COVID-19 Drug Research Articles

Are we ready to combat the ecotoxicity of COVID-19 pharmaceuticals? An in silico aquatic risk assessment

To fight COVID-19 with uncountable medications and bioproducts throughout the world has taken us to another challenge of ecotoxicity. The indiscriminate usage followed by improper disposal of unused antibacterials, antivirals, antimalarials, immunomodulators, angiotensin II receptor blockers, corticosteroids, anthelmintics, anticoagulants etc. can lead us to an unimaginable ecotoxicity in the long run. A series of studies already identified active pharmaceutical ingredients (APIs) of the mentioned therapeutic classes and their metabolites in aquatic bodies as well as in wastewater treatment plants. Therefore, an initial ecotoxicity assessment of the majorly used pharmaceuticals is utmost requirement of the present time. The present in silico risk assessment study is focused on the aquatic toxicity prediction of 81 pharmaceuticals where 77 are most-used pharmaceuticals for COVID-19 throughout the world based on the literature along with one drug nirmatrelvir [PF-07321332] approved for emergency use by US-FDA and three other molecules under clinical trial. The ecotoxicity of the studied compounds were predicted based on the three aquatic species fish, algae and crustaceans employing the highest quality QSAR models available from the literature as well as using ECOSAR and QSAR Toolbox. To compare the toxicity thresholds, we have also used 4 control pharmaceuticals based on the worldwide occurrence from river, lake, STP, WWTPs, influent and effluent followed by high reported aquatic toxicity over the years as per the literature. Based on the statistical comparison, we have proposed top 3 pharmaceuticals used for the COVID-19 most toxic to the aquatic environment. The study will provide confident predictions of aquatic ecotoxicity data related to abundant use of COVID-19 drugs. The major aim of the study is to fill up the aquatic ecotoxicity data gap of major medications used for COVID-19.

Global landscape of randomized controlled trials responding to the COVID-19 pandemic: a literature review protocol

Introduction: Evidence-based care is challenging during public health crisis. During the COVID-19 pandemic, although the tremendous number of clinical trials were conducted, small trials were prevalent, which posed the risk of duplication, heterogeneity, underreporting and limited applicability of the trial results to patients in the clinical setting. These factors are known to potentially jeopardize the efficient production of scientific data for evidence-based care. The objective of this review is to critically appraise the characteristics of randomized controlled trials related to COVID-19 therapeutics and vaccines. This article is a protocol for literature review. Methods: This review will include randomized controlled trials (RCTs) on therapeutics and vaccines for COVID-19. Therapeutics include a single drug or a combination of multiple drugs for COVID-19. Non-human trials will be excluded. The search strategy is designed for identifying publication of study results in peer-review journals. Databases to be searched include MEDLINE, Cochrane Central Register of Controlled Trials (CENTRAL), Web of science and CINAHL. Two or more independent reviewers will screen identified publications for inclusion/exclusion and retrieve data including standard information of studies and specific details about RCT designs as well as reporting, for which we will follow the set of information in international trial registries and the CONSORT statement. Discussion: It remains unclear what should be improved or strengthened for ecosystems of clinical trials for future pandemics. This review is expected to provide a landscape of RCTs related to COVID-19 therapeutics and vaccines and to explicitly show successful factors for evidence generation in response to pandemics.

Reconstruction of the alveolar‐capillary barrier in vitro based on a photo‐responsive stretchable Janus membrane (1/2023)

A novel photo-responsive stretchable Janus membrane was proposed for constructing a lung-on-a-chip and reconstructing the alveolar-capillary barrier. The constructed lung tissue model with the dynamically stretchable Janus membrane is well-suited for COVID-19 infection studies and drug testing.

Computational Search for Potential COVID-19 Drugs from Ayurvedic Medicinal Plants to Identify Potential Inhibitors against SARS-CoV-2 Targets.

To date, very few small drug molecules are used for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) that has been discovered since the epidemic commenced in November 2019. SARS-CoV-2 RdRp and spike protein are essential targets for drug development amidst whole variants of coronaviruses. This study aims to discover and recognize the most effective and promising small molecules against SARS-CoV-2 RNA-dependent RNA polymerase (RdRp) and spike protein targets through molecular docking screening of 39 phytochemicals from five different Ayurveda medicinal plants. The phytochemicals were downloaded from PubChem, and SARS-CoV-2 RdRp and spike protein were taken from the protein data bank. The molecular interactions, binding energy, and ADMET properties were analyzed. Molecular docking analysis identified some phytochemicals, oleanolic acid, friedelin, serratagenic acid, uncinatone, clemaphenol A, sennosides B, trilobine and isotrilobine from ayurvedic medicinal plants possessing greater affinity against SARS-CoV-2-RdRp and spike protein targets. Two molecules, namely oleanolic acid and sennosides B, with low binding energies, were the most promising. Furthermore, based on the docking score, we carried out MD simulations for the oleanolic acid and sennosides B-protein complexes. Molecular ADMET profile estimation showed that the docked phytochemicals were safe. The present study suggested that active phytochemicals from medicinal plants could inhibit RdRp and spike protein of SARS-CoV-2.

Green and efficient one-pot three-component synthesis of novel drug-like furo[2,3-d]pyrimidines as potential active site inhibitors and putative allosteric hotspots modulators of both SARS-CoV-2 MPro and PLPro

In this paper, an environmentally benign, convenient, and efficient one-pot three-component reaction has been developed for the regioselective synthesis of novel 5-aroyl(or heteroaroyl)-6-(alkylamino)-1,3-dimethylfuro[2,3-d]pyrimidine-2,4(1H,3H)-diones (4a‒n) through the sequential condensation of aryl(or heteroaryl)glyoxal monohydrates (1a‒g), 1,3-dimethylbarbituric acid (2), and alkyl(viz. cyclohexyl or tert-butyl)isocyanides (3a or 3b) catalyzed by ultra-low loading ZrOCl2•8H2O (just 2 mol%) in water at 50 ˚C. After synthesis and characterization of the mentioned furo[2,3-d]pyrimidines (4a‒n), their multi-targeting inhibitory properties were investigated against the active site and putative allosteric hotspots of both SARS-CoV-2 main protease (MPro) and papain-like protease (PLPro) based on molecular docking studies and compare the attained results with various medicinal compounds which approximately in three past years were used, introduced, and or repurposed to fight against COVID-19. Furthermore, drug-likeness properties of the mentioned small heterocyclic frameworks (4a‒n) have been explored using in silico ADMET analyses. Interestingly, the molecular docking studies and ADMET-related data revealed that the novel series of furo[2,3-d]pyrimidines (4a‒n), especially 5-(3,4-methylendioxybenzoyl)-6-(cyclohexylamino)-1,3-dimethylfuro[2,3-d]pyrimidine-2,4(1H,3H)-dione (4g) as hit one is potential COVID-19 drug candidate, can subject to further in vitro and in vivo studies. It is worthwhile to note that the protein–ligand-type molecular docking studies on the human body temperature-dependent MPro protein that surprisingly contains zincII (ZnII) ion between His41/Cys145 catalytic dyad in the active site, which undoubtedly can make new plans for designing novel SARS-CoV-2 MPro inhibitors, is performed for the first time in this paper, to the best of our knowledge.

Generalized Quasi Trees with Respect to Degree Based Topological Indices and Their Applications to COVID-19 Drugs

The l-generalized quasi tree is a graph G for which we can find W⊂V(G) with |W|=l such that G−W is a tree but for an arbitrary Y⊂V(G) with |Y|<l, G−Y is not a tree. In this paper, inequalities with respect to zeroth-order Randić and hyper-Zagreb indices are studied in the class of l-generalized quasi trees. The corresponding extremal graphs corresponding to these indices in the class of l-generalized quasi trees are also obtained. In addition, we carry QSPR analysis of COVID-19 drugs with zeroth-order Randić and hyper-Zagreb indices (energy).

A Mini-Review On Emerging Trends and Recent Advances in Analytical Methods for Covid-19: Analytical Chemistry Perspective

In recent times SARS-CoV-2 pandemic, public health experts have slated testing, tracking infected people, as well as tracing their contacts as an efficient method to reduce the viral spread. Numerous diagnostic approaches are reported for detecting the coronavirus in public health, clinical and research laboratories. Most tests detect the infection directly by detecting the viral RNA while other test may indirectly detect the host antibodies in the course of detecting the infection. A diagnostic test during the pandemic should aid in making proper clinical decision within a short time frame. In this review, we describe the various techniques involved in sample collection from nasal, throat and sputum specimens, standard and developed methods for diagnosis of covid 19 such as the polymerase chain reaction (RT-PCR), CRISPR-based assays and Serological and immunological assays. General information on selected electroactive antiviral Covid-19 drugs have been highlighted including: Favipiravir (FAV), Remdesivir (REM), Lopinavir + Ritonavir (LOP + RIT), Hydroxychloroquine (HCQ) and Chloroquine (CQ), Ribavirin (RIB) and Sofosbuvir. This review presents the major standard, commercial and designed methods for detecting SARS-CoV-2 and their analytical performance. Also, chromatographic techniques have been highlighted as a rapid examination for SARS-CoV-2 identification, and some recent advances and emerging trends in analytical methods for covid-19 diagnosis have been addressed.

Reconsidering the role of receptors for SARS‐CoV‐2 in clear cell renal cell carcinoma: Friends or foes

Reconsidering the role of receptors for SARS‐CoV‐2 in clear cell renal cell carcinoma: Friends or foes

Ln-MOF Based Ratiometric Luminescent Sensor for the Detection of Potential COVID-19 Drugs.

Countless people have been affected by the COVID-19 pandemic on a global scale. Favipiravir, has shown potential as an effective drug for SARS-CoV-2, attracting scientists' attention. However, overuse of Favipiravir easily leads to serious side effects, requiring real-time monitoring in body fluids. Given this, a new lanthanide metal-organic framework (MOF) was prepared under solvothermal conditions from either Eu (Eu-MOF or (1)) or Tb (Tb-MOF or (2)) using the highly delocalized imidazoledicarboxylic acid linker H2 L (H2 L=5-(4-(imidazol-1-yl) phenyl) isophthalic acid) and could be successfully applied to selective optical detection of Favipiravir. In this MOF framework, the organic linker H2 L provides a high excitation energy transfer efficiency that can sensitize luminescence in lanthanides. In addition, through deliberate tuning of Eu/Tb molar ratio and reaction concentration in the lanthanide framework, ratiometric recyclable luminescent Eux Tb1-x -MOF nanoparticles with open metal sites have been constructed, which present a high detection sensitivity (Ksv =1×107 [M-1 ], detection limit is 4.63 nM) for Favipiravir. The detection mechanism is discussed with the help of Density Functional Theory (DFT) calculations that sheds light over the selective sensing of Favipiravir over other related COVID-19 drug candidates. Finally, to explore the practical application of Favipiravir sensing, MOF based thin films have been used for visual detection of Favipiravir and recycled 5 times.

QM/MM study of N501 involved intermolecular interaction between SARS-CoV-2 receptor binding domain and antibody of human origin

Intermolecular interaction between key residue N501 of the epitope on SARS-CoV-2 RBD and screening antibody B38 was studied using the QM/MM and QM approach. The QM/MM optimized geometry shows that angle X-H---Y is 165° for O-H---O between mAb light chain S30 and RBD N501. High level MP2 calculations indicated the interaction between RBD N501 and S30 of B38 Fab light chain provide a relatively strong attractive force of − 3.32 kcal/mol, whereas the hydrogen bond between RBD Q498 and S30 was quantified as 0.10 kcal/mol. The decrease in ESP partial charge on hydrogen atom of hydroxyl group on S30 drops from 0.38 a.u. to 0.31 a.u., exhibiting the sharing of 0.07 a.u. from the lone pair electron oxygen of N501 due to hydrogen bond formation. The NBO occupancy of hydrogen atom also decreases from 25.79 % to 22.93 % in the hydroxyl H-O NBO bond of S30. However, the minor change of NBO hybridization of hydroxyl oxygen of S30 from sp3.00 to sp3.05 implies the rigidity of hydrogen bond tetrahedral geometry in the relative dynamic protein complex. The O-H---O angle is 165° which is close but not exactly linear. The structural requirement for sp3 hybridization of oxygen for hydroxyl group on S30 and dimension of protein likely prevent O-H---O from adopting linear geometry. The hydrogen bond strengths were also calculated using a variety of DFT methods, and the result of − 3.33 kcal/mol from the M06L method is the closest to that of the MP2 calculation. Results of this work may aid in the COVID-19 vaccine and drug screening.

How toxic is the COVID-19 drug azithromycin in the presence of Posidonia oceanica? Toxicokinetics and experimental approach of meiobenthic nematodes from a metallically pristine area

The current study presents the results of an experiment carried to assess the impact of azithromycin, a COVID-19 drug, probably accumulated in marine sediments for three years, since the start of the pandemic, on benthic marine nematodes. It was explored the extent to which a common macrophyte from the Mediterranean Sea influenced the toxic impact of azithromycin on meiobenthic nematodes. Metals are known to influence toxicity of azithromycin. The nematofauna from a metallically pristine site situated in Bizerte bay, Tunisia, was exposed to two concentrations of azithromycin [i.e. 5 and 10 μg l−1]. In addition, two masses of the common macrophyte Posidonia oceanica [10 and 20% Dry Weight (DW)] were considered and associated with azithromycin into four possible combinations. The abundance and the taxonomic diversity of the nematode communities decreased significantly following the exposure to azithromycin, which was confirmed by the toxicokinetic data and behaving as substrate for P-glycoprotein (P-gp). The toxicity of 5 μg l−1 dosage of azithromycin was partially reduced at 10% DW of Posidonia and completely at 20% DW. The results showed that 5 μg l−1 of azithromycin can be reduced by the macrophyte P. oceanica when present in the environment at low masses as 10% DW.

QSPR/QSAR analysis of some eccentricity based topological descriptors of antiviral drugs used in COVID-19 treatment via $ \mathscr{D}\varepsilon $- polynomials.

In the field of chemical and medical sciences, topological indices are used to study the chemical, biological, clinical, and therapeutic aspects of pharmaceuticals. The COVID-19 pandemic is largely recognized as the most life-threatening crisis confronting medical advances. Scientists have tested various antiviral drugs and discovered that they help people recover from viral infections like COVID-19. Antiviral medications, such as Arbidol, Chloroquine, Hydroxy-Chloroquine, Lopinavir, Remdesivir, Ritonavir, Thalidomide and Theaflavin, are often used to treat COVID-19. In this paper, we define Diameter Eccentricity Based vertex degree and employ it to introduce a new polynomial called $ D\varepsilon- $ Polynomial. Using the newly introduced polynomial, we derive new topological indices, namely, diameter eccentricity based and hyper diameter eccentricity based indices. In order to check the efficacy of our indices, we derive the $ D\varepsilon- $ polynomials for the eight COVID-19 drugs mentioned above. Using these polynomials, we compute our proposed topological descriptors for the eight COVID-19 drugs. We perform quantitative structure-property relationship (QSPR) analysis by identifying the best fit curvilinear/multilinear regression models based on our topological descriptors for 8 physico- chemical properties of the COVID-19 drugs. We also perform quantitative structure-activity relationship (QSAR) analysis by identifying the best fit multilinear regression model for predicting the $ IC_{50} $ values for the eight COVID-19 drugs. Our findings and models may be useful in the development of new COVID-19 medication.

Pain in COVID-19: Quis est culpa?

<b>Background</b>: At present, during the coronavirus disease (COVID-19) pandemic, chronic pain is becoming more prominent, and it is also associated with the post-COVID-19 syndrome. Thanks to quick decisions on the therapy and as part of COVID-19 prevention, we have succeeded in stabilising the situation all over the world. On the other hand, ‘quick decisions’ have contributed to other significant issues which we are beginning to deal with now: in the effort to defeat the virus, many experts regarded the adverse effects of the medications used to be of secondary importance.<br /> <b>Purpose:</b> The article aims to demonstrate the side effects of treatment with various drugs (and their combinations) that are used to treat COVID-19 disease.<br /> <b>Method: </b>From the beginning of January until mid-May, the COVID-19 department of the 2nd Surgical Clinic of the Faculty of Medicine of the Comenius University in Bratislava (University Hospital Bratislava, Hospital of Saints Cyril and Methodius) treated 221 patients with moderate and severe course of COVID-19 (2nd wave of the pandemic). We saw some adverse effects and lack of effect of certain drugs for COVID-19.<br /> <b>Results: </b>The benefits of preventive measures compared to treatment are enormous. For example, corticoids can impair metabolism, cause diabetes, or suppress immunity. Antibiotics may cause colitis and blood pressure medications may negatively impact blood circulation.<br /> <b>Conclusion: </b>Preventive measures such as vaccination and activation of intrinsic antiviral immune systems are based on an incomparable benefit. Important in the process of the activation of antiviral immunity (linked to interferon synthesis) in the prevention of COVID-19 is the improvement of vitamin D deficit and the use of other micronutrients.<br /> <b>Practical value:</b> The results of the study will be valuable in the field of medicine, for virologists, pharmacologists, pharmacists, and medical professionals.

Multi-omic analysis characterizes molecular susceptibility of receptors to SARS-CoV-2 spike protein

In the post COVID-19 era, new SARS-CoV-2 variant strains may continue emerging and long COVID is poised to be another public health challenge. Deciphering the molecular susceptibility of receptors to SARS-CoV-2 spike protein is critical for understanding the immune responses in COVID-19 and the rationale of multi-organ injuries. Currently, such systematic exploration remains limited. Here, we conduct multi-omic analysis of protein binding affinities, transcriptomic expressions, and single-cell atlases to characterize the molecular susceptibility of receptors to SARS-CoV-2 spike protein. Initial affinity analysis explains the domination of delta and omicron variants and demonstrates the strongest affinities between BSG (CD147) receptor and most variants. Further transcriptomic data analysis on 4100 experimental samples and single-cell atlases of 1.4 million cells suggest the potential involvement of BSG in multi-organ injuries and long COVID, and explain the high prevalence of COVID-19 in elders as well as the different risks for patients with underlying diseases. Correlation analysis validated moderate associations between BSG and viral RNA abundance in multiple cell types. Moreover, similar patterns were observed in primates and validated in proteomic expressions. Overall, our findings implicate important therapeutic targets for the development of receptor-specific vaccines and drugs for COVID-19.

Efficacy and bioequivalence study of Zithromax and Azithral a drug for the treatment COVID-19

Efficacy and bioequivalence study of Zithromax and Azithral a drug for the treatment COVID-19

Modeling mechanisms underlying differential inflammatory responses to COVID-19 in type 2 diabetes using a patient-derived microphysiological organ-on-a-chip system.

Background: COVID-19 pandemic has caused more than 6 million deaths worldwide. Co-morbid conditions such as Type 2 Diabetes (T2D) have increased mortality in COVID-19. With limited translatability of in vitro and small animal models to human disease, human organ-on-a-chip models are an attractive platform to model in vivo disease conditions and test potential therapeutics. Methods: T2D or non-diabetic patient-derived macrophages and human liver sinusoidal endothelial cells were seeded, along with normal hepatocytes and stellate cells in the liver-on-a-chip (LAMPS - liver acinus micro physiological system), perfused with media mimicking non-diabetic fasting or T2D (high levels of glucose, fatty acids, insulin, glucagon) states. The macrophages and endothelial cells were transduced to overexpress the SARS-CoV2-S (spike) protein with appropriate controls before their incorporation into LAMPS. Cytokine concentrations in the efflux served as a read-out of the effects of S-protein expression in the different experimental conditions (non-diabetic-LAMPS, T2D-LAMPS), including incubation with tocilizumab, an FDA-approved drug for severe COVID-19. Findings: S-protein expression in the non-diabetic LAMPS led to increased cytokines, but in the T2D-LAMPS, this was significantly amplified both in the number and magnitude of key pro-inflammatory cytokines (IL6, CCL3, IL1β, IL2, TNFα, etc.) involved in cytokine storm syndrome (CSS), mimicking severe COVID-19 infection in T2D patients. Compared to vehicle control, tocilizumab (IL6-receptor antagonist) decreased the pro-inflammatory cytokine secretion in T2D-COVID-19-LAMPS but not in non-diabetic-COVID-19-LAMPS. Interpretation: macrophages and endothelial cells play a synergistic role in the pathophysiology of the hyper-inflammatory response seen with COVID-19 and T2D. The effect of Tocilizumab was consistent with large clinical trials that demonstrated Tocilizumab's efficacy only in critically ill patients with severe disease, providing confirmatory evidence that the T2D-COVID-19-LAMPS is a robust platform to model human in vivo pathophysiology of COVID-19 in T2D and for screening potential therapeutics.

The evidence base for emergency use authorizations for COVID-19 treatments: A rapid review.

During the COVID-19 pandemic, US Food and Drug Administration (FDA) permitted emergency use authorizations (EUAs) for vaccines/treatments with promising data. Eight treatments were issued EUAs by May 31, 2021; one of these was approved (Remdesivir for certain populations) and two were revoked (chloroquine phosphate/hydroxychloroquine and bamlanivimab) by September 30, 2021. The aim of this study is to find out what evidence the EUAs were based on and how many studies were published while they remained active (up to September 30, 2021). A review of published clinical studies for the 6 months before each EUA was issued, and the time after (until September 30, 2021, or until revoked). PubMed and the identified systematic reviews were the sources for identifying published literature. The number of clinical studies published pre-EUA varied from a single case study (for chloroquine phosphate/hydroxychloroquine) to numerous studies of multiple types (for convalescent plasma). Four treatments had a single randomized controlled trial (RCT) as evidence (bamlanivimab monotherapy, REGN-COV, bamlanivimab + etesevimab, sotrovimab) and two also had other study types (remdesivir and baricitinib). The number of clinical studies published post-EUA (for those active onSeptember 30, 2021) was widely varied. Eighteen RCTs were published for Convalescent plasma, while Remdesivir had eight. Baricitinib, REGN-COV, and bamlanivimab + etesevimab all had one, but none were published for sotrovimab. The number of trials for treatments with EUAs was limited in all cases before the EUA was issued, and in most cases for those with EUAs ongoing at the end of September 2021. The presence of EUAs may discourage participation in relevant clinical trials, which delays the widespread implementation of evidenced-based therapies. Large, robust RCTs should be completed, such as the RECOVERY trial in the United Kingdom, to quickly find the answers desperately required during a pandemic.

A MOF/DNA luminescent sensing platform for detection of potential COVID-19 biomarkers and drugs.

COVID-19 has afflicted people's lives worldwide. Interleukin-6 (IL-6) is an important COVID-19 biomarker in human body fluids that can be used as a reference to monitor COVID-19 in real-time and therefore to reduce the risk of virus transmission. On the other hand, oseltamivir is a potential COVID-19 curing drug, but its overuse easily leads to hazardous side effects, calling for its real time monitoring in body fluids. For these purposes, a new yttrium metal-organic framework (Y-MOF) has been synthesized, in which the 5-(4-(imidazole-1-yl)phenyl)isophthalic linker contains a large aromatic backbone capable of strongly interacting with DNA sequences through π-π stacking interactions, which makes it appealing to build a unique sensor based on DNA functionalized MOFs. The MOF/DNA sequence hybrid luminescent sensing platform presents excellent optical properties associated with a high Förster resonance energy transfer (FRET) efficiency. Furthermore, to construct a dual emission sensing platform, a 5'-carboxylfluorescein (FAM) labeled DNA sequence (S2) with a stem-loop structure that can specifically interact with IL-6 has been associated with the Y-MOF. The resulting Y-MOF@S2 exhibits an efficient ratiometric detection of IL-6 in human body fluids with an extremely high Ksv value 4.3 × 108 M-1 and a low detection limit (LOD) of 70 pM. Finally, the Y-MOF@S2@IL-6 hybrid platform allows the detection of oseltamivir with high sensitivity (Ksv value is as high as 5.6 × 105 M-1 and LOD is 54 nM), due to the fact that oseltamivir can disconnect the loop stem structure constructed by S2, leading to a strong quenching effect towards Y-MOF@S2@IL-6. The nature of the interactions between oseltamivir and Y-MOF has been elucidated using density functional theory calculations while the sensing mechanism for the dual detection of IL-6 and oseltamivir has been deciphered based on luminescence lifetime tests and confocal laser scanning microscopy.

Drug Repositioning for Coronavirus (COVID-19) using Different Deep Learning Architectures

In December 2019, the COVID-19 epidemic was found in Wuhan, China, and soon hundreds of millions were infected. Therefore, several efforts were made to identify commercially available drugs to repurpose them against COVID-19. Inferring potential drug indications through computational drug repositioning is an efficient method. The drug repositioning problem is a top-K recommendation function that presents the most likely drugs for specific diseases based on drug and disease-related data. The accurate prediction of drug-target interactions (DTI) is very important for drug repositioning. Deep learning (DL) models were recently exploited for promising DTI prediction performance. To build deep learning models for DTI prediction, encoder-decoder architectures can be utilized. In this paper, a deep learning-based drug repositioning approach is proposed, which is composed of two experimental phases. Firstly, training and evaluating different deep learning encoder-decoder architecture models using the benchmark DAVIS Dataset. The trained deep learning models have been evaluated using two evaluation metrics; mean square error and the concordance index. Secondly, predicting antiviral drugs for Covid-19 using the trained deep learning models created during the first phase. In this phase, these models have been experimented to predict different antiviral drug lists, which then have been compared with a recently published antiviral drug list for Covid-19 using the concordance index metric. The overall experimental results of both phases showed that the most accurate three deep learning compound-encoder/protein-encoder architectures are Morgan/AAC, CNN/AAC, and CNN/CNN with best values for the mean square error, the first phase concordance index, and the second phase concordance index.

Antiandrogen activity of drugs for COVID-19. The case of sabizabulin

Signa Vitae is an international peer-reviewed open access journal, which is currently indexed in SCIE, scopus, etc. It covers many aspects of adult, pediatric and neonatal intensive care, anesthesia and emergency medicine