Artificial intelligence approach fighting COVID-19 with repurposing drugs.

Background: The ongoing COVID-19 pandemic has caused more than 193,825 deaths during the past few months. A quick-to-be-identified cure for the disease will be a therapeutic medicine that has prior use experiences in patients in order to resolve the current pandemic situation before it could become worsening. Artificial intelligence (AI) technology is hereby applied to identify the marketed drugs with potential for treating COVID-19. Methods: An AI platform was established to identify potential old drugs with anti-coronavirus activities by using two different learning databases; one consisted of the compounds reported or proven active against SARS-CoV, SARS-CoV-2, human immunodeficiency virus, influenza virus, and the other one containing the known 3C-like protease inhibitors. All AI predicted drugs were then tested for activities against a feline coronavirus in in vitro cell-based assay. These assay results were feedbacks to the AI system for relearning and thus to generate a modified AI model to search for old drugs again. Results: After a few runs of AI learning and prediction processes, the AI system identified 80 marketed drugs with potential. Among them, 8 drugs (bedaquiline, brequinar, celecoxib, clofazimine, conivaptan, gemcitabine, tolcapone, and vismodegib) showed in vitro activities against the proliferation of a feline infectious peritonitis (FIP) virus in Fcwf-4 cells. In addition, 5 other drugs (boceprevir, chloroquine, homoharringtonine, tilorone, and salinomycin) were also found active during the exercises of AI approaches. Conclusion: Having taken advantages of AI, we identified old drugs with activities against FIP coronavirus. Further studies are underway to demonstrate their activities against SARS-CoV-2 in vitro and in vivo at clinically achievable concentrations and doses. With prior use experiences in patients, these old drugs if proven active against SARS-CoV-2 can readily be applied for fighting COVID-19 pandemic.

Synthesis and biological evaluation of N-heterocyclic indolyl glyoxylamides as orally active anticancer agents.

A series of N-heterocyclic indolyl glyoxylamides were synthesized and evaluated for in vitro and in vivo anticancer activities. They exhibited a broad spectrum of anticancer activity not only in murine leukemic cancer cells but also in human gastric, breast, and uterus cancer cells as well as their multidrug resistant sublines with a wide range of IC(50) values. They also induced apoptosis and caused DNA fragmentation in human gastric cancer cells. Among the compounds studied, 7 showed the most potent activity of growth inhibition (IC(50) = 17-1711 nM) in several human cancer cells. Given orally, compounds 7 and 13 dose-dependently prolonged the survival of animals inoculated with P388 leukemic cancer cells. N-Heterocyclic indolyl glyoxylamides may be useful as orally active chemotherapeutic agents against cancer and refractory cancerous diseases of multidrug resistance phenotype.

Synthesis and structure-activity relationship of 2-aminobenzophenone derivatives as antimitotic agents.

A new type of inhibitor of tubulin polymerization was discovered on the basis of the combretastatin molecular skeleton. The lead compounds in this series, compounds 6 and 7, strongly inhibited tubulin polymerization in vitro and significantly arrested cells at the G(2)/M phase. Compounds 6 and 7 yielded 50- to 100-fold lower IC(50) values than did combretastatin A-4 against Colo 205, NUGC3, and HA22T human cancer cell lines as well as similar or greater growth inhibitory activities than did combretastain A-4 against DLD-1, HR, MCF-7, DU145, HONE-1, and MES-SA/DX5 human cancer cell lines. Structure-activity relationship information revealed that introduction of an amino group at the ortho position of the benzophenone ring plays an integral role for increased growth inhibition.