Search

Cefiderocol is a novel siderophore cephalosporin that displays activity against Gram-negative bacteria. To establish cefiderocol susceptibility levels of Acinetobacter baumannii strains from China, we performed susceptibility testing and genomic analyses on 131 clinical isolates. Cefiderocol shows high activity against the strains. The production of PER-1 is the key mechanism of cefiderocol resistance. In silico studies predicted that avibactam and durlobactam could inhibit cefiderocol hydrolysis by PER-1, which was confirmed by determining cefiderocol MICs in combination with inhibitors.

This study aimed to characterize a novel KPC-113 variant from a clinical Pseudomonas aeruginosa isolate R20-14.Genomic DNA of R20-14 was subjected to Illumina and Oxford Nanopore sequencing. The horizontal transmission of plasmid was evaluated with conjugation experiments. Minimum inhibitory concentrations of bacterial strains were obtained using broth microdilution methods. KPC-113 detectability of different carbapenemase detection methods was tested. The kinetic parameters of KPC-113 were compared with those of KPC-2 by a spectrophotometer. Structure modelling and molecular docking of KPC-2 and KPC-113 were performed using Schrödinger.R20-14, a sequence type 3903 multidrug-resistant strain, was resistant to carbapenems and ceftazidime-avibactam (CZA) concurrently. S1-nuclease pulsed-field gel electrophoresis and genomic analysis revealed a blaKPC-113 is a novel KPC variant mediating both CZA resistance and carbapenem resistance. It is of great concern that bla

Although a wide variety of machine learning (ML) algorithms have been utilized to learn quantitative structure–activity relationships (QSARs), there is no agreed single best algorithm for QSAR learning. Therefore, a comprehensive understanding of the performance characteristics of popular ML algorithms used in QSAR learning is highly desirable. In this study, five linear algorithms [linear function Gaussian process regression (linear-GPR), linear function support vector machine (linear-SVM), partial least squares regression (PLSR), multiple linear regression (MLR) and principal component regression (PCR)], three analogizers [radial basis function support vector machine (rbf-SVM), K-nearest neighbor (KNN) and radial basis function Gaussian process regression (rbf-GPR)], six symbolists [extreme gradient boosting (XGBoost), Cubist, random forest (RF), multiple adaptive regression splines (MARS), gradient boosting machine (GBM), and classification and regression tree (CART)] and two connectionists [principal component analysis artificial neural network (pca-ANN) and deep neural network (DNN)] were employed to learn the regression-based QSAR models for 14 public data sets comprising nine physicochemical properties and five toxicity endpoints. The results show that rbf-SVM, rbf-GPR, XGBoost and DNN generally illustrate better performances than the other algorithms. The overall performances of different algorithms can be ranked from the best to the worst as follows: rbf-SVM > XGBoost > rbf-GPR > Cubist > GBM > DNN > RF > pca-ANN > MARS > linear-GPR ≈ KNN > linear-SVM ≈ PLSR > CART ≈ PCR ≈ MLR. In terms of prediction accuracy and computational efficiency, SVM and XGBoost are recommended to the regression learning for small data sets, and XGBoost is an excellent choice for large data sets. We then investigated the performances of the ensemble models by integrating the predictions of multiple ML algorithms. The results illustrate that the ensembles of two or three algorithms in different categories can indeed improve the predictions of the best individual ML algorithms.

The number of solved G-protein-coupled receptor (GPCR) crystal structures has expanded rapidly, but most GPCR structures remain unsolved. Therefore, computational techniques, such as homology modeling, have been widely used to produce the theoretical structures of various GPCRs for structure-based drug design (SBDD). Due to the low sequence similarity shared by the transmembrane domains of GPCRs, accurate prediction of GPCR structures by homology modeling is quite challenging. In this study, angiotensin II type I receptor (AT1R) was taken as a typical case to assess the reliability of class A GPCR homology models for SBDD. Four homology models of angiotensin II type I receptor (AT1R) at the inactive state were built based on the crystal structures of CXCR4 chemokine receptor, CCR5 chemokine receptor, and δ-opioid receptor, and refined through molecular dynamics (MD) simulations and induced-fit docking, to allow for backbone and side-chain flexibility. Then, the quality of the homology models was assessed relative to the crystal structures in terms of two criteria commonly used in SBDD: prediction accuracy of ligand-binding poses and screening power of docking-based virtual screening. It was found that the crystal structures outperformed the homology models prior to any refinement in both assessments. MD simulations could generally improve the docking results for both the crystal structures and homology models. Moreover, the optimized homology model refined by MD simulations and induced-fit docking even shows a similar performance of the docking assessment to the crystal structures. Our results indicate that it is possible to establish a reliable class A GPCR homology model for SBDD through the refinement by integrating multiple molecular modeling techniques.

Molecular docking provides a computationally efficient way to predict the atomic structural details of protein–RNA interactions (PRI), but accurate prediction of the three-dimensional structures and binding affinities for PRI is still notoriously difficult, partly due to the unreliability of the existing scoring functions for PRI. MM/PBSA and MM/GBSA are more theoretically rigorous than most scoring functions for protein–RNA docking, but their prediction performance for protein–RNA systems remains unclear. Here, we systemically evaluated the capability of MM/PBSA and MM/GBSA to predict the binding affinities and recognize the near-native binding structures for protein–RNA systems with different solvent models and interior dielectric constants (εin). For predicting the binding affinities, the predictions given by MM/GBSA based on the minimized structures in explicit solvent and the GBGBn1 model with εin = 2 yielded the highest correlation with the experimental data. Moreover, the MM/GBSA calculations based on the minimized structures in implicit solvent and the GBGBn1 model distinguished the near-native binding structures within the top 10 decoys for 117 out of the 148 protein–RNA systems (79.1%). This performance is better than all docking scoring functions studied here. Therefore, the MM/GBSA rescoring is an efficient way to improve the prediction capability of scoring functions for protein–RNA systems.

Xenobiotic chemicals and their metabolites are mainly excreted out of our bodies by the urinary tract through the urine. Chemical-induced urinary tract toxicity is one of the main reasons that cause failure during drug development, and it is a common adverse event for medications, natural supplements, and environmental chemicals. Despite its importance, there are only a few in silico models for assessing urinary tract toxicity for a large number of compounds with diverse chemical structures. Here, we developed a series of qualitative and quantitative structure-activity relationship (QSAR) models for predicting urinary tract toxicity. In our study, the recursive feature elimination method incorporated with random forests (RFE-RF) was used for dimension reduction, and then eight machine learning approaches were used for QSAR modeling, i.e., relevance vector machine (RVM), support vector machine (SVM), regularized random forest (RRF), C5.0 trees, eXtreme gradient boosting (XGBoost), AdaBoost.M1, SVM boosting (SVMBoost), and RVM boosting (RVMBoost). For building classification models, the synthetic minority oversampling technique was used to handle the imbalance data set problem. Among all the machine learning approaches, SVMBoost based on the RBF kernel achieves both the best quantitative (q

Summary Protein-protein interactions (PPIs) have been regarded as an attractive emerging class of therapeutic targets for the development of new treatments. Computational approaches, especially molecular docking, have been extensively employed to predict the binding structures of PPI-inhibitors or discover novel small molecule PPI inhibitors. However, due to the relatively ‘undruggable’ features of PPI interfaces, accurate predictions of the binding structures for ligands towards PPI targets are quite challenging for most docking algorithms. Here, we constructed a non-redundant pose ranking benchmark dataset for small-molecule PPI inhibitors, which contains 900 binding poses for 184 protein-ligand complexes. Then, we evaluated the performance of MM/PB(GB)SA approaches to identify the correct binding poses for PPI inhibitors, including two Prime MM/GBSA procedures from the Schrödinger suite and seven different MM/PB(GB)SA procedures from the Amber package. Our results showed that MM/PBSA outperformed the Glide SP scoring function (success rate of 58.6%) and MM/GBSA in most cases, especially the PB3 procedure which could achieve an overall success rate of ∼74%. Moreover, the GB6 procedure (success rate of 68.9%) performed much better than the other MM/GBSA procedures, highlighting the excellent potential of the GBNSR6 implicit solvation model for pose ranking. Finally, we developed the webserver of Fast Amber Rescoring for PPI Inhibitors (farPPI), which offers a freely available service to rescore the docking poses for PPI inhibitors by using the MM/PB(GB)SA methods. Availability and implementation farPPI web server is freely available at http://cadd.zju.edu.cn/farppi/. Supplementary information Supplementary data are available at Bioinformatics online.

Adverse effects induced by drug-drug interactions may result in early termination of drug development or even withdrawal of drugs from the market, and many drug-drug interactions are caused by the inhibition of cytochrome P450 (CYP450) enzymes. Therefore, the accurate prediction of the inhibition capability of a given compound against a specific CYP450 isoform is highly desirable. In this study, three ensemble learning methods, including random forest, gradient boosting decision tree, and eXtreme gradient boosting (XGBoost), and two deep learning methods, including deep neural networks and convolutional neural networks, were used to develop classification models to discriminate inhibitors and noninhibitors for five major CYP450 isoforms (1A2, 2C9, 2C19, 2D6, and 3A4). The results demonstrate that the ensemble learning models generally give better predictions than the deep learning models for the external test sets. Among all of the models, the XGBoost models achieve the best classification capability (average prediction accuracy of 90.4%) for the test sets, which even outperform the previously reported model developed by the multitask deep autoencoder neural network (88.5%). The Shapley additive explanation method was then used to interpret the models and analyze the misclassified molecules. The important molecular descriptors given by our models are consistent with the structural preferences for inhibitors of different CYP450 isoforms, which may provide valuable clues to detect potential drug-drug interactions in the early stage of drug discovery.

Breast cancer resistance protein (BCRP/ABCG2), an ATP-binding cassette (ABC) efflux transporter, plays a critical role in multi-drug resistance (MDR) to anti-cancer drugs and drug–drug interactions. The prediction of BCRP inhibition can facilitate evaluating potential drug resistance and drug–drug interactions in early stage of drug discovery. Here we reported a structurally diverse dataset consisting of 1098 BCRP inhibitors and 1701 non-inhibitors. Analysis of various physicochemical properties illustrates that BCRP inhibitors are more hydrophobic and aromatic than non-inhibitors. We then developed a series of quantitative structure–activity relationship (QSAR) models to discriminate between BCRP inhibitors and non-inhibitors. The optimal feature subset was determined by a wrapper feature selection method named rfSA (simulated annealing algorithm coupled with random forest), and the classification models were established by using seven machine learning approaches based on the optimal feature subset, including a deep learning method, two ensemble learning methods, and four classical machine learning methods. The statistical results demonstrated that three methods, including support vector machine (SVM), deep neural networks (DNN) and extreme gradient boosting (XGBoost), outperformed the others, and the SVM classifier yielded the best predictions (MCC = 0.812 and AUC = 0.958 for the test set). Then, a perturbation-based model-agnostic method was used to interpret our models and analyze the representative features for different models. The application domain analysis demonstrated the prediction reliability of our models. Moreover, the important structural fragments related to BCRP inhibition were identified by the information gain (IG) method along with the frequency analysis. In conclusion, we believe that the classification models developed in this study can be regarded as simple and accurate tools to distinguish BCRP inhibitors from non-inhibitors in drug design and discovery pipelines.

NF-κB inducing kinase (NIK), which is considered as the central component of the non-canonical NF-κB pathway, has been proved to be an important target for the regulation of the immune system. In the past few years, NIK inhibitors with various scaffolds have been successively reported, among which type I1/2 inhibitors that can not only bind in the ATP-binding pocket at the DFG-in state but also extend into an additional back pocket, make up the largest proportion of the NIK inhibitors, and are worthy of more attention. In this study, an integration protocol that combines molecule docking, MD simulations, ensemble docking, MM/GB(PB)SA binding free energy calculations, and decomposition was employed to understand the binding mechanism of 21 tricyclic type I1/2 NIK inhibitors. It is found that the docking accuracy is largely dependent on the selection of docking protocols as well as the crystal structures. The predictions given by the ensemble docking based on multiple receptor conformations (MRCs) and the MM/GB(PB)SA calculations based on MD simulations showed higher linear correlations with the experimental data than those given by conventional rigid receptor docking (RRD) methods (Glide, GOLD, and Autodock Vina), highlighting the importance of incorporating protein flexibility in predicting protein–ligand interactions. Further analysis based on MM/GBSA demonstrates that the hydrophobic interactions play the most essential role in the ligand binding to NIK, and the polar interactions also make an important contribution to the NIK-ligand recognition. A deeper comparison of several pairs of representative derivatives reveals that the hydrophobic interactions are vitally important in the structural optimization of analogs as well. Besides, the H-bond interactions with some key residues and the large desolvation effect in the back pocket devote to the affinity distinction. It is expected that our study could provide valuable insights into the design of novel and potent type I1/2 NIK inhibitors.

Protein kinases have been regarded as important therapeutic targets for many diseases. Currently, a total of 41 kinase inhibitors have been approved by the Food and Drug Administration, along with a large number of kinase inhibitors being evaluated in clinical and preclinical trials. Among all, allosteric inhibitors, such as type II kinase inhibitors, have attracted extensive attention owing to their potential high selectivity. Nowadays, molecular docking has become a powerful tool to search for novel kinase inhibitors. However, as for type II kinase inhibitors, their allosteric characteristics may exert a deep influence on docking accuracy. In this study, a comprehensive assessment was conducted to evaluate the effectiveness of nine docking algorithms towards type II kinase inhibitors. The calculation results showed that most tested docking programs, especially Glide with XP scoring, LeDock and Surflex-Dock, succeeded in the accurate identification of near-native binding poses, with the success rates ranging from 0.80 to 0.90, and the scoring functions in GOLD and LeDock outperformed the others in the prediction of relative binding affinities. In terms of the P-values, areas under the curve and enrichment factors, Glide with XP scoring, Surflex-Dock, GOLD with Astex Statistical Potential scoring and LeDock had better screening power to discriminate between active compounds and decoys. However, the screening power is sensitive to different initial conformations of the same target. It is expected that our study can provide some guidance for docking-based virtual screening to discover novel type II kinase inhibitors, as well as other allosteric inhibitors.

NIMA-related kinase 2 (Nek2) plays a significant role in cell cycle regulation, and overexpression of Nek2 has been observed in several types of carcinoma, suggesting it is a potential target for cancer therapy. In this study, we attempted to gain more insight into the binding mechanisms of a series of aminopyrazine inhibitors of Nek2 through multiple molecular modeling techniques, including molecular docking, molecular dynamics (MD) simulations and free energy calculations. The simulation results showed that the induced fit docking and ensemble docking based on multiple protein structures yield better predictions than conventional rigid receptor docking, highlighting the importance of incorporating receptor flexibility into the accurate predictions of the binding poses and binding affinities of Nek2 inhibitors. Additionally, we observed that the Molecular Mechanics/Generalized Born Surface Area (MM/GBSA) calculations did not show better performance than the docking scoring to rank the binding affinities of the studied inhibitors, suggesting that MM/GBSA is system-dependent and may not be the best choice for the Nek2 systems. Moreover, the detailed information on protein–ligand binding was characterized by the MM/GBSA free energy decomposition, and a number of derivatives with improved docking scores were designed. It is expected that our study can provide valuable information for the future rational design of novel and potent inhibitors of Nek2.

As a dangerous end point, respiratory toxicity can cause serious adverse health effects and even death. Meanwhile, it is a common and traditional issue in occupational and environmental protection. Pharmaceutical and chemical industries have a strong urge to develop precise and convenient computational tools to evaluate the respiratory toxicity of compounds as early as possible. Most of the reported theoretical models were developed based on the respiratory toxicity data sets with one single symptom, such as respiratory sensitization, and therefore these models may not afford reliable predictions for toxic compounds with other respiratory symptoms, such as pneumonia or rhinitis. Here, based on a diverse data set of mouse intraperitoneal respiratory toxicity characterized by multiple symptoms, a number of quantitative and qualitative predictions models with high reliability were developed by machine learning approaches. First, a four-tier dimension reduction strategy was employed to find an optimal set of 20 molecular descriptors for model building. Then, six machine learning approaches were used to develop the prediction models, including relevance vector machine (RVM), support vector machine (SVM), regularized random forest (RRF), extreme gradient boosting (XGBoost), naïve Bayes (NB), and linear discriminant analysis (LDA). Among all of the models, the SVM regression model shows the most accurate quantitative predictions for the test set (q

Determination of acute toxicity, expressed as median lethal dose (LD50), is one of the most important steps in drug discovery pipeline. Because in vivo assays for oral acute toxicity in mammals are time-consuming and costly, there is thus an urgent need to develop in silico prediction models of oral acute toxicity. In this study, based on a comprehensive data set containing 7314 diverse chemicals with rat oral LD50 values, relevance vector machine (RVM) technique was employed to build the regression models for the prediction of oral acute toxicity in rate, which were compared with those built using other six machine learning approaches, including k-nearest-neighbor regression, random forest (RF), support vector machine, local approximate Gaussian process, multilayer perceptron ensemble, and eXtreme gradient boosting. A subset of the original molecular descriptors and structural fingerprints (PubChem or SubFP) was chosen by the Chi squared statistics. The prediction capabilities of individual QSAR models, measured by q ext 2 for the test set containing 2376 molecules, ranged from 0.572 to 0.659. Considering the overall prediction accuracy for the test set, RVM with Laplacian kernel and RF were recommended to build in silico models with better predictivity for rat oral acute toxicity. By combining the predictions from individual models, four consensus models were developed, yielding better prediction capabilities for the test set (q ext 2 = 0.669–0.689). Finally, some essential descriptors and substructures relevant to oral acute toxicity were identified and analyzed, and they may be served as property or substructure alerts to avoid toxicity. We believe that the best consensus model with high prediction accuracy can be used as a reliable virtual screening tool to filter out compounds with high rat oral acute toxicity.