Viruses. 2021 Nov 9;13(11):2246. doi: 10.3390/v13112246.

ABSTRACT

Since its licensing in 1971, the synthetic compound inosine pranobex has been effectively combating viral infections, including herpes zoster, varicella, measles, and infections caused by the herpes simplex virus, human papillomavirus, Epstein-Barr virus, cytomegalovirus, and respiratory viruses. With the emergence of SARS-CoV-2, new and existing drugs have been intensively evaluated for their potential as COVID-19 medication. Due to its potent immunomodulatory properties, inosine pranobex, an orally administered drug with pleiotropic effects, can, during early treatment, alter the course of the disease. We describe the action of inosine pranobex in the body and give an overview of existing evidence collected to support further efforts to study this drug in a rigorous clinical trial setup.

PMID:34835052 | DOI:10.3390/v13112246

J Pers Med. 2021 Oct 24;11(11):1072. doi: 10.3390/jpm11111072.

ABSTRACT

The MINERVA platform is currently the most widely used platform for visualizing and providing access to disease maps. Disease maps are systems biological maps of molecular interactions relevant in a certain disease context, where they can be used to support drug discovery. For this purpose, we extended MINERVA's own drug and chemical search using the MINERVA plugin starter kit. We developed a plugin to provide a linkage between disease maps in MINERVA and application-specific databases of candidate therapeutics. The plugin has three main functionalities; one shows all the targets of all the compounds in the database, the second is a compound-based search to highlight targets of specific compounds, and the third can be used to find compounds that affect a certain target. As a use case, we applied the plugin to link a disease map and compound database we previously established in the context of cystic fibrosis and, herein, point out possible issues and difficulties. The plugin is publicly available on GitLab; the use-case application to cystic fibrosis, connecting disease maps and the compound database CandActCFTR, is available online.

PMID:34834423 | DOI:10.3390/jpm11111072

Pharmaceutics. 2021 Nov 18;13(11):1956. doi: 10.3390/pharmaceutics13111956.

ABSTRACT

Uveal melanoma is the second most common melanoma and the most common intraocular malignant tumour of the eye. Among various treatments currently studied, Sorafenib was also proposed as a promising drug, often administered with other compounds in order to avoid resistance mechanisms. Despite its promising cellular activities, the use of Sorafenib by oral administration is limited by its severe side effects and the difficulty to reach the target. The encapsulation into drug delivery systems represents an interesting strategy to overcome these limits. In this study, different lipid nanoparticulate formulations were prepared and compared in order to select the most suitable for the encapsulation of Sorafenib. In particular, two solid lipids (Softisan or Suppocire) at different concentrations were used to produce solid lipid nanoparticles, demonstrating that higher amounts were able to achieve smaller particle sizes, higher homogeneity, and longer physical stability. The selected formulations, which demonstrated to be biocompatible on Statens Seruminstitut Rabbit Cornea cells, were modified to improve their mucoadhesion, evaluating the effect of two monovalent cationic lipids with two lipophilic chains. Sorafenib encapsulation allowed obtaining a sustained and prolonged drug release, thus confirming the potential use of the developed strategy to topically administer Sorafenib in the treatment of uveal melanoma.

PMID:34834371 | DOI:10.3390/pharmaceutics13111956

Pharmaceutics. 2021 Nov 10;13(11):1906. doi: 10.3390/pharmaceutics13111906.

ABSTRACT

An important stage in the process of discovering new drugs is when candidate molecules are tested of their efficacy. It is reported that testing drug efficacy empirically costs billions of dollars in the drug discovery pipeline. As a mechanism of expediting this process, researchers have resorted to using computational methods to predict the action of molecules in silico. Here, we present a way of predicting the therapeutic-use class of drugs from chemical structures only using graph convolutional networks. In comparison with existing methods which use fingerprints or images as training samples, our approach has yielded better results in all metrics under consideration. In particular, validation accuracy increased from 83-88% to 86-90% for single label tasks. Similarly, the model achieved an accuracy of over 88% on new test data. Finally, our multi-label classification model made new predictions which indicated that some of the drugs could have other therapeutic uses other than those indicated in the dataset. We performed a literature-based evaluation of these predictions and found evidence that validates them. This renders the model a potential tool to be used in search of drugs that are candidates for repurposing.

PMID:34834320 | DOI:10.3390/pharmaceutics13111906

Life (Basel). 2021 Oct 20;11(11):1115. doi: 10.3390/life11111115.

ABSTRACT

The discovery of new drugs is required in the time of global aging and increasing populations. Traditional drug development strategies are expensive, time-consuming, and have high risks. Thus, drug repurposing, which treats new/other diseases using existing drugs, has become a very admired tactic. It can also be referred to as the re-investigation of the existing drugs that failed to indicate the usefulness for the new diseases. Previously published literature used maximum flow approaches to identify new drug targets for drug-resistant infectious diseases but not for drug repurposing. Therefore, we are proposing a maximum flow-based protein-protein interactions (PPIs) network analysis approach to identify new drug targets (proteins) from the targets of the FDA (Food and Drug Administration) drugs and their associated drugs for chronic diseases (such as breast cancer, inflammatory bowel disease (IBD), and chronic obstructive pulmonary disease (COPD)) treatment. Experimental results showed that we have successfully turned the drug repurposing into a maximum flow problem. Our top candidates of drug repurposing, Guanidine, Dasatinib, and Phenethyl Isothiocyanate for breast cancer, IBD, and COPD were experimentally validated by other independent research as the potential candidate drugs for these diseases, respectively. This shows the usefulness of the proposed maximum flow approach for drug repurposing.

PMID:34832991 | DOI:10.3390/life11111115

Pharmaceuticals (Basel). 2021 Nov 22;14(11):1204. doi: 10.3390/ph14111204.

ABSTRACT

Epilepsy is a neurodegenerative disorder that causes recurring seizures. Thirty-five percent of patients remain refractory, with a higher prevalence of depression. We investigated the anticonvulsant efficacy of carbamazepine (CBZ; 20 and 50 mg/kg), imipramine (IMI; 10 and 20 mg/kg) alone, and as a low dose combination. This preclinical investigation included dosing of rats for 14 days followed by elicitation of electroshock on the last day of treatment. Along with behavioral monitoring, the rat hippocampus was processed for quantification of mTOR, IL-1β, IL-6 and TNF-α levels. The histopathological analysis of rat hippocampus was performed to ascertain neuroprotection. In vitro studies and in silico studies were also conducted. We found that the low dose combinatorial therapy of CBZ (20 mg/kg) + IMI (10 mg/kg) exhibits synergism (p < 0.001) in abrogation of maximal electroshock (MES) induced convulsions/tonic hind limb extension (THLE), by reducing levels of pro-inflammatory cytokines, and weakening of the PI3K/Akt/mTOR signal. The combination also exhibits cooperative binding at the Akt. As far as neuroprotection is concerned, the said combination increased cell viability by 166.37% compared to Pentylenetetrazol (PTZ) treated HEK-293 cells. Thus, the combination of CBZ (20 mg/kg) + IMI (10 mg/kg) is a fruitful combination therapy to elevate seizure threshold and provide neuroprotection.

PMID:34832986 | DOI:10.3390/ph14111204

Pharmaceuticals (Basel). 2021 Nov 5;14(11):1126. doi: 10.3390/ph14111126.

ABSTRACT

Crizotinib was a first generation of ALK tyrosine kinase inhibitor approved for the treatment of ALK-positive non-small-cell lung carcinoma (NSCLC) patients. COMPARE and cluster analyses of transcriptomic data of the NCI cell line panel indicated that genes with different cellular functions regulated the sensitivity or resistance of cancer cells to crizotinib. Transcription factor binding motif analyses in gene promoters divulged two transcription factors possibly regulating the expression of these genes, i.e., RXRA and GATA1, which are important for leukemia and erythroid development, respectively. COMPARE analyses also implied that cell lines of various cancer types displayed varying degrees of sensitivity to crizotinib. Unexpectedly, leukemia but not lung cancer cells were the most sensitive cells among the different types of NCI cancer cell lines. Re-examining this result in another panel of cell lines indeed revealed that crizotinib exhibited potent cytotoxicity towards acute myeloid leukemia and multiple myeloma cells. P-glycoprotein-overexpressing CEM/ADR5000 leukemia cells were cross-resistant to crizotinib. NCI-H929 multiple myeloma cells were the most sensitive cells. Hence, we evaluated the mode of action of crizotinib on these cells. Although crizotinib is a TKI, it showed highest correlation rates with DNA topoisomerase II inhibitors and tubulin inhibitors. The altered gene expression profiles after crizotinib treatment predicted several networks, where TOP2A and genes related to cell cycle were downregulated. Cell cycle analyses showed that cells incubated with crizotinib for 24 h accumulated in the G2M phase. Crizotinib also increased the number of p-H3(Ser10)-positive NCI-H929 cells illustrating crizotinib's ability to prevent mitotic exit. However, cells accumulated in the sub-G0G1 fraction with longer incubation periods, indicating apoptosis induction. Additionally, crizotinib disassembled the tubulin network of U2OS cells expressing an α-tubulin-GFP fusion protein, preventing migration of cancer cells. This result was verified by in vitro tubulin polymerization assays. In silico molecular docking also revealed a strong binding affinity of crizotinib to the colchicine and Vinca alkaloid binding sites. Taken together, these results demonstrate that crizotinib destabilized microtubules. Additionally, the decatenation assay showed that crizotinib partwise inhibited the catalytic activity of DNA topoisomerase II. In conclusion, crizotinib exerted kinase-independent cytotoxic effects through the dual inhibition of tubulin polymerization and topoisomerase II and might be used to treat not only NSCLC but also multiple myeloma.

PMID:34832908 | DOI:10.3390/ph14111126

Int J Biol Macromol. 2021 Nov 23:S0141-8130(21)02530-7. doi: 10.1016/j.ijbiomac.2021.11.124. Online ahead of print.

ABSTRACT

The molecular mechanisms underlying the pathogenesis of COVID-19 have not been fully discovered. This study aims to decipher potentially hidden parts of the pathogenesis of COVID-19, potential novel drug targets, and identify potential drug candidates. Two gene expression profiles were analyzed, and overlapping differentially expressed genes (DEGs) were selected for which top enriched transcription factors and kinases were identified, and pathway analysis was performed. Protein-protein interaction (PPI) of DEGs was constructed, hub genes were identified, and module analysis was also performed. DGIdb database was used to identify drugs for the potential targets (hub genes and the most enriched transcription factors and kinases for DEGs). A drug-potential target network was constructed, and drugs were ranked according to the degree. L1000FDW was used to identify drugs that can reverse transcriptional profiles of COVID-19. We identified drugs currently in clinical trials, others predicted by different methods, and novel potential drug candidates Entrectinib, Omeprazole, and Exemestane for combating COVID-19. Besides the well-known pathogenic pathways, it was found that axon guidance is a potential pathogenic pathway. Sema7A, which may exacerbate hypercytokinemia, is considered a potential novel drug target. Another potential novel pathway is related to TINF2 overexpression, which may induce potential telomere dysfunction and damage DNA that may exacerbate lung fibrosis. This study identified new potential insights regarding COVID-19 pathogenesis and treatment, which might help us improve our understanding of the mechanisms of COVID-19.

PMID:34826456 | DOI:10.1016/j.ijbiomac.2021.11.124

Nat Commun. 2021 Nov 25;12(1):6848. doi: 10.1038/s41467-021-27138-2.

ABSTRACT

Traditional drug discovery faces a severe efficacy crisis. Repurposing of registered drugs provides an alternative with lower costs and faster drug development timelines. However, the data necessary for the identification of disease modules, i.e. pathways and sub-networks describing the mechanisms of complex diseases which contain potential drug targets, are scattered across independent databases. Moreover, existing studies are limited to predictions for specific diseases or non-translational algorithmic approaches. There is an unmet need for adaptable tools allowing biomedical researchers to employ network-based drug repurposing approaches for their individual use cases. We close this gap with NeDRex, an integrative and interactive platform for network-based drug repurposing and disease module discovery. NeDRex integrates ten different data sources covering genes, drugs, drug targets, disease annotations, and their relationships. NeDRex allows for constructing heterogeneous biological networks, mining them for disease modules, prioritizing drugs targeting disease mechanisms, and statistical validation. We demonstrate the utility of NeDRex in five specific use-cases.

PMID:34824199 | DOI:10.1038/s41467-021-27138-2

Comput Biol Med. 2021 Nov 20:105049. doi: 10.1016/j.compbiomed.2021.105049. Online ahead of print.

ABSTRACT

The ongoing pandemic of Coronavirus Disease 2019 (COVID-19) has posed a serious threat to global public health. Drug repurposing is a time-efficient approach to finding effective drugs against SARS-CoV-2 in this emergency. Here, we present a robust experimental design combining deep learning with molecular docking experiments to identify the most promising candidates from the list of FDA-approved drugs that can be repurposed to treat COVID-19. We have employed a deep learning-based Drug Target Interaction (DTI) model, called DeepDTA, with few improvements to predict drug-protein binding affinities, represented as KIBA scores, for 2440 FDA-approved and 8168 investigational drugs against 24 SARS-CoV-2 viral proteins. FDA-approved drugs with the highest KIBA scores were selected for molecular docking simulations. We ran around 50,000 docking simulations for 168 selected drugs against 285 total predicted and/or experimentally proven active sites of all 24 SARS-CoV-2 viral proteins. A list of 49 most promising FDA-approved drugs with the best consensus KIBA scores and binding affinity values against selected SARS-CoV-2 viral proteins was generated. Most importantly, 16 drugs including anidulafungin, velpatasvir, glecaprevir, rifapentine, flavin adenine dinucleotide (FAD), terlipressin, and selinexor demonstrated the highest predicted inhibitory potential against key SARS-CoV-2 viral proteins. We further measured the inhibitory activity of 5 compounds (rifapentine, velpatasvir, glecaprevir, anidulafungin, and FAD disodium) on SARS-CoV-2 PLpro using Ubiquitin-Rhodamine 110 Gly fluorescent intensity assay. The highest inhibition of PLpro activity was seen with rifapentine (IC50: 15.18 μM) and FAD disodium (IC50: 12.39 μM), the drugs with high predicted KIBA scores and binding affinities.

PMID:34823857 | DOI:10.1016/j.compbiomed.2021.105049

Transl Oncol. 2021 Nov 22;15(1):101272. doi: 10.1016/j.tranon.2021.101272. Online ahead of print.

ABSTRACT

High-risk neuroblastoma (NB) represents a major clinical challenge in pediatric oncology due to relapse of metastatic, drug-resistant disease, and treatment-related toxicities. An analysis of 1235 primary NB patient dataset revealed significant increase in AKT1 and AKT2 gene expression with cancer stage progression. Additionally, Both AKT1 and AKT2 expression inversely correlate with poor overall survival of NB patients. AKT1 and AKT2 genes code for AKT that drive a major oncogenic cell signaling pathway known in many cancers, including NB. To inhibit AKT pathway, we repurposed an antiviral inhibitor BX-795 that inhibits PDK1, an upstream activator of AKT. BX-795 potently inhibits NB cell proliferation and colony growth in a dose-dependent manner. BX-795 significantly enhances apoptosis and blocks cell cycle progression at mitosis phase in NB. Additionally, BX-795 potently inhibits tumor formation and growth in a NB spheroid tumor model. We further tested dual therapeutic approaches by combining BX-795 with either doxorubicin or crizotinib and found synergistic and significant inhibition of NB growth, in contrast to either drug alone. Overall, our data demonstrate that BX-795 inhibits AKT pathway to inhibit NB growth, and combining BX-795 with current therapies is an effective and clinically tractable therapeutic approach for NB.

PMID:34823094 | DOI:10.1016/j.tranon.2021.101272

Mol Biol Rep. 2021 Nov 25. doi: 10.1007/s11033-021-06977-8. Online ahead of print.

ABSTRACT

Beta-hemoglobinopathies exhibit a heterogeneous clinical picture with varying degrees of clinical severity. Pertaining to the limited treatment options available, where blood transfusion still remains the commonest mode of treatment, pharmacological induction of fetal hemoglobin (HbF) has been a lucrative therapeutic intervention. Till now more than 70 different HbF inducers have been identified. The practical usage of many pharmacological drugs has been limited due to safety concerns. Natural compounds, like Resveratrol, Ripamycin and Bergaptene, with limited cytotoxicity and high efficacy have started capturing the attention of researchers. In this review, we have summarized pharmacological drugs and bioactive compounds isolated from natural sources that have been shown to increase HbF significantly. It primarily discusses recently identified synthetic and natural compounds, their mechanism of action, and their suitable screening platforms, including high throughput drug screening technology and biosensors. It also delves into the topic of combinatorial therapy and drug repurposing for HbF induction. Overall, we aim to provide insights into where we stand in HbF induction strategies for treating β-hemoglobinopathies.

PMID:34822068 | DOI:10.1007/s11033-021-06977-8

Expert Opin Drug Discov. 2021 Nov 24. doi: 10.1080/17460441.2022.2005025. Online ahead of print.

ABSTRACT

INTRODUCTION: SARS-CoV-2 is a highly infectious and deadly coronavirus whose study requires the use of a biosafety level 3 (BSL-3) containment facility to investigate viral biology and pathogenesis, which limits the study of live virus and slows progress towards finding suitable treatments for infection. While vaccines from several companies have proven very effective in combating the virus, few treatments exist for those who do succumb to the viral-induced systemic disease called COVID-19.

AREAS COVERED: This short review focuses on fluorescent quantum dot-based modeling of SARS-CoV-2. New BSL-2 viral models are essential to find small molecules and biologics that may be effective in stopping viral infection as well as treating already infected individuals. Nanoparticles are invaluable tools for biological research as they can be used to both modeling pathogens and serve as a platform for developing vaccines.

EXPERT OPINION: Visualizing viral activity with fluorescent quantum dots enables both biochemical and cell-based assays to detect virus-host receptor interactions, cellular activity after binding to cell plasma membrane, screening for interventions using small molecule drug repurposing, and testing of novel biologics. Quantum dots can also be used for diagnostic assays, vaccine development, and importantly, pan-antiviral drugs to address variants that may escape the immune response.

PMID:34817309 | DOI:10.1080/17460441.2022.2005025

Adv Sci (Weinh). 2021 Nov 23:e2104051. doi: 10.1002/advs.202104051. Online ahead of print.

ABSTRACT

Toll-like receptor (TLR) activation in macrophages plays a critical role in the pathogenesis of acute lung injury (ALI). While TLR inhibition is a promising strategy to control the overwhelming inflammation in ALI, there still lacks effective TLR inhibitors for clinical uses to date. A unique class of peptide-coated gold nanoparticles (GNPs) is previously discovered, which effectively inhibited TLR signaling and protected mice from lipopolysaccharide (LPS)-induced ALI. To fast translate such a discovery into potential clinical applicable nanotherapeutics, herein an elegant strategy of "nano-enabled drug repurposing" with "nano-targeting" is introduced to empower the existing drugs for new uses. Combining transcriptome sequencing with Connectivity Map analysis, it is identified that the proton pump inhibitors (PPIs) share similar mechanisms of action to the discovered GNP-based TLR inhibitor. It is confirmed that PPIs (including omeprazole) do inhibit endosomal TLR signaling and inflammatory responses in macrophages and human peripheral blood mononuclear cells, and exhibits anti-inflammatory activity in an LPS-induced ALI mouse model. The omeprazole is then formulated into a nanoform with liposomes to enhance its macrophage targeting ability and the therapeutic efficacy in vivo. This research provides a new translational strategy of nano-enabled drug repurposing to translate bioactive nanoparticles into clinically used drugs and targeted nano-therapeutics for ALI.

PMID:34816630 | DOI:10.1002/advs.202104051

J Mol Struct. 2021 Nov 19:131920. doi: 10.1016/j.molstruc.2021.131920. Online ahead of print.

ABSTRACT

A new coronavirus strain called as SARS-CoV-2 has emerged from Wuhan, China in late 2019 and it caused a worldwide pandemic in a few months. After the Second World War, it is the biggest calamity observed as there is no specific US Food and Drugs Administration (USFDA) approved drug or vaccine available globally for the treatment. Several clinical trials are ongoing for therapeutic alternatives, however with little success rate. Considering that the time is crucial, the drug repurposing and data obtained from in silico models are one of the most important approaches to identify possible lead inhibitors against SARS-CoV-2. More recently, the Direct Acting Antivirals (DAAs) are emerged as the most promising drugs to control viral infection. The Main Protease (Mpro), a key enzyme in the SARS-CoV-2 replication cycle, is found close homolog to the Hepatitis C Virus (HCV) protease and could be susceptible of blocking its activity by DAAs. In the current study, the DAAs were investigated as antivirals using structure based computational approach against Mpro of SARS-CoV-2 to propose them as new therapeutics. In total, 20 DAAs of HCV, including a reference compound O6K were docked against Mpro. The docked structures were examined and resulted in the identification of six highly promising DAAs i.e. beclabuvir, elbasvir, paritaprevir, grazoprevir, simeprevir, and asunapevir exhibiting high theoretical binding affinity to Mpro from SARS-CoV-2 in comparison to other DAAs. Furthermore, the post docking analysis revealed that Cys145, Glu166, His163, Thr26, His41, and Met165 played potential role for the binding of these DAAs inside binding site of Mpro. Furthermore, the correlation between binding energies were found in accord with the results from the reported IC50s for some DAAs. Overall, the current study provides insight to combat COVID-19 using FDA-approved DAAs as repurposed drugs.

PMID:34815586 | PMC:PMC8602124 | DOI:10.1016/j.molstruc.2021.131920

Biomed Pharmacother. 2021 Nov 20;145:112436. doi: 10.1016/j.biopha.2021.112436. Online ahead of print.

ABSTRACT

Disruption or loss of oligodendrocytes (OLs) and myelin has devastating effects on CNS function and integrity, which occur in diverse neurological disorders, including Multiple Sclerosis (MS), Alzheimer's disease and neuropsychiatric disorders. Hence, there is a need to develop new therapies that promote oligodendrocyte regeneration and myelin repair. A promising approach is drug repurposing, but most agents have potentially contrasting biological actions depending on the cellular context and their dose-dependent effects on intracellular pathways. Here, we have used a combined systems biology and neurobiological approach to identify compounds that exert positive and negative effects on oligodendroglia, depending on concentration. Notably, next generation pharmacogenomic analysis identified the PI3K/Akt modulator LY294002 as the most highly ranked small molecule with both pro- and anti-oligodendroglial concentration-dependent effects. We validated these in silico findings using multidisciplinary approaches to reveal a profoundly bipartite effect of LY294002 on the generation of OPCs and their differentiation into myelinating oligodendrocytes in both postnatal and adult contexts. Finally, we employed transcriptional profiling and signalling pathway activity assays to determine cell-specific mechanisms of action of LY294002 on oligodendrocytes and resolve optimal in vivo conditions required to promote myelin repair. These results demonstrate the power of multidisciplinary strategies in determining the therapeutic potential of small molecules in neurodegenerative disorders.

PMID:34813998 | DOI:10.1016/j.biopha.2021.112436

J Med Chem. 2021 Nov 23. doi: 10.1021/acs.jmedchem.1c01547. Online ahead of print.

ABSTRACT

To fight COVID-19, much effort has been directed toward in vitro drug repurposing. Here, we investigate the impact of colloidal aggregation, a common screening artifact, in these repurposing campaigns. We tested 56 drugs reported as active in biochemical assays for aggregation by dynamic light scattering and by detergent-based enzyme counter screening; 19 formed colloids at concentrations similar to their literature IC50's, and another 14 were problematic. From a common repurposing library, we further selected another 15 drugs that had physical properties resembling known aggregators, finding that six aggregated at micromolar concentrations. This study suggests not only that many of the drugs repurposed for SARS-CoV-2 in biochemical assays are artifacts but that, more generally, at screening-relevant concentrations, even drugs can act artifactually via colloidal aggregation. Rapid detection of these artifacts will allow the community to focus on those molecules that genuinely have potential for treating COVID-19.

PMID:34812616 | DOI:10.1021/acs.jmedchem.1c01547

Mol Inform. 2021 Nov 23:e2100190. doi: 10.1002/minf.202100190. Online ahead of print.

ABSTRACT

Current pandemics propelled research efforts in unprecedented fashion, primarily triggering computational efforts towards new vaccine and drug development as well as drug repurposing. There is an urgent need to design novel drugs with targeted biological activity and minimum adverse reactions that may be useful to manage viral outbreaks. Hence an attempt has been made to develop Machine Learning based predictive models that can be used to assess whether a compound has the potency to be antiviral or not. To this end, a set of 2358 antiviral compounds were compiled from the CAS COVID-19 antiviral SAR dataset whose activity was reported based on IC50 value. A total 1157 two-dimensional molecular descriptors were computed among which, the most highly correlated descriptors were selected using Tree-based, Correlation-based and Mutual information-based feature selection methods. Seven Machine Learning algorithms i. e., Random Forest, XGBoost, Support Vector Machine, KNN, Decision Tree, MLP Classifier and Logistic Regression were benchmarked. The best performance was achieved by the models developed using Random Forest and XGBoost algorithms in all the feature selection methods. The maximum predictive accuracy of both these models was 88 % with internal validation. Whereas, with an external dataset, a maximum accuracy of 93.10 % for XGBoost and 100 % for Random Forest based model was achievable. Furthermore, the study demonstrated scaffold analysis of the molecules as a pragmatic approach to explore the importance of structurally diverse compounds in data driven studies.

PMID:34811938 | DOI:10.1002/minf.202100190

Nat Commun. 2021 Nov 22;12(1):6775. doi: 10.1038/s41467-021-27137-3.

ABSTRACT

Prediction of drug-target interactions (DTI) plays a vital role in drug development in various areas, such as virtual screening, drug repurposing and identification of potential drug side effects. Despite extensive efforts have been invested in perfecting DTI prediction, existing methods still suffer from the high sparsity of DTI datasets and the cold start problem. Here, we develop KGE_NFM, a unified framework for DTI prediction by combining knowledge graph (KG) and recommendation system. This framework firstly learns a low-dimensional representation for various entities in the KG, and then integrates the multimodal information via neural factorization machine (NFM). KGE_NFM is evaluated under three realistic scenarios, and achieves accurate and robust predictions on four benchmark datasets, especially in the scenario of the cold start for proteins. Our results indicate that KGE_NFM provides valuable insight to integrate KG and recommendation system-based techniques into a unified framework for novel DTI discovery.

PMID:34811351 | DOI:10.1038/s41467-021-27137-3

Drug Discov Today. 2021 Nov 19:S1359-6446(21)00494-3. doi: 10.1016/j.drudis.2021.11.013. Online ahead of print.

ABSTRACT

Autophagy is a multistep degradation pathway involving the lysosome, which supports nutrient reuse and metabolic balance, and has been implicated as a process that regulates cancer genesis and development. Targeting tumors by regulating autophagy has become a therapeutic strategy of interest. Drugs with other indications can have antitumor activity by modulating autophagy, providing a shortcut to developing novel antitumor drugs (i.e., drug repurposing/repositioning), as successfully performed for chloroquine (CQ); an increasing number of repurposed drugs have since advanced into clinical trials. In this review, we describe the application of different drug-repurposing approaches in autophagy for the treatment of cancer and focus on repurposing drugs that target autophagy to treat malignant neoplasms.

PMID:34808390 | DOI:10.1016/j.drudis.2021.11.013