Classification of Cyclooxygenase-2 Inhibitors Using Support Vector Machine and Random Forest Methods

Artificial intelligence-based prediction model for the elemental occurrence form of tailings and mine wastes

With the advent of the second industrial revolution, mining and metallurgical processes generate large volumes of tailings and mine wastes (TMW), which worsens global environmental pollution. Studying the occurrence of metal and metalloid elements in TMW is an effective approach to evaluating pollution linked to TMW. However, traditional laboratory-based measurements are complicated and time-consuming; thus, an empirical method is urgently needed that can rapidly and accurately determine elemental occurrence forms. In this study, a model combining Bayesian optimization and random forest (RF) approaches was proposed to predict TMW occurrence forms. To build the RF model, a dataset of 2376 samples was obtained, with mineral composition, elemental properties, and total concentration composition used as inputs and the percentage of occurrence forms as the model output. The correlation coefficient (R), coefficient of determination, mean absolute error, root mean squared error, and root mean squared logarithmic error metrics were used for model evaluation. After Bayesian optimization, the optimal RF model achieved accurate predictive performance, with R values of 0.99 and 0.965 on the training and test sets, respectively. The feature significance was analyzed using feature importance and Shapley additive explanatory values, which revealed that the electronegativity and total concentration of the elements were the two features with the greatest influence on the model output. As the electronegativity of an element increases, its corresponding residual fraction content gradually decreases. This is because the solubility typically increases with the solvent's polarity and electronegativity. Overall, this study proposes an RF model based on the nature of TMW that can rapidly and accurately predict the percentage values of metal and metalloid element occurrence forms in TMW. This method can minimize testing time requirements and help to assess TMW pollution risks, as well as further promote safe TMW management and recycling.

Identification and validation of cuproptosis-related genes for diagnosis and therapy in nonalcoholic fatty liver disease

In recent years, nonalcoholic fatty liver disease (NAFLD) has become a more serious public health issue worldwide. This study strived to investigate the molecular mechanism of pathogenesis of NAFLD and explore promising diagnostic and therapeutic targets for NAFLD. Raw data from GSE130970 were downloaded from the Gene Expression Omnibus database. We used the dataset to analyze the expression levels of cuproptosis-related genes in NAFLD patients and healthy controls to identify the differentially expressed cuproptosis-related genes (DECRGs). The relationship and potential mechanism between DECRGs and clinicopathological factors were examined by enrichment analysis and two consensus clustering methods. We screened key DECRGs based on Random Forest (RF), and then verified the key DECRGs in NAFLD patients, high-fat diet (HFD)-fed mice, and palmitic acid-induced AML12 cells. ROC analysis showed good diagnostic function of DECRGs in normal and NAFLD liver tissue. Two consensus clusters indicated the important role of cuproptosis in the development of NAFLD. We screened for key DECRGs (DLD, DLAT) based on RF and found a close relationship between the DECRGs and clinicopathological factors. We collected clinical blood samples to verify the differences in gene expression levels by qPCR. In addition, we further verified the expression levels of DLD and DLAT in HFD mice and AML12 cells, which showed the same results. This study provides a novel perspective on the pathogenesis of NAFLD. We identified two cuproptosis-related genes that are closely related to NAFLD. These genes may play a significant role in the molecular pathogenesis of NAFLD, which may be useful to make progress in the diagnosis and treatment of NAFLD.

COX2 expression plays a role in spinal cord injury-induced neuropathic pain

BACKGROUND CONTEXT

Elucidating the mechanism of neuropathic pain (NeP) is crucial as it can result in motor dysfunction and negatively impact quality of life in patients with spinal cord injury (SCI). Although it has been reported that cyclooxygenase 2 (COX2) is involved in NeP in rat models of peripheral nerve injury and that COX2 inhibitors can alleviate NeP, these mechanisms after SCI have not been fully investigated.

PURPOSE

The purpose is to investigate whether the thoracic SCI affects the expression of mRNAs for COX1 and COX2 in the lumbar spinal cord, and the effect of COX2 inhibitor on its behavior.

STUDY DESIGN

Male Sprague-Dawley (SD) rats underwent thoracic (T10) spinal cord contusion injury using an Infinite Horizon (IH) impactor device. SCI rats received COX2 inhibitors (50 μg/day) on days 5 and 6 after SCI.

METHODS

Male SD rats underwent T10 laminectomy under mixed anesthesia, and IH impactors were applied to the same site to create a rat SCI model. Rats that underwent only laminectomy were designated as sham. Lumbar spinal cord at the L4-5 level was harvested at 3, 5, 7, 14, and 28 days after SCI, and COX2 and COX1 were quantified by reverse-transcription PCR (RT-PCR). COX2 expression, expression site, and expression time were determined by immunohistochemistry (IHC) and in situ hybridization histochemistry (ISHH) at the same time points. The expression site and time of COX2 expression were also examined at the same time point by ISHH. On 5th and 6th day after SCI, saline and COX2 inhibitor (50 μg/day) were administered into the subarachnoid space as a single dose, and the two groups were compared in terms of mechanical withdrawal latency using the dynamic plantar esthesiometer, which is an automated von Frey-type system.

RESULTS

COX2 was significantly increased at 5 and 7 days after SCI, but no significant difference in COX1 was observed after SCI by RT-PCR. ISHH targeting COX2 showed clear expression of COX2 in spinal cord vascular endothelial cells at 5 and 7 days after SCI. COX2 expression was almost abolished at day 14 and 28. Behavioral experiments showed that pain was significantly improved from day 2 after COX2 inhibitor administration compared to the saline group, with improvement up to day 14 after SCI, but no significant difference was observed after day 21.

CONCLUSIONS

The present findings suggest that thoracic SCI increased COX2 in vascular endothelial cells in the lumbar spinal cord and that the administration of COX2 inhibitor significantly alleviated mechanical hypersensitivity of the hind-paw following the thoracic SCI. Therefore, endothelial cell derived COX2 in the lumbar spinal cord may be involved in the induction of neuropathic pain in the SCI model rats.

CLINICAL SIGNIFICANCE

The findings in the present study regarding the induction of endothelial COX2 and the effect of its inhibitor on the mechanical hypersensitivity suggest that endothelial cell-derived COX2 is one of the focuses for the treatment for neuropathic pain in the acute phase of SCI.

Machine Learning-Guided Discovery of AcrB and MexB Efflux Pump Inhibitors

Multidrug efflux pump is one of the reasons behind the antimicrobial inactivity related to infection caused by Gram-negative pathogens. The inner membrane resistance-nodulation-cell division transporter proteins, AcrB and MexB, in association with outer membrane proteins, TolC and OprM, are responsible for the extrusion of a broad range of substrates, followed by recognizing them. Although various inhibitors were proposed to stop the efflux activity of the transporter protein, none of them had been approved clinically. Our study aims to identify potent inhibitor-like molecules employing supervised classification models trained upon the molecular descriptors of previously known inhibitors. Based on the intrinsic minimum inhibitory concentration (MIC) values of the reported inhibitors, they were classified into highly potent and less potent categories. A total of 10 different classification models were built using various molecular descriptors; among them, support vector machine, Random Forest, AdaBoost, and LightGBM models appeared to deliver promising results with >80% accuracy. These top four models were implemented on a library of 5043 to obtain 8 hit molecules after the multistep filtering process. To assess their activity toward AcrB and MexB, several molecular dynamics simulations of their ligand-bound structures were performed. We also calculated the binding free-energy values and analyzed other structural properties. Mol.3488 of the unknown molecules showed higher binding affinities for both AcrB and MexB. Also, the presence of "pyridopyrimidone" and "benzothiazole" moieties in the molecules and "V"-shaped orientation of ligands inside the deep binding pocket increase the binding affinity, thereby higher inhibitory properties.

Ligand and structure based hierarchical virtual screening cascade for finding novel epidermal growth factor receptor inhibitors

The epidermal growth factor receptor (EGFR) tyrosine kinase plays an important role in tumor formation and growth by mediating cell growth and other physiological processes. Therefore, EGFR is a promising target for the treatment of cancer. In this work, we combined ligand-based and structure-based virtual screening methods to identify novel EGFR inhibitors from a library of more than 103 thousand compounds. We first obtained hundreds of compounds with similar physiochemical properties through 3D molecular shape and electrostatic similarity screening with potent inhibitors AEE788 and Afatinib as queries. Next, we identified compounds with strong binding affinities to the EGFR pocket through molecular docking, which makes good use of the structure information of the receptor. After molecular scaffold analysis, our bioassay confirmed 13 compounds with EGFR inhibitory activity and three compounds had IC50 values below 1000 nM. In addition, we collected 5371 EGFR inhibitors from online databases, and clustered them into 7 groups by K-means method using their ECFP4 fingerprints as input. Each cluster had typical molecular fragments and corresponding activity characteristics, which could guide the design of EGFR inhibitors, and we concluded that the fragments from some of the hits are indicated in the highly active scaffolds.

Discovering the Active Ingredients of Medicine and Food Homologous Substances for Inhibiting the Cyclooxygenase-2 Metabolic Pathway by Machine Learning Algorithms

Cyclooxygenase-2 (COX-2) and microsomal prostaglandin E2 synthase (mPGES-1) are two key targets in anti-inflammatory therapy. Medicine and food homology (MFH) substances have both edible and medicinal properties, providing a valuable resource for the development of novel, safe, and efficient COX-2 and mPGES-1 inhibitors. In this study, we collected active ingredients from 503 MFH substances and constructed the first comprehensive MFH database containing 27,319 molecules. Subsequently, we performed Murcko scaffold analysis and K-means clustering to deeply analyze the composition of the constructed database and evaluate its structural diversity. Furthermore, we employed four supervised machine learning algorithms, including support vector machine (SVM), random forest (RF), deep neural networks (DNNs), and eXtreme Gradient Boosting (XGBoost), as well as ensemble learning, to establish 640 classification models and 160 regression models for COX-2 and mPGES-1 inhibitors. Among them, ModelA_ensemble_RF_1 emerged as the optimal classification model for COX-2 inhibitors, achieving predicted Matthews correlation coefficient (MCC) values of 0.802 and 0.603 on the test set and external validation set, respectively. ModelC_RDKIT_SVM_2 was identified as the best regression model based on COX-2 inhibitors, with root mean squared error (RMSE) values of 0.419 and 0.513 on the test set and external validation set, respectively. ModelD_ECFP_SVM_4 stood out as the top classification model for mPGES-1 inhibitors, attaining MCC values of 0.832 and 0.584 on the test set and external validation set, respectively. The optimal regression model for mPGES-1 inhibitors, ModelF_3D_SVM_1, exhibited predictive RMSE values of 0.253 and 0.35 on the test set and external validation set, respectively. Finally, we proposed a ligand-based cascade virtual screening strategy, which integrated the well-performing supervised machine learning models with unsupervised learning: the self-organized map (SOM) and molecular scaffold analysis. Using this virtual screening workflow, we discovered 10 potential COX-2 inhibitors and 15 potential mPGES-1 inhibitors from the MFH database. We further verified candidates by molecular docking, investigated the interaction of the candidate molecules upon binding to COX-2 or mPGES-1. The constructed comprehensive MFH database has laid a solid foundation for the further research and utilization of the MFH substances. The series of well-performing machine learning models can be employed to predict the COX-2 and mPGES-1 inhibitory capabilities of unknown compounds, thereby aiding in the discovery of anti-inflammatory medications. The COX-2 and mPGES-1 potential inhibitor molecules identified through the cascade virtual screening approach provide insights and references for the design of highly effective and safe novel anti-inflammatory drugs.

Bio-activity prediction of drug candidate compounds targeting SARS-Cov-2 using machine learning approaches

The SARS-CoV-2 3CLpro protein is one of the key therapeutic targets of interest for COVID-19 due to its critical role in viral replication, various high-quality protein crystal structures, and as a basis for computationally screening for compounds with improved inhibitory activity, bioavailability, and ADMETox properties. The ChEMBL and PubChem database contains experimental data from screening small molecules against SARS-CoV-2 3CLpro, which expands the opportunity to learn the pattern and design a computational model that can predict the potency of any drug compound against coronavirus before in-vitro and in-vivo testing. In this study, Utilizing several descriptors, we evaluated 27 machine learning classifiers. We also developed a neural network model that can correctly identify bioactive and inactive chemicals with 91% accuracy, on CheMBL data and 93% accuracy on combined data on both CheMBL and Pubchem. The F1-score for inactive and active compounds was 93% and 94%, respectively. SHAP (SHapley Additive exPlanations) on XGB classifier to find important fingerprints from the PaDEL descriptors for this task. The results indicated that the PaDEL descriptors were effective in predicting bioactivity, the proposed neural network design was efficient, and the Explanatory factor through SHAP correctly identified the important fingertips. In addition, we validated the effectiveness of our proposed model using a large dataset encompassing over 100,000 molecules. This research employed various molecular descriptors to discover the optimal one for this task. To evaluate the effectiveness of these possible medications against SARS-CoV-2, more in-vitro and in-vivo research is required.

A novel FCTF evaluation and prediction model for food efficacy based on association rule mining

Introduction

Food-components-target-function (FCTF) is an evaluation and prediction model based on association rule mining (ARM) and network interaction analysis, which is an innovative exploration of interdisciplinary integration in the food field.

Methods

Using the components as the basis, the targets and functions are comprehensively explored in various databases and platforms under the guidance of the ARM concept. The focused active components, key targets and preferred efficacy are then analyzed by different interaction calculations. The FCTF model is particularly suitable for preliminary studies of medicinal plants in remote and poor areas.

Results

The FCTF model of the local medicinal food Laoxianghuang focuses on the efficacy of digestive system cancers and neurological diseases, with key targets ACE, PTGS2, CYP2C19 and corresponding active components citronellal, trans-nerolidol, linalool, geraniol, α-terpineol, cadinene and α-pinene.

Discussion

Centuries of traditional experience point to the efficacy of Laoxianghuang in alleviating digestive disorders, and our established FCTF model of Laoxianghuang not only demonstrates this but also extends to its possible adjunctive efficacy in neurological diseases, which deserves later exploration. The FCTF model is based on the main line of components to target and efficacy and optimizes the research level from different dimensions and aspects of interaction analysis, hoping to make some contribution to the future development of the food discipline.

A machine learning-based KNIME workflow to predict VEGFR-2 inhibitors

Vascular endothelial growth factors (VEGFs) are specific cytokines involved in angiogenesis and do so via binding to vascular endothelial growth factor receptors (VEGFRs), a type of receptor tyrosine kinase. VEGFs are reported to facilitate angiogenesis in physiological (embryogenesis) and pathological (tumor) conditions. The overexpression of VEGFs and consequently VEGFRs is reported in tumorigenic conditions. Several VEGFR inhibitors currently used as anticancer drugs to prevent angiogenesis are sunitinib, sorafenib, etc. To identify new potential candidates as VEGFR inhibitors, a classification study using a large and diverse dataset of VEGFR inhibitors from the BindingDB database has been conducted. The KNIME platform was used to calculate molecular and fingerprint-based descriptors and several classification algorithms viz. linear regression (LR), k-nearest neighbor (kNN), decision tree (DT), random forest (RF), and gradient boosted tree (GBT) were employed to build the classification model. The model performance was evaluated by accuracy, precision, recall, and F1 score of the test set. The best LR, kNN, DT, RF, and GBT classifiers had the F1 score of 0.81, 0.87, 0.82, 0.87, and 0.87, respectively. The assorted 5120 VEGFR inhibitors were clustered into 10 subsets, and the structural features of each subset were assessed along with the identification of significant fragments in active and inactive compounds. The automated classifier model developed using the KNIME platform could serve as an important platform for screening and designing molecules as VEGFR inhibitors.

Identification of RNA N6-methyladenosine regulation in epilepsy: Significance of the cell death mode, glycometabolism, and drug reactivity

Epilepsy, a functional disease caused by abnormal discharge of neurons, has attracted the attention of neurologists due to its complex characteristics. N6-methyladenosine (m6A) is a reversible mRNA modification that plays essential role in various biological processes. Nevertheless, no previous study has systematically evaluated the role of m6A regulators in epilepsy. Here, using gene expression screening in the Gene Expression Omnibus GSE143272, we identified seven significant m6A regulator genes in epileptic and non-epileptic patients. The random forest (RF) model was applied to the screening, and seven m6A regulators (HNRNPC, WATP, RBM15, YTHDC1, YTHDC2, CBLL1, and RBMX) were selected as the candidate genes for predicting the risk of epilepsy. A nomogram model was then established based on the seven-candidate m6A regulators. Decision curve analysis preliminarily showed that patients with epilepsy could benefit from the nomogram model. The consensus clustering method was performed to divide patients with epilepsy into two m6A patterns (clusterA and clusterB) based on the selected significant m6A regulators. Principal component analysis algorithms were constructed to calculate the m6A score for each sample to quantify the m6A patterns. Patients in clusterB had higher m6A scores than those in clusterA. Furthermore, the patients in each cluster had unique immune cell components and different cell death patterns. Meanwhile, based on the M6A classification, a correlation between epilepsy and glucose metabolism was laterally verified. In conclusion, the m6A regulation pattern plays a vital role in the pathogenesis of epilepsy. The research on m6A regulatory factors will play a key role in guiding the immune-related treatment, drug selection, and identification of metabolism conditions and mechanisms of epilepsy in the future.

Classification models and SAR analysis on HDAC1 inhibitors using machine learning methods

Histone deacetylase (HDAC) 1, a member of the histone deacetylases family, plays a pivotal role in various tumors. In this study, we collected 7313 human HDAC1 inhibitors with bioactivities to form a dataset. Then, the dataset was divided into a training set and a test set using two splitting methods: (1) Kohonen's self-organizing map and (2) random splitting. The molecular structures were represented by MACCS fingerprints, RDKit fingerprints, topological torsions fingerprints and ECFP4 fingerprints. A total of 80 classification models were built by using five machine learning methods, including decision tree (DT), random forest, support vector machine, eXtreme Gradient Boosting and deep neural network. Model 15A_2 built by the XGBoost algorithm based on ECFP4 fingerprints showed the best performance, with an accuracy of 88.08% and an MCC value of 0.76 on the test set. Finally, we clustered the 7313 HDAC1 inhibitors into 31 subsets, and the substructural features in each subset were investigated. Moreover, using DT algorithm we analyzed the structure-activity relationship of HDAC1 inhibitors. It may conclude that some substructures have a significant effect on high activity, such as N-(2-amino-phenyl)-benzamide, benzimidazole, AR-42 analogues, hydroxamic acid with a middle chain alkyl and 4-aryl imidazole with a midchain of alkyl whose α carbon is chiral.

Combined machine learning and pharmacophore based virtual screening approaches to screen for antibiofilm inhibitors targeting LasR of Pseudomonas aeruginosa

Pseudomonas aeruginosa, a virulent pathogen affects patients with cystic fibrosis and nosocomial infections. Quorum sensing (QS) mechanism plays a crucial role in causing these ailments by mediating biofilm formation and expressing virulent genes. A novel approach to circumvent this bacterial infection is by hindering its QS network. Targeting LasR of las system serves beneficial as it holds the top position in QS system cascade. Here, we have integrated machine learning, pharmacophore based virtual screening, molecular docking and simulation studies to look for new leads as inhibitors for LasR. Support vector machine (SVM) learning algorithm was used to generate QSAR models from 66 antagonist dataset. The top three models resulted in correlation coefficient (R²) values of 0.67, 0.86, and 0.91, respectively. The correlation coefficient (R²_test) values on external test set were found to be 0.62, 0.57, and 0.55, respectively. A four-point pharmacophore model was developed. The pharmacophore hypothesis AAAD_1 was used to screen for potential leads against MolPort database in ZincPharmer. The leads which showed predicted pIC50 value of >8.00 by SVM models were subjected to docking analysis that reranked the compounds based on docking scores. Four top leads namely ZINC3851967 N-[3,5-bis(trifluoromethyl)phenyl]-5-tert-butyl-6-chloropyrazine-2-carboxamide, ZINC4024175 4-Amino-1-[(2R,3S,4S,5S)-3,4-dihydroxy-5-(hydroxymethyl)oxolan-2-yl]-2-oxopyrimidine-5-carbonitrile, ZINC2125703 N-[(5-Methoxy-4,7-dimethyl-2-oxo-2H-chromen-3-yl)acetyl]-beta-alanine, and ZINC3851966 N-[3,5-Bis(trifluoromethyl)phenyl]5-tert-butylpyrazine-2-carboxamide were selected. These compounds were checked for its stability by performing a molecular dynamics simulation for a period of 100 ns. The ADME properties of the leads were also determined. Hence, the compounds identified in this study can be used as possible leads for developing a novel inhibitor for LasR.Communicated by Ramaswamy H. Sarma.

Identification of Natural Compounds with Analgesic and Antiinflammatory Properties Using Machine Learning and Molecular Docking Studies

Background:

Natural products have been a rich source of compounds for drug discovery. Usually, compounds obtained from natural sources have little or no side effects, thus searching for new lead compounds from traditionally used plant species is still a rational strategy.

Introduction:

Natural products serve as a useful repository of compounds for new drugs; however, their use has been decreasing, in part because of technical barriers to screening natural products in highthroughput assays against molecular targets. To address this unmet demand, we have developed and validated a high throughput in silico machine learning screening method to identify potential compounds from natural sources.

Methods:

In the current study, three machine learning approaches, including Support Vector Machine (SVM), Random Forest (RF) and Gradient Boosting Machine (GBM) have been applied to develop the classification model. The model was generated using the cyclooxygenase-2 (COX-2) inhibitors reported in the ChEMBL database. The developed model was validated by evaluating the accuracy, sensitivity, specificity, Matthews correlation coefficient and Cohen’s kappa statistic of the test set. The molecular docking study was conducted on AutoDock vina and the results were analyzed in PyMOL.

Results:

The accuracy of the model for SVM, RF and GBM was found to be 75.40 %, 74.97 % and 74.60 %, respectively, which indicates the good performance of the developed model. Further, the model has demonstrated good sensitivity (61.25 % - 68.60 %) and excellent specificity (77.72 %- 81.41 %). Application of the model on the NuBBE database, a repository of natural compounds, led us to identify a natural compound, enhydrin possessing analgesic and anti-inflammatory activities. The ML methods and the molecular docking study suggest that enhydrin likely demonstrates its analgesic and anti-inflammatory actions by inhibiting COX-2.

Conclusion:

Our developed and validated in silico high throughput ML screening methods may assist in identifying drug-like compounds from natural sources.

Analysis of Influencing Factors on the Gas Separation Performance of Carbon Molecular Sieve Membrane Using Machine Learning Technique

Gas separation performance of the carbon molecular sieve (CMS) membrane is influenced by multiple factors including the microstructural characteristics of carbon and gas properties. In this work, the support vector regression (SVR) method as a machine learning technique was applied to the correlation between the gas separation performance, the multiple membrane structure, and gas characteristic factors of the self-manufactured CMS membrane. A simple quantitative index based on the Robeson’s upper bound line, which indicated the gas permeability and selectivity simultaneously, was proposed to measure the gas separation performance of CMS membrane. Based on the calculation results, the inferred key factors affecting the gas permeability of CMS membrane were the fractional free volume (FFV) of the precursor, the average interlayer spacing of graphite-like carbon sheet, and the final carbonization temperature. Moreover, the most influential factors for the gas separation performance were supposed to be the two structural factors of precursor influencing the porosity of CMS membrane, the carbon residue and the FFV, and the ratio of the gas kinetic diameters. The results would be helpful to the structural optimization and the separation performance improvement of CMS membrane.

Discovery of Novel Epidermal Growth Factor Receptor (EGFR) Inhibitors Using Computational Approaches

The epidermal growth factor receptor (EGFR) signaling pathway plays an important role in cell growth, proliferation, differentiation, and other physiological processes, which makes the EGFR a promising target for anticancer therapies. The discovery of novel EGFR inhibitors may provide a solution to the problem of drug resistance. In this work, we performed a ligand-based virtual screening (LBVS) protocol for finding novel EGFR inhibitors from a 5.3 million compound library. First, the 3D shape-based similarity was used to obtain structurally novel EGFR inhibitors. In this study, we tried three queries; two were crystal structures and one was generated from deep generative models of graphs (DGMG). Next, we have built four structure-activity relationship (SAR) models and three quantitative structure-activity relationship (QSAR) models based on an SVM method for further screening of highly active EGFR inhibitors. Experimental validations led to the identification of nine hits out of 18 tested compounds. Among them, hit 1, hit 5, and hit 6 had IC₅₀ values around 80 nM against EGFR whose interactions with EGFR were further investigated by molecular dynamics simulations.