The Role of Structural Biology Task Force: Validation of the Binding Mode of Repurposed Drugs Against SARS-CoV-2 Protein Targets: Focus on SARS-CoV-2 Main Protease (Mpro): A Promising Target for COVID-19 Treatment

The main protease (Mpro) of SARS-CoV-2, a cysteine protease that plays a key role in generating the active proteins essential for coronavirus replication, is a validated drug target for treating COVID-19. The structure of Mpro has been elucidated by macromolecular crystallography, but owing to its conformational flexibility, finding effective inhibitory ligands was challenging. Screening libraries of ligands as part of EXaSCale smArt pLatform Against paThogEns (ExScalate4CoV) yielded several potential drug molecules that inhibit SARS-CoV-2 replication in vitro. We solved the crystal structures of Mpro in complex with repurposed drugs like myricetin, a natural flavonoid, and MG-132, a synthetic peptide aldehyde. We found that both inhibitors covalently bind the catalytic cysteine. Notably, myricetin has an unexpected binding mode, showing an inverted orientation with respect to that of the flavonoid baicalein. Moreover, the crystallographic model validates the docking pose suggested by molecular dynamics experiments. The mechanism of MG-132 activity against SARS-CoV-2 Mpro was elucidated by comparison of apo and inhibitor-bound crystals, showing that regardless of the redox state of the environment and the crystalline symmetry, this inhibitor binds covalently to Cys145 with a well-preserved binding pose that extends along the whole substrate binding site. MG-132 also fits well into the catalytic pocket of human cathepsin L, as shown by computational docking, suggesting that it might represent a good start to developing dual-targeting drugs against COVID-19. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Updates on drug designing approach through computational strategies: a review.

The drug discovery and development (DDD) process in pursuit of novel drug candidates is a challenging procedure requiring lots of time and resources. Therefore, computer-aided drug design (CADD) methodologies are used extensively to promote proficiency in drug development in a systematic and time-effective manner. The point in reference is SARS-CoV-2 which has emerged as a global pandemic. In the absence of any confirmed drug moiety to treat the infection, the science fraternity adopted hit and trial methods to come up with a lead drug compound. This article is an overview of the virtual methodologies, which assist in finding novel hits and help in the progression of drug development in a short period with a specific medicinal solution.

An extensive survey of technological applications in drug discovery and development, encompassing offline and online approaches, is presented in this review. The span of research issues that can be tackled using these advances is vast, opening new horizons for future innovations. The article is designed to incite further research investments into drug development procedures and bridge existing research voids by outlining multiple pharmaceutical products that resulted from employing systematic computational methodologies.

Future perspectives of emerging novel drug targets and immunotherapies to control drug addiction.

Substance Use Disorder (SUD) is one of the major mental illnesses that is terrifically intensifying worldwide. It is becoming overwhelming due to limited options for treatment. The complexity of addiction disorders is the main impediment to understanding the pathophysiology of the illness. Hence, unveiling the complexity of the brain through basic research, identification of novel signaling pathways, the discovery of new drug targets, and advancement in cutting-edge technologies will help control this disorder. Additionally, there is a great hope of controlling the SUDs through immunotherapeutic measures like therapeutic antibodies and vaccines. Vaccines have played a cardinal role in eliminating many diseases like polio, measles, and smallpox. Further, vaccines have controlled many diseases like cholera, dengue, diphtheria, Haemophilus influenza type b (Hib), human papillomavirus, influenza, Japanese encephalitis, etc. Recently, COVID-19 was controlled in many countries by vaccination. Currently, continuous effort is done to develop vaccines against nicotine, cocaine, morphine, methamphetamine, and heroin. Antibody therapy against SUDs is another important area where serious attention is required. Antibodies have contributed substantially against many serious diseases like diphtheria, rabies, Crohn's disease, asthma, rheumatoid arthritis, and bladder cancer. Antibody therapy is gaining immense momentum due to its success rate in cancer treatment. Furthermore, enormous advancement has been made in antibody therapy due to the generation of high-efficiency humanized antibodies with a long half-life. The advantage of antibody therapy is its instant outcome. This article's main highlight is discussing the drug targets of SUDs and their associated mechanisms. Importantly, we have also discussed the scope of prophylactic measures to eliminate drug dependence.

A Matrix Factorization-Based Drug-Virus Link Prediction Method for SARS-CoV-2 Drug Prioritization

Matrix factorization (MF) has been widely used in drug discovery for link prediction, which aims to reveal new drug-target links by integrating drug-drug and target-target similarity information with a drug-target interaction matrix. The MF method is based on the assumption that similar drugs share similar targets and vice versa. However, one major disadvantage is that only one similarity metric is used in MF models, which is not enough to represent the similarity between drugs or targets. In this work, we develop a similarity fusion enhanced MF model to incorporate different types of similarity for novel drug-target link prediction. We apply the proposed model on a drug-virus association dataset for anti-COVID drug prioritization, and compare the performance with other existing MF models developed for COVID. The results show that the similarity fusion method can provide more useful information for drug-drug and virus-virus similarity and hence improve the performance of MF models. The top 10 drugs as prioritized by our model are provided, together with supporting evidence from literature. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

COVID-19: Insights into Structure-Function Relationship, Drug Targets and Drug Design Strategies for Novel-Coronavirus 2019

Background: Novel coronavirus (2019-nCov) imposed deadly health calamity with unexpected disastrous situation alarming the globe for urgent treatment regimes. World Health Organization (WHO) termed the coronavirus disease as COVID-2019 on February 11, 2020 and announced its outbreak as pandemic on 11 March 2020. The first infection was noticed in Wuhan, Hubei province, China, in December 2019, and it is believed that the corona-virus is transmitted to humans through bats as a reservoir involving human to human transfer. However, the proper intermediary transmission channel is yet to be unestablished. Method(s): Elderly populations and patients with concomitant symptoms are more at risk as compared to middle-aged patients as it may progress to pneumonia followed by severe acute respiratory syndrome (SARS) and multi-organ failure. Morbidity rates estimated in patients are less, i.e., 2-3%, but the dearth of a specific treatment strategy to prevent coronavirus infection is a major concern. Result(s): Currently, anti-viral and anti-malarial drugs are in practice for the management of COVID-19 disease along with plasma therapy in the absence of a potent vaccine. Besides, home isolation and social distancing are the precautionary measures adopted by many countries to minimize the spread of infection. Various studies have been conducted, and numerous are still going on to establish specific treatment for COVID-19. Conclusion(s): In this review, we summarized information on the structural components of COVID19 virus with special emphasis on the virus genome, life cycle, the importance of protease enzyme, the role of spike proteins in viral replication, validated drug targets, ongoing effective treatments for COVID-19 management and the latest research on drug design to develop anti-CoV drugs.Copyright © 2021 Bentham Science Publishers.

Discussion on the mechanism of Xiyanping injection in the treatment of human coronavirus infection based on network pharmacology and molecular docking

Objective: To explore the mechanism of Xiyanping injection in the treatment of human coronavirus infection based on network pharmacology and molecular docking method. Methods: The active components and targets of Xiyanping injection were screened by CNKI, SwissTarget Prediction and Targetnet. The Human Gene Database (Genecards), Online Human Mendelian Inheritance Database (OMIM) and Therapeutic Target Database (TTD) were searched to predict disease targets. Venny 2.1.0, Cytoscape 3.8.2 and STRING11.5 were used to construct "drug target-disease target Venn diagram", "drug-active ingredient-target-disease network" and "protein interaction network". The Database for Annotation, Visualization and Integrated Discovery (DAVID) and Bioinformatics, Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG) were used for the enrichment analysis and visualization. Finally, molecular docking was performed by AutoDock Vina and PyMOL. Results: The active ingredient of Xiyanping injection was andrographolide, andrographolide had 140 targets, 1 812 potential targets of human coronavirus infection, and 35 common targets of Xiyanping and human coronavirus infection;PPI network analysis and molecular docking showed that MAPK9, MAPK8, TYK2, CDKI and interleukin (IL)-6 among the 35 common targets might be the key targets of Xiyanping injection in the treatment of human coronavirus infection. Lactone was tightly bound;enrichment analysis showed that key targets were closely related to protein phosphorylation, cell signal transduction, and gene expression regulation, and key targets were NOD-like receptor signaling pathway, Toll-like receptor signaling pathway, FOXO signaling pathway, there was also an important link in the TNF signaling pathway. Conclusion: The active ingredient of Xiyanping injection was andmgrapholide, and its treatment of human coronavirus infection might affect NOD-like receptor signaling pathway, Toll-like receptor signaling pathway and FOXO signaling by inhibiting the activities of MAPK9, MAPK8, TYK2, CDK1 and IL-6. The activation of the pathway and the TNF signaling pathway regulates protein phosphorylation, cell signal transduction and gene expression, thereby exerting anti-inflammatory effects.

Identification and vitro verification of the potential drug targets of active ingredients of Chonglou in the treatment of lung adenocarcinoma based on EMT-related genes.

Lung adenocarcinoma (LUAD) is the main histological type of lung cancer with an unfavorable survival rate. Metastasis is the leading LUAD-related death with Epithelial-Mesenchymal Transition (EMT) playing an essential role. The anticancer efficacies of the active ingredients in Chonglou have been widely reported in various cancers. However, the potential therapeutic targets of the Chonglou active ingredients in LUAD patients remain unknown. Here, the network pharmacology and bioinformatics were performed to analyze the associations of the clinical characteristics, immune infiltration factors and m6A-related genes with the EMT-related genes associated with LUAD (EMT-LUAD related genes), and the molecular docking, STRING, GO, and KEGG enrichment for the drug targets of Chonglou active ingredients associated with EMT (EMT-LUAD-Chonglou related genes). And, cell viability analysis and cell invasion and infiltration analysis were used to confirm the theoretical basis of this study. A total of 166 EMT-LUAD related genes were identified and a multivariate Cox proportional hazards regression model with a favorable predictive accuracy was constructed. Meanwhile, the immune cell infiltration, immune cell subsets, checkpoint inhibitors and the expression of m6A-related genes were significantly associated with the risk scores for EMT-LUAD related genes with independent significant prognostic value of all included LUAD patients. Furthermore, 12 EMT-LUAD-Chonglou related genes with five core drug targets were identified, which participated in LUAD development through extracellular matrix disassembly, collagen metabolic process, collagen catabolic process, extracellular matrix organization, extracellular structure organization and inflammatory response. Moreover, we found that the active ingredients of Chonglou could indeed inhibit the progression of lung adenocarcinoma cells. These results are oriented towards EMT-related genes to achieve a better understanding of the role of Chonglou and its targets in osteosarcoma development and metastasis, thus guiding future preclinical studies and facilitating clinical translation of LUAD treatment.

Tuberculosis: Pathogenesis, Current Treatment Regimens and New Drug Targets.

Mycobacterium tuberculosis (M. tb), the causative agent of TB, is a recalcitrant pathogen that is rife around the world, latently infecting approximately a quarter of the worldwide population. The asymptomatic status of the dormant bacteria escalates to the transmissible, active form when the host's immune system becomes debilitated. The current front-line treatment regimen for drug-sensitive (DS) M. tb strains is a 6-month protocol involving four different drugs that requires stringent adherence to avoid relapse and resistance. Poverty, difficulty to access proper treatment, and lack of patient compliance contributed to the emergence of more sinister drug-resistant (DR) strains, which demand a longer duration of treatment with more toxic and more expensive drugs compared to the first-line regimen. Only three new drugs, bedaquiline (BDQ) and the two nitroimidazole derivatives delamanid (DLM) and pretomanid (PMD) were approved in the last decade for treatment of TB-the first anti-TB drugs with novel mode of actions to be introduced to the market in more than 50 years-reflecting the attrition rates in the development and approval of new anti-TB drugs. Herein, we will discuss the M. tb pathogenesis, current treatment protocols and challenges to the TB control efforts. This review also aims to highlight several small molecules that have recently been identified as promising preclinical and clinical anti-TB drug candidates that inhibit new protein targets in M. tb.

Discovery of compounds inhibiting SARS-COV-2 multi-targets.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has become a pandemic that has devastated the lives of millions. Researchers around the world are relentlessly working in hopes of finding a cure. Even though the virus shares similarities with reported SARS-CoV and MERS-CoV at the genomic and proteomic level, efforts to repurpose already known drugs against SARS-CoV-2 have resulted ineffective. In this succinct review, we discuss the different potential targets in SARS-CoV-2 at both the genomic and proteomic levels. In addition, we analyze the compounds inhibiting individual target protein as well as multiple targets of SARS-CoV-2. ACE-2 receptor in humans has also been considered a target, keeping the role of the receptor in mind. The mechanism of action of these compounds has also been highlighted along with their clinical manifestation. Towards the end of the review, a brief note on the drugs currently in clinical trials and the current status of the vaccines are also examined. In conclusion, compounds targeting multiple targets of the virus hold the key in putting an end to the coronavirus malady.Communicated by Ramaswamy H. Sarma.

In silico screening of potential antiviral inhibitors against SARS-CoV-2 main protease

Respiratory illness due to SARS-CoV-2 emerged in 2019 and has a significant morbidity and mortality rate. The main protease (Mpro) is mainly responsible for viral replications, which acts as a good drug target to inhibit SARS-CoV-2-related diseases. Chemical compounds obtained from various herbal plants are showing potent antiviral activity against numerous viral diseases. Initial screening was performed with the phytochemicals against Mpro using molecular docking. This result shows that there is a strong interaction exhibited between active sites (His-41 and Cys-145) of Mpro with chemical compounds. In addition, ADME prediction and Lipinski's rule of five (RO5) calculations demonstrated that the selected compounds have potential drug-like properties. Further, molecular dynamics (MD) simulations were performed to understand the stability and structural changes of protein–ligand complexes for the top five compounds. MM/PBSA studies strongly suggested that compounds, β-spinasterol, and asarinin form stable complexes with Mpro. The most significant hot spot residues such as Thr-25, Met-49, Cys-145, Met-165, and Gln-189 have strongly interacted with the selected chemical compounds. Our calculations suggest that asarinin is the best inhibitor to the Mpro, which supports these candidates and could be potent antiviral agent against SARS-CoV-2. © 2022 Informa UK Limited, trading as Taylor & Francis Group.

Plant-Derived Products with Therapeutic Potential against Gastrointestinal Bacteria.

The rising burden of antimicrobial resistance and increasing infectious disease outbreaks, including the recent COVID-19 pandemic, has led to a growing demand for the development of natural products as a valuable source of leading medicinal compounds. There is a wide variety of active constituents found in plants, making them an excellent source of antimicrobial agents with therapeutic potential as alternatives or potentiators of antibiotics. The structural diversity of phytochemicals enables them to act through a variety of mechanisms, targeting multiple biochemical pathways, in contrast to traditional antimicrobials. Moreover, the bioactivity of the herbal extracts can be explained by various metabolites working in synergism, where hundreds to thousands of metabolites make up the extract. Although a vast amount of literature is available regarding the use of these herbal extracts against bacterial and viral infections, critical assessments of their quality are lacking. This review aims to explore the efficacy and antimicrobial effects of herbal extracts against clinically relevant gastrointestinal infections including pathogenic Escherichia coli, toxigenic Clostridioides difficile, Campylobacter and Salmonella species. The review will discuss research gaps and propose future approaches to the translational development of plant-derived products for drug discovery purposes for the treatment and prevention of gastrointestinal infectious diseases.

Drugs swapping in coronavirus strains: a structural biology view.

Coronavirus belongs to the coronaviridae family, having a single-stranded RNA as genetic material of 26-42 kb in size. The first coronavirus infection emerged in 2002, caused by SARS-CoV1. Since then, genome sequences and three-dimensional structures of crucial proteins and enzymes of the virus have been studied in detail. The novel coronavirus (nCoV) outbreak has caused the COVID19 pandemic, which is responsible for the deaths of millions of people worldwide. The nCoV was later renamed as SARS-CoV2. The details of most of the COV proteins are available at the atomic and molecular levels. The entire genome is made up of 12 open reading frames that code for 27 different proteins. The spike surface glycoprotein, the envelope protein, the nucleocapsid protein, and the membrane protein are the four structural proteins which are required for virus attachment, entrance, assembly, and pathogenicity. The remaining proteins encoded are called non-structural (NSPs) and support the survival of the virus. Several non-structural proteins are also validated targets for drug development against coronavirus and are being used for drug design purposes. To perform a comparative study, sequences and three-dimensional structures of four crucial viral enzymes, Mpro, PLpro, RdRp, and EndoU from SARS-CoV1 and SARS-CoV2 variants were analyzed. The key structural elements and ligands recognizing amino acid residues were found to be similar in enzymes from both strains. The significant sequences and structural resemblance also suggest that a drug developed either for SARS-CoV1 or SARS-CoV2 using these enzymes may also have the potential to cross-react.Communicated by Ramaswamy H. Sarma.

Plasma kallikrein in inflammation

As an important component of kallikrein-kinin system(KKS), plasma kallikrein(pKal) is involved in inflammation process via KKS, complement system and renin-angiotensin system(RAS)and plays an important role in angioedema(HAE), rheumatoid arthritis(RA)and corona virus disease 2019(COVID-19). pKal maybe a therapeutic target against inflammatory diseases, and pKal inhibitors are being researched and developed for the prevention and treatment of inflammatory diseases such as HAE and RA, and may also be new agents for the prevention and treatment of COVID-19.

Development of Machine Learning Regression Model for COVID-19 Drug Target Prediction

There is a perennial need to identify novel, effective therapeutic agents to combat rising infections. Recently, prediction of therapeutic targets to decrease the impact of COVID-19 has posed an urgent challenge requiring innovative solutions. Successful identification of novel drug-target combinations may greatly facilitate drug development. To meet this need, we developed a COVID-19 drug target prediction model using machine learning approaches to quickly identify drug candidates for 18 COVID-19 protein targets. Specifically, we analyzed the performance of three prediction models to predict drug-target docking scores, which represents the strength of interactions between ligands and proteins. Docking scores were predicted for 300,457 molecules on 18 different COVID-19 related protein docking targets. Our proposed approach achieved a competitive performance with mathrm{R}-{2}=0.69,MAE=0.285, MSE=0.627. In addition, we identify chemical structures associated with stronger binding affinities across target binding sites. We believe our work could potentially save pharmaceutical companies significant resources, especially during the early stages of drug development. © 2022 IEEE.

Epigenetic Targets and Pathways Linked to SARS-CoV-2 Infection and Pathology.

The scale at which the SARS-CoV-2/COVID-19 pandemic has spread remains enormous. Provided the genetic makeup of the virus and humans is readily available, the quest for knowing the mechanism and epidemiology continues to prevail across the entire scientific community. Several aspects, including immunology, molecular biology, and host-pathogen interaction, are continuously being dug into for preparing the human race for future pandemics. The exact reasons for vast differences in symptoms, pathophysiological implications of COVID-infections, and mortality differences remain elusive. Hence, researchers are also looking beyond traditional genomics, proteomics, and transcriptomics approach, especially entrusting the environmental regulation of the genetic landscape of COVID-human interactions. In line with these questions lies a critical process called epigenetics. The epigenetic perturbations in both host and parasites are a matter of great interest to unravel the disparities in COVID-19 mortalities and pathology. This review provides a deeper insight into current research on the epigenetic landscape of SARS-CoV-2 infection in humans and potential targets for augmenting the ongoing investigation. It also explores the potential targets, pathways, and networks associated with the epigenetic regulation of processes involved in SARS-CoV-2 pathology.

FingerDTA: A Fingerprint-Embedding Framework for Drug-Target Binding Affinity Prediction

Many efforts have been exerted toward screening potential drugs for targets, and conducting wet experiments remains a laborious and time-consuming approach. Artificial intelligence methods, such as Convolutional Neural Network (CNN), are widely used to facilitate new drug discovery. Owing to the structural limitations of CNN, features extracted from this method are local patterns that lack global information. However, global information extracted from the whole sequence and local patterns extracted from the special domain can influence the drugtarget affinity. A fusion of global information and local patterns can construct neural network calculations closer to actual biological processes. This paper proposes a Fingerprint-embedding framework for Drug-Target binding Affinity prediction (FingerDTA), which uses CNN to extract local patterns and utilize fingerprints to characterize global information. These fingerprints are generated on the basis of the whole sequence of drugs or targets. Furthermore, FingerDTA achieves comparable performance on Davis and KIBA data sets. In the case study of screening potential drugs for the spike protein of the coronavirus disease 2019 (COVID-19), 7 of the top 10 drugs have been confirmed potential by literature. Ultimately, the docking experiment demonstrates that FingerDTA can find novel drug candidates for targets. All codes are available at http://lanproxy.biodwhu.cn:9099/mszjaas/FingerDTA.git. © 2018 Tsinghua University Press.

Reinforcement Learning and Graph Neural Networks for Designing Novel Drugs with Optimized Affinity: Application to SARS-CoV-2

Drugs are generally designed for a specific target protein. Recent studies have demonstrated the capability of deep learning-based models to accelerate and cheapen the drug development process. The proposed deep learning models can generate novel molecules with optimized drug-like properties. However, the properties addressed are often limited and may be misleading. This is because they do not reflect the complete information about the binding affinity of the designed drug and the target protein. In this work, we exploit the state-of-The-Art progress made in drug-Target-Affinity (DTA) prediction to assess the binding affinity of drugs generated by a developed molecular generator against the corona-virus main protease (SARS-CoV-2 Mpro). The molecular generator is a recurrent neural network-based model, while the DTA predictor is a graph neural network (GNN), famously known as GraphDTA. We train the molecular generator using reinforcement learning (RL) to optimize the GraphDTA-predicted score. As this is the first benchmark of this kind (to the best of our knowledge), we report our benchmarking results;of 1.79% desirability;with the hope of motivating future improvements in this regard. © 2022 IEEE.

Structural insights into the activity regulation of full-length non-structural protein 1 from SARS-CoV-2.

Non-structural protein 1 (Nsp1) of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is a major virulence factor and thus an attractive drug target. The last 33 amino acids of Nsp1 have been shown to bind within the mRNA entry tunnel of the 40S ribosomal subunit, shutting off host gene expression. Here, we report the solution-state structure of full-length Nsp1, which features an α/ß fold formed by a six-stranded, capped ß-barrel-like globular domain (N-terminal domain [NTD]), flanked by short N-terminal and long C-terminal flexible tails. The NTD has been found to be critical for 40S-mediated viral mRNA recognition and promotion of viral gene expression. We find that in free Nsp1, the NTD mRNA-binding surface is occluded by interactions with the acidic C-terminal tail, suggesting a mechanism of activity regulation based on the interplay between the folded NTD and the disordered C-terminal region. These results are relevant for drug-design efforts targeting Nsp1.

Unpacking COVID-19 Systems Biology in Lung and Whole Blood with Transcriptomics and miRNA Regulators.

COVID-19 is a systemic disease affecting tissues and organs, including and beyond the lung. Apart from the current pandemic context, we also have vastly inadequate knowledge of consequences of repeated exposures to SARS-CoV-2 (severe acute respiratory syndrome coronavirus 2), the virus causing COVID-19, in multiple organ systems and the whole organism scales when the disease evolves from a pandemic to an endemic state. This calls for a systems biology and systems medicine approach and unpacking the effects of COVID-19 in lung as well as other tissues. We report here original findings from transcriptomics analyses and differentially expressed genes (DEGs) in lung samples from 60 patients and 27 healthy controls, and in whole blood samples from 255 patients and 103 healthy individuals. A total of 11 datasets with RNA-seq transcriptomic data were obtained from the Gene Expression Omnibus and the European Nucleotide Archive. The identified DEGs were used to construct protein interaction and functional networks and to identify related pathways and miRNAs. We found 35 DEGs common between lung and the whole blood, and importantly, 2 novel genes, namely CYP1B1 and TNFAIP6, which have not been previously implicated with COVID-19. We also identified four novel miRNA potential regulators, hsa-mir-192-5p, hsa-mir-221-3p, hsa-mir-4756-3p, and hsa-mir-10a-5p, implicated in lung or other diseases induced by coronaviruses. In summary, these findings offer new molecular leads and insights to unpack COVID-19 systems biology in a whole organism context and might inform future antiviral drug, diagnostics, and vaccine discovery efforts.

ML-DTD: Machine Learning-Based Drug Target Discovery for the Potential Treatment of COVID-19.

Recent research has highlighted that a large section of druggable protein targets in the Human interactome remains unexplored for various diseases. It might lead to the drug repurposing study and help in the in-silico prediction of new drug-human protein target interactions. The same applies to the current pandemic of COVID-19 disease in global health issues. It is highly desirable to identify potential human drug targets for COVID-19 using a machine learning approach since it saves time and labor compared to traditional experimental methods. Structure-based drug discovery where druggability is determined by molecular docking is only appropriate for the protein whose three-dimensional structures are available. With machine learning algorithms, differentiating relevant features for predicting targets and non-targets can be used for the proteins whose 3-D structures are unavailable. In this research, a Machine Learning-based Drug Target Discovery (ML-DTD) approach is proposed where a machine learning model is initially built up and tested on the curated dataset consisting of COVID-19 human drug targets and non-targets formed by using the Therapeutic Target Database (TTD) and human interactome using several classifiers like XGBBoost Classifier, AdaBoost Classifier, Logistic Regression, Support Vector Classification, Decision Tree Classifier, Random Forest Classifier, Naive Bayes Classifier, and K-Nearest Neighbour Classifier (KNN). In this method, protein features include Gene Set Enrichment Analysis (GSEA) ranking, properties derived from the protein sequence, and encoded protein network centrality-based measures. Among all these, XGBBoost, KNN, and Random Forest models are satisfactory and consistent. This model is further used to predict novel COVID-19 human drug targets, which are further validated by target pathway analysis, the emergence of allied repurposed drugs, and their subsequent docking study.