Combined deep learning and molecular docking simulations approach identifies potentially effective FDA approved drugs for repurposing against SARS-CoV-2

Evaluation of molecular mechanisms of riboflavin anti-COVID-19 action reveals anti-inflammatory efficacy rather than antiviral activity

BACKGROUND

Riboflavin (vitamin B2) is one of the most important water-soluble vitamins and a coenzyme involved in many biochemical processes. It has previously been shown that adjuvant therapy with flavin mononucleotide (a water-soluble form of riboflavin) correlates with normalization of clinically relevant immune markers in patients with COVID-19, but the mechanism of this effect remains unclear. Here, the antiviral and anti-inflammatory effects of riboflavin were investigated to elucidate the molecular mechanisms underlying the riboflavin-induced effects.

METHODS

Riboflavin was evaluated for recombinant SARS-CoV-2 PLpro inhibition in an enzyme kinetic assay and for direct inhibition of SARS-CoV-2 replication in Vero E6 cells, as well as for anti-inflammatory activity in polysaccharide-induced inflammation models, including endothelial cells in vitro and acute lung inflammation in vivo.

RESULTS

For the first time, the ability of riboflavin at high concentrations (above 50 μM) to inhibit SARS-CoV-2 PLpro protease in vitro was demonstrated; however, no inhibition of viral replication in Vero E6 cells in vitro was found. At the same time, riboflavin exerted a pronounced anti-inflammatory effect in the polysaccharide-induced inflammation model, both in vitro, preventing polysaccharide-induced cell death, and in vivo, reducing inflammatory markers (IL-1β, IL-6, and TNF-α) and normalizing lung histology.

CONCLUSIONS

It is concluded that riboflavin reveals anti-inflammatory rather than antiviral activity for SARS-CoV-2 infection.

GENERAL SIGNIFICANCE

Riboflavin could be suggested as a promising compound for the therapy of inflammatory diseases of broad origin.

Attention Mechanism-Based Graph Neural Network Model for Effective Activity Prediction of SARS-CoV-2 Main Protease Inhibitors: Application to Drug Repurposing as Potential COVID-19 Therapy

Compared to de novo drug discovery, drug repurposing provides a time-efficient way to treat coronavirus disease 19 (COVID-19) that is caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). SARS-CoV-2 main protease (Mpro) has been proved to be an attractive drug target due to its pivotal involvement in viral replication and transcription. Here, we present a graph neural network-based deep-learning (DL) strategy to prioritize the existing drugs for their potential therapeutic effects against SARS-CoV-2 Mpro. Mpro inhibitors were represented as molecular graphs ready for graph attention network (GAT) and graph isomorphism network (GIN) modeling for predicting the inhibitory activities. The result shows that the GAT model outperforms the GIN and other competitive models and yields satisfactory predictions for unseen Mpro inhibitors, confirming its robustness and generalization. The attention mechanism of GAT enables to capture the dominant substructures and thus to realize the interpretability of the model. Finally, we applied the optimal GAT model in conjunction with molecular docking simulations to screen the Drug Repurposing Hub (DRH) database. As a result, 18 drug hits with best consensus prediction scores and binding affinity values were identified as the potential therapeutics against COVID-19. Both the extensive literature searching and evaluations on adsorption, distribution, metabolism, excretion, and toxicity (ADMET) illustrate the premium drug-likeness and pharmacokinetic properties of the drug candidates. Overall, our work not only provides an effective GAT-based DL prediction tool for inhibitory activity of SARS-CoV-2 Mpro inhibitors but also provides theoretical guidelines for drug discovery in the COVID-19 treatment.

D3CARP: a comprehensive platform with multiple-conformation based docking, ligand similarity search and deep learning approaches for target prediction and virtual screening

Resource- and time-consuming biological experiments are unavoidable in traditional drug discovery, which have directly driven the evolution of various computational algorithms and tools for drug-target interaction (DTI) prediction. For improving the prediction reliability, a comprehensive platform is highly expected as some previously reported webservers are small in scale, single-method, or even out of service. In this study, we integrated the multiple-conformation based docking, 2D/3D ligand similarity search and deep learning approaches to construct a comprehensive webserver, namely D3CARP, for target prediction and virtual screening. Specifically, 9352 conformations with positive control of 1970 targets were used for molecular docking, and approximately 2 million target-ligand pairs were used for 2D/3D ligand similarity search and deep learning. Besides, the positive compounds were added as references, and related diseases of therapeutic targets were annotated for further disease-based DTI study. The accuracies of the molecular docking and deep learning approaches were 0.44 and 0.89, respectively. And the average accuracy of five ligand similarity searches was 0.94. The strengths of D3CARP encompass the support for multiple computational methods, ensemble docking, utilization of positive controls as references, cross-validation of predicted outcomes, diverse disease types, and broad applicability in drug discovery. The D3CARP is freely accessible at https://www.d3pharma.com/D3CARP/index.php.

Staying Ahead of the Game: How SARS-CoV-2 has Accelerated the Application of Machine Learning in Pandemic Management

In recent years, machine learning (ML) techniques have garnered considerable interest for their potential use in accelerating the rate of drug discovery. With the emergence of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic, the utilization of ML has become even more crucial in the search for effective antiviral medications. The pandemic has presented the scientific community with a unique challenge, and the rapid identification of potential treatments has become an urgent priority. Researchers have been able to accelerate the process of identifying drug candidates, repurposing existing drugs, and designing new compounds with desirable properties using machine learning in drug discovery. To train predictive models, ML techniques in drug discovery rely on the analysis of large datasets, including both experimental and clinical data. These models can be used to predict the biological activities, potential side effects, and interactions with specific target proteins of drug candidates. This strategy has proven to be an effective method for identifying potential coronavirus disease 2019 (COVID-19) and other disease treatments. This paper offers a thorough analysis of the various ML techniques implemented to combat COVID-19, including supervised and unsupervised learning, deep learning, and natural language processing. The paper discusses the impact of these techniques on pandemic drug development, including the identification of potential treatments, the understanding of the disease mechanism, and the creation of effective and safe therapeutics. The lessons learned can be applied to future outbreaks and drug discovery initiatives.

A review of SARS-CoV-2 drug repurposing: databases and machine learning models

The emergence of Severe Acute Respiratory Syndrome Corona Virus 2 (SARS-CoV-2) posed a serious worldwide threat and emphasized the urgency to find efficient solutions to combat the spread of the virus. Drug repurposing has attracted more attention than traditional approaches due to its potential for a time- and cost-effective discovery of new applications for the existing FDA-approved drugs. Given the reported success of machine learning (ML) in virtual drug screening, it is warranted as a promising approach to identify potential SARS-CoV-2 inhibitors. The implementation of ML in drug repurposing requires the presence of reliable digital databases for the extraction of the data of interest. Numerous databases archive research data from studies so that it can be used for different purposes. This article reviews two aspects: the frequently used databases in ML-based drug repurposing studies for SARS-CoV-2, and the recent ML models that have been developed for the prospective prediction of potential inhibitors against the new virus. Both types of ML models, Deep Learning models and conventional ML models, are reviewed in terms of introduction, methodology, and its recent applications in the prospective predictions of SARS-CoV-2 inhibitors. Furthermore, the features and limitations of the databases are provided to guide researchers in choosing suitable databases according to their research interests.

AiKPro: deep learning model for kinome-wide bioactivity profiling using structure-based sequence alignments and molecular 3D conformer ensemble descriptors

The discovery of selective and potent kinase inhibitors is crucial for the treatment of various diseases, but the process is challenging due to the high structural similarity among kinases. Efficient kinome-wide bioactivity profiling is essential for understanding kinase function and identifying selective inhibitors. In this study, we propose AiKPro, a deep learning model that combines structure-validated multiple sequence alignments and molecular 3D conformer ensemble descriptors to predict kinase-ligand binding affinities. Our deep learning model uses an attention-based mechanism to capture complex patterns in the interactions between the kinase and the ligand. To assess the performance of AiKPro, we evaluated the impact of descriptors, the predictability for untrained kinases and compounds, and kinase activity profiling based on odd ratios. Our model, AiKPro, shows good Pearson's correlation coefficients of 0.88 and 0.87 for the test set and for the untrained sets of compounds, respectively, which also shows the robustness of the model. AiKPro shows good kinase-activity profiles across the kinome, potentially facilitating the discovery of novel interactions and selective inhibitors. Our approach holds potential implications for the discovery of novel, selective kinase inhibitors and guiding rational drug design.

Cyclic lipopeptides as membrane fusion inhibitors against SARS-CoV-2: New tricks for old dogs

With the resurgence of the coronavirus pandemic, the repositioning of FDA-approved drugs against coronovirus and finding alternative strategies for antiviral therapy are both important. We previously identified the viral lipid envelope as a potential target for the prevention and treatment of SARS-CoV-2 infection with plant alkaloids (Shekunov et al., 2021). Here, we investigated the effects of eleven cyclic lipopeptides (CLPs), including well-known antifungal and antibacterial compounds, on the liposome fusion triggered by calcium, polyethylene glycol 8000, and a fragment of SARS-CoV-2 fusion peptide (816-827) by calcein release assays. Differential scanning microcalorimetry of the gel-to-liquid-crystalline and lamellar-to-inverted hexagonal phase transitions and confocal fluorescence microscopy demonstrated the relation of the fusion inhibitory effects of CLPs to alterations in lipid packing, membrane curvature stress and domain organization. The antiviral effects of CLPs were evaluated in an in vitro Vero-based cell model, and aculeacin A, anidulafugin, iturin A, and mycosubtilin attenuated the cytopathogenicity of SARS-CoV-2 without specific toxicity.

Drug Repurposing against KRAS Mutant G12C: A Machine Learning, Molecular Docking, and Molecular Dynamics Study

The Kirsten rat sarcoma viral G12C (KRAS^G12C) protein is one of the most common mutations in non-small-cell lung cancer (NSCLC). KRAS^G12C inhibitors are promising for NSCLC treatment, but their weaker activity in resistant tumors is their drawback. This study aims to identify new KRAS^G12C inhibitors from among the FDA-approved covalent drugs by taking advantage of artificial intelligence. The machine learning models were constructed using an extreme gradient boosting (XGBoost) algorithm. The models can predict KRAS^G12C inhibitors well, with an accuracy score of validation = 0.85 and Q²_Ext = 0.76. From 67 FDA-covalent drugs, afatinib, dacomitinib, acalabrutinib, neratinib, zanubrutinib, dutasteride, and finasteride were predicted to be active inhibitors. Afatinib obtained the highest predictive log-inhibitory concentration at 50% (pIC₅₀) value against KRAS^G12C protein close to the KRAS^G12C inhibitors. Only afatinib, neratinib, and zanubrutinib covalently bond at the active site like the KRAS^G12C inhibitors in the KRAS^G12C protein (PDB ID: 6OIM). Moreover, afatinib, neratinib, and zanubrutinib exhibited a distance deviation between the KRAS^G2C protein-ligand complex similar to the KRAS^G12C inhibitors. Therefore, afatinib, neratinib, and zanubrutinib could be used as drug candidates against the KRAS^G12C protein. This finding unfolds the benefit of artificial intelligence in drug repurposing against KRAS^G12C protein.

Identification of Diosmin and Flavin Adenine Dinucleotide as Repurposing Treatments for Monkeypox Virus: A Computational Study

The World Health Organization declared monkeypox a global public health emergency on 23 July 2022. This disease was caused by the monkeypox virus (MPXV), which was first identified in 1958 in Denmark. The MPXV is a member of the Poxviridae family, the Chordopoxvirinae subfamily, and the genus Orthopoxvirus, which share high similarities with the vaccinia virus (the virus used to produce the smallpox vaccine). For the initial stage of infection, the MPXV needs to attach to the human cell surface glycosaminoglycan (GAG) adhesion molecules using its E8 protein. However, up until now, neither a structure for the MPXV E8 protein nor a specific cure for the MPXV exists. This study aimed to search for small molecules that inhibit the MPXV E8 protein, using computational approaches. In this study, a high-quality three-dimensional structure of the MPXV E8 protein was retrieved by homology modeling using the AlphaFold deep learning server. Subsequent molecular docking and molecular dynamics simulations (MDs) for a cumulative duration of 2.1 microseconds revealed that ZINC003977803 (Diosmin) and ZINC008215434 (Flavin adenine dinucleotide-FAD) could be potential inhibitors against the E8 protein with the MM/GBSA binding free energies of −38.19 ± 9.69 and −35.59 ± 7.65 kcal·mol⁻¹, respectively.

Deep learning-based molecular dynamics simulation for structure-based drug design against SARS-CoV-2

Coronavirus disease 2019 (COVID-19), caused by severe acute respiratory syndrome coronavirus type 2 (SARS-CoV-2), has led to a global pandemic. Deep learning (DL) technology and molecular dynamics (MD) simulation are two mainstream computational approaches to investigate the geometric, chemical and structural features of protein and guide the relevant drug design. Despite a large amount of research papers focusing on drug design for SARS-COV-2 using DL architectures, it remains unclear how the binding energy of the protein-protein/ligand complex dynamically evolves which is also vital for drug development. In addition, traditional deep neural networks usually have obvious deficiencies in predicting the interaction sites as protein conformation changes. In this review, we introduce the latest progresses of the DL and DL-based MD simulation approaches in structure-based drug design (SBDD) for SARS-CoV-2 which could address the problems of protein structure and binding prediction, drug virtual screening, molecular docking and complex evolution. Furthermore, the current challenges and future directions of DL-based MD simulation for SBDD are also discussed.

In Silico Study of Alkaloids: Neferine and Berbamine Potentially Inhibit the SARS-CoV-2 RNA-Dependent RNA Polymerase

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the virus that causes COVID-19, has been a global concern. While there have been some vaccines and drugs, the rapid emergence of variants due to mutations has threatened public health. As the de novo drug development process is expensive and time-consuming, repurposing existing antiviral drugs against SARS-CoV-2 is an alternative and promising approach to mitigate the current situation. Several studies have indicated that some natural products exhibit inhibitory activities against SARS-CoV-2. This study is aimed at analyzing the potential of natural alkaloids, using various computational tools, as drug candidates against SARS-CoV-2. The molecular docking analysis predicted that naturally occurring alkaloids can bind with RNA-dependent RNA-polymerase (RdRP). The QSAR analysis was conducted by using the way2drug/PASS online web resource, and the pharmacokinetics and toxicity properties of these alkaloids were predicted using pkCSM, SwissADME, and ProTox-II webserver. Among the different alkaloids studied, neferine and berbamine were repurposed as potential drug candidates based on their binding affinity and interactions with RdRP. Further, molecular dynamics simulation of 90 ns revealed the conformational stability of the neferine-RdRP complex.

Riboflavin for COVID-19 Adjuvant Treatment in Patients With Mental Health Disorders: Observational Study

Background: COVID-19 treatment remains a challenge for medicine because of the extremely short time for clinical studies of drug candidates, so the drug repurposing strategy, which implies the use of well-known and safe substances, is a promising approach.

Objective: We present the results of an observational clinical study that focused on the influence of riboflavin (vitamin B2) supplementation on the immune markers of COVID-19 severity in patients with mental health disorders.

Results: We have found that 10 mg of flavin mononucleotide (a soluble form of riboflavin) intramuscularly twice a day within 7 days correlated with the normalization of clinically relevant immune markers (neutrophils and lymphocytes counts, as well as their ratio) in COVID-19 patients. Additionally, we demonstrated that total leucocytes, neutrophils, and lymphocytes counts, as well as the neutrophils to leucocytes ratio (NLR), correlated with the severity of the disease. We also found that patients with organic disorders (F0 in ICD-10) demonstrated higher inflammation then patients with schizophrenia (F2 in ICD-10).

Conclusion: We suggest that riboflavin supplementation could be promising for decreasing inflammation in COVID-19, and further evaluation is required.

This observational clinical trial has been registered by the Sverzhevsky Research Institute of Clinical Otorhinolaryngology (Moscow, Russia), Protocol No. 4 dated 05/27/2020.

Proteomics advances towards developing SARS-CoV-2 therapeutics using in silico drug repurposing approaches

Standing amidst the COVID-19 pandemic, we have faced major medical and economic crisis in recent times which remains to be an unresolved issue till date. Although the scientific community has made significant progress towards diagnosis and understanding the disease; however, effective therapeutics are still lacking. Several omics-based studies, especially proteomics and interactomics, have contributed significantly in terms of identifying biomarker panels that can potentially be used for the disease prognosis. This has also paved the way to identify the targets for drug repurposing as a therapeutic alternative. US Food and Drug Administration (FDA) has set in motion more than 500 drug development programs on an emergency basis, most of them are focusing on repurposed drugs. Remdesivir is one such success of a robust and quick drug repurposing approach. The advancements in omics-based technologies has allowed to explore altered host proteins, which were earlier restricted to only SARS-CoV-2 protein signatures. In this article, we have reviewed major contributions of proteomics and interactomics techniques towards identifying therapeutic targets for COVID-19. Furthermore, in-silico molecular docking approaches to streamline potential drug candidates are also discussed.

Molecular Docking and Dynamics Investigations for Identifying Potential Inhibitors of the 3-Chymotrypsin-like Protease of SARS-CoV-2: Repurposing of Approved Pyrimidonic Pharmaceuticals for COVID-19 Treatment

This study demonstrates the inhibitory effect of 42 pyrimidonic pharmaceuticals (PPs) on the 3-chymotrypsin-like protease of SARS-CoV-2 (3CL^pro) through molecular docking, molecular dynamics simulations, and free binding energies by means of molecular mechanics-Poisson Boltzmann surface area (MM-PBSA) and molecular mechanics-generalized Born surface area (MM-GBSA). Of these tested PPs, 11 drugs approved by the US Food and Drug Administration showed an excellent binding affinity to the catalytic residues of 3CL^pro of His41 and Cys145: uracil mustard, cytarabine, floxuridine, trifluridine, stavudine, lamivudine, zalcitabine, telbivudine, tipiracil, citicoline, and uridine triacetate. Their percentage of residues involved in binding at the active sites ranged from 56 to 100, and their binding affinities were in the range from -4.6 ± 0.14 to -7.0 ± 0.19 kcal/mol. The molecular dynamics as determined by a 200 ns simulation run of solvated docked complexes confirmed the stability of PP conformations that bound to the catalytic dyad and the active sites of 3CL^pro. The free energy of binding also demonstrates the stability of the PP-3CL^pro complexes. Citicoline and uridine triacetate showed free binding energies of -25.53 and -7.07 kcal/mol, respectively. Therefore, I recommend that they be repurposed for the fight against COVID-19, following proper experimental and clinical validation.

New Insights Into Drug Repurposing for COVID-19 Using Deep Learning

The coronavirus disease 2019 (COVID-19) has continued to spread worldwide since late 2019. To expedite the process of providing treatment to those who have contracted the disease and to ensure the accessibility of effective drugs, numerous strategies have been implemented to find potential anti-COVID-19 drugs in a short span of time. Motivated by this critical global challenge, in this review, we detail approaches that have been used for drug repurposing for COVID-19 and suggest improvements to the existing deep learning (DL) approach to identify and repurpose drugs to treat this complex disease. By optimizing hyperparameter settings, deploying suitable activation functions, and designing optimization algorithms, the improved DL approach will be able to perform feature extraction from quality big data, turning the traditional DL approach, referred to as a "black box," which generalizes and learns the transmitted data, into a "glass box" that will have the interpretability of its rationale while maintaining a high level of prediction accuracy. When adopted for drug repurposing for COVID-19, this improved approach will create a new generation of DL approaches that can establish a cause and effect relationship as to why the repurposed drugs are suitable for treating COVID-19. Its ability can also be extended to repurpose drugs for other complex diseases, develop appropriate treatment strategies for new diseases, and provide precision medical treatment to patients, thus paving the way to discover new drugs that can potentially be effective for treating COVID-19.