Front Microbiol. 2022 Mar 4;13:743147. doi: 10.3389/fmicb.2022.743147. eCollection 2022.

ABSTRACT

Zika virus (ZIKV) is a mosquito-borne, single-stranded RNA virus belonging to the genus Flavivirus. Although ZIKV infection is usually known to exhibit mild clinical symptoms, intrauterine ZIKV infections have been associated with severe neurological manifestations, including microcephaly and Guillain Barre syndrome (GBS). Therefore, it is imperative to understand the mechanisms of ZIKV entry into the central nervous system (CNS) and its effect on brain cells. Several routes of neuro-invasion have been identified, among which blood-brain barrier (BBB) disruption is the commonest mode of access. The molecular receptors involved in viral entry remain unknown; with various proposed molecular ZIKV-host interactions including potential non-receptor mediated cellular entry. As ZIKV invade neuronal cells, they trigger neurotoxic mechanisms via cell-autonomous and non-cell autonomous pathways, resulting in neurogenesis dysfunction, viral replication, and cell death, all of which eventually lead to microcephaly. Together, our understanding of the biological mechanisms of ZIKV exposure would aid in the development of anti-ZIKV therapies targeting host cellular and/or viral components to combat ZIKV infection and its neurological manifestations. In this present work, we review the current understanding of ZIKV entry mechanisms into the CNS and its implications on the brain. We also highlight the status of the drug repurposing approach for the development of potential antiviral drugs against ZIKV.

PMID:35308394 | PMC:PMC8931420 | DOI:10.3389/fmicb.2022.743147

Cell Death Dis. 2022 Mar 19;13(3):252. doi: 10.1038/s41419-022-04694-z.

ABSTRACT

Neuroendocrine differentiation (NED) frequently occurs in androgen-deprivation therapy (ADT)-resistant prostate cancer (PCa) and is typically associated with metabolic pathway alterations, acquisition of lineage plasticity, and malignancy. There is no conventional therapeutic approach for PCa patients with NED pathologic features because the molecular targets are unknown. Here, we evaluated the regulatory mechanism of NED-associated metabolic reprogramming induced by ADT. We detected that the loss of the androgen-responsive transcription factor, zinc finger, and BTB domain containing 10 (ZBTB10), can activate pyruvate kinase L/R (PKLR) to enhance a NED response that is associated with glucose uptake by PCa cells. PKLR exhibits a tumor-promoting effect in PCa after ADT, but ZBTB10 can compensate for the glucose metabolism and NED capacity of PKLR through the direct transcriptional downregulation of PKLR. Targeting PKLR by drug repurposing with FDA-approved compounds can reduce the aggressiveness and NED of ADT-resistant PCa. We demonstrated that PKLR acts as a modulator to activate NED in PCa enhancement by loss of ZBTB10, thereby enabling PCa cells to mount a glycolysis response essential for therapeutic resistance. Our findings highlight the broad relation between NED and metabolic dysfunction to provide gene expression-based biomarkers for NEPC treatment.

PMID:35306527 | DOI:10.1038/s41419-022-04694-z

Sci Rep. 2022 Mar 19;12(1):4751. doi: 10.1038/s41598-022-08787-9.

ABSTRACT

Drug-target interaction (DTI) prediction plays a crucial role in drug repositioning and virtual drug screening. Most DTI prediction methods cast the problem as a binary classification task to predict if interactions exist or as a regression task to predict continuous values that indicate a drug's ability to bind to a specific target. The regression-based methods provide insight beyond the binary relationship. However, most of these methods require the three-dimensional (3D) structural information of targets which are still not generally available to the targets. Despite this bottleneck, only a few methods address the drug-target binding affinity (DTBA) problem from a non-structure-based approach to avoid the 3D structure limitations. Here we propose Affinity2Vec, as a novel regression-based method that formulates the entire task as a graph-based problem. To develop this method, we constructed a weighted heterogeneous graph that integrates data from several sources, including drug-drug similarity, target-target similarity, and drug-target binding affinities. Affinity2Vec further combines several computational techniques from feature representation learning, graph mining, and machine learning to generate or extract features, build the model, and predict the binding affinity between the drug and the target with no 3D structural data. We conducted extensive experiments to evaluate and demonstrate the robustness and efficiency of the proposed method on benchmark datasets used in state-of-the-art non-structured-based drug-target binding affinity studies. Affinity2Vec showed superior and competitive results compared to the state-of-the-art methods based on several evaluation metrics, including mean squared error, rm2, concordance index, and area under the precision-recall curve.

PMID:35306525 | DOI:10.1038/s41598-022-08787-9

Sci Rep. 2022 Mar 18;12(1):4724. doi: 10.1038/s41598-022-08454-z.

ABSTRACT

Effective and successful clinical trials are essential in developing new drugs and advancing new treatments. However, clinical trials are very expensive and easy to fail. The high cost and low success rate of clinical trials motivate research on inferring knowledge from existing clinical trials in innovative ways for designing future clinical trials. In this manuscript, we present our efforts on constructing the first publicly available Clinical Trials Knowledge Graph, denoted as [Formula: see text]. [Formula: see text] includes nodes representing medical entities in clinical trials (e.g., studies, drugs and conditions), and edges representing the relations among these entities (e.g., drugs used in studies). Our embedding analysis demonstrates the potential utilities of [Formula: see text] in various applications such as drug repurposing and similarity search, among others.

PMID:35304504 | DOI:10.1038/s41598-022-08454-z

Pharmacol Ther. 2022 Mar 15:108171. doi: 10.1016/j.pharmthera.2022.108171. Online ahead of print.

ABSTRACT

Alzheimer's disease (AD) is one of the biggest human health threats due to increases in aging of the global population. Unfortunately, drugs for treating AD have been largely ineffective. Interestingly, downregulation of macroautophagy (autophagy) plays an essential role in AD pathogenesis. Therefore, targeting autophagy has drawn considerable attention as a therapeutic approach for the treatment of AD. However, developing new therapeutics is time-consuming and requires huge investments. One of the strategies currently under consideration for many diseases is "drug repositioning" or "drug repurposing". In this comprehensive review, we have provided an overview of the impact of autophagy on AD pathophysiology, reviewed the therapeutics that upregulate autophagy and are currently used in the treatment of other diseases, including cancers, and evaluated their repurposing as a possible treatment option for AD. In addition, we discussed the potential of applying nano-drug delivery to neurodegenerative diseases, such as AD, to overcome the challenge of crossing the blood brain barrier and specifically target molecules/pathways of interest with minimal side effects.

PMID:35304223 | DOI:10.1016/j.pharmthera.2022.108171

Curr Microbiol. 2022 Mar 18;79(5):137. doi: 10.1007/s00284-022-02794-9.

ABSTRACT

The identification of molecules that exhibit potent antibacterial activity and are capable of circumventing resistance mechanisms is an unmet need. The repositioning of approved drugs is considered an advantageous alternative in this case, and has gained prominence. In addition, drug synergism can reduce morbidity and mortality in the treatment of nosocomial infections caused by multi-drug resistant microorganisms (MDR). Whole cell growth inhibition assays were used to define the in vitro antibacterial activity of disulfiram against two standard American Type Culture Collection (ATCC) strains and 35 clinical isolates of vancomycin-resistant enterococci (VRE). The ability of disulfiram to synergize with vancomycin was determined by fractional inhibitory concentration index, preceded by the checkerboard test. The cytotoxicity of drugs alone and in combination was tested against Raw 264.7 cells. Disulfiram exhibited potent antibacterial activity against VRE (MIC 16-64 µg mL-1). Results: Associated with vancomycin, disulfiram it had a reduction in MIC of up to 64 times, with values of 0.5-4 µg mL-1. Vancomycin had a MIC of 128-1024 µg mL-1; combined, reduced this value by up to 124 times (8 µg mL-1), with synergy occurring against all strains. Disulfiram and vancomycin alone and in combination did not show cytotoxicity against the eukaryotic cell line. Based on these results, we suggest that the redirection of disulfiram may be promising in the treatment of infections caused by VRE, since it was able to potentiate the activity of vancomycin against the strains, being able to act as an adjuvant in cases of serious infections caused by Enterococcus.

PMID:35303186 | DOI:10.1007/s00284-022-02794-9

J Biomol Struct Dyn. 2022 Mar 18:1-15. doi: 10.1080/07391102.2022.2051743. Online ahead of print.

ABSTRACT

Experimental evidence indicated that bacterial pyruvate kinase of glycolysis can be evaluated as an alternative target to eliminate infections, while antibiotic resistance poses a global threat. Here, we use a computational workflow to reveal and investigate the potential allosteric sites of methicillin-resistant S. aureus PK, which can help in designing species-specific drugs to inhibit activity of this organism. Residue interaction networks point to a known allosteric site at the small C-C interface, a potential allosteric site near the small interface (site #1), and a second potential allosteric site at the large interface (site #2). 2 µs-long molecular dynamics (MD) simulations with AMBER16 generate different conformations of one narrow target site. Known and potential allosteric sites on the selected conformers are investigated using ensemble docking with AutoDock Vina and a library of 2447 FDA-approved drugs. We determine 18 hits, comprising ergot-alkaloids, anti-cancer-agents, antivirals, analgesics, cardiac glycosides, all with a high docking z-score for three sites. 5 selected compounds with high, average and low z-scores are subjected to 50 ns-long MD simulations for MM-GBSA calculations. ΔGbind values up to -49.3 kcal/mol at the C-C interface, up to -32.7 kcal/mol at site #1, and up to -53.3 kcal/mol at site #2 support the docking calculations. We investigate mitapivat and TT-232 as reference compounds under clinical trial, targeting human PK isomers. We suggest 18 FDA-approved hits from the docking calculations and TT-232 as potential inhibitors with multiple target sites on S. aureus PK. This study also proposes pharmacophores models for de novo drug design.Communicated by Ramaswamy H. Sarma.

PMID:35302925 | DOI:10.1080/07391102.2022.2051743

Curr Top Med Chem. 2022 Mar 17. doi: 10.2174/1568026622666220317164016. Online ahead of print.

ABSTRACT

High cost and risks are common issues in traditional drug research and development. Usually, it takes a long time to research and develop a drug, the effects of which are limited to relatively few targets. At present, studies are aiming to identify unknown new uses for existing drugs. Drug repositioning enables drugs to be quickly launched into clinical practice at a low cost because they have undergone clinical safety testing during the development process, which can greatly reduce costs and the risks of failed development. In addition to existing drugs with known indications, drugs that were shelved because of clinical trial failure can also be options for repositioning. In fact, many widely used drugs are identified via drug repositioning at present. This article reviews some popular research areas in the field of drug repositioning and briefly introduces the advantages and disadvantages of these methods, aiming to provide useful insights into future development in this field.

PMID:35301952 | DOI:10.2174/1568026622666220317164016

Anticancer Agents Med Chem. 2022 Mar 17. doi: 10.2174/1871520622666220317140557. Online ahead of print.

ABSTRACT

Global efforts invested for the prevention and treatment of cancer need to be repositioned to develop safe, effective, and economic anticancer therapeutics by adopting rational approaches of drug discovery. Drug repurposing is one of the established approaches to reposition old, clinically approved off patent noncancer drugs with known targets into newer indications. The literature review suggests key role of drug repurposing in the development of drugs intended for cancer as well as noncancer therapeutics. A wide category of noncancer drugs namely, drugs acting on CNS, anthelmintics, cardiovascular drugs, antimalarial drugs, anti-inflammatory drugs have come out with interesting outcomes during preclinical and clinical phases. In the present article a comprehensive overview of the current scenario of drug repurposing for the treatment of cancer has been focused. The details of some successful studies along with examples have been included followed by associated challenges.

PMID:35301945 | DOI:10.2174/1871520622666220317140557

Drug Discov Today. 2022 Mar 14:S1359-6446(22)00112-X. doi: 10.1016/j.drudis.2022.03.006. Online ahead of print.

ABSTRACT

The current global health emergency in the form of the Coronavirus 2019 (COVID-19) pandemic has highlighted the need for fast, accurate, and efficient drug discovery pipelines. Traditional drug discovery projects relying on in vitro high-throughput screening (HTS) involve large investments and sophisticated experimental set-ups, affordable only to big biopharmaceutical companies. In this scenario, application of efficient state-of-the-art computational methods and modern artificial intelligence (AI)-based algorithms for rapid screening of repurposable chemical space [approved drugs and natural products (NPs) with proven pharmacokinetic profiles] to identify the initial leads is a powerful option to save resources and time. Structure-based drug repurposing is a popular in silico repurposing approach. In this review, we discuss traditional and modern AI-based computational methods and tools applied at various stages for structure-based drug discovery (SBDD) pipelines. Additionally, we highlight the role of generative models in generating molecules with scaffolds from repurposable chemical space. Teaser: This review highlights the importance of repurposable chemical space, and the contributions of conventional in silico approaches and modern machine-learning algorithms for rapid structure-based drug repurposing.

PMID:35301148 | DOI:10.1016/j.drudis.2022.03.006

J Exp Pharmacol. 2022 Mar 8;14:97-115. doi: 10.2147/JEP.S346006. eCollection 2022.

ABSTRACT

Drug repurposing process aims to identify new uses for the existing drugs to overcome traditional de novo drug discovery and development challenges. At the same time, as viral infections became a serious threat to humans and the viral organism itself has a high ability to mutate genetically, and due to serious adverse effects that result from antiviral drugs, there are crucial needs for the discovery of new antiviral drugs, and to identify new antiviral effects for the exciting approved drugs towards different types of viral infections depending on the observed antiviral activity in preclinical studies or clinical findings is one of the approaches to counter the viral infections problems. This narrative review article summarized mainly the published preclinical studies that evaluated the antiviral activity of drugs that are approved and used mainly as antibacterial, antifungal, antiprotozoal, and anthelmintic drugs, and the preclinical studies included the in silico, in vitro, and in vivo findings, additionally some clinical observations were also included while trying to relate them to the preclinical findings. Finally, the structure used for writing about the antiviral activity of the drugs was according to the families of the viruses used in the studies to form a better image for the target of antiviral activity of different drugs in the different kinds of viruses and to relate between the antiviral activity of the drugs against different strains of viruses within the same viral family.

PMID:35299994 | PMC:PMC8922315 | DOI:10.2147/JEP.S346006

ChemMedChem. 2022 Mar 17. doi: 10.1002/cmdc.202200092. Online ahead of print.

ABSTRACT

A focused drug repurposing approach is described where an FDA-approved drug is rationally selected for biological testing based on structural similarities to a fragment compound found to bind a target protein by an NMR screen. The approach is demonstrated by first screening a curated fragment library using 19F NMR to discover a quality binder to ACE2, the human receptor required for entry and infection by the SARS-CoV-2 virus. Based on this binder, a highly related scaffold was derived and used as a "smart scaffold" or template in a computer-aided finger-print search of a library of FDA-approved or marketed drugs. The most interesting structural match involved the drug vortioxetine which was then experimentally shown by NMR spectroscopy to bind directly to human ACE2. Also, an ELISA assay showed that the drug inhibits the interaction of human ACE2 to the SARS-CoV-2 receptor-binding-domain (RBD). Moreover, our cell-culture infectivity assay confirmed that vortioxetine is active against SARS-CoV-2 and inhibits viral replication. Thus, the use of "smart scaffolds" based on binders from fragment screens may have general utility for identifying candidates of FDA-approved or marketed drugs as a rapid repurposing strategy. Similar approaches can be envisioned for other fields involving small-molecule chemical applications.

PMID:35298873 | DOI:10.1002/cmdc.202200092

J Antimicrob Chemother. 2022 Mar 17:dkac064. doi: 10.1093/jac/dkac064. Online ahead of print.

ABSTRACT

This review was designed to discuss the emerging and current pharmacotherapeutic agents for the treatment of Lassa viral haemorrhagic fever disease (LVHFD), also known as Lassa fever (LF). Original peer-reviewed articles that investigated LF were identified using the Medline Entrez-PubMed search. Information was also sourced from printed textbooks and reports by recognized health professional bodies such as the WHO, CDC, the Nigerian Federal Ministry of Health and the United Nations Children's Fund (UNICEF). A total of 103 articles were reviewed and 78 were found to contain information relevant to the study. LF remains an endemic disease of public health concern in the West Africa region, and in the rest of the world as cases have been imported into non-endemic regions as well. Currently, there are no approved vaccines or therapeutics for the treatment of Lassa mammarenavirus (LASV) infection. There are, however, off-label therapeutics being used (ribavirin and convalescent plasma) whose efficacy is suboptimal. Research is still ongoing on possible therapeutic options and drug repurposing of therapeutic agents currently in use for other clinical conditions. Considered therapeutic options include favipiravir, taribavirin, Arevirumab-3 and experimental drugs such as losmapimod, adamantyl diphenyl piperazine 3.3, Arbidol (umifenovir) and decanoyl-RRLL-chloromethyl ketone (dec-RRLL-CMK). Current treatments for LF are limited, hence the institution of mitigating measures to prevent infection is of utmost importance and should be prioritized, especially in endemic regions. Heightened searches for other therapeutic options with greater efficacy and lower toxicity are still ongoing, as well as for vaccines as the absence of these classifies the disease as a priority disease of high public health impact.

PMID:35296886 | DOI:10.1093/jac/dkac064

Front Microbiol. 2022 Feb 28;13:740382. doi: 10.3389/fmicb.2022.740382. eCollection 2022.

ABSTRACT

Coronavirus disease 2019 (COVID-19) is rapidly spreading. Researchers around the world are dedicated to finding the treatment clues for COVID-19. Drug repositioning, as a rapid and cost-effective way for finding therapeutic options from available FDA-approved drugs, has been applied to drug discovery for COVID-19. In this study, we develop a novel drug repositioning method (VDA-KLMF) to prioritize possible anti-SARS-CoV-2 drugs integrating virus sequences, drug chemical structures, known Virus-Drug Associations, and Logistic Matrix Factorization with Kernel diffusion. First, Gaussian kernels of viruses and drugs are built based on known VDAs and nearest neighbors. Second, sequence similarity kernel of viruses and chemical structure similarity kernel of drugs are constructed based on biological features and an identity matrix. Third, Gaussian kernel and similarity kernel are diffused. Forth, a logistic matrix factorization model with kernel diffusion is proposed to identify potential anti-SARS-CoV-2 drugs. Finally, molecular dockings between the inferred antiviral drugs and the junction of SARS-CoV-2 spike protein-ACE2 interface are implemented to investigate the binding abilities between them. VDA-KLMF is compared with two state-of-the-art VDA prediction models (VDA-KATZ and VDA-RWR) and three classical association prediction methods (NGRHMDA, LRLSHMDA, and NRLMF) based on 5-fold cross validations on viruses, drugs, and VDAs on three datasets. It obtains the best recalls, AUCs, and AUPRs, significantly outperforming other five methods under the three different cross validations. We observe that four chemical agents coming together on any two datasets, that is, remdesivir, ribavirin, nitazoxanide, and emetine, may be the clues of treatment for COVID-19. The docking results suggest that the key residues K353 and G496 may affect the binding energies and dynamics between the inferred anti-SARS-CoV-2 chemical agents and the junction of the spike protein-ACE2 interface. Integrating various biological data, Gaussian kernel, similarity kernel, and logistic matrix factorization with kernel diffusion, this work demonstrates that a few chemical agents may assist in drug discovery for COVID-19.

PMID:35295301 | PMC:PMC8919055 | DOI:10.3389/fmicb.2022.740382

Elife. 2022 Mar 16;11:e77444. doi: 10.7554/eLife.77444. Online ahead of print.

ABSTRACT

Coagulopathy is a significant aspect of morbidity in COVID-19 patients. The clotting cascade is propagated by a series of proteases, including factor Xa and thrombin. While certain host proteases, including TMPRSS2 and furin, are known to be important for cleavage activation of SARS-CoV-2 spike to promote viral entry in the respiratory tract, other proteases may also contribute. Using biochemical and cell-based assays, we demonstrate that factor Xa and thrombin can also directly cleave SARS-CoV-2 spike, enhancing infection at the stage of viral entry. Coagulation factors increased SARS-CoV-2 infection in human lung organoids. A drug-repurposing screen identified a subset of protease inhibitors that promiscuously inhibited spike cleavage by both transmembrane serine proteases as well as coagulation factors. The mechanism of the protease inhibitors nafamostat and camostat may extend beyond inhibition of TMPRSS2 to coagulation-induced spike cleavage. Anticoagulation is critical in the management of COVID-19, and early intervention could provide collateral benefit by suppressing SARS-CoV-2 viral entry. We propose a model of positive feedback whereby infection-induced hypercoagulation exacerbates SARS-CoV-2 infectivity.

PMID:35294338 | DOI:10.7554/eLife.77444

Expert Opin Investig Drugs. 2022 Mar 16. doi: 10.1080/13543784.2022.2054325. Online ahead of print.

ABSTRACT

INTRODUCTION: Drug repurposing can be a successful approach to deal with the scarcity of cost-effective therapies in situations such as the COVID-19 pandemic. Tetracyclines have previously shown efficacy in preclinical acute respiratory distress syndrome (ARDS) models and initial predictions and experimental reports suggest a direct anti-viral activity against SARS-CoV2. Furthermore, a few clinical reports indicate their potential in COVID-19 patients. Besides the scarcity and limitations of the scientific evidence, the effectiveness of tetracyclines in experimental ARDS has been proven extensively, counteracting the overt inflammatory reaction and fibrosis sequelae due to a synergic combination of pharmacological activities.

AREAS COVERED: This paper discusses the scientific evidence behind the application of tetracyclines for ARDS/COVID-19.

EXPERT OPINION: The benefits of their multi-target pharmacology and their safety profile overcome the limitations, such as antibiotic activity and low commercial interest. Immunomodulatory tetracyclines and novel chemically modified non-antibiotic tetracyclines have therapeutic potential. Further drug repurposing studies in ARDS and severe COVID-19 are necessary.

PMID:35294307 | DOI:10.1080/13543784.2022.2054325

J Chem Theory Comput. 2022 Mar 16. doi: 10.1021/acs.jctc.2c00002. Online ahead of print.

ABSTRACT

Cocaine addiction is a psychosocial disorder induced by the chronic use of cocaine and causes a large number of deaths around the world. Despite decades of effort, no drugs have been approved by the Food and Drug Administration (FDA) for the treatment of cocaine dependence. Cocaine dependence is neurological and involves many interacting proteins in the interactome. Among them, the dopamine (DAT), serotonin (SERT), and norepinephrine (NET) transporters are three major targets. Each of these targets has a large protein-protein interaction (PPI) network, which must be considered in the anticocaine addiction drug discovery. This work presents DAT, SERT, and NET interactome network-informed machine learning/deep learning (ML/DL) studies of cocaine addiction. We collected and analyzed 61 protein targets out of 460 proteins in the DAT, SERT, and NET PPI networks that have sufficiently large existing inhibitor datasets. Utilizing autoencoder (AE) and other ML/DL algorithms, including gradient boosting decision tree (GBDT) and multitask deep neural network (MT-DNN), we built predictive models for these targets with 115 407 inhibitors to predict drug repurposing potential and possible side effects. We further screened their absorption, distribution, metabolism, and excretion, and toxicity (ADMET) properties to search for leads having potential for developing treatments for cocaine addiction. Our approach offers a new systematic protocol for artificial intelligence (AI)-based anticocaine addiction lead discovery.

PMID:35294204 | DOI:10.1021/acs.jctc.2c00002

Mem Inst Oswaldo Cruz. 2022 Mar 16;117:e210386. doi: 10.1590/0074-02760210386. eCollection 2022.

ABSTRACT

Chagas disease (CD) is an old neglected problem that affects more than 6 million people through 21 endemic countries in Latin America. Despite being responsible for more than 12 thousand deaths per year, the disease disposes basically of two drugs for its treatment, the nitroimidazole benznidazole and the nitrofuran nifurtimox. However, these drugs have innumerous limitations that greatly reduce the chances of cure. In Brazil, for example, only benznidazole is available to treat CD patients. Therefore, some proof-of-concept phase II clinical trials focused on improving the current treatment with benznidazole, also comparing it with repositioned drugs or combining them. Indeed, repositioning already marketed drugs in view of combating neglected tropical diseases is a very interesting approach in the context of decreased time for approval, better treatment options and low cost for development and implementation. After the introduction of human immunodeficiency virus aspartyl peptidase inhibitors (HIV-PIs) in the treatment of acquired immune deficiency syndrome (AIDS), the prevalence and incidence of parasitic, fungal and bacterial co-infections suffered a marked reduction, making these HIV-PIs attractive for drug repositioning. In this line, the present perspective presents the promising and beneficial data concerning the effects of HIV-PIs on the clinically relevant forms of Trypanosoma cruzi (i.e., trypomastigotes and amastigotes) and also highlights the ultrastructural and physiological targets for the HIV-PIs on this parasite. Therefore, we raise the possibility that HIV-PIs could be considered as alternative treatment options in the struggle against CD.

PMID:35293428 | DOI:10.1590/0074-02760210386

J Cheminform. 2022 Mar 15;14(1):17. doi: 10.1186/s13321-022-00592-w.

ABSTRACT

BACKGROUND: Structure-based drug repositioning has emerged as a promising alternative to conventional drug development. Regardless of the many success stories reported over the past years and the novel breakthroughs on the AI-based system AlphaFold for structure prediction, the availability of structural data for protein-drug complexes remains very limited. Whereas the chemical libraries contain millions of drug compounds, the vast majority of them do not have structures to crystallized targets,and it is, therefore, impossible to characterize their binding to targets from a structural view. However, the concept of building blocks offers a novel perspective on the structural problem. A drug compound is considered a complex of small chemical blocks or fragments, which confer the relevant properties to the drug and have a high proportion of functional groups involved in protein binding. Based on this, we propose a novel approach to expand the scope of structure-based repositioning approaches by transferring the structural knowledge from a fragment to a compound level.

RESULTS: We fragmented over 100,000 compounds in the Protein Data Bank (PDB) and characterized the structural binding mode of 153,000 fragments to their crystallized targets. Using the fragment's data, we were able to artificially reconstruct the binding mode of over 7,800 complexes between ChEMBL compounds and their known targets, for which no structural data is available. We proved that the conserved binding tendency of fragments, when binding to the same targets, highly influences the drug's binding specificity and carries the key information to reconstruct full drugs binding mode. Furthermore, our approach was able to reconstruct multiple compound-target pairs at optimal thresholds and high similarity to the actual binding mode.

CONCLUSIONS: Such reconstructions are of great value and benefit structure-based drug repositioning since they automatically enlarge the technique's scope and allow exploring the so far 'unexplored compounds' from a structural perspective. In general, the transfer of structural information is a promising technique that could be applied to any chemical library, to any compound that has no crystal structure available in PDB, and even to transfer any other feature that may be relevant for the drug discovery process and that due to data limitations is not yet fully available. In that sense, the results of this work document the full potential of structure-based screening even beyond PDB.

PMID:35292113 | DOI:10.1186/s13321-022-00592-w

J Cheminform. 2022 Mar 15;14(1):14. doi: 10.1186/s13321-022-00591-x.

ABSTRACT

MOTIVATION: Drug-target binding affinity (DTA) reflects the strength of the drug-target interaction; therefore, predicting the DTA can considerably benefit drug discovery by narrowing the search space and pruning drug-target (DT) pairs with low binding affinity scores. Representation learning using deep neural networks has achieved promising performance compared with traditional machine learning methods; hence, extensive research efforts have been made in learning the feature representation of proteins and compounds. However, such feature representation learning relies on a large-scale labelled dataset, which is not always available.

RESULTS: We present an end-to-end deep learning framework, ELECTRA-DTA, to predict the binding affinity of drug-target pairs. This framework incorporates an unsupervised learning mechanism to train two ELECTRA-based contextual embedding models, one for protein amino acids and the other for compound SMILES string encoding. In addition, ELECTRA-DTA leverages a squeeze-and-excitation (SE) convolutional neural network block stacked over three fully connected layers to further capture the sequential and spatial features of the protein sequence and SMILES for the DTA regression task. Experimental evaluations show that ELECTRA-DTA outperforms various state-of-the-art DTA prediction models, especially with the challenging, interaction-sparse BindingDB dataset. In target selection and drug repurposing for COVID-19, ELECTRA-DTA also offers competitive performance, suggesting its potential in speeding drug discovery and generalizability for other compound- or protein-related computational tasks.

PMID:35292100 | DOI:10.1186/s13321-022-00591-x