| Baricitinib | An artificial intelligence (AI) platform recognized baricitinib agents as a probable COVID-19 therapy. However, detailed information about its mode of action is limited. | (37, 38) |
| Remdesivir; aprepitant; valrubicin; fulvestrant | With the support of the artificial intelligence approach, we can select particular repurposed drugs, selectively directing the central coronavirus protease (6LU7) utilizing receptor-ligand interactions with liquid simulation algorithms to recognize greater binding compounds. In addition, drug compounds, after molecular dynamic simulations, are directed for absorption, digestion, metabolism, excretion, and toxicity studies. | (34) |
| Cinametic acid; guaifenesin; lauric acid; ascorbyl palmitrate; nabumetone; octacosanol; palmidrol; salmeterol; nafcillin | Advancement in AI machinery with much machine knowledge and deep learning program was employed for comprehension of in-silico methodologies along with pattern identification technology for monitoring FDA-approved pharmaceuticals and nutraceuticals to target the CoV envelope (E) protein. Protein E is indulged in the association and discharge of the virion interior into the host. A multitude of open-source drug databases was considered, such as Enamine Bio-reference compounds (https://www.enaminestore.com/products/bioreference-compounds, accessed on 24t February 2022) | (39) |
| Brequinar; clofazimine; tolcapone; bedaquiline; conivaptan; gemcitabine; vismodegib; celecoxib | Earlier, artificial intelligence technology was established to recognize repurposed/ traditional drugs with anti-coronavirus activities. With the introduction of machine learning programs, further prediction of medicines with the help of AI machinery was later tested for their in-vitro potential against a feline coronavirus. However, the deep neural network algorithm is currently employed to recognize the most applicable descriptors for the fabrication of AI prediction models. | (40) |
| Lisinopril; spirapril; captopril | Artificial intelligence-amalgamated automatic modeling platform BIOiSIM was employed to simulate the systemic treatment of blockers of calcium channels and ACE compounds in tissues related to the COVID-19 pathogenesis, namely the disposition and site-of-action penetration (in-silico modeling). The most scalable dynamic computer-based prediction is BIOiSIM, which predicts in-vivo pharmacokinetic-pharmacodynamic (PK-PD) phenomena. | (41) |
| Albuterol; artemisinin; amprenavir; chloroquine; ciprofloxacin; fluoroquinolones; hydroxymethylglutaryl-coa reductase inhibitors; cyclosporine; quinolone; antibacterial agents; methotrexate; zidovudine; suramin | To predict the link, an AI text-mining model was developed. Various other approaches, such as SemNe, and biomedical knowledge graph, were employed to predict missing links in biomedical literature, which was helpful in drug repurposing. However, RotatE, TransE, and CompleX methods are based on the knowledge of graph embeddings and outcomes predicted with web application | (42) |
| Fulvestrant; aprepitant; valrubicin; remdesivir | For repurposed drugs, a machine-learning approach was utilized. Specifically, repurposed drugs targeted the main coronavirus protease (6LU7) employing ligand-receptor docking, which was optimized using liquid simulation algorithms to recognize high-affinity compounds. In addition, drug candidates were subjected to molecular dynamic simulations and further examined for adsorption, distribution, metabolism excretion, and toxicity studies (ADMET). | (34) |
| Dihydroergotamine; venetoclax; conivaptan; eltrombopag; ergotamine; idarubicin; ledipasvir; lifitegrast; lumacaftor; eribulin; nilotinib; nystatin; paritaprevir; ponatinib; regorafenib; rifapentine; simeprevir; teniposide; trabectedin; trypan blue; ivermectin; velpatasvir | Different in-silico approaches were combined for decreeing virtual drugs or utilizing molecular docking and supervised machine learning algorithms. However, all were used in a determined manner to recognize repurposed drug activity against COVID-19. | (43) |