Front Chem. 2021 Oct 22;9:736509. doi: 10.3389/fchem.2021.736509. eCollection 2021.

ABSTRACT

Clinical trials of novel therapeutics for Alzheimer's Disease (AD) have consumed a significant amount of time and resources with largely negative results. Repurposing drugs already approved by the Food and Drug Administration (FDA), European Medicines Agency (EMA), or Worldwide for another indication is a more rapid and less expensive option. Therefore, we apply the scaffold searching approach based on known amyloid-beta (Aβ) inhibitor tramiprosate to screen the DrugCentral database (n = 4,642) of clinically tested drugs. As a result, menadione bisulfite and camphotamide substances with protrombogenic and neurostimulation/cardioprotection effects were identified as promising Aβ inhibitors with an improved binding affinity (ΔGbind) and blood-brain barrier permeation (logBB). Finally, the data was also confirmed by molecular dynamics simulations using implicit solvation, in particular as Molecular Mechanics Generalized Born Surface Area (MM-GBSA) model. Overall, the proposed in silico pipeline can be implemented through the early stage rational drug design to nominate some lead candidates for AD, which will be further validated in vitro and in vivo, and, finally, in a clinical trial.

PMID:34751244 | PMC:PMC8571023 | DOI:10.3389/fchem.2021.736509

Sci Rep. 2021 Nov 8;11(1):21872. doi: 10.1038/s41598-021-01410-3.

ABSTRACT

Severe acute respiratory syndrome (SARS) is a highly contagious viral respiratory illness. This illness is spurred on by a coronavirus known as SARS-associated coronavirus (SARS-CoV). SARS was first detected in Asia in late February 2003. The genome of this virus is very similar to the SARS-CoV-2. Therefore, the study of SARS-CoV disease and the identification of effective drugs to treat this disease can be new clues for the treatment of SARS-Cov-2. This study aimed to discover novel potential drugs for SARS-CoV disease in order to treating SARS-Cov-2 disease based on a novel systems biology approach. To this end, gene co-expression network analysis was applied. First, the gene co-expression network was reconstructed for 1441 genes, and then two gene modules were discovered as significant modules. Next, a list of miRNAs and transcription factors that target gene co-expression modules' genes were gathered from the valid databases, and two sub-networks formed of transcription factors and miRNAs were established. Afterward, the list of the drugs targeting obtained sub-networks' genes was retrieved from the DGIDb database, and two drug-gene and drug-TF interaction networks were reconstructed. Finally, after conducting different network analyses, we proposed five drugs, including FLUOROURACIL, CISPLATIN, SIROLIMUS, CYCLOPHOSPHAMIDE, and METHYLDOPA, as candidate drugs for SARS-CoV-2 coronavirus treatment. Moreover, ten miRNAs including miR-193b, miR-192, miR-215, miR-34a, miR-16, miR-16, miR-92a, miR-30a, miR-7, and miR-26b were found to be significant miRNAs in treating SARS-CoV-2 coronavirus.

PMID:34750486 | DOI:10.1038/s41598-021-01410-3

Int J Biochem Cell Biol. 2021 Nov 5:106114. doi: 10.1016/j.biocel.2021.106114. Online ahead of print.

ABSTRACT

Severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) emerged from Wuhan in China before it spread to the entire globe. It causes coronavirus disease of 2019 (COVID-19) where mostly individuals present mild symptoms, some remain asymptomatic and some show severe lung inflammation and pneumonia in the host through the induction of a marked inflammatory 'cytokine storm'. New and efficacious vaccines have been developed and put into clinical practice in record time, however, there is a still a need for effective treatments for those who are not vaccinated or remain susceptible to emerging SARS-CoV-2 variant strains. Despite this, effective therapeutic interventions against COVID-19 remain elusive. Here we review potential drugs for COVID-19 classified on the basis of their mode of action. The mechanisms of action of each are discussed in detail to highlight the therapeutic targets that may help in reducing the global pandemic. The review was done up to July 2021 and the data was assessed through the official websites of WHO and CDC for collecting the information on the clinical trials. Moreover, the recent research papers were also assessed for the relevant data. The search was made based on keywords like Coronavirus, SARS-C0V-2, drugs (specific name of the drugs), COVID-19, clinical efficiency, safety profile, side-effects etc.This review outlines potential areas for future research into COVID-19 treatment strategies.

PMID:34748991 | DOI:10.1016/j.biocel.2021.106114

Life Sci. 2021 Nov 5:120122. doi: 10.1016/j.lfs.2021.120122. Online ahead of print.

ABSTRACT

AIMS: Bethanidine (BW467C60) is a newly presented strong adrenergic neuron blocking factor which has a hypotensive operation in man. SENPs are essential for maintaining a balance between SUMOylation and deSUMOylation which can be disturbed by changing the expression of (sentrin-specific proteases) SENPs. SENP1 is the most studied isoform of SENPs. Hypertrophic stimuli can increase SENP1 expression using calcium/calcineurin-NFAT3 signaling in heart. Moreover, SENP1 expression may positively relate to the expression of mitochondrial genes of the heart, and can cause the heart and mitochondrial dysfunction.

MATERIALS AND METHODS: In order to inhibit SENP1 using Bethanidine, molecular docking and molecular dynamics (MD) simulation of SENP1 with Bethanidine were performed. Molecular docking showed that Bethanidine can inhibit SENP1.

KEY FINDINGS: MD Simulation showed that Bethanidine constitutes a stable complex with SENP1 as was evident from RMSD, RMSF, H-bond and DSSP plots. Free binding energy and the interaction patterns were obtained from molecular docking, and MD trajectory exhibited Bethanidine can be a potential drug candidate for SENP1 inhibition.

SIGNIFICANCE: This study supplies enough evidences that Bethanidine is a potential inhibitor of SENP1 and can be applied for the treatment of cardiovascular diseases.

PMID:34748762 | DOI:10.1016/j.lfs.2021.120122

J Egypt Natl Canc Inst. 2021 Nov 8;33(1):33. doi: 10.1186/s43046-021-00091-3.

ABSTRACT

BACKGROUND: The expression of hERG K+ channels is observed in various cancer cells including epithelial, neuronal, leukemic, and connective tissue. The role of hERG potassium channels in regulating the growth and death of cancer cells include cell proliferation, survival, secretion of proangiogenic factors, invasiveness, and metastasis.

METHODS: In the reported study, an attempt has been made to investigate some non-cancer hERG blockers as potential cancer therapeutics using a computational drug repurposing strategy. Preliminary investigation for hERG blockers/non-blockers has identified 26 potential clinically approved compounds for further studies using molecular modeling.

RESULTS: The interactions at the binding pockets have been investigated along with the prioritization based on the binding score. Some of the identified potential hERG inhibitors, i.e., Bromocriptine, Darglitazone, and Troglitazone, have been investigated to derive the mechanism of cancer inhibition.

CONCLUSIONS: The proposed mechanism for anti-cancer properties via hERG blocking for some of the potential compounds is required to be explored using other experimental methodologies. The drug repurposing approach applied to investigate anti-cancer therapeutics may direct to provide a therapeutic solution to late-stage cancer and benefit a significant population of patients.

PMID:34746987 | DOI:10.1186/s43046-021-00091-3

Acta Pharm Sin B. 2021 Nov 1. doi: 10.1016/j.apsb.2021.10.026. Online ahead of print.

ABSTRACT

SARS-CoV-2 main protease (Mpro) is one of the most extensively exploited drug targets for COVID-19. Structurally disparate compounds have been reported as Mpro inhibitors, raising the question of their target specificity. To elucidate the target specificity and the cellular target engagement of the claimed Mpro inhibitors, we systematically characterize their mechanism of action using the cell-free FRET assay, the thermal shift-binding assay, the cell lysate Protease-Glo luciferase assay, and the cell-based FlipGFP assay. Collectively, our results have shown that majority of the Mpro inhibitors identified from drug repurposing including ebselen, carmofur, disulfiram, and shikonin are promiscuous cysteine inhibitors that are not specific to Mpro, while chloroquine, oxytetracycline, montelukast, candesartan, and dipyridamole do not inhibit Mpro in any of the assays tested. Overall, our study highlights the need of stringent hit validation at the early stage of drug discovery.

PMID:34745850 | PMC:PMC8558150 | DOI:10.1016/j.apsb.2021.10.026

Biophys Physicobiol. 2021 Oct 5;18:226-240. doi: 10.2142/biophysico.bppb-v18.025. eCollection 2021.

ABSTRACT

More than one and half years have passed, as of August 2021, since the COVID-19 caused by the novel coronavirus named SARS-CoV-2 emerged in 2019. While the recent success of vaccine developments likely reduces the severe cases, there is still a strong requirement of safety and effective therapeutic drugs for overcoming the unprecedented situation. Here we review the recent progress and the status of the drug discovery against COVID-19 with emphasizing a structure-based perspective. Structural data regarding the SARS-CoV-2 proteome has been rapidly accumulated in the Protein Data Bank, and up to 68% of the total amino acid residues encoded in the genome were covered by the structural data. Despite a global effort of in silico and in vitro screenings for drug repurposing, there is only a limited number of drugs had been successfully authorized by drug regulation organizations. Although many approved drugs and natural compounds, which exhibited antiviral activity in vitro, were considered potential drugs against COVID-19, a further multidisciplinary investigation is required for understanding the mechanisms underlying the antiviral effects of the drugs.

PMID:34745807 | PMC:PMC8550875 | DOI:10.2142/biophysico.bppb-v18.025

Front Pharmacol. 2021 Oct 20;12:746987. doi: 10.3389/fphar.2021.746987. eCollection 2021.

ABSTRACT

Background: The European Commission highlights in its Pharmaceutical Strategy the role of academic researchers in drug repurposing, especially in the development of orphan medicinal products (OMPs). This study summarizes the contribution of academia over the last 5 years to registered repurposed OMPs and describes barriers to success, based upon three real world cases. Methods: OMPs granted marketing authorization between January 2016 and December 2020 were reviewed for repurposing and whether the idea originated from academia or industry. Three cases of drug repurposing were selected from different therapeutic areas and stages of development to identify obstacles to success. Results: Thirteen of the 68 OMPs were the result of drug repurposing. In three OMPs, there were two developments such as both a new indication and a modified application. In total, twelve developments originated from academia and four from industry. The three cases showed as barriers to success: lack of outlook for sufficient return of investments (abatacept), lack of regulatory alignment and timing of interaction between healthcare professionals and regulators (etidronate), failure to register an old drug for a fair price, resulting in commercialization as a high priced orphan drug (mexiletine). Conclusion: While the majority of repurposed OMPs originates in academia, a gap exists between healthcare professionals, regulators and industry. Future strategies should aim to overcome these hurdles leading to more patient benefit through sustainable access of repurposed drugs. Potential solutions include improved regulatory and reimbursement knowledge by academia and the right for regulators to integrate new effectiveness data into product labels.

PMID:34744726 | PMC:PMC8564285 | DOI:10.3389/fphar.2021.746987

Front Pharmacol. 2021 Oct 21;12:737637. doi: 10.3389/fphar.2021.737637. eCollection 2021.

ABSTRACT

Background: Tumor therapeutics are aimed to affect tumor cells selectively while sparing healthy ones. For this purpose, a huge variety of different drugs are in use. Recently, also blockers of voltage-gated sodium channels (VGSCs) have been recognized to possess potentially beneficial effects in tumor therapy. As these channels are a frequent target of numerous drugs, we hypothesized that currently used tumor therapeutics might have the potential to block VGSCs in addition to their classical anti-cancer activity. In the present work, we have analyzed the imipridone TIC10, which belongs to a novel class of anti-cancer compounds, for its potency to interact with VGSCs. Methods: Electrophysiological experiments were performed by means of the patch-clamp technique using heterologously expressed human heart muscle sodium channels (hNav1.5), which are among the most common subtypes of VGSCs occurring in tumor cells. Results: TIC10 angular inhibited the hNav1.5 channel in a state- but not use-dependent manner. The affinity for the resting state was weak with an extrapolated Kr of about 600 μM. TIC10 most probably did not interact with fast inactivation. In protocols for slow inactivation, a half-maximal inhibition occurred around 2 µM. This observation was confirmed by kinetic studies indicating that the interaction occurred with a slow time constant. Furthermore, TIC10 also interacted with the open channel with an affinity of approximately 4 µM. The binding site for local anesthetics or a closely related site is suggested as a possible target as the affinity for the well-characterized F1760K mutant was reduced more than 20-fold compared to wild type. Among the analyzed derivatives, ONC212 was similarly effective as TIC10 angular, while TIC10 linear more selectively interacted with the different states. Conclusion: The inhibition of VGSCs at low micromolar concentrations might add to the anti-tumor properties of TIC10.

PMID:34744721 | PMC:PMC8567104 | DOI:10.3389/fphar.2021.737637

J Cell Biochem. 2021 Nov 6. doi: 10.1002/jcb.30174. Online ahead of print.

ABSTRACT

As per the World Health Organization report, around 226 844 344 confirmed positive cases and 4 666 334 deaths are reported till September 17, 2021 due to the recent viral outbreak. A novel coronavirus (severe acute respiratory syndrome coronavirus 2 [SARS-CoV-2]) is responsible for the associated coronavirus disease (COVID-19), which causes serious or even fatal respiratory tract infection and yet no approved therapeutics or effective treatment is currently available to combat the outbreak. Due to the emergency, the drug repurposing approach is being explored for COVID-19. In this study, we attempt to understand the potential mechanism and also the effect of the approved antiviral drugs against the SARS-CoV-2 main protease (Mpro). To understand the mechanism of inhibition of the malaria drug hydroxychloroquine (HCQ) against SARS-CoV-2, we performed molecular interaction studies. The studies revealed that HCQ docked at the active site of the Human ACE2 receptor as a possible way of inhibition. Our in silico analysis revealed that the three drugs Lopinavir, Ritonavir, and Remdesivir showed interaction with the active site residues of Mpro. During molecular dynamics simulation, based on the binding free energy contributions, Lopinavir showed better results than Ritonavir and Remdesivir.

PMID:34741481 | DOI:10.1002/jcb.30174

Parasitol Res. 2021 Nov 6. doi: 10.1007/s00436-021-07354-x. Online ahead of print.

ABSTRACT

The infection caused by Entamoeba histolytica is still a serious public health problem, especially in developing countries. The goal of this study was to evaluate the effect of terfenadine against Entamoeba histolytica. The trophozoites were exposed to 1, 2, 3, and 4 μM of terfenadine, for 24 and 48 h. Consequently, the viability of cells was determined by trypan blue exclusion test. The effect of terfenadine on adhesion of Entamoeba histolytica was evaluated in Caco-2 cells. In addition, the effect of terfenadine on the erythrophagocytic capacity of the parasite was investigated. The results show that terfenadine affects the growth and cell viability in a time- and dose-dependent manner. The higher inhibitory effects were observed with 4 µM at 48 h; 91.6% of growth inhibition and only 22.5% of trophozoites were viable. Additionally, we demonstrate that terfenadine is highly selective for the parasite and has low toxicity on Caco-2 cells. Furthermore, adhesion to Caco-2 cells and erythrophagocytic capacity were significantly inhibited. These findings demonstrate that terfenadine exerts significant effects on the virulence of Entamoeba histolytica. This is the first study demonstrating the amoebicidal activity of terfenadine and the results suggest it may be effective in the treatment of amoebiasis.

PMID:34741218 | DOI:10.1007/s00436-021-07354-x

Metabolism. 2021 Nov 2:154925. doi: 10.1016/j.metabol.2021.154925. Online ahead of print.

ABSTRACT

Nonalcoholic fatty liver disease (NAFLD) is the most common form of chronic liver disease worldwide. With no Food and Drug Administration approved drugs, current treatment options include dietary restrictions and lifestyle modification. NAFLD is closely associated with metabolic disorders such as obesity, type 2 diabetes, and dyslipidemia. Hence, clinically various pharmacological approaches using existing drugs such as antidiabetic, anti-obesity, antioxidants, and cytoprotective agents have been considered in the management of NAFLD and nonalcoholic steatohepatitis (NASH). However, several pharmacological therapies aiming to alleviate NAFLD-NASH are currently being examined at various phases of clinical trials. Emerging data from these studies with drugs targeting diverse molecular mechanisms show promising outcomes. This review summarizes the current understanding of the pathogenic mechanisms of NAFLD and provides an insight into the pharmacological targets and emerging therapeutics with specific interventional mechanisms. In addition, we also discuss the importance and utility of new approach methodologies and regulatory perspectives for NAFLD-NASH drug development.

PMID:34740573 | DOI:10.1016/j.metabol.2021.154925

J Exp Clin Cancer Res. 2021 Nov 5;40(1):347. doi: 10.1186/s13046-021-02144-w.

ABSTRACT

BACKGROUND: Glioblastoma (GBM; grade IV glioma) is characterized by a very short overall survival time and extremely low 5-year survival rates. We intend to promote experimental and clinical research on rationale and scientifically driven drug repurposing. This may represent a safe and often inexpensive way to propose novel pharmacological approaches to GBM. Our precedent work describes the role of chlorpromazine (CPZ) in hindering malignant features of GBM. Here, we investigate in greater detail the molecular mechanisms at the basis of the effect of CPZ on GBM cells.

METHODS: We employed proteomics platforms, i.e., activity-based protein profiling plus mass spectrometry, to identify potential cellular targets of the drug. Then, by means of established molecular and cellular biology techniques, we assessed the effects of this drug on GBM cell metabolic and survival pathways.

RESULTS: The experimental output indicated as putative targets of CPZ several of factors implicated in endoplasmic reticulum (ER) stress, with consequent unfolded protein response (UPR). Such a perturbation culminated in a noticeable reactive oxygen species generation and intense autophagic response that resulted in cytotoxic and abortive effects for six GBM cell lines, three of which growing as neurospheres, while it appeared cytoprotective for the RPE-1 human non-cancer neuro-ectodermal cell line.

CONCLUSIONS: This discrepancy could be central in explaining the lethal effects of the drug on GBM cells and the relatively scarce cytotoxicity toward normal tissues attributed to this compound. The data presented here offer support to the multicenter phase II clinical trial we have undertaken, which consists of the addition of CPZ to first-line treatment of GBM patients carrying a hypo- or un-methylated MGMT gene, i.e. those characterized by intrinsic resistance to temozolomide.

PMID:34740374 | DOI:10.1186/s13046-021-02144-w

Cell Res. 2021 Nov 4. doi: 10.1038/s41422-021-00581-y. Online ahead of print.

ABSTRACT

In contrast to the extensive research about viral protein-host protein interactions that has revealed major insights about how RNA viruses engage with host cells during infection, few studies have examined interactions between host factors and viral RNAs (vRNAs). Here, we profiled vRNA-host protein interactomes for three RNA virus pathogens (SARS-CoV-2, Zika, and Ebola viruses) using ChIRP-MS. Comparative interactome analyses discovered both common and virus-specific host responses and vRNA-associated proteins that variously promote or restrict viral infection. In particular, SARS-CoV-2 binds and hijacks the host factor IGF2BP1 to stabilize vRNA and augment viral translation. Our interactome-informed drug repurposing efforts identified several FDA-approved drugs (e.g., Cepharanthine) as broad-spectrum antivirals in cells and hACE2 transgenic mice. A co-treatment comprising Cepharanthine and Trifluoperazine was highly potent against the newly emerged SARS-CoV-2 B.1.351 variant. Thus, our study illustrates the scientific and medical discovery utility of adopting a comparative vRNA-host protein interactome perspective.

PMID:34737357 | DOI:10.1038/s41422-021-00581-y

Methods. 2021 Nov 1:S1046-2023(21)00247-4. doi: 10.1016/j.ymeth.2021.10.007. Online ahead of print.

ABSTRACT

Computational prediction of drug-target interactions (DTIs) is of particular importance in the process of drug repositioning because of its efficiency in selecting potential candidates for DTIs. A variety of computational methods for predicting DTIs have been proposed oade. Our interest is which methods or techniques are the most advantageous for increasing prediction accuracy. This article provides a comprehensive overview of network-based, machine learning, and integrated DTI prediction methods. The network-based methods handle a DTI network along with drug and target similarities in a matrix form and apply graph-theoretic algorithms to identify new DTIs. Machine learning methods use known DTIs and the features of drugs and target proteins as training data to build a predictive model. Integrated methods combine these two techniques. We assessed the prediction performance of the selected state-of-the-art methods using two different benchmark datasets. Our experimental results demonstrate that the integrated methods outperform the others in general. Some previous methods showed low accuracy on predicting interactions of unknown drugs which do not exist in the training dataset. Combining similarity matrices from multiple features by data fusion was not beneficial in increasing prediction accuracy. Finally, we analyzed future directions for further improvements in DTI predictions.

PMID:34737033 | DOI:10.1016/j.ymeth.2021.10.007

BMC Med Inform Decis Mak. 2021 Nov 4;21(Suppl 1):308. doi: 10.1186/s12911-021-01648-x.

ABSTRACT

BACKGROUND: Disease-drug associations provide essential information for drug discovery and disease treatment. Many disease-drug associations remain unobserved or unknown, and trials to confirm these associations are time-consuming and expensive. To better understand and explore these valuable associations, it would be useful to develop computational methods for predicting unobserved disease-drug associations. With the advent of various datasets describing diseases and drugs, it has become more feasible to build a model describing the potential correlation between disease and drugs.

RESULTS: In this work, we propose a new prediction method, called LMFDA, which works in several stages. First, it studies the drug chemical structure, disease MeSH descriptors, disease-related phenotypic terms, and drug-drug interactions. On this basis, similarity networks of different sources are constructed to enrich the representation of drugs and diseases. Based on the fused disease similarity network and drug similarity network, LMFDA calculated the association score of each pair of diseases and drugs in the database. This method achieves good performance on Fdataset and Cdataset, AUROCs were 91.6% and 92.1% respectively, higher than many of the existing computational models.

CONCLUSIONS: The novelty of LMFDA lies in the introduction of multimodal fusion using low-rank tensors to fuse multiple similar networks and combine matrix complement technology to predict potential association. We have demonstrated that LMFDA can display excellent network integration ability for accurate disease-drug association inferring and achieve substantial improvement over the advanced approach. Overall, experimental results on two real-world networks dataset demonstrate that LMFDA able to delivers an excellent detecting performance. Results also suggest that perfecting similar networks with as much domain knowledge as possible is a promising direction for drug repositioning.

PMID:34736437 | DOI:10.1186/s12911-021-01648-x

Anticancer Res. 2021 Nov;41(11):5477-5480. doi: 10.21873/anticanres.15360.

ABSTRACT

BACKGROUND/AIM: Itraconazole shows anticancer activity in various types of cancer but its underlying mechanism is unclear. We investigated the effect of itraconazole on membrane-associated lipids.

MATERIALS AND METHODS: To investigate the influences of itraconazole on cholesterol trafficking, cervical cancer CaSki cells were cultured with itraconazole and analyzed by Filipin staining followed by confocal microscopy. Effect on the glycerophospholipid profiles was analyzed by liquid chromatography/mass spectrometry (LC/MS).

RESULTS: After itraconazole treatment, Filipin staining revealed cholesterol accumulation in the intracellular compartments, which was similar to the distribution after treatment of U18666A (cholesterol transport inhibitor). LC/MS analysis showed a significant decrease in phosphatidylserine levels and an increase in lysophosphatidylcholine levels in CaSki cells.

CONCLUSION: Itraconazole inhibited cholesterol trafficking and altered the phospholipid composition. Alterations in the cell membrane can potentiate the anticancer activity of itraconazole.

PMID:34732417 | DOI:10.21873/anticanres.15360

Methods Mol Biol. 2022;2390:383-407. doi: 10.1007/978-1-0716-1787-8_16.

ABSTRACT

The discovery and development of drugs is a long and expensive process with a high attrition rate. Computational drug discovery contributes to ligand discovery and optimization, by using models that describe the properties of ligands and their interactions with biological targets. In recent years, artificial intelligence (AI) has made remarkable modeling progress, driven by new algorithms and by the increase in computing power and storage capacities, which allow the processing of large amounts of data in a short time. This review provides the current state of the art of AI methods applied to drug discovery, with a focus on structure- and ligand-based virtual screening, library design and high-throughput analysis, drug repurposing and drug sensitivity, de novo design, chemical reactions and synthetic accessibility, ADMET, and quantum mechanics.

PMID:34731478 | DOI:10.1007/978-1-0716-1787-8_16

Methods Mol Biol. 2022;2390:103-112. doi: 10.1007/978-1-0716-1787-8_3.

ABSTRACT

The development of vaccines for the treatment of COVID-19 is paving the way for new hope. Despite this, the risk of the virus mutating into a vaccine-resistant variant still persists. As a result, the demand of efficacious drugs to treat COVID-19 is still pertinent. To this end, scientists continue to identify and repurpose marketed drugs for this new disease. Many of these drugs are currently undergoing clinical trials and, so far, only one has been officially approved by FDA. Drug repurposing is a much faster route to the clinic than standard drug development of novel molecules, nevertheless in a pandemic this process is still not fast enough to halt the spread of the virus. Artificial intelligence has already played a large part in hastening the drug discovery process, not only by facilitating the selection of potential drug candidates but also in monitoring the pandemic and enabling faster diagnosis of patients. In this chapter, we focus on the impact and challenges that artificial intelligence has demonstrated thus far with respect to drug repurposing of therapeutics for the treatment of COVID-19.

PMID:34731465 | DOI:10.1007/978-1-0716-1787-8_3

Interdiscip Sci. 2021 Nov 3. doi: 10.1007/s12539-021-00488-7. Online ahead of print.

ABSTRACT

Accurate prediction of drug-target interactions (DTIs), which is often used in the fields of drug discovery and drug repositioning, is regarded a key challenge in the study of drug science. In this paper, a new method called DeepStack-DTIs is proposed to predict DTIs. First, for the target protein, pseudo-position specific score matrix, pseudo amino acid composition and SPIDER3 are used to extract the different feature information of the target protein. Meanwhile, the path-based fingerprint features of each drug are extracted. Then, the synthetic minority oversampling technique (SMOTE) and light gradient boosting machine (LightGBM) are used for data balancing and feature selection, respectively. Finally, the processed features are input to the deep-stacked ensemble classifier composed of gated recurrent unit (GRU), deep neural network (DNN), support vector machine (SVM), eXtreme gradient boosting (XGBoost) and logistic regression (LR) to predict DTIs. Under the five-fold cross-validation and compared with existing methods, the proposed method achieves higher prediction accuracy on the gold standard dataset. To evaluate the predictive power of DeepStack-DTIs, we validate the method on another dataset and predict the drug-target interaction network. The results indicate that DeepStack-DTIs has excellent predictive ability than the other methods, and provides novel insights for the prediction of DTIs. A novel method DeepStack-DTIs for drug-target interactions prediction. PsePSSM, PseAAC, SPIDER3 and FP2 are fused to convert protein sequence and drug molecule information into digital information, respectively. The SMOTE algorithm is used to balance the dataset and LightGBM feature selection algorithm is employed to remove redundant and irrelevant features to select the optimal feature subset. This optimal feature subset is inputted into the deep-stacked ensemble classifier to predict drug-target interactions. The experimental results show DeepStack-DTIs method can significantly improve the prediction accuracy of drug-target interactions.

PMID:34731411 | DOI:10.1007/s12539-021-00488-7