J Biomed Inform. 2021 Sep 1:103902. doi: 10.1016/j.jbi.2021.103902. Online ahead of print.

ABSTRACT

The effectiveness of machine learning models to provide accurate and consistent results in drug discovery and clinical decision support is strongly dependent on the quality of the data used. However, substantive amounts of open data that drive drug discovery suffer from a number of issues including inconsistent representation, inaccurate reporting, and incomplete context. For example, databases of FDA-approved drug indications used in computational drug repositioning studies do not distinguish between treatments that simply offer symptomatic relief from those that target the underlying pathology. Moreover, drug indication sources often lack proper provenance and have little overlap. Consequently, new predictions can be of poor quality as they offer little in the way of new insights. Hence, work remains to be done to establish higher quality databases of drug indications that are suitable for use in drug discovery and repositioning studies. Here, we report on the combination of weak supervision (programmatic labeling, crowdsourcing) and deep learning methods for relation extraction from DailyMed text to create a higher quality drug-disease relation dataset. The generated drug-disease relation data shows a high overlap with DrugCentral, a manually curated dataset. Using this dataset, we constructed a machine learning model to classify relations between drugs and diseases from text into four categories; treatment, symptomatic relief, contradiction, and effect, exhibiting an improvement of 15.5 % with Bi-LSTM (F1 score of 71.8%) over the best performing discrete method. Access to high quality data is crucial for building accurate and reliable drug repurposing prediction models. Our work suggests how the combination of crowds, experts, and machine learning methods can go hand-in-hand to improve datasets and predictive models.

PMID:34481057 | DOI:10.1016/j.jbi.2021.103902

BMC Bioinformatics. 2021 Sep 3;22(1):418. doi: 10.1186/s12859-021-04327-w.

ABSTRACT

BACKGROUND: Prediction of the drug-target interaction (DTI) is a critical step in the drug repurposing process, which can effectively reduce the following workload for experimental verification of potential drugs' properties. In recent studies, many machine-learning-based methods have been proposed to discover unknown interactions between drugs and protein targets. A recent trend is to use graph-based machine learning, e.g., graph embedding to extract features from drug-target networks and then predict new drug-target interactions. However, most of the graph embedding methods are not specifically designed for DTI predictions; thus, it is difficult for these methods to fully utilize the heterogeneous information of drugs and targets (e.g., the respective vertex features of drugs and targets and path-based interactive features between drugs and targets).

RESULTS: We propose a DTI prediction method DTI-HeNE (DTI based on Heterogeneous Network Embedding), which is specifically designed to cope with the bipartite DTI relations for generating high-quality embeddings of drug-target pairs. This method splits a heterogeneous DTI network into a bipartite DTI network, multiple drug homogeneous networks and target homogeneous networks, and extracts features from these sub-networks separately to better utilize the characteristics of bipartite DTI relations as well as the auxiliary similarity information related to drugs and targets. The features extracted from each sub-network are integrated using pathway information between these sub-networks to acquire new features, i.e., embedding vectors of drug-target pairs. Finally, these features are fed into a random forest (RF) model to predict novel DTIs.

CONCLUSIONS: Our experimental results show that, the proposed DTI network embedding method can learn higher-quality features of heterogeneous drug-target interaction networks for novel DTIs discovery.

PMID:34479477 | DOI:10.1186/s12859-021-04327-w

CNS Neurol Disord Drug Targets. 2021 Sep 2. doi: 10.2174/1871527320666210902163756. Online ahead of print.

ABSTRACT

Alzheimer's disease (AD) is one of the most common neurodegenerative disease, which affect millions of people worldwide. Accumulation of amyloid-β plaques and hyperphosphorylated neurofibrillary tangles are the key mechanisms involved in the etiopathogenesis of AD, characterized by memory loss and behavioural changes. Effective therapies targeting AD pathogenesis are limited, making it the largest unmet clinical need. Unfortunately, the available drugs provide symptomatic relief and primary care, with no substantial impact on the disease pathology. However, in recent years researchers are working hard on several potential therapeutic targets to combat disease pathogenesis and few drugs have also reached clinical trials. In addition, drugs are being repurposed both in the preclinical and clinical studies for the treatment of AD. For instance, montelukast is most commonly used leukotriene receptor antagonist, for treating asthma and seasonal allergy. Its leukotriene antagonistic action can also be beneficial for the reduction of detrimental effects of leukotriene against neuro-inflammation, an hallmark feature of AD. The available marketed formulations of montelukast present challenges such as poor bioavailability and reduced uptake, reflecting the lack of effectiveness of its desired action in the CNS. While on the other side targeted drug delivery is a satisfactory approach to surpass the challenges associated with the therapeutic agents. This review will discuss the enhancement of montelukast treatment efficacy and its access to CNS, by using new approaches like nano-formulation, nasal gel, solid lipid formulation, nano-structure lipid carrier (NSLC), highlighting lessons learned to target AD pathologies and hurdles that persist.

PMID:34477536 | DOI:10.2174/1871527320666210902163756

Proteomics. 2021 Sep 3:e2100160. doi: 10.1002/pmic.202100160. Online ahead of print.

ABSTRACT

Severe COVID-19 is reflected by significant changes in urine peptides. Based on this observation, a clinical test predicting COVID-19 severity, CoV50, was developed and registered as in vitro diagnostic in Germany. We have hypothesized that molecular changes displayed by CoV50, likely reflective of endothelial damage, may be reversed by specific drugs. Such an impact by a drug could indicate potential benefits in the context of COVID-19. To test this hypothesis, urinary peptide data from patients without COVID-19 prior to and after drug treatment were collected from the human urinary proteome database. The drugs chosen were selected based on availability of sufficient number of participants in the dataset (n>20) and potential value of drug therapies in the treatment of COVID-19 based on reports in the literature. In these participants without COVID-19, spironolactone did not demonstrate a significant impact on CoV50 scoring. Empagliflozin treatment resulted in a significant change in CoV50 scoring, indicative of a potential therapeutic benefit. The study serves as a proof-of-principle for a drug repurposing approach based on human urinary peptide signatures. The results support the initiation of a randomised control trial testing a potential positive effect of empagliflozin for severe COVID-19, possibly via endothelial protective mechanisms. This article is protected by copyright. All rights reserved.

PMID:34477316 | DOI:10.1002/pmic.202100160

Int Microbiol. 2021 Sep 3. doi: 10.1007/s10123-021-00203-y. Online ahead of print.

ABSTRACT

Infectious diseases are among the main causes of morbidity and mortality today. In facing this crisis, the development of new drug options and combat strategies is necessary. In this sense, drug repositioning or drug redirection has emerged for the faster identification of effective drugs. In this "Commentary," the anti-infective properties of the class of proton pump inhibitors (PPIs) are emphasized. Studies report activities against bacterial, fungal, parasitic, and viral agents. In addition, we have provided in a table a summary of the specific characteristics of PPIs and some of their anti-infective activities.

PMID:34476634 | DOI:10.1007/s10123-021-00203-y

Front Cell Infect Microbiol. 2021 Aug 12;11:657257. doi: 10.3389/fcimb.2021.657257. eCollection 2021.

ABSTRACT

T. cruzi, the causal agent of Chagas disease, is a parasite able to infect different types of host cells and to persist chronically in the tissues of human and animal hosts. These qualities and the lack of an effective treatment for the chronic stage of the disease have contributed to the durability and the spread of the disease around the world. There is an urgent necessity to find new therapies for Chagas disease. Drug repurposing is a promising and cost-saving strategy for finding new drugs for different illnesses. In this work we describe the effect of carvedilol on T. cruzi. This compound, selected by virtual screening, increased the accumulation of immature autophagosomes characterized by lower acidity and hydrolytic properties. As a consequence of this action, the survival of trypomastigotes and the replication of epimastigotes and amastigotes were impaired, resulting in a significant reduction of infection and parasite load. Furthermore, carvedilol reduced the whole-body parasite burden peak in infected mice. In summary, in this work we present a repurposed drug with a significant in vitro and in vivo activity against T. cruzi. These data in addition to other pharmacological properties make carvedilol an attractive lead for Chagas disease treatment.

PMID:34476220 | PMC:PMC8406938 | DOI:10.3389/fcimb.2021.657257

Sci Rep. 2021 Sep 2;11(1):17624. doi: 10.1038/s41598-021-97005-z.

ABSTRACT

The Connectivity Map (CMap) is a popular resource designed for data-driven drug repositioning using a large transcriptomic compendium. However, evaluations of its performance are limited. We used two iterations of CMap (CMap 1 and 2) to assess their comparability and reliability. We queried CMap 2 with CMap 1-derived signatures, expecting CMap 2 would highly prioritize the queried compounds; the success rate was 17%. Analysis of previously published prioritizations yielded similar results. Low recall is caused by low differential expression (DE) reproducibility both between CMaps and within each CMap. DE strength was predictive of reproducibility, and is influenced by compound concentration and cell-line responsiveness. Reproducibility of CMap 2 sample expression levels was also lower than expected. We attempted to identify the "better" CMap by comparison with a third dataset, but they were mutually discordant. Our findings have implications for CMap usage and we suggest steps for investigators to limit false positives.

PMID:34475469 | DOI:10.1038/s41598-021-97005-z

Anticancer Res. 2021 Sep;41(9):4321-4331. doi: 10.21873/anticanres.15237. Epub 2021 Sep 1.

ABSTRACT

BACKGROUND/AIM: Epidermal growth factor receptor tyrosine kinase inhibitors (EGFR-TKIs) are key drugs in cancer treatment due to their minor adverse effects and outstanding anticancer effects. However, drugs for overcoming EGFR-TKI resistance are not in clinical use so far. Therefore, to overcome resistance, we focused on lurasidone, a new antipsychotic drug, due to its mild adverse effect profile from the viewpoint of drug repositioning.

MATERIALS AND METHODS: We explored the effects of lurasidone alone or in combination with EGFR-TKI on the growth of osimertinib-resistant cancer cells the anti-apoptotic marker expression such as survivin, and autophagy levels by LC-3B expression.

RESULTS: Within a non-toxic concentration range in normal cells, lurasidone and osimertinib combination therapy showed a growth-inhibitory effect in osimertinib-resistant cancer cells in vitro and in vivo. Furthermore, lurasidone decreased survivin expression and mildly induced autophagy.

CONCLUSION: Lurasidone may increase the sensitivity to osimertinib in osimertinib-resistant cancer cells in drug repurposing.

PMID:34475052 | DOI:10.21873/anticanres.15237

Anticancer Res. 2021 Sep;41(9):4271-4276. doi: 10.21873/anticanres.15231.

ABSTRACT

BACKGROUND/AIM: The anticancer mechanism of itraconazole remains unsolved; therefore, we studied itraconazole-induced alterations in specialized pro-resolving mediators (SPMs) in cancer cells.

MATERIALS AND METHODS: The human cervical squamous carcinoma cell line CaSki was cultured with or without 1 μM itraconazole. Liquid chromatography/mass spectrometry analysis was conducted to identify SPMs that were influenced by itraconazole. Cell growth experiments were conducted using itraconazole and inhibitors targeting the metabolic pathways of candidate SPMs.

RESULTS: Resolvin E3, resolvin E2, prostaglandin J2 (PGJ2), delta-12-PGJ2, and maresin 2 were identified as candidate SPMs. The 12/15-lipoxygenase inhibitor, which is involved in the conversion of 18-hydroxy-eicosapentaenoic acid to resolvin E3, attenuated the inhibitory effect of itraconazole. Inhibition of the PGJ2 metabolic pathway did not interfere with itraconazole treatment.

CONCLUSION: The metabolic pathway of SPMs, including resolving E3, could be proposed as an anticancer target of itraconazole.

PMID:34475046 | DOI:10.21873/anticanres.15231

Comput Struct Biotechnol J. 2021 Aug 9;19:4559-4573. doi: 10.1016/j.csbj.2021.08.003. eCollection 2021.

ABSTRACT

Drug repurposing has become a widely used strategy to accelerate the process of finding treatments. While classical de novo drug development involves high costs, risks, and time-consuming paths, drug repurposing allows to reuse already-existing and approved drugs for new indications. Numerous research has been carried out in this field, both in vitro and in silico. Computational drug repurposing methods make use of modern heterogeneous biomedical data to identify and prioritize new indications for old drugs. In the current paper, we present a new complete methodology to evaluate new potentially repurposable drugs based on disease-gene and disease-phenotype associations, identifying significant differences between repurposing and non-repurposing data. We have collected a set of known successful drug repurposing case studies from the literature and we have analysed their dissimilarities with other biomedical data not necessarily participating in repurposing processes. The information used has been obtained from the DISNET platform. We have performed three analyses (at the genetical, phenotypical, and categorization levels), to conclude that there is a statistically significant difference between actual repurposing-related information and non-repurposing data. The insights obtained could be relevant when suggesting new potential drug repurposing hypotheses.

PMID:34471499 | PMC:PMC8387760 | DOI:10.1016/j.csbj.2021.08.003

Biol Pharm Bull. 2021;44(9):1323-1331. doi: 10.1248/bpb.b21-00353.

ABSTRACT

Disulfiram (DSF), an old anti-alcoholism drug, has emerged as a candidate for drug repurposing in oncology. In exploratory studies on its therapeutic effects, we unexpectedly discovered that DSF increased the phosphorylation of SRC, a proto-oncogene tyrosine-protein kinase elevated in 70% of pancreatic ductal adenocarcinoma (PDAC) cases. This serendipitous and novel finding led to our hypothesis for the current study which proposes DSF may synergize with SRC inhibitors in suppressing PDAC. Human PDAC PANC-1 and BXPC-3 cells were incubated with DSF chelated with copper (Cu2+), SRC inhibitors (PP2 and dasatinib), or transfected with lentiviral short hairpin RNA (shRNA), and their proliferation and apoptosis were analyzed. A xenograft model was employed to verify the in vitro results. The expression of key molecules was detected. DSF significantly inhibited cell proliferation and induced cell apoptosis by increasing the cleavage of poly ADP ribose polymerase (PARP), downregulating Bcl-2 and upregulating p27 in concentration- and time-dependent manners. DSF had little effect on signal transducer and activator of transcription 3 (STAT3) expression but inhibited its phosphorylation. DSF did not alter SRC expression but significantly increased its phosphorylation through upregulating actin filament associated protein 1 like 2 (AFAP1L2). DSF exhibited a synergistic effect, as analyzed by drug coefficient interactions, with either PP2, or dasatinib, or SRC depletion in suppressing PDAC cells in vitro and/or in vivo. The present results indicate DSF is a potential therapeutic drug, particularly when it is combined with SRC inhibitors, and warrant further studies on the pharmacological utility of DSF as a promising adjunct therapy for the treatment of PDAC.

PMID:34471060 | DOI:10.1248/bpb.b21-00353

Mol Divers. 2021 Sep 1. doi: 10.1007/s11030-021-10296-2. Online ahead of print.

ABSTRACT

Development of potential antitubercular molecules is a challenging task due to the rapidly emerging drug-resistant strains of Mycobacterium tuberculosis (M.tb). Structure-based approaches hold greater benefit in identifying compounds/drugs with desired polypharmacological profiles. These methods can be employed based on the knowledge of protein binding sites to identify the complementary ligands. In this study, polypharmacology guided computational drug repurposing approach was applied to identify potential antitubercular drugs. 20 important druggable protein targets in M.tb were considered from the target library of Molecular Property Diagnostic Suite-Tuberculosis (MPDSTB- http://mpds.neist.res.in:8084 ) for virtual screening. FDA approved drugs were collected, preprocessed and docked in the active sites of the 20 M.tb targets. The top 300 drug molecules from each target (20 × 300) were filtered-in and subsequently screened for possible antitubercular and antimycobacterial activity using PASS tool. Using this approach, 34 drugs with predicted antitubercular and anti-mycobacterial activity were identified along with good binding affinity against multiple M.tb targets. Interestingly, 21 out of the 34 identified drugs are antibiotics while 4 drug molecules (nitrofural, stavudine, quinine and quinidine) are non-antibiotics showing promising predicted antitubercular activity. Most of these molecules have the similar privileged antimycobacterial drugs scaffold. Further drug likeness properties were calculated to get deeper insights to M.tb lead molecules. Interestingly, it was also observed that the drugs identified from the study are under different stages of drug discovery (i.e., in vitro, clinical trials) for the effective treatment of various diseases including cancer, degenerative diseases, dengue virus infection, tuberculosis, etc. Krasavin et al., 2017 synthesized nitrofuran analogues with appreciable MICs (22-23 µM) against M.tb H37Rv. These experiments further add to the credibility of the drugs identified in this study (TB).

PMID:34468898 | DOI:10.1007/s11030-021-10296-2

Oncol Lett. 2021 Oct;22(4):744. doi: 10.3892/ol.2021.13005. Epub 2021 Aug 20.

ABSTRACT

Pancreatic cancer cells (PCCs) are surrounded by an abundant stroma, which is produced by pancreatic stellate cells (PSCs). PSCs promote tumor cell proliferation and invasion. The objective of the current study was to identify compounds that suppress PSC activation. Gene expression profiles of cancer-derived fibroblasts and normal fibroblasts were used, and the pathway analysis suggested altered pathways that were chosen for validation. It was found that the 'neuroactive ligand-receptor interaction' pathway from the Kyoto Encyclopedia of Genes and Genomes pathway analysis was one of the altered pathways. Several compounds related with this pathway were chosen, and changes in PSC activity were investigated using fluorescence staining of lipid droplets, reverse transcription-quantitative PCR, western blotting, and invasion and migration assays. Among these candidates, duloxetine, a serotonin-noradrenaline reuptake inhibitor, was found to suppress PSC activation and disrupt tumor-stromal interaction. Thus, duloxetine may be a potential drug for suppressing PSC activation and pancreatic cancer growth.

PMID:34466156 | PMC:PMC8387862 | DOI:10.3892/ol.2021.13005

J Biomater Sci Polym Ed. 2021 Aug 31:1-27. doi: 10.1080/09205063.2021.1975020. Online ahead of print.

ABSTRACT

The limited time indorsed to face the COVID-19 emergency and large number of deaths across the globe, poses an unrelenting challenge to find apt therapeutic approaches. However, lead candidate selection to phase III trials of new chemical entity is a time-consuming procedure, and not feasible in pandemic, such as the one we are facing. Drug repositioning, an exploration of existing drug for new therapeutic use, could be an effective alternative as it allows fast-track estimation in phase II-III trials, or even forthright compassionate use. Although, drugs repurposed for COVID-19 pandemic are commercially available, yet the evaluation of their safety and efficacy is tiresome and painstaking. In absence of any specific treatment the easy alternatives such as over the counter products, phytotherapies and home remedies have been largely adopted for prophylaxis and therapy as well. In recent years, it has been demonstrated that several pharmaceutical excipients possess antiviral properties making them prospective candidates against SARS-CoV-2. This review highlights the mechanism of action of various antiviral excipients and their propensity to act against SARs-CoV2. Though, repurposing of pharmaceutical excipients against COVID-19 has the edge over therapeutic agents in terms of safety, cost and fast-track approval trial burdened, this hypothesis needs to be experimentally verified for COVID-19 patients.

PMID:34464232 | DOI:10.1080/09205063.2021.1975020

Antivir Chem Chemother. 2021 Jan-Dec;29:20402066211036822. doi: 10.1177/20402066211036822.

ABSTRACT

BACKGROUND: Drug repurposing is a cost-effective strategy to identify drugs with novel effects. We searched for drugs exhibiting inhibitory activity to Herpes Simplex virus 1 (HSV-1). Our strategy utilized gene expression data generated from HSV-1-infected cell cultures which was paired with drug effects on gene expression. Gene expression data from HSV-1 infected and uninfected neurons were analyzed using BaseSpace Correlation Engine (Illumina®). Based on the general Signature Reversing Principle (SRP), we hypothesized that the effects of candidate antiviral drugs on gene expression would be diametrically opposite (negatively correlated) to those effects induced by HSV-1 infection.

RESULTS: We initially identified compounds capable of inducing changes in gene expression opposite to those which were consequent to HSV-1 infection. The most promising negatively correlated drugs (Valproic acid, Vorinostat) did not significantly inhibit HSV-1 infection further in African green monkey kidney epithelial cells (Vero cells). Next, we tested Sulforaphane and Menadione which showed effects similar to those caused by viral infections (positively correlated). Intriguingly, Sulforaphane caused a modest but significant inhibition of HSV-1 infection in Vero cells (IC50 = 180.4 µM, p = 0.008), but exhibited toxicity when further explored in human neuronal progenitor cells (NPCs) derived from induced pluripotent stem cells.

CONCLUSIONS: These results reveal the limits of the commonly used SRP strategy when applied to the identification of novel antiviral drugs and highlight the necessity to refine the SRP strategy to increase its utility.

PMID:34463534 | DOI:10.1177/20402066211036822

Metabol Open. 2021 Aug 26:100121. doi: 10.1016/j.metop.2021.100121. Online ahead of print.

ABSTRACT

The coronavirus SARS-CoV-2 which causes the COVID-19 disease is a global public health emergency. Coronavirus are single-stranded positive-sense RNA viruses and their genome size is approximately 30 kb, which encodes some important structural proteins. The interaction between viral Spike protein and ACE2 on the host cell surface is of significant interest since it initiates the infection process. This review will focus on the effectiveness of reuse of currently used drugs against COVID-19, including clinical trials, molecular docking, and computational modelling approach.

METHODS: A systematic search in Pubmed, MEDLINE, EMBASE was conducted from from January 2020 to July 2021.Applying computational, clinical and experimental approaches, numerous drugs such as remdesivir, favipiravir, ribavirin, lopinavir, ritonavir, tocilizumab have been repurposed and have shown promising protection against SARS-CoV2 both in vitro and in clinical conditions. Although there is only one repurposed drug approved by the U.S. Food and Drug Administration (FDA) to treat coronavirus disease 2019 (COVID-19), i.e, Remdesivir. However, the FDA withdrew the authorization of the drugs Hydroxychloroquine and chloroquine,that are not effective for COVID-19 and can also cause serious heart problems. Molecular coupling would be the ideal technique to identify such therapeutic agents against COVID19.

PMID:34462734 | PMC:PMC8387125 | DOI:10.1016/j.metop.2021.100121

J Biomol Struct Dyn. 2021 Aug 30:1-12. doi: 10.1080/07391102.2021.1970629. Online ahead of print.

ABSTRACT

Emergence of oncogenic mutations in the MAPK pathway gaining more impact in the recent years. Importantly, MEK is a core element of this pathway as it is easy to inhibit and is a gatekeeper of multiple malignancies. Therefore, we performed in-silico strategy to screen repurposed candidate for MEK protein using a library of 11,808 compounds from different clusters in the DrugBank database. Glide docking, Prime-MM/GBSA and QikProp analysis were implemented to retrieve the hits with high precision. The stability of the binding mode and binding affinity of the resultant hit were explored using molecular dynamic simulations and MM/PBSA approach. The results highlight that Nebivolol (DB04861) not only achieved a stable conformation in the MEK binding pocket but also displayed highest binding affinity than the other molecules investigated in our study. Taken together, we hypothesized that Nebivolol is an excellent candidate for the inhibition of MEK in NSCLC patients in future.Communicated by Ramaswamy H. Sarma.

PMID:34459701 | DOI:10.1080/07391102.2021.1970629

Front Genet. 2021 Aug 12;12:683082. doi: 10.3389/fgene.2021.683082. eCollection 2021.

ABSTRACT

Stroke is a leading cause of death and disability worldwide. However, our understanding of its underlying biology and the number of available treatment options remain limited. Mendelian randomization (MR) offers a powerful approach to identify novel biological pathways and therapeutic targets for this disease. Around ~100 MR studies have been conducted so far to explore, confirm, and quantify causal relationships between several exposures and risk of stroke. In this review, we summarize the current evidence arising from these studies, including those investigating ischemic stroke, hemorrhagic stroke, or both. We highlight the different types of exposures that are currently under study, ranging from well-known cardiovascular risk factors to less established inflammation-related mechanisms. Finally, we provide an overview of future avenues of research and novel approaches, including drug target validation MR, which is poised to have a substantial impact on drug development and drug repurposing.

PMID:34456968 | PMC:PMC8387928 | DOI:10.3389/fgene.2021.683082

Appl Soft Comput. 2021 Aug 23:107831. doi: 10.1016/j.asoc.2021.107831. Online ahead of print.

ABSTRACT

The COVID-19 has now spread all over the world and causes a huge burden for public health and world economy. Drug repositioning has become a promising treatment strategy in COVID-19 crisis because it can shorten drug development process, reduce pharmaceutical costs and reposition approval drugs. Existing computational methods only focus on single information, such as drug and virus similarity or drug-virus network feature, which is not sufficient to predict potential drugs. In this paper, a sequence combined attentive network embedding model SANE is proposed for identifying drugs based on sequence features and network features. On the one hand, drug SMILES and virus sequence features are extracted by encoder-decoder in SANE as node initial embedding in drug-virus network. On the other hand, SANE obtains fields for each node by attention-based Depth-First-Search (DFS) to reduce noises and improve efficiency in representation learning and adopts a bottom-up aggregation strategy to learn node network representation from selected fields. Finally, a forward neural network is used for classifying. Experiment results show that SANE has achieved the performance with 81.98% accuracy and 0.8961 AUC value and outperformed state-of-the-art baselines. Further case study on COVID-19 indicates that SANE has a strong predictive ability since 25 of the top 40 (62.5%) drugs are verified by valuable dataset and literatures. Therefore, SANE is powerful to reposition drugs for COVID-19 and provides a new perspective for drug repositioning.

PMID:34456656 | PMC:PMC8381638 | DOI:10.1016/j.asoc.2021.107831

Methods. 2021 Aug 26:S1046-2023(21)00205-X. doi: 10.1016/j.ymeth.2021.08.007. Online ahead of print.

ABSTRACT

With the gradual increase in the COVID-19 mortality rate, there is an urgent need for an effective drug/vaccine. Several drugs like Remdesivir, Azithromycin, Favirapir, Ritonavir, Darunavir, etc., are put under evaluation in more than 300 clinical trials to treat COVID-19. On the other hand, several vaccines like Pfizer-BioNTech, Moderna, Johnson & Johnson's Janssen, Sputnik V, Covishield, Covaxin, etc., also evolved from the research study. While few of them already gets approved, others show encouraging results and are still under assessment. In parallel, there are also significant developments in new drug development. But, since the approval of new molecules takes substantial time, drug repurposing studies have also gained considerable momentum. The primary agent of the disease progression of COVID-19 is SARS-CoV2/nCoV, which is believed to have ∼89% genetic resemblance with SARS-CoV, a coronavirus responsible for the massive outbreak in 2003. With this hypothesis, Human-SARS-CoV protein interactions are used to develop an in-silico Human-nCoV network by identifying potential COVID-19 human spreader proteins by applying the SIS model and fuzzy thresholding by a possible COVID-19 FDA drugs target-based validation. At first, the complete list of FDA drugs is identified for the level-1 and level-2 spreader proteins in this network, followed by applying a drug consensus scoring strategy. The same consensus strategy is involved in the second analysis but on a curated overlapping set of key genes/proteins identified from COVID-19 symptoms. Validation using subsequent docking study has also been performed on COVID-19 potential drugs with the available major COVID-19 crystal structures whose PDB IDs are: 6LU7, 6M2Q, 6W9C, 6M0J, 6M71 and 6VXX. Our computational study and docking results suggest that Fostamatinib (R406 as its active promoiety) may also be considered as one of the potential candidates for further clinical trials in pursuit to counter the spread of COVID-19.

PMID:34455072 | DOI:10.1016/j.ymeth.2021.08.007