the breadth of expertise, quality of research, and notable advancements that were contributed by members of ISAR and other participants at the meeting. ICAR aims to continue to provide a platform for sharing information, fostering collaborations, and supporting trainees in the field of antiviral research. The 37th ICAR will be held in Gold Coast, Australia, May 20-24, 2024.

Efficacy of an isoxazole-3-carboxamide analog of pleconaril in mouse models of Enterovirus-D68 and Coxsackie B5.

Enteroviruses (EV) cause a number of life-threatening infectious diseases. EV-D68 is known to cause respiratory illness in children that can lead to acute flaccid myelitis. Coxsackievirus B5 (CVB5) is commonly associated with hand-foot-mouth disease. There is no antiviral treatment available for either. We have developed an isoxazole-3-carboxamide analog of pleconaril (11526092) which displayed potent inhibition of EV-D68 (IC50 58 nM) as well as other enteroviruses including the pleconaril-resistant Coxsackievirus B3-Woodruff (IC50 6-20 nM) and CVB5 (EC50 1 nM). Cryo-electron microscopy structures of EV-D68 in complex with 11526092 and pleconaril demonstrate destabilization of the EV-D68 MO strain VP1 loop, and a strain-dependent effect. A mouse respiratory model of EV-D68 infection, showed 3-log decreased viremia, favorable cytokine response, as well as statistically significant 1-log reduction in lung titer reduction at day 5 after treatment with 11526092. An acute flaccid myelitis neurological infection model did not show efficacy. 11526092 was tested in a mouse model of CVB5 infection and showed a 4-log TCID50 reduction in the pancreas. In summary, 11526092 represents a potent in vitro inhibitor of EV with in vivo efficacy in EV-D68 and CVB5 animal models suggesting it is worthy of further evaluation as a potential broad-spectrum antiviral therapeutic against EV.

An Isomer of Galidesivir That Potently Inhibits Influenza Viruses and Members of the Bunyavirales Order.

We report for the first time the antiviral activities of two iminovirs (antiviral imino-C-nucleosides) 1 and 2, structurally related to galidesivir (Immucillin A, BCX4430). An iminovir containing the 4-aminopyrrolo[2,1-f][1,2,4-triazine] nucleobase found in remdesivir exhibited submicromolar inhibition of multiple strains of influenza A and B viruses, as well as members of the Bunyavirales order. We also report the first syntheses of ProTide prodrugs of iminovir monophosphates, which unexpectedly displayed poorer viral inhibition than their parent nucleosides in vitro. An efficient synthesis of the 4-aminopyrrolo[2,1-f][1,2,4-triazine]-containing iminovir 2 was developed to enable preliminary in vivo studies, wherein it displayed significant toxicity in BALB/c mice and limited protection against influenza. Further modification of this anti-influenza iminovir will therefore be required to improve its therapeutic value.

Potent and selective covalent inhibition of the papain-like protease from SARS-CoV-2.

Direct-acting antivirals are needed to combat coronavirus disease 2019 (COVID-19), which is caused by severe acute respiratory syndrome-coronavirus-2 (SARS-CoV-2). The papain-like protease (PLpro) domain of Nsp3 from SARS-CoV-2 is essential for viral replication. In addition, PLpro dysregulates the host immune response by cleaving ubiquitin and interferon-stimulated gene 15 protein from host proteins. As a result, PLpro is a promising target for inhibition by small-molecule therapeutics. Here we design a series of covalent inhibitors by introducing a peptidomimetic linker and reactive electrophile onto analogs of the noncovalent PLpro inhibitor GRL0617. The most potent compound inhibits PLpro with kinact/KI = 9,600 M-1 s-1, achieves sub-µM EC50 values against three SARS-CoV-2 variants in mammalian cell lines, and does not inhibit a panel of human deubiquitinases (DUBs) at >30 µM concentrations of inhibitor. An X-ray co-crystal structure of the compound bound to PLpro validates our design strategy and establishes the molecular basis for covalent inhibition and selectivity against structurally similar human DUBs. These findings present an opportunity for further development of covalent PLpro inhibitors.

Human IVIG treatment in a neurological disease model for Enterovirus A71 infection in 28-day-old AG129 mice.

Enterovirus A71 can cause serious neurological disease in young children. Animal models for EV-A71 are needed to evaluate potential antiviral therapies. Existing models have limitations, including lack of lethality or crucial disease signs. Here we report the development of an EV-A71 model in 28-day-old mice. Virus was serially passaged until it produced consistent lethality and rear-limb paralysis. Onset of disease occurred between days 6-9 post-infection, with mortality following weight loss and neurological signs on days 9-14. In addition, a single administration of human intravenous immunoglobulin at doses of 200, 400 and 800 mg/kg at 4h post-infection was evaluated in the model. Protection from weight loss, neurological signs, and mortality (between 50 and 89%) were observed at doses of 400 mg/kg or greater. Based on these results, IVIG was selected for use as a positive control in this acute model, and suggest that IVIG is a potential therapeutic for EV-A71 infections.

Anti-SARS-CoV-2 activity of targeted kinase inhibitors: Repurposing clinically available drugs for COVID-19 therapy.

Coronavirus disease 2019 (COVID-19) remains a major public health concern, and vaccine unavailability, hesitancy, or failure underscore the need for discovery of efficacious antiviral drug therapies. Numerous approved drugs target protein kinases associated with viral life cycle and symptoms of infection. Repurposing of kinase inhibitors is appealing as they have been vetted for safety and are more accessible for COVID-19 treatment. However, an understanding of drug mechanism is needed to improve our understanding of the factors involved in pathogenesis. We tested the in vitro activity of three kinase inhibitors against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), including inhibitors of AXL kinase, a host cell factor that contributes to successful SARS-CoV-2 infection. Using multiple cell-based assays and approaches, gilteritinib, nintedanib, and imatinib were thoroughly evaluated for activity against SARS-CoV-2 variants. Each drug exhibited antiviral activity, but with stark differences in potency, suggesting differences in host dependency for kinase targets. Importantly, for gilteritinib, the amount of compound needed to achieve 90% infection inhibition, at least in part involving blockade of spike protein-mediated viral entry and at concentrations not inducing phospholipidosis (PLD), approached a clinically achievable concentration. Knockout of AXL, a target of gilteritinib and nintedanib, impaired SARS-CoV-2 variant infectivity, supporting a role for AXL in SARS-CoV-2 infection and supporting further investigation of drug-mediated AXL inhibition as a COVID-19 treatment. This study supports further evaluation of AXL-targeting kinase inhibitors as potential antiviral agents and treatments for COVID-19. Additional mechanistic studies are needed to determine underlying differences in virus response.

Vandetanib Blocks the Cytokine Storm in SARS-CoV-2-Infected Mice.

The portfolio of SARS-CoV-2 small molecule drugs is currently limited to a handful that are either approved (remdesivir), emergency approved (dexamethasone, baricitinib, paxlovid, and molnupiravir), or in advanced clinical trials. Vandetanib is a kinase inhibitor which targets the vascular endothelial growth factor receptor (VEGFR), the epidermal growth factor receptor (EGFR), as well as the RET-tyrosine kinase. In the current study, it was tested in different cell lines and showed promising results on inhibition versus the toxic effect on A549-hACE2 cells (IC50 0.79 µM) while also showing a reduction of >3 log TCID50/mL for HCoV-229E. The in vivo efficacy of vandetanib was assessed in a mouse model of SARS-CoV-2 infection and statistically significantly reduced the levels of IL-6, IL-10, and TNF-α and mitigated inflammatory cell infiltrates in the lungs of infected animals but did not reduce viral load. Vandetanib also decreased CCL2, CCL3, and CCL4 compared to the infected animals. Vandetanib additionally rescued the decreased IFN-1ß caused by SARS-CoV-2 infection in mice to levels similar to that in uninfected animals. Our results indicate that the FDA-approved anticancer drug vandetanib is worthy of further assessment as a potential therapeutic candidate to block the COVID-19 cytokine storm.

TEMPOL inhibits SARS-CoV-2 replication and development of lung disease in the Syrian hamster model.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused a worldwide outbreak, known as coronavirus disease 2019 (COVID-19). Alongside vaccines, antiviral therapeutics is an important part of the healthcare response to COVID-19. We previously reported that TEMPOL, a small molecule stable nitroxide, inactivated the RNA-dependent RNA polymerase (RdRp) of SARS-CoV-2 by causing the oxidative degradation of its iron-sulfur cofactors. Here, we demonstrate that TEMPOL is effective in vivo in inhibiting viral replication in the Syrian hamster model. The inhibitory effect of TEMPOL on SARS-CoV-2 replication was observed in animals when the drug was administered 2 h before infection in a high-risk exposure model. These data support the potential application of TEMPOL as a highly efficacious antiviral against SARS-CoV-2 infection in humans.

Programmable antivirals targeting critical conserved viral RNA secondary structures from influenza A virus and SARS-CoV-2.

Influenza A virus's (IAV's) frequent genetic changes challenge vaccine strategies and engender resistance to current drugs. We sought to identify conserved and essential RNA secondary structures within IAV's genome that are predicted to have greater constraints on mutation in response to therapeutic targeting. We identified and genetically validated an RNA structure (packaging stem-loop 2 (PSL2)) that mediates in vitro packaging and in vivo disease and is conserved across all known IAV isolates. A PSL2-targeting locked nucleic acid (LNA), administered 3 d after, or 14 d before, a lethal IAV inoculum provided 100% survival in mice, led to the development of strong immunity to rechallenge with a tenfold lethal inoculum, evaded attempts to select for resistance and retained full potency against neuraminidase inhibitor-resistant virus. Use of an analogous approach to target SARS-CoV-2, prophylactic administration of LNAs specific for highly conserved RNA structures in the viral genome, protected hamsters from efficient transmission of the SARS-CoV-2 USA_WA1/2020 variant. These findings highlight the potential applicability of this approach to any virus of interest via a process we term 'programmable antivirals', with implications for antiviral prophylaxis and post-exposure therapy.

Potent and Selective Covalent Inhibition of the Papain-like Protease from SARS-CoV-2.

Direct-acting antivirals are needed to combat coronavirus disease 2019 (COVID-19), which is caused by severe acute respiratory syndrome-coronavirus-2 (SARS-CoV-2). The papain-like protease (PLpro) domain of Nsp3 from SARS-CoV-2 is essential for viral replication. In addition, PLpro dysregulates the host immune response by cleaving ubiquitin and interferon-stimulated gene 15 protein (ISG15) from host proteins. As a result, PLpro is a promising target for inhibition by small-molecule therapeutics. Here we have designed a series of covalent inhibitors by introducing a peptidomimetic linker and reactive electrophile onto analogs of the noncovalent PLpro inhibitor GRL0617. The most potent compound inhibited PLpro with k inact /K I = 10,000 M - 1 s - 1 , achieved sub-µM EC 50 values against three SARS-CoV-2 variants in mammalian cell lines, and did not inhibit a panel of human deubiquitinases at > 30 µM concentrations of inhibitor. An X-ray co-crystal structure of the compound bound to PLpro validated our design strategy and established the molecular basis for covalent inhibition and selectivity against structurally similar human DUBs. These findings present an opportunity for further development of covalent PLpro inhibitors.

Development of optimized drug-like small molecule inhibitors of the SARS-CoV-2 3CL protease for treatment of COVID-19.

The SARS-CoV-2 3CL protease is a critical drug target for small molecule COVID-19 therapy, given its likely druggability and essentiality in the viral maturation and replication cycle. Based on the conservation of 3CL protease substrate binding pockets across coronaviruses and using screening, we identified four structurally distinct lead compounds that inhibit SARS-CoV-2 3CL protease. After evaluation of their binding specificity, cellular antiviral potency, metabolic stability, and water solubility, we prioritized the GC376 scaffold as being optimal for optimization. We identified multiple drug-like compounds with <10 nM potency for inhibiting SARS-CoV-2 3CL and the ability to block SARS-CoV-2 replication in human cells, obtained co-crystal structures of the 3CL protease in complex with these compounds, and determined that they have pan-coronavirus activity. We selected one compound, termed coronastat, as an optimized lead and characterized it in pharmacokinetic and safety studies in vivo. Coronastat represents a new candidate for a small molecule protease inhibitor for the treatment of SARS-CoV-2 infection for eliminating pandemics involving coronaviruses.

Potent and Selective Covalent Inhibition of the Papain-like Protease from SARS-CoV-2.

Direct-acting antivirals are needed to combat coronavirus disease 2019 (COVID-19), which is caused by severe acute respiratory syndrome-coronavirus-2 (SARS-CoV-2). The papain-like protease (PLpro) domain of Nsp3 from SARS-CoV-2 is essential for viral replication. In addition, PLpro dysregulates the host immune response by cleaving ubiquitin and interferon-stimulated gene 15 protein (ISG15) from host proteins. As a result, PLpro is a promising target for inhibition by small-molecule therapeutics. Here we have designed a series of covalent inhibitors by introducing a peptidomimetic linker and reactive electrophile onto analogs of the noncovalent PLpro inhibitor GRL0617. The most potent compound inhibited PLpro with kinact/KI = 10,000 M- 1 s- 1, achieved sub-µM EC50 values against three SARS-CoV-2 variants in mammalian cell lines, and did not inhibit a panel of human deubiquitinases at > 30 µM concentrations of inhibitor. An X-ray co-crystal structure of the compound bound to PLpro validated our design strategy and established the molecular basis for covalent inhibition and selectivity against structurally similar human DUBs. These findings present an opportunity for further development of covalent PLpro inhibitors.

ProLung™-budesonide Inhibits SARS-CoV-2 Replication and Reduces Lung Inflammation.

BACKGROUND: Inhaled budesonide benefits patients with COVID-19. ProLung™-budesonide enables the sustained, low dose administration of budesonide within a delivery vehicle similar to lung surfactant. ProLung™-budesonide may offer anti-inflammatory and protective effects to the lung in COVID-19, yet it's effect on SARS-CoV-2 replication is unknown. OBJECTIVE: To determine the efficacy of ProLung™-budesonide against SARS-CoV-2-infection in vitro, evaluate its ability to decrease inflammation, and airway hyperresponsiveness in an animal model of lung inflammation. METHODS: SARS-CoV-2-infected Vero 76 cells were treated with ProLung™-budesonide ([0.03-100 µg/ml]) for 3 days, and virus yield in the supernatant was measured. Ovalbumin-sensitized C57BL/6 mice received aerosolized (a) ProLung™-budesonide weekly, (b) only budesonide, either daily or weekly, or (c) weekly empty ProLung™ carrier (without budesonide). All treatment groups were compared to sensitized untreated, or normal mice using histopathologic examination, electron microscopy (EM), airway hyperresponsiveness (AHR) to Methacholine (Mch) challenge, and eosinophil peroxidase activity (EPO) measurements in bronchioalveolar lavage (BAL). RESULTS: ProLung™-budesonide showed significant inhibition of viral replication of SARS-CoV-2-infected cells with the selectivity index (SI) value >24. Weekly ProLung™-budesonide and daily budesonide therapy significantly decreased lung inflammation and EPO in BAL. ProLung™-budesonide localized in type II pneumocytes, and was the only group to significantly decrease AHR, and EPO in BAL with Mch challenge. CONCLUSIONS: ProLung™-budesonide significantly inhibited viral replication in SARS-CoV-2-infected cells. It localized into type II pneumocytes, decreased lung inflammation, AHR and EPO activity with Mch challenge. This novel drug formulation may offer a potential inhalational treatment for COVID-19.

An oral SARS-CoV-2 Mpro inhibitor clinical candidate for the treatment of COVID-19.

The worldwide outbreak of COVID-19 caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has become a global pandemic. Alongside vaccines, antiviral therapeutics are an important part of the healthcare response to countering the ongoing threat presented by COVID-19. Here, we report the discovery and characterization of PF-07321332, an orally bioavailable SARS-CoV-2 main protease inhibitor with in vitro pan-human coronavirus antiviral activity and excellent off-target selectivity and in vivo safety profiles. PF-07321332 has demonstrated oral activity in a mouse-adapted SARS-CoV-2 model and has achieved oral plasma concentrations exceeding the in vitro antiviral cell potency in a phase 1 clinical trial in healthy human participants.

Visible blue light inhibits infection and replication of SARS-CoV-2 at doses that are well-tolerated by human respiratory tissue.

The delivery of safe, visible wavelengths of light can be an effective, pathogen-agnostic, countermeasure that would expand the current portfolio of SARS-CoV-2 intervention strategies beyond the conventional approaches of vaccine, antibody, and antiviral therapeutics. Employing custom biological light units, that incorporate optically engineered light-emitting diode (LED) arrays, we harnessed monochromatic wavelengths of light for uniform delivery across biological surfaces. We demonstrated that primary 3D human tracheal/bronchial-derived epithelial tissues tolerated high doses of a narrow spectral band of visible light centered at a peak wavelength of 425 nm. We extended these studies to Vero E6 cells to understand how light may influence the viability of a mammalian cell line conventionally used for assaying SARS-CoV-2. The exposure of single-cell monolayers of Vero E6 cells to similar doses of 425 nm blue light resulted in viabilities that were dependent on dose and cell density. Doses of 425 nm blue light that are well-tolerated by Vero E6 cells also inhibited infection and replication of cell-associated SARS-CoV-2 by > 99% 24 h post-infection after a single five-minute light exposure. Moreover, the 425 nm blue light inactivated cell-free betacoronaviruses including SARS-CoV-1, MERS-CoV, and SARS-CoV-2 up to 99.99% in a dose-dependent manner. Importantly, clinically applicable doses of 425 nm blue light dramatically inhibited SARS-CoV-2 infection and replication in primary human 3D tracheal/bronchial tissue. Safe doses of visible light should be considered part of the strategic portfolio for the development of SARS-CoV-2 therapeutic countermeasures to mitigate coronavirus disease 2019 (COVID-19).

Trivalent Subunit Vaccine Candidates for COVID-19 and Their Delivery Devices.

The COVID-19 pandemic highlights the need for platform technologies enabling rapid development of vaccines for emerging viral diseases. The current vaccines target the SARS-CoV-2 spike (S) protein and thus far have shown tremendous efficacy. However, the need for cold-chain distribution, a prime-boost administration schedule, and the emergence of variants of concern (VOCs) call for diligence in novel SARS-CoV-2 vaccine approaches. We studied 13 peptide epitopes from SARS-CoV-2 and identified three neutralizing epitopes that are highly conserved among the VOCs. Monovalent and trivalent COVID-19 vaccine candidates were formulated by chemical conjugation of the peptide epitopes to cowpea mosaic virus (CPMV) nanoparticles and virus-like particles (VLPs) derived from bacteriophage Qß. Efficacy of this approach was validated first using soluble vaccine candidates as solo or trivalent mixtures and subcutaneous prime-boost injection. The high thermal stability of our vaccine candidates allowed for formulation into single-dose injectable slow-release polymer implants, manufactured by melt extrusion, as well as microneedle (MN) patches, obtained through casting into micromolds, for prime-boost self-administration. Immunization of mice yielded high titers of antibodies against the target epitope and S protein, and data confirms that antibodies block receptor binding and neutralize SARS-CoV and SARS-CoV-2 against infection of human cells. We present a nanotechnology vaccine platform that is stable outside the cold-chain and can be formulated into delivery devices enabling single administration or self-administration. CPMV or Qß VLPs could be stockpiled, and epitopes exchanged to target new mutants or emergent diseases as the need arises.

Machine Learning Models Identify Inhibitors of SARS-CoV-2.

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 (COVID-19). 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 (Kd 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.