Deep Learning-Based construction of a Drug-Like compound database and its application in virtual screening of HsDHODH inhibitors.

The process of virtual screening relies heavily on the databases, but it is disadvantageous to conduct virtual screening based on commercial databases with patent-protected compounds, high compound toxicity and side effects. Therefore, this paper utilizes generative recurrent neural networks (RNN) containing long short-term memory (LSTM) cells to learn the properties of drug compounds in the DrugBank, aiming to obtain a new and virtual screening compounds database with drug-like properties. Ultimately, a compounds database consisting of 26,316 compounds is obtained by this method. To evaluate the potential of this compounds database, a series of tests are performed, including chemical space, ADME properties, compound fragmentation, and synthesizability analysis. As a result, it is proved that the database is equipped with good drug-like properties and a relatively new backbone, its potential in virtual screening is further tested. Finally, a series of seedling compounds with completely new backbones are obtained through docking and binding free energy calculations.

First report on chemometrics-driven multilayered lead prioritization in addressing oxysterol-mediated overexpression of G protein-coupled receptor 183.

Contemporary research has convincingly demonstrated that upregulation of G protein-coupled receptor 183 (GPR183), orchestrated by its endogenous agonist, 7α,25-dihydroxyxcholesterol (7α,25-OHC), leads to the development of cancer, diabetes, multiple sclerosis, infectious, and inflammatory diseases. A recent study unveiled the cryo-EM structure of 7α,25-OHC bound GPR183 complex, presenting an untapped opportunity for computational exploration of potential GPR183 inhibitors, which served as our inspiration for the current work. A predictive and validated two-dimensional QSAR model using genetic algorithm (GA) and multiple linear regression (MLR) on experimental GPR183 inhibition data was developed. QSAR study highlighted that structural features like dissimilar electronegative atoms, quaternary carbon atoms, and CH2RX fragment (X: heteroatoms) influence positively, while the existence of oxygen atoms with a topological separation of 3, negatively affects GPR183 inhibitory activity. Post assessment of true external set prediction capability, the MLR model was deployed to screen 12,449 DrugBank compounds, followed by a screening pipeline involving molecular docking, druglikeness, ADMET, protein-ligand stability assessment using deep learning algorithm, molecular dynamics, and molecular mechanics. The current findings strongly evidenced DB05790 as a potential lead for prospective interference of oxysterol-mediated GPR183 overexpression, warranting further in vitro and in vivo validation.

Identifying potential anti-metastasis drugs for prostate cancer through integrative bioinformatics analysis and compound library screening.

BACKGROUND: Metastasis poses the greatest threat to the lives of individuals with prostate cancer. Therefore, it is imperative to identify the underlying mechanism driving metastasis. Doing so would facilitate the detection of new diagnostic biomarkers and the advancement of treatment options for patients. METHODS: Metastasis-related modules were identified through weighted gene co-expression network analysis based on microarray GSE6919. Hub genes were confirmed by quantitative real-time PCR across different prostate cell lines and clinic samples. Pivotal genes were determined through integration of RNA and transcription factor-target associated interactions. To predict drugs with potential to suppress tumor metastasis, we applied molecular networks using the DrugBank database. Drug repositioning analysis and confirmation of drug screen were conducted using the compound library. Confirmation of selective cytotoxicity of cupric oxide was carried out via invasion, transwell and apoptosis assays. RESULTS: We identified five metastasis-related modules. Of these modules, two were identified to represent core dysfunction modules in which five hub genes were determined for each module. Five of these 10 genes correlating with prostate cancer progression. Furthermore, our analysis revealed that there are 36 drugs with the potential to be active against tumor metastasis. Finally, we identified four compounds that have not previously been reported to have any association with cancer therapy. Of these, cupric oxide was determined to have the best chemotherapeutic potential in treating prostate cancer metastasis. CONCLUSIONS: By combining bioinformatics methods with compound library screening, this study proposes a valuable approach to drug discovery. Cupric oxide showed the potential in the treatment of prostate cancer metastasis and deserves further study.

Combined in silico strategy for repurposing DrugBank entries towards introducing potential anti-SARS-CoV-2 drugs.

The emergence of severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) from China in December 2019 led to the coronavirus disorder 2019 pandemic, which has affected tens of millions of humans worldwide. Various in silico research via bio-cheminformatics methods were performed to examine the efficiency of a range of repurposed approved drugs with a new role as anti-SARS-CoV-2 drugs. The current study has been performed to screen the approved drugs in the DrugBank database based on a novel bioinformatics/cheminformatics strategy to repurpose available approved drugs towards introducing them as a possible anti-SARS-CoV-2 drug. As a result, 96 approved drugs with the best docking scores passed through several relevant filters were presented as the candidate drugs with potential novel antiviral activities against the SARS-CoV-2 virus.

Development and Validation of an Explainable Machine Learning-Based Prediction Model for Drug-Food Interactions from Chemical Structures.

Possible drug-food constituent interactions (DFIs) could change the intended efficiency of particular therapeutics in medical practice. The increasing number of multiple-drug prescriptions leads to the rise of drug-drug interactions (DDIs) and DFIs. These adverse interactions lead to other implications, e.g., the decline in medicament's effect, the withdrawals of various medications, and harmful impacts on the patients' health. However, the importance of DFIs remains underestimated, as the number of studies on these topics is constrained. Recently, scientists have applied artificial intelligence-based models to study DFIs. However, there were still some limitations in data mining, input, and detailed annotations. This study proposed a novel prediction model to address the limitations of previous studies. In detail, we extracted 70,477 food compounds from the FooDB database and 13,580 drugs from the DrugBank database. We extracted 3780 features from each drug-food compound pair. The optimal model was eXtreme Gradient Boosting (XGBoost). We also validated the performance of our model on one external test set from a previous study which contained 1922 DFIs. Finally, we applied our model to recommend whether a drug should or should not be taken with some food compounds based on their interactions. The model can provide highly accurate and clinically relevant recommendations, especially for DFIs that may cause severe adverse events and even death. Our proposed model can contribute to developing more robust predictive models to help patients, under the supervision and consultants of physicians, avoid DFI adverse effects in combining drugs and foods for therapy.

Targeting the I7L Protease: A Rational Design for Anti-Monkeypox Drugs?

The latest monkeypox virus outbreak in 2022 showcased the potential threat of this viral zoonosis to public health. The lack of specific treatments against this infection and the success of viral protease inhibitors-based treatments against HIV, Hepatitis C, and SARS-CoV-2, brought the monkeypox virus I7L protease under the spotlight as a potential target for the development of specific and compelling drugs against this emerging disease. In the present work, the structure of the monkeypox virus I7L protease was modeled and thoroughly characterized through a dedicated computational study. Furthermore, structural information gathered in the first part of the study was exploited to virtually screen the DrugBank database, consisting of drugs approved by the Food and Drug Administration (FDA) and clinical-stage drug candidates, in search for readily repurposable compounds with similar binding features as TTP-6171, the only non-covalent I7L protease inhibitor reported in the literature. The virtual screening resulted in the identification of 14 potential inhibitors of the monkeypox I7L protease. Finally, based on data collected within the present work, some considerations on developing allosteric modulators of the I7L protease are reported.

Discovery of potent Covid-19 main protease inhibitors using integrated drug-repurposing strategy.

The emergence and rapid spreading of novel SARS-CoV-2 across the globe represent an imminent threat to public health. Novel antiviral therapies are urgently needed to overcome this pandemic. Given the significant role of the main protease of Covid-19 for virus replication, we performed a drug-repurposing study using the recently deposited main protease structure, 6LU7. For instance, pharmacophore- and e-pharmacophore-based hypotheses such as AARRH and AARR, respectively, were developed using available small molecule inhibitors and utilized in the screening of the DrugBank repository. Further, a hierarchical docking protocol was implemented with the support of the Glide algorithm. The resultant compounds were then examined for their binding free energy against the main protease of Covid-19 by means of the Prime-MM/GBSA algorithm. Most importantly, the machine learning-based AutoQSAR algorithm was used to predict the antiviral activities of resultant compounds. The hit molecules were also examined for their drug-likeness and toxicity parameters through the QikProp algorithm. Finally, the hit compounds activity against the main protease was validated using molecular dynamics simulation studies. Overall, the present analysis yielded two potential inhibitors (DB02986 and DB08573) that are predicted to bind with the main protease of Covid-19 better than currently used drug molecules such as N3 (cocrystallized native ligand), lopinavir, and ritonavir.

Prediction of adverse drug reactions based on knowledge graph embedding.

BACKGROUND: Adverse drug reactions (ADRs) are an important concern in the medication process and can pose a substantial economic burden for patients and hospitals. Because of the limitations of clinical trials, it is difficult to identify all possible ADRs of a drug before it is marketed. We developed a new model based on data mining technology to predict potential ADRs based on available drug data. METHOD: Based on the Word2Vec model in Nature Language Processing, we propose a new knowledge graph embedding method that embeds drugs and ADRs into their respective vectors and builds a logistic regression classification model to predict whether a given drug will have ADRs. RESULT: First, a new knowledge graph embedding method was proposed, and comparison with similar studies showed that our model not only had high prediction accuracy but also was simpler in model structure. In our experiments, the AUC of the classification model reached a maximum of 0.87, and the mean AUC was 0.863. CONCLUSION: In this paper, we introduce a new method to embed knowledge graph to vectorize drugs and ADRs, then use a logistic regression classification model to predict whether there is a causal relationship between them. The experiment showed that the use of knowledge graph embedding can effectively encode drugs and ADRs. And the proposed ADRs prediction system is also very effective.

In Silico Screening of the DrugBank Database to Search for Possible Drugs against SARS-CoV-2.

Coronavirus desease 2019 (COVID-19) is responsible for more than 1.80 M deaths worldwide. A Quantitative Structure-Activity Relationships (QSAR) model is developed based on experimental pIC50 values reported for a structurally diverse dataset. A robust model with only five descriptors is found, with values of R2 = 0.897, Q2LOO = 0.854, and Q2ext = 0.876 and complying with all the parameters established in the validation Tropsha's test. The analysis of the applicability domain (AD) reveals coverage of about 90% for the external test set. Docking and molecular dynamic analysis are performed on the three most relevant biological targets for SARS-CoV-2: main protease, papain-like protease, and RNA-dependent RNA polymerase. A screening of the DrugBank database is executed, predicting the pIC50 value of 6664 drugs, which are IN the AD of the model (coverage = 79%). Fifty-seven possible potent anti-COVID-19 candidates with pIC50 values > 6.6 are identified, and based on a pharmacophore modelling analysis, four compounds of this set can be suggested as potent candidates to be potential inhibitors of SARS-CoV-2. Finally, the biological activity of the compounds was related to the frontier molecular orbitals shapes.

From Riluzole to Dexpramipexole via Substituted-Benzothiazole Derivatives for Amyotrophic Lateral Sclerosis Disease Treatment: Case Studies.

The 1,3-benzothiazole (BTZ) ring may offer a valid option for scaffold-hopping from indole derivatives. Several BTZs have clinically relevant roles, mainly as CNS medicines and diagnostic agents, with riluzole being one of the most famous examples. Riluzole is currently the only approved drug to treat amyotrophic lateral sclerosis (ALS) but its efficacy is marginal. Several clinical studies have demonstrated only limited improvements in survival, without benefits to motor function in patients with ALS. Despite significant clinical trial efforts to understand the genetic, epigenetic, and molecular pathways linked to ALS pathophysiology, therapeutic translation has remained disappointingly slow, probably due to the complexity and the heterogeneity of this disease. Many other drugs to tackle ALS have been tested for 20 years without any success. Dexpramipexole is a BTZ structural analog of riluzole and was a great hope for the treatment of ALS. In this review, as an interesting case study in the development of a new medicine to treat ALS, we present the strategy of the development of dexpramipexole, which was one of the most promising drugs against ALS.

Updates on drug-target network; facilitating polypharmacology and data integration by growth of DrugBank database.

Network pharmacology elucidates the relationship between drugs and targets. As the identified targets for each drug increases, the corresponding drug-target network (DTN) evolves from solely reflection of the pharmaceutical industry trend to a portrait of polypharmacology. The aim of this study was to evaluate the potentials of DrugBank database in advancing systems pharmacology. We constructed and analyzed DTN from drugs and targets associations in the DrugBank 4.0 database. Our results showed that in bipartite DTN, increased ratio of identified targets for drugs augmented density and connectivity of drugs and targets and decreased modular structure. To clear up the details in the network structure, the DTNs were projected into two networks namely, drug similarity network (DSN) and target similarity network (TSN). In DSN, various classes of Food and Drug Administration-approved drugs with distinct therapeutic categories were linked together based on shared targets. Projected TSN also showed complexity because of promiscuity of the drugs. By including investigational drugs that are currently being tested in clinical trials, the networks manifested more connectivity and pictured the upcoming pharmacological space in the future years. Diverse biological processes and protein-protein interactions were manipulated by new drugs, which can extend possible target combinations. We conclude that network-based organization of DrugBank 4.0 data not only reveals the potential for repurposing of existing drugs, also allows generating novel predictions about drugs off-targets, drug-drug interactions and their side effects. Our results also encourage further effort for high-throughput identification of targets to build networks that can be integrated into disease networks.

Quo vadis G protein-coupled receptor ligands? A tool for analysis of the emergence of new groups of compounds over time.

Exponential growth in the number of compounds with experimentally verified activity towards particular target has led to the emergence of various databases gathering data on biological activity. In this study, the ligands of family A of the G Protein-Coupled Receptors that are collected in the ChEMBL database were examined, and special attention was given to serotonin receptors. Sets of compounds were examined in terms of their appearance over time, they were mapped to the chemical space of drugs deposited in DrugBank, and the emergence of structurally new clusters of compounds was indicated. In addition, a tool for detailed analysis of the obtained visualizations was prepared and made available online at http://chem.gmum.net/vischem, which enables the investigation of chemical structures while referring to particular data points depicted in the figures and changes in compounds datasets over time.

Identification of Novel Inhibitors of Organic Anion Transporting Polypeptides 1B1 and 1B3 (OATP1B1 and OATP1B3) Using a Consensus Vote of Six Classification Models.

Organic anion transporting polypeptides 1B1 and 1B3 are transporters selectively expressed on the basolateral membrane of the hepatocyte. Several studies reveal that they are involved in drug-drug interactions, cancer, and hyperbilirubinemia. In this study, we developed a set of classification models for OATP1B1 and 1B3 inhibition based on more than 1700 carefully curated compounds from literature, which were validated via cross-validation and by use of an external test set. After combining several sets of descriptors and classifiers, the 6 best models were selected according to their statistical performance and were used for virtual screening of DrugBank. Consensus scoring of the screened compounds resulted in the selection and purchase of nine compounds as potential dual inhibitors and of one compound as potential selective OATP1B3 inhibitor. Biological testing of the compounds confirmed the validity of the models, yielding an accuracy of 90% for OATP1B1 and 80% for OATP1B3, respectively. Moreover, at least half of the new identified inhibitors are associated with hyperbilirubinemia or hepatotoxicity, implying a relationship between OATP inhibition and these severe side effects.

Identification of Novel PI3Kα Inhibitor Against Gastric Cancer: QSAR-, Molecular Docking-, and Molecular Dynamics Simulation-Based Analysis.

Gastric cancer (GC) is a malignant tumor with global incidence and death ranking fifth and fourth, respectively. GC patients nevertheless have a poor prognosis despite the effectiveness of more advanced chemotherapy and surgical treatment options. The second most frequently mutated gene in GC is PI3Kalpha, a confirmed oncogene that results in abnormal PI3K/AKT/mTOR signaling, causing enhanced translation, proliferation, and survival, and is mutated in 7-25% of GC patients. The protein PI3Kalpha was targeted in the present study by utilizing machine learning (ML), molecular docking, and simulation. A total of 9214 molecules from the DrugBank database were chosen for the first screening. A training set for 6770 compounds tested against PI3Kalpha was assessed to create a quantitative structure-activity relationship-based machine learning model using five different classification algorithms: random forest, random tree, J48 pruned tree, decision stump, and REPTree. Furthermore, consideration was given to the random forest classifier for screening based on its performance index (Kappa statistics, ROC, and MCC). Overall, 1539 of the 9214 drug bank compounds were predicted to be active. Thereafter, three pharmacological filters, Lipinski's rule, Ghose filter, and Veber rule, were applied to test the drug-like properties of the screened compounds. Twenty-six of 1593 compounds showed excellent drug-like properties and were further considered for molecular docking. Thereafter, two compounds were screened as hits because they possessed the molecular docked position with the lowest binding energy and an excellent bonding profile. The binding stability of the selected compounds was further assessed through molecular dynamics simulations for up to 100 ns. Furthermore, compound 1-(3-(2,4-dimethylthiazol-5-YL)-4-oxo-2,4-dihydroindeno[1,2-C]pyrazol-5-YL)-3-(4-methylpiperazin-1-YL) urea was selected as a potential hit in the final screening by analyzing a number of parameters, including the Rg, RMSD, RMSF, H bonding, and SASA profile. Therefore, we conclude that compound 1-(3-(2, 4-dimethylthiazol-5-YL)-4-oxo-2,4-dihydroindeno[1,2-C]pyrazol-5-YL)-3-(4-methylpiperazin-1-YL) urea has efficient inhibitory potential against PI3Kalpha protein and could be utilized for the development of effective drugs against GC.

Computational approaches for lead compound discovery in dipeptidyl peptidase-4 inhibition using machine learning and molecular dynamics techniques.

The prediction of possible lead compounds from already-known drugs that may present DPP-4 inhibition activity imply a advantage in the drug development in terms of time and cost to find alternative medicines for the treatment of Type 2 Diabetes Mellitus (T2DM). The inhibition of dipeptidyl peptidase-4 (DPP-4) has been one of the most explored strategies to develop potential drugs against this condition. A diverse dataset of molecules with known experimental inhibitory activity against DPP-4 was constructed and used to develop predictive models using different machine-learning algorithms. Model M36 is the most promising one based on the internal and external performance showing values of Q2CV = 0.813, and Q2EXT = 0.803. The applicability domain evaluation and Tropsha's analysis were conducted to validate M36, indicating its robustness and accuracy in predicting pIC50 values for organic molecules within the established domain. The physicochemical properties of the ligands, including electronegativity, polarizability, and van der Waals volume were relevant to predict the inhibition process. The model was then employed in the virtual screening of potential DPP4 inhibitors, finding 448 compounds from the DrugBank and 9 from DiaNat with potential inhibitory activity. Molecular docking and molecular dynamics simulations were used to get insight into the ligand-protein interaction. From the screening and the favorable molecular dynamic results, several compounds including Skimmin (pIC50 = 3.54, Binding energy = -8.86 kcal/mol), bergenin (pIC50 = 2.69, Binding energy = -13.90 kcal/mol), and DB07272 (pIC50 = 3.97, Binding energy = -25.28 kcal/mol) seem to be promising hits to be tested and optimized in the treatment of T2DM. This results imply a important reduction in cost and time on the application of this drugs because all the information about the its metabolism is already available.

A computational strategy for systematic virtual screening of plasmodium falciparum heme detoxification protein inhibitors from the Drugbank database.

Antimalarial drug resistance poses one of the greatest threats to malaria treatment, resulting in increased morbidity and mortality. Heme Detoxification Protein (HDP) is among the essential hemoglobinases of P. falciparum (Pf), a vital molecular target for the treatment of malaria. In this study, we utilized the virtual screening workflow tool of the Schrodinger suite to find the best hits for the PfHDP from the DrugBank library. A total of 14,942 compounds were identified against the PfHDP. The top compounds with the highest docking scores and least energy scores were subjected to molecular simulations for 500 nanosecond to check the stability of the protein-drug complexes. The top three DrugBank compounds were found to be stable over 500 ns, namely DB09298 (silibinin), DB07426 (1-Hydroxy-2-(1,1':3',1''-Terphenyl-3-Yloxy) Ethane-1,1-Diyl] Bis (Phosphonic Acid), and DB07410 [(2-(3-Dibenzofuran-4-yl-Phenyl)-1-Hydroxy-1-Phosphono-Ethyl]-Phosphonic Acid). Overall analysis suggests that the top three compounds, DB09298, DB07426, and DB07410, have good stability for 500 ns. Their scaffolds can be used to design and develop new analogs of the target HDP protein. Silibinin, the anti-cancer drug, was found to be highly stable for the entire simulation period as compared to the other compounds. DB07426 shows its therapeutic effect on bones, especially in the treatment of osteoporosis, and DB07410 has anti-tumor, antibacterial, anti-oxidative, and anti-viral activities. All three compounds can be considered for repurposing as antimalarial drugs to evaluate the binding capacity or inhibition potential of these compounds. Further in-vivo and in-vitro analysis against the PfHDP protein should be conducted.Communicated by Ramaswamy H. Sarma.

Identification and analysis of mitochondria-related central genes in steroid-induced osteonecrosis of the femoral head, along with drug prediction.

Purpose: Steroid-induced osteonecrosis of the femoral head (SONFH) is a refractory orthopedic hip joint disease that primarily affects middle-aged and young individuals. SONFH may be caused by ischemia and hypoxia of the femoral head, where mitochondria play a crucial role in oxidative reactions. Currently, there is limited literature on whether mitochondria are involved in the progression of SONFH. Here, we aim to identify and validate key potential mitochondrial-related genes in SONFH through bioinformatics analysis. This study aims to provide initial evidence that mitochondria play a role in the progression of SONFH and further elucidate the mechanisms of mitochondria in SONFH. Methods: The GSE123568 mRNA expression profile dataset includes 10 non-SONFH (non-steroid-induced osteonecrosis of the femoral head) samples and 30 SONFH samples. The GSE74089 mRNA expression profile dataset includes 4 healthy samples and 4 samples with ischemic necrosis of the femoral head. Both datasets were downloaded from the Gene Expression Omnibus (GEO) database. The mitochondrial-related genes are derived from MitoCarta3.0, which includes data for all 1136 human genes with high confidence in mitochondrial localization based on integrated proteomics, computational, and microscopy approaches. By intersecting the GSE123568 and GSE74089 datasets with a set of mitochondrial-related genes, we screened for mitochondrial-related genes involved in SONFH. Subsequently, we used the good Samples Genes method in R language to remove outlier genes and samples in the GSE123568 dataset. We further used WGCNA to construct a scale-free co-expression network and selected the hub gene set with the highest connectivity. We then intersected this gene set with the previously identified mitochondrial-related genes to select the genes with the highest correlation. A total of 7 mitochondrial-related genes were selected. Next, we performed Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis on the selected mitochondrial-related genes using R software. Furthermore, we performed protein network analysis on the differentially expressed proteins encoded by the mitochondrial genes using STRING. We used the GSEA software to group the genes within the gene set in the GSE123568 dataset based on their coordinated changes and evaluate their impact on phenotype changes. Subsequently, we grouped the samples based on the 7 selected mitochondrial-related genes using R software and observed the differences in immune cell infiltration between the groups. Finally, we evaluated the prognostic significance of these features in the two datasets, consisting of a total of 48 samples, by integrating disease status and the 7 gene features using the cox method in the survival R package. We performed ROC analysis using the roc function in the pROC package and evaluated the AUC and confidence intervals using the ci function to obtain the final AUC results. Results: Identification and analysis of 7 intersecting DEGs (differentially expressed genes) were obtained among peripheral blood, cartilage samples, hub genes, and mitochondrial-related genes. These 7 DEGs include FTH1, LACTB, PDK3, RAB5IF, SOD2, and SQOR, all of which are upregulated genes with no intersection in the downregulated gene set. Subsequently, GO and KEGG pathway enrichment analysis revealed that the upregulated DEGs are primarily involved in processes such as oxidative stress, release of cytochrome C from mitochondria, negative regulation of intrinsic apoptotic signaling pathway, cell apoptosis, mitochondrial metabolism, p53 signaling pathway, and NK cell-mediated cytotoxicity. GSEA also revealed enriched pathways associated with hub genes. Finally, the diagnostic value of these key genes for hormone-related ischemic necrosis of the femoral head (SONFH) was confirmed using ROC curves. Conclusion: BID, FTH1, LACTB, PDK3, RAB5IF, SOD2, and SQOR may serve as potential diagnostic mitochondrial-related biomarkers for SONFH. Additionally, they hold research value in investigating the involvement of mitochondria in the pathogenesis of ischemic necrosis of the femoral head.

First report on ecotoxicological QSTR and i-QSTR modeling for the prediction of acute ecotoxicity of diverse organic chemicals against three protozoan species.

The recent years have witnessed an upsurge of interest to assess the toxicity of organic chemicals exhibiting harmful impacts on the environment. In this investigation, we have developed regression-based quantitative structure-toxicity relationship (QSTR) models against three protozoan species (Entosiphon sulcantum, Uronema parduczi, and Chilomonas paramecium) using three sets of descriptor combinations such as ETA indices only, non-ETA descriptors only, and both ETA and non-ETA descriptors to examine the key structural features that determine the toxic properties of protozoa. The interspecies QSTR models (i-QSTRs) were also generated for efficient data gap-filling of toxicity databases. The statistical results of the validated models in terms of both internal and external validation metrics suggested that the models are statistically reliable and robust. Additionally, using these validated models, we screened the DrugBank database containing 11,300 pharmaceuticals for assessing the ecotoxicological properties. The features appearing in the models suggested that non-polar characteristics, electronegativity, hydrogen bonding, π-π, and hydrophobic interactions are responsible for chemical toxicity toward protozoan. The validated models may be utilized for the development of eco-friendly drugs & chemicals, data gap-filling of toxicity databases for regulatory purposes and research, as well as to decrease the use of toxic and hazardous chemicals in the environment.

The international clinical trials registry platform (ICTRP): data integrity and the trends in clinical trials, diseases, and drugs.

Introduction: Clinical trials are the gold standard for testing new therapies. Databases like ClinicalTrials.gov provide access to trial information, mainly covering the US and Europe. In 2006, WHO introduced the global ICTRP, aggregating data from ClinicalTrials.gov and 17 other national registers, making it the largest clinical trial platform by June 2019. This study conducts a comprehensive global analysis of the ICTRP database and provides framework for large-scale data analysis, data preparation, curation, and filtering. Materials and methods: The trends in 689,793 records from the ICTRP database (covering trials registered from 1990 to 2020) were analyzed. Records were adjusted for duplicates and mapping of agents to drug classes was performed. Several databases, including DrugBank, MESH, and the NIH Drug Information Portal were used to investigate trends in agent classes. Results: Our novel approach unveiled that 0.5% of the trials we identified were hidden duplicates, primarily originating from the EUCTR database, which accounted for 82.9% of these duplicates. However, the overall number of hidden duplicates within the ICTRP seems to be decreasing. In total, 689 793 trials (478 345 interventional) were registered in the ICTRP between 1990 and 2020, surpassing the count of trials in ClinicalTrials.gov (362 500 trials by the end of 2020). We identified 4 865 unique agents in trials with DrugBank, whereas 2 633 agents were identified with NIH Drug Information Portal data. After the ClinicalTrials.gov, EUCTR had the most trials in the ICTRP, followed by CTRI, IRCT, CHiCTR, and ISRCTN. CHiCTR displayed a significant surge in trial registration around 2015, while CTRI experienced rapid growth starting in 2016. Conclusion: This study highlights both the strengths and weaknesses of using the ICTRP as a data source for analyzing trends in clinical trials, and emphasizes the value of utilizing multiple registries for a comprehensive analysis.

Machine-learning repurposing of DrugBank compounds for opioid use disorder.

Opioid use disorder (OUD) is a chronic and relapsing condition that involves the continued and compulsive use of opioids despite harmful consequences. The development of medications with improved efficacy and safety profiles for OUD treatment is urgently needed. Drug repurposing is a promising option for drug discovery due to its reduced cost and expedited approval procedures. Computational approaches based on machine learning enable the rapid screening of DrugBank compounds, identifying those with the potential to be repurposed for OUD treatment. We collected inhibitor data for four major opioid receptors and used advanced machine learning predictors of binding affinity that fuse the gradient boosting decision tree algorithm with two natural language processing (NLP)-based molecular fingerprints and one traditional 2D fingerprint. Using these predictors, we systematically analyzed the binding affinities of DrugBank compounds on four opioid receptors. Based on our machine learning predictions, we were able to discriminate DrugBank compounds with various binding affinity thresholds and selectivities for different receptors. The prediction results were further analyzed for ADMET (absorption, distribution, metabolism, excretion, and toxicity), which provided guidance on repurposing DrugBank compounds for the inhibition of selected opioid receptors. The pharmacological effects of these compounds for OUD treatment need to be tested in further experimental studies and clinical trials. Our machine learning studies provide a valuable platform for drug discovery in the context of OUD treatment.