In Silico Prediction of Cytochrome P450 2D6 and 3A4 Inhibition Using Gaussian Kernel Weighted k-Nearest Neighbor and Extended Connectivity Fingerprints, Including Structural Fragment Analysis of Inhibitors versus Noninhibitors

DDI-GCN: Drug-drug interaction prediction via explainable graph convolutional networks

Drug-drug interactions (DDI) may lead to unexpected side effects, which is a growing concern in both academia and industry. Many DDIs have been reported, but the underlying mechanisms are not well understood. Predicting and understanding DDIs can help researchers to improve drug safety and protect patient health. Here, we introduce DDI-GCN, a method that utilizes graph convolutional networks (GCN) to predict DDIs based on chemical structures. We demonstrate that this method achieves state-of-the-art prediction performance on the independent hold-out set. It can also provide visualization of structural features associated with DDIs, which can help us to study the underlying mechanisms. To make it easy and accessible to use, we developed a web server for DDI-GCN, which is freely available at http://wengzq-lab.cn/ddi/.

A unified GCNN model for predicting CYP450 inhibitors by using graph convolutional neural networks with attention mechanism

Undesirable drug-drug interactions (DDIs) may lead to serious adverse side effects when more than two drugs are administered to a patient simultaneously. One of the most common DDIs is caused by unexpected inhibition of a specific human cytochrome P450 (CYP450), which plays a dominant role in the metabolism of the co-administered drugs. Therefore, a unified and reliable method for predicting the potential inhibitors of CYP450 family is extremely important in drug development. In this work, graph convolutional neural network (GCN) with attention mechanism and 1-D convolutional neural network (CNN) were used to extract the features of CYP ligands and the binding sites of CYP450 respectively, which were then combined to establish a unified GCN-CNN (GCNN) model for predicting the inhibitors of 5 dominant CYP isoforms, i.e., 1A2, 2C9, 2C19, 2D6, and 3A4. Overall, the established GCNN model showed good performances on the test samples and achieved better performances than the recently proposed iCYP-MFE model by using the same datasets. Based on the heat-map analysis of the resulting molecular graphs, the key structural determinants of the CYP inhibitors were further explored.

In silico prediction models for thyroid peroxidase inhibitors and their application to synthetic flavors

Systematic toxicity tests are often waived for the synthetic flavors as they are added in a very small amount in foods. However, their safety for some endpoints such as endocrine disruption should be concerned as they are likely to be active in low levels. In this case, structure–activity-relationship (SAR) models are good alternatives. In this study, therefore, binary, ternary, and quaternary prediction models were designed using simple or complex machine-learning methods. Overall, hard-voting classifiers outperformed other methods. The test scores for the best binary, ternary, and quaternary models were 0.6635, 0.5083, and 0.5217, respectively. Along with model development, some substructures including primary aromatic amine, (enol)ether, phenol, heterocyclic sulfur, and heterocyclic nitrogen, dominantly occurred in the most highly active compounds. The best predicting models were applied to synthetic flavors, and 22 agents appeared to have a strong inhibitory potential towards TPO activities.

iCYP-MFE: Identifying Human Cytochrome P450 Inhibitors Using Multitask Learning and Molecular Fingerprint-Embedded Encoding

The human cytochrome P450 (CYP) superfamily holds responsibilities for the metabolism of both endogenous and exogenous compounds such as drugs, cellular metabolites, and toxins. The inhibition exerted on the CYP enzymes is closely associated with adverse drug reactions encompassing metabolic failures and induced side effects. In modern drug discovery, identification of potential CYP inhibitors is, therefore, highly essential. Alongside experimental approaches, numerous computational models have been proposed to address this biochemical issue. In this study, we introduce iCYP-MFE, a computational framework for virtual screening on CYP inhibitors toward 1A2, 2C9, 2C19, 2D6, and 3A4 isoforms. iCYP-MFE contains a set of five robust, stable, and effective prediction models developed using multitask learning incorporated with molecular fingerprint-embedded features. The results show that multitask learning can remarkably leverage useful information from related tasks to promote global performance. Comparative analysis indicates that iCYP-MFE achieves three predominant tasks, one equivalent task, and one less effective task compared to state-of-the-art methods. The area under the receiver operating characteristic curve (AUC-ROC) and the area under the precision-recall curve (AUC-PR) were two decisive metrics used for model evaluation. The prediction task for CYP2D6-inhibition achieves the highest AUC-ROC value of 0.93 while the prediction task for CYP1A2-inhibition obtains the highest AUC-PR value of 0.92. The substructural analysis preliminarily explains the nature of the CYP-inhibitory activity of compounds. An online web server for iCYP-MFE with a user-friendly interface was also deployed to support scientific communities in identifying CYP inhibitors.

In silico prediction of mitochondrial toxicity of chemicals using machine learning methods

Mitochondria are important organelles in human cells, providing more than 95% of the energy. However, some drugs and environmental chemicals could induce mitochondrial dysfunction, which might cause complex diseases and even worsen the condition of patients with mitochondrial damage. Some drugs have been withdrawn from the market due to their severe mitochondrial toxicity, such as troglitazone. Therefore, there is an urgent need to develop models that could accurately predict the mitochondrial toxicity of chemicals. In this paper, suitable data were obtained from literature and databases first. Then nine types of fingerprints were used to characterize these compounds. Finally, different algorithms were used to build models. Meanwhile, the applicability domain of the prediction models was defined. We have also explored the structural alerts of mitochondrial toxicity, which would be helpful for medicinal chemists to better predict mitochondrial toxicity and further optimize lead compounds.

Discovering novel P38α inhibitors for the treatment of prostate cancer through virtual screening methods

Aim: P38α plays a crucial role in the development of castration-resistant prostate cancer. Discovering novel inhibitors of P38α offers potential for the development of new anticancer drugs. Methods & results: Compounds from the Chemdiv and Enamine virtual libraries were filtered to construct the P38α inhibitor-like library. A total of 58 new P38α inhibitors were discovered via virtual screening; these included three compounds (compound 1, 5, 9) with kinase IC₅₀ of below 10 μM. In vitro, these three compounds have the potential to suppress the viabilities of prostate cancer cell lines, however, only compound 9 can inhibit the proliferation and migration of prostate cancer cells. Conclusion: The potent compounds discovered in this study demonstrate anticancer functions by targeting the P38α mitogen-activated protein kinases signaling pathway and are worthy of further investigation.

ADMET evaluation in drug discovery. 20. Prediction of breast cancer resistance protein inhibition through machine learning

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.

Computational prediction of cytochrome P450 inhibition and induction

Cytochrome P450 (CYP) enzymes play an important role in the phase I metabolism of many xenobiotics. Most drug-drug interactions (DDIs) associated with CYP are caused by either CYP inhibition or induction. The early detection of potential DDIs is highly desirable in the pharmaceutical industry because DDIs can cause serious adverse events, which can lead to poor patient health and drug development failures. Recently, many computational studies predicting CYP inhibition and induction have been reported. The current computational modeling approaches for CYP metabolism are classified as ligand- and structure-based; various techniques, such as quantitative structure-activity relationships, machine learning, docking, and molecular dynamic simulation, are involved in both the approaches. Recently, combining these two approaches have resulted in improvements in the prediction accuracy of DDIs. In this review, we present important, recent developments in the computational prediction of the inhibition of four clinically crucial CYP isoforms (CYP1A2, 2C9, 2D6, and 3A4) and three nuclear receptors (aryl hydrocarbon receptor, constitutive androstane receptor, and pregnane X receptor) involved in the induction of CYP1A2, 2B6, and 3A4, respectively.

Exploring the Chemical Space of Cytochrome P450 Inhibitors Using Integrated Physicochemical Parameters, Drug Efficiency Metrics and Decision Tree Models

The cytochrome P450s (CYPs) play a central role in the metabolism of various endogenous and exogenous compounds including drugs. CYPs are vulnerable to inhibition and induction which can lead to adverse drug reactions. Therefore, insights into the underlying mechanism of CYP450 inhibition and the estimation of overall CYP inhibitor properties might serve as valuable tools during the early phases of drug discovery. Herein, we present a large data set of inhibitors against five major metabolic CYPs (CYP1A2, CYP2C9, CYP2C19, CYP2D6 and CYP3A4) for the evaluation of important physicochemical properties and ligand efficiency metrics to define property trends across various activity levels (active, efficient and inactive). Decision tree models for CYP inhibition were developed with an accuracy >90% for both the training set and 10-folds cross validation. Overall, molecular weight (MW), hydrogen bond acceptors/donors (HBA/HBD) and lipophilicity (clogP/logPo/w) represent important physicochemical descriptors for CYP450 inhibitors. However, highly efficient CYP inhibitors show mean MW, HBA, HBD and logP values between 294.18–482.40,5.0–8.2,1–7.29 and 1.68–2.57, respectively. Our results might help in optimization of toxicological profiles associated with new chemical entities (NCEs), through a better understanding of inhibitor properties leading to CYP-mediated interactions.

Virtual Screening Meets Deep Learning

BACKGROUND

Automated compound testing is currently the de facto standard method for drug screening, but it has not brought the great increase in the number of new drugs that was expected. Computer- aided compounds search, known as Virtual Screening, has shown the benefits to this field as a complement or even alternative to the robotic drug discovery. There are different methods and approaches to address this problem and most of them are often included in one of the main screening strategies. Machine learning, however, has established itself as a virtual screening methodology in its own right and it may grow in popularity with the new trends on artificial intelligence.

OBJECTIVE

This paper will attempt to provide a comprehensive and structured review that collects the most important proposals made so far in this area of research. Particular attention is given to some recent developments carried out in the machine learning field: the deep learning approach, which is pointed out as a future key player in the virtual screening landscape.

In Silico Prediction of O⁶-Methylguanine-DNA Methyltransferase Inhibitory Potency of Base Analogs with QSAR and Machine Learning Methods

O⁶-methylguanine-DNA methyltransferase (MGMT), a unique DNA repair enzyme, can confer resistance to DNA anticancer alkylating agents that modify the O⁶-position of guanine. Thus, inhibition of MGMT activity in tumors has a great interest for cancer researchers because it can significantly improve the anticancer efficacy of such alkylating agents. In this study, we performed a quantitative structure activity relationship (QSAR) and classification study based on a total of 134 base analogs related to their ED50 values (50% inhibitory concentration) against MGMT. Molecular information of all compounds were described by quantum chemical descriptors and Dragon descriptors. Genetic algorithm (GA) and multiple linear regression (MLR) analysis were combined to develop QSAR models. Classification models were generated by seven machine-learning methods based on six types of molecular fingerprints. Performances of all developed models were assessed by internal and external validation techniques. The best QSAR model was obtained with Q²Loo = 0.83, R² = 0.87, Q²ext = 0.67, and R²ext = 0.69 based on 84 compounds. The results from QSAR studies indicated topological charge indices, polarizability, ionization potential (IP), and number of primary aromatic amines are main contributors for MGMT inhibition of base analogs. For classification studies, the accuracies of 10-fold cross-validation ranged from 0.750 to 0.885 for top ten models. The range of accuracy for the external test set ranged from 0.800 to 0.880 except for PubChem-Tree model, suggesting a satisfactory predictive ability. Three models (Ext-SVM, Ext-Tree and Graph-RF) showed high and reliable predictive accuracy for both training and external test sets. In addition, several representative substructures for characterizing MGMT inhibitors were identified by information gain and substructure frequency analysis method. Our studies might be useful for further study to design and rapidly identify potential MGMT inhibitors.

Evaluating parameters for ligand-based modeling with random forest on sparse data sets

Ligand-based predictive modeling is widely used to generate predictive models aiding decision making in e.g. drug discovery projects. With growing data sets and requirements on low modeling time comes the necessity to analyze data sets efficiently to support rapid and robust modeling. In this study we analyzed four data sets and studied the efficiency of machine learning methods on sparse data structures, utilizing Morgan fingerprints of different radii and hash sizes, and compared with molecular signatures descriptor of different height. We specifically evaluated the effect these parameters had on modeling time, predictive performance, and memory requirements using two implementations of random forest; Scikit-learn as well as FEST. We also compared with a support vector machine implementation. Our results showed that unhashed fingerprints yield significantly better accuracy than hashed fingerprints ([Formula: see text]), with no pronounced deterioration in modeling time and memory usage. Furthermore, the fast execution and low memory usage of the FEST algorithm suggest that it is a good alternative for large, high dimensional sparse data. Both support vector machines and random forest performed equally well but results indicate that the support vector machine was better at using the extra information from larger values of the Morgan fingerprint's radius.

QSAR and Classification Study on Prediction of Acute Oral Toxicity of N-Nitroso Compounds

To better understand the mechanism of in vivo toxicity of N-nitroso compounds (NNCs), the toxicity data of 80 NNCs related to their rat acute oral toxicity data (50% lethal dose concentration, LD50) were used to establish quantitative structure-activity relationship (QSAR) and classification models. Quantum chemistry methods calculated descriptors and Dragon descriptors were combined to describe the molecular information of all compounds. Genetic algorithm (GA) and multiple linear regression (MLR) analyses were combined to develop QSAR models. Fingerprints and machine learning methods were used to establish classification models. The quality and predictive performance of all established models were evaluated by internal and external validation techniques. The best GA-MLR-based QSAR model containing eight molecular descriptors was obtained with Q²loo = 0.7533, R² = 0.8071, Q²ext = 0.7041 and R²ext = 0.7195. The results derived from QSAR studies showed that the acute oral toxicity of NNCs mainly depends on three factors, namely, the polarizability, the ionization potential (IP) and the presence/absence and frequency of C⁻O bond. For classification studies, the best model was obtained using the MACCS keys fingerprint combined with artificial neural network (ANN) algorithm. The classification models suggested that several representative substructures, including nitrile, hetero N nonbasic, alkylchloride and amine-containing fragments are main contributors for the high toxicity of NNCs. Overall, the developed QSAR and classification models of the rat acute oral toxicity of NNCs showed satisfying predictive abilities. The results provide an insight into the understanding of the toxicity mechanism of NNCs in vivo, which might be used for a preliminary assessment of NNCs toxicity to mammals.

The current limits in virtual screening and property prediction

Beyond finding inhibitors that show high binding affinity to the respective target, there is the challenge of optimizing their properties with respect to metabolic and toxicological issues, as well as further off-target effects. To reduce the experimental effort of synthesizing and testing actual substances in corresponding assays, virtual screening has become an indispensable toolbox in preclinical development. The scope of application covers the prediction of molecular properties including solubility, metabolic liability and binding to antitargets, such as the hERG channel. Furthermore, prediction of binding sites and drugable targets are emerging aspects of virtual screening. Issues involved with the currently applied computational models including machine learning algorithms are outlined, such as limitations to the accuracy of prediction and overfitting.

In silico prediction of potential chemical reactions mediated by human enzymes

Background

Administered drugs are often converted into an ineffective or activated form by enzymes in our body. Conventional in silico prediction approaches focused on therapeutically important enzymes such as CYP450. However, there are more than thousands of different cellular enzymes that potentially convert administered drug into other forms.

Result

We developed an in silico model to predict which of human enzymes including metabolic enzymes as well as CYP450 family can catalyze a given chemical compound. The prediction is based on the chemical and physical similarity between known enzyme substrates and a query chemical compound. Our in silico model was developed using multiple linear regression and the model showed high performance (AUC = 0.896) despite of the large number of enzymes. When evaluated on a test dataset, it also showed significantly high performance (AUC = 0.746). Interestingly, evaluation with literature data showed that our model can be used to predict not only enzymatic reactions but also drug conversion and enzyme inhibition.

Conclusion

Our model was able to predict enzymatic reactions of a query molecule with a high accuracy. This may foster to discover new metabolic routes and to accelerate the computational development of drug candidates by enabling the prediction of the potential conversion of administered drugs into active or inactive forms.

Classification of Cytochrome P450 1A2 Inhibitors and Noninhibitors Based on Deep Belief Network

The cytochrome P450 (CYP) superfamily, exists in the human liver, is responsible for more than 90% of the metabolism of clinical drugs. So it is necessary to adopt a new kind of computer simulation methods that can predict the rejection capability of compounds for a concrete CYPs isoform. In this work, a model is presented for classification of CYP450 1A2 inhibitors and noninhibitors based on a multi-tiered deep belief network (DBN) on a large dataset. The dataset composed of more than 13,000 heterogeneous compounds was acquired from PubChem. Firstly, 139 2D and 53 3D descriptors are calculated and preprocessed. Then, the unsupervised learning method is used to train DBN model to automatically extract multiple levels of distributed representation from the descriptors of training set. Finally, by using testing set and external validation set, we evaluate the classified performance of DBN for the inhibition of CYP1A2. Meanwhile, the proposed model is compared with shallow machine learning models (support vector machine (SVM) and artificial neural network (ANN)). We also discussed the performance of DBN by comparing it with different features combination. The experimental results showed that DBN has a better prediction ability compared with SVM and ANN. And these models combined with the features of 2D and 3D obtain the best forecast accuracy.

In silico prediction of chronic toxicity with chemical category approaches

Chemical chronic toxicity, referring to the toxic effect of a chemical following long-term or repeated sub lethal exposures, is an important toxicological end point in drug design and environmental risk assessment.

In silico prediction of serious eye irritation or corrosion potential of chemicals

Chemical fingerprints combined with machine learning methods were used to build binary classification models for predicting the potential EC/EI of compounds.

Multiple machine learning based descriptive and predictive workflow for the identification of potential PTP1B inhibitors

In insulin and leptin signaling pathway, Protein-Tyrosine Phosphatase 1B (PTP1B) plays a crucial controlling role as a negative regulator, which makes it an attractive therapeutic target for both Type-2 Diabetes (T2D) and obesity. In this work, we have generated classification models by using the inhibition data set of known PTP1B inhibitors to identify new inhibitors of PTP1B utilizing multiple machine learning techniques like naïve Bayesian, random forest, support vector machine and k-nearest neighbors, along with structural fingerprints and selected molecular descriptors. Several models from each algorithm have been constructed and optimized, with the different combination of molecular descriptors and structural fingerprints. For the training and test sets, most of the predictive models showed more than 90% of overall prediction accuracies. The best model was obtained with support vector machine approach and has Matthews Correlation Coefficient of 0.82 for the external test set, which was further employed for the virtual screening of Maybridge small compound database. Five compounds were subsequently selected for experimental assay. Out of these two compounds were found to inhibit PTP1B with significant inhibitory activity in in-vitro inhibition assay. The structural fragments which are important for PTP1B inhibition were identified by naïve Bayesian method and can be further exploited to design new molecules around the identified scaffolds. The descriptive and predictive modeling strategy applied in this study is capable of identifying PTP1B inhibitors from the large compound libraries.

In Silico Prediction of Cytochrome P450-Drug Interaction: QSARs for CYP3A4 and CYP2C9

Cytochromes P450 (CYP) are the main actors in the oxidation of xenobiotics and play a crucial role in drug safety, persistence, bioactivation, and drug-drug/food-drug interaction. This work aims to develop Quantitative Structure-Activity Relationship (QSAR) models to predict the drug interaction with two of the most important CYP isoforms, namely 2C9 and 3A4. The presented models are calibrated on 9122 drug-like compounds, using three different modelling approaches and two types of molecular description (classical molecular descriptors and binary fingerprints). For each isoform, three classification models are presented, based on a different approach and with different advantages: (1) a very simple and interpretable classification tree; (2) a local (k-Nearest Neighbor) model based classical descriptors and; (3) a model based on a recently proposed local classifier (N-Nearest Neighbor) on binary fingerprints. The salient features of the work are (1) the thorough model validation and the applicability domain assessment; (2) the descriptor interpretation, which highlighted the crucial aspects of P450-drug interaction; and (3) the consensus aggregation of models, which largely increased the prediction accuracy.

In silico Prediction of Drug Induced Liver Toxicity Using Substructure Pattern Recognition Method

Drug-induced liver injury (DILI) is a leading cause of acute liver failure in the US and less severe liver injury worldwide. It is also one of the major reasons of drug withdrawal from the market. Thus, DILI has become one of the most important concerns of drugs, and should be predicted in very early stage of drug discovery process. In this study, a comprehensive data set containing 1317 diverse compounds was collected from publications. Then, high accuracy classification models were built using five machine learning methods based on MACCS and FP4 fingerprints after evaluating by substructure pattern recognition method. The best model was built using SVM method together with FP4 fingerprint at the IG value threshold of 0.0005. Its overall predictive accuracies were 79.7 % and 64.5 % for the training and test sets, separately, which yielded overall accuracy of 75.0 % for the external validation dataset, consisting of 88 compounds collected from a benchmark DILI database - the Liver Toxicity Knowledge Base. This model could be used for drug-induced liver toxicity prediction. Moreover, some key substructure patterns correlated with drug-induced liver toxicity were also identified as structural alerts.

In silico prediction of hERG potassium channel blockage by chemical category approaches

The human ether-a-go-go related gene (hERG) plays an important role in cardiac action potential. It encodes an ion channel protein named Kv11.1, which is related to long QT syndrome and may cause avoidable sudden cardiac death. Therefore, it is important to assess the hERG channel blockage of lead compounds in an early drug discovery process. In this study, we collected a large data set containing 1163 diverse compounds with IC₅₀ values determined by the patch clamp method on mammalian cell lines. The whole data set was divided into 80% as the training set and 20% as the test set. Then, five machine learning methods were applied to build a series of binary classification models based on 13 molecular descriptors, five fingerprints and molecular descriptors combining fingerprints at four IC₅₀ thresholds to discriminate hERG blockers from nonblockers, respectively. Models built by molecular descriptors combining fingerprints were validated by using an external validation set containing 407 compounds collected from the hERGCentral database. The performance indicated that the model built by molecular descriptors combining fingerprints yielded the best results and each threshold had its best suitable method, which means that hERG blockage assessment might depend on threshold values. Meanwhile, kNN and SVM methods were better than the others for model building. Furthermore, six privileged substructures were identified using information gain and frequency analysis methods, which could be regarded as structural alerts of cardiac toxicity mediated by hERG channel blockage.

Artificial neural network cascade identifies multi-P450 inhibitors in natural compounds

Substantial evidence has shown that most exogenous substances are metabolized by multiple cytochrome P450 (P450) enzymes instead of by merely one P450 isoform. Thus, multi-P450 inhibition leads to greater drug-drug interaction risk than specific P450 inhibition. Herein, we innovatively established an artificial neural network cascade (NNC) model composed of 23 cascaded networks in a ladder-like framework to identify potential multi-P450 inhibitors among natural compounds by integrating 12 molecular descriptors into a P450 inhibition score (PIS). Experimental data reporting in vitro inhibition of five P450 isoforms (CYP1A2, CYP2C9, CYP2C19, CYP2D6, and CYP3A4) were obtained for 8,148 compounds from the Cytochrome P450 Inhibitors Database (CPID). The results indicate significant positive correlation between the PIS values and the number of inhibited P450 isoforms (Spearman’s ρ = 0.684, p < 0.0001). Thus, a higher PIS indicates a greater possibility for a chemical to inhibit the enzyme activity of at least three P450 isoforms. Ten-fold cross-validation of the NNC model suggested an accuracy of 78.7% for identifying whether a compound is a multi-P450 inhibitor or not. Using our NNC model, 22.2% of the approximately 160,000 natural compounds in TCM Database@Taiwan were identified as potential multi-P450 inhibitors. Furthermore, chemical similarity calculations suggested that the prevailing parent structures of natural multi-P450 inhibitors were alkaloids. Our findings show that dissection of chemical structure contributes to confident identification of natural multi-P450 inhibitors and provides a feasible method for virtually evaluating multi-P450 inhibition risk for a known structure.

Cheminformatics Based Machine Learning Models for AMA1-RON2 Abrogators for Inhibiting Plasmodium falciparum Erythrocyte Invasion

Malaria remains a dreadful disease by putting every year about 3.4 billion people at risk and resulting into mortality of 627 thousand people worldwide. Existing therapies based upon Quinines and Artemisinin-based combination therapies have started showing resistance, pressing the need for search of anti-malarials with different mechanisms of action. In this respect erythrocyte invasion by Plasmodium is immensely crucial, as being obligate intracellular parasite it must invade host cells. This process is mediated by interaction between conserved Apical Membrane Antigen (AMA1) and Rhoptry Neck (RON2) protein, which is compulsory for successful invasion of erythrocyte by Plasmodium and manifestation of the disease Malaria. Here, using the physicochemical properties of the compounds available from a confirmatory high throughput screening, which were tested for their disruption capability of this crucial molecular interaction, we trained supervised classifiers and validated their robustness by various statistical parameters. Best model was used for screening new compounds from Traditional Chinese Medicine Database. Some of the best hits already find their use as anti-malarials and the model predicts that an essential part of their effectiveness is likely due to inhibition of AMA1-RON2 interaction. Pharmacophoric features have also been identified to ease further designing of possible leads in an effective way.

In silico prediction of chemical toxicity on avian species using chemical category approaches

Avian species are sensitive to pesticides and industrial chemicals, and hence used as model species in evaluation of chemical toxicity. In present study, we assessed the toxicity of more than 663 diverse chemicals on 17 avian species. All the chemicals were classified into three categories, i.e. highly toxic, slightly toxic and non-toxic, based on the toxicity classification criteria of the United States Environmental Protection Agency (EPA). To evaluate these chemicals, the toxicity prediction models were built using chemical category approaches with molecular descriptors and five commonly used fingerprints, in which five machine learning methods were performed on two standard test species: aquatic bird mallard duck and terrestrial bird northern bobwhite quail. The support vector machine (SVM) method with Pubchem fingerprint performed best as revealed by 5-fold cross-validation and the external validation set on Japanese quail. No species difference existed in our database despite several chemicals with different toxicity on some avian species. The best model had an overall accuracy at 0.851 for the prediction of toxicity on avian species, which outperformed the work of Mazzatorta et al. Furthermore, several representative substructures for characterizing avian toxicity were identified via information gain (IG) method. This study would provide a new tool for chemical safety assessment.

Cheminformatics models based on machine learning approaches for design of USP1/UAF1 abrogators as anticancer agents

Cancer cells have upregulated DNA repair mechanisms, enabling them survive DNA damage induced during repeated rapid cell divisions and targeted chemotherapeutic treatments. Cancer cell proliferation and survival targeting via inhibition of DNA repair pathways is currently a very promiscuous anti-tumor approach. The deubiquitinating enzyme, USP1 is known to promote DNA repair via complexing with UAF1. The USP1/UAF1 complex is responsible for regulating DNA break repair pathways such as trans-lesion synthesis pathway, Fanconi anemia pathway and homologous recombination. Thus, USP1/UAF1 inhibition poses as an efficient anti-cancer strategy. The recently made available high throughput screen data for anti USP1/UAF1 activity prompted us to compute bioactivity predictive models that could help in screening for potential USP1/UAF1 inhibitors having anti-cancer properties. The current study utilizes publicly available high throughput screen data set of chemical compounds evaluated for their potential USP1/UAF1 inhibitory effect. A machine learning approach was devised for generation of computational models that could predict for potential anti USP1/UAF1 biological activity of novel anticancer compounds. Additional efficacy of active compounds was screened by applying SMARTS filter to eliminate molecules with non-drug like features. The structural fragment analysis was further performed to explore structural properties of the molecules. We demonstrated that modern machine learning approaches could be efficiently employed in building predictive computational models and their predictive performance is statistically accurate. The structure fragment analysis revealed the structures that could play an important role in identification of USP1/UAF1 inhibitors.

Applying machine learning techniques for ADME-Tox prediction: a review

INTRODUCTION

Pharmacokinetics involves the study of absorption, distribution, metabolism, excretion and toxicity of xenobiotics (ADME-Tox). In this sense, the ADME-Tox profile of a bioactive compound can impact its efficacy and safety. Moreover, efficacy and safety were considered some of the major causes of clinical failures in the development of new chemical entities. In this context, machine learning (ML) techniques have been often used in ADME-Tox studies due to the existence of compounds with known pharmacokinetic properties available for generating predictive models.

AREAS COVERED

This review examines the growth in the use of some ML techniques in ADME-Tox studies, in particular supervised and unsupervised techniques. Also, some critical points (e.g., size of the data set and type of output variable) must be considered during the generation of models that relate ADME-Tox properties and biological activity.

EXPERT OPINION

ML techniques have been successfully employed in pharmacokinetic studies, helping the complex process of designing new drug candidates from the use of reliable ML models. An application of this procedure would be the prediction of ADME-Tox properties from studies of quantitative structure-activity relationships or the discovery of new compounds from a virtual screening using filters based on results obtained from ML techniques.

Activity-limiting role of molecular size: size-dependency of maximum activity for P450 inhibition as revealed by qHTS data

Analysis of a large number of data on cytochrome P450 (P450) inhibition obtained from quantitative high-throughput screening assays from the PubChem BioAssay Database clearly indicates that molecular size has an important activity-limiting role for datasets focused on drug-like compounds (PubChem BioAssay Identifier [AID] 1851) as well as for datasets also incorporating a wider range of environmental chemicals (AIDs 410, 899, 883, 891, and 884). Maximum inhibitory activity increases with size for small enough structures then plateaus and begins to show a decreasing trend for larger structures. Log-scaled maximum median inhibitory concentration (pIC50) as a function of molecular size could be fitted well with a bilinear model (LinBiExp), and the shape of the curve is quite similar across five P450 isozymes (CYP1A2, 2C9, 2C19, 2D6, and 3A4) with a turning-point of maximum inhibition around 300-500 Da. While the present size-based approach cannot account for the variability of activity in general, using data for a very large number of compounds, it still provides an intuitive interpretation of the maximum P450-inhibitory activity obtainable for a given molecular size and highlights the presence of an "optimum" size range.

Predicting mTOR inhibitors with a classifier using recursive partitioning and Naïve Bayesian approaches

Background

Mammalian target of rapamycin (mTOR) is a central controller of cell growth, proliferation, metabolism, and angiogenesis. Thus, there is a great deal of interest in developing clinical drugs based on mTOR. In this paper, in silico models based on multi-scaffolds were developed to predict mTOR inhibitors or non-inhibitors.

Methods

First 1,264 diverse compounds were collected and categorized as mTOR inhibitors and non-inhibitors. Two methods, recursive partitioning (RP) and naïve Bayesian (NB), were used to build combinatorial classification models of mTOR inhibitors versus non-inhibitors using physicochemical descriptors, fingerprints, and atom center fragments (ACFs).

Results

A total of 253 models were constructed and the overall predictive accuracies of the best models were more than 90% for both the training set of 964 and the external test set of 300 diverse compounds. The scaffold hopping abilities of the best models were successfully evaluated through predicting 37 new recently published mTOR inhibitors. Compared with the best RP and Bayesian models, the classifier based on ACFs and Bayesian shows comparable or slightly better in performance and scaffold hopping abilities. A web server was developed based on the ACFs and Bayesian method (http://rcdd.sysu.edu.cn/mtor/). This web server can be used to predict whether a compound is an mTOR inhibitor or non-inhibitor online.

Conclusion

In silico models were constructed to predict mTOR inhibitors using recursive partitioning and naïve Bayesian methods, and a web server (mTOR Predictor) was also developed based on the best model results. Compound prediction or virtual screening can be carried out through our web server. Moreover, the favorable and unfavorable fragments for mTOR inhibitors obtained from Bayesian classifiers will be helpful for lead optimization or the design of new mTOR inhibitors.

In silico prediction of chemical acute oral toxicity using multi-classification methods

Chemical acute oral toxicity is an important end point in drug design and environmental risk assessment. However, it is difficult to determine by experiments, and in silico methods are hence developed as an alternative. In this study, a comprehensive data set containing 12, 204 diverse compounds with median lethal dose (LD₅₀) was compiled. These chemicals were classified into four categories, namely categories I, II, III and IV, based on the criterion of the U.S. Environmental Protection Agency (EPA). Then several multiclassification models were developed using five machine learning methods, including support vector machine (SVM), C4.5 decision tree (C4.5), random forest (RF), κ-nearest neighbor (kNN), and naïve Bayes (NB) algorithms, along with MACCS and FP4 fingerprints. One-against-one (OAO) and binary tree (BT) strategies were employed for SVM multiclassification. Performances were measured by two external validation sets containing 1678 and 375 chemicals, separately. The overall accuracy of the MACCS-SVM(OAO) model was 83.0% and 89.9% for external validation sets I and II, respectively, which showed reliable predictive accuracy for each class. In addition, some representative substructures responsible for acute oral toxicity were identified using information gain and substructure frequency analysis methods, which might be very helpful for further study to avoid the toxicity.

Designing of inhibitors against drug tolerant Mycobacterium tuberculosis (H37Rv)

Background

Mycobacterium tuberculosis (M.tb) is the causative agent of tuberculosis, killing ~1.7 million people annually. The remarkable capacity of this pathogen to escape the host immune system for decades and then to cause active tuberculosis disease, makes M.tb a successful pathogen. Currently available anti-mycobacterial therapy has poor compliance due to requirement of prolonged treatment resulting in accelerated emergence of drug resistant strains. Hence, there is an urgent need to identify new chemical entities with novel mechanism of action and potent activity against the drug resistant strains.

Results

This study describes novel computational models developed for predicting inhibitors against both replicative and non-replicative phase of drug-tolerant M.tb under carbon starvation stage. These models were trained on highly diverse dataset of 2135 compounds using four classes of binary fingerprint namely PubChem, MACCS, EState, SubStructure. We achieved the best performance Matthews correlation coefficient (MCC) of 0.45 using the model based on MACCS fingerprints for replicative phase inhibitor dataset. In case of non-replicative phase, Hybrid model based on PubChem, MACCS, EState, SubStructure fingerprints performed better with maximum MCC value of 0.28. In this study, we have shown that molecular weight, polar surface area and rotatable bond count of inhibitors (replicating and non-replicating phase) are significantly different from non-inhibitors. The fragment analysis suggests that substructures like hetero_N_nonbasic, heterocyclic, carboxylic_ester, and hetero_N_basic_no_H are predominant in replicating phase inhibitors while hetero_O, ketone, secondary_mixed_amine are preferred in the non-replicative phase inhibitors. It was observed that nitro, alkyne, and enamine are important for the molecules inhibiting bacilli residing in both the phases. In this study, we introduced a new algorithm based on Matthews correlation coefficient called MCCA for feature selection and found that this algorithm is better or comparable to frequency based approach.

Conclusion

In this study, we have developed computational models to predict phase specific inhibitors against drug resistant strains of M.tb grown under carbon starvation. Based on simple molecular properties, we have derived some rules, which would be useful in robust identification of tuberculosis inhibitors. Based on these observations, we have developed a webserver for predicting inhibitors against drug tolerant M.tb H37Rv available at http://crdd.osdd.net/oscadd/mdri/.

Three-dimensional quantitative structure-activity relationship analysis of inhibitors of human and rat cytochrome P4503A enzymes

Cytochrome P450 3A4 (CYP3A4) is a member of the CYP family and is an important enzyme in drug metabolism. A compound that inhibits CYP3A4 activity could also affect the pharmacokinetics of other substrates, resulting in drug-drug interactions (DDIs) that could cause side effects. Pharmacokinetic data from drug-development studies in rats often determine the dosage used in human clinical trials. It is therefore useful to understand differences in metabolism in different species at an early stage in drug development. Human and rat CYP3A enzymes show different inhibition profiles with different drugs, although the mechanisms involved are not yet clear. Here we built three-dimensional quantitative structure-activity relationship (3D-QSAR) models using structure-based comparative molecular field analysis (CoMFA), to predict the direct inhibitory activity of ligands for human CYP3A4 and rat CYP3A1, based on computer-ligand docking. The alignment of the ligand docking poses suggested that key amino acid-ligand interactions (e.g., Thr309 in CYP3A4 and Pro310 in CYP3A1) characterized the different potencies with which the ligands inhibited CYP3A4 and CYP3A1. The 3D-QSAR models for human and rat CYP3A family inhibitors predicted the potency of inhibitors and could be useful for assessing DDIs at an early stage in drug discovery.

Benchmarking ligand-based virtual High-Throughput Screening with the PubChem database

With the rapidly increasing availability of High-Throughput Screening (HTS) data in the public domain, such as the PubChem database, methods for ligand-based computer-aided drug discovery (LB-CADD) have the potential to accelerate and reduce the cost of probe development and drug discovery efforts in academia. We assemble nine data sets from realistic HTS campaigns representing major families of drug target proteins for benchmarking LB-CADD methods. Each data set is public domain through PubChem and carefully collated through confirmation screens validating active compounds. These data sets provide the foundation for benchmarking a new cheminformatics framework BCL::ChemInfo, which is freely available for non-commercial use. Quantitative structure activity relationship (QSAR) models are built using Artificial Neural Networks (ANNs), Support Vector Machines (SVMs), Decision Trees (DTs), and Kohonen networks (KNs). Problem-specific descriptor optimization protocols are assessed including Sequential Feature Forward Selection (SFFS) and various information content measures. Measures of predictive power and confidence are evaluated through cross-validation, and a consensus prediction scheme is tested that combines orthogonal machine learning algorithms into a single predictor. Enrichments ranging from 15 to 101 for a TPR cutoff of 25% are observed.

QSAR Modelling of CYP3A4 Inhibition as a Screening Tool in the Context of DrugDrug Interaction Studies

Drugdrug interaction potential (DDI), especially cytochrome P450 (CYP) 3A4 inhibition potential, is one of the most important parameters to be optimized before preclinical and clinical pharmaceutical development as regard to the number of marketed drug metabolized mainly by this CYP and potentially co-administered with the future drug. The present study aims to develop in silico models for CYP3A4 inhibition prediction to help medicinal chemists during the discovery phase and even before the synthesis of new chemical entities (NCEs), focusing on NCEs devoid of any inhibitory potential toward this CYP. In order to find a relevant relationship between CYP3A4 inhibition and chemical features of the screened compounds, we applied a genetic-algorithm-based QSAR exploratory tool SQS (Stochastic QSAR Sampler) in combination with different description approaches comprising alignment-independent Volsurf descriptors, ISIDA fragments and Topological Fuzzy Pharmacophore Triplets. The experimental data used to build models were extracted from an in-house database. We derived a model with good prediction ability that was confirmed on both newly synthesized compound and public dataset retrieved from Pubchem database. This model is a promising efficient tool for filtering out potentially problematic compounds.

Redefining Cheminformatics with Intuitive Collaborative Mobile Apps

The proliferation of mobile devices such as smartphones and tablet computers has recently been extended to include a growing ecosystem of increasingly sophisticated chemistry software packages, commonly known as apps. The capabilities that these apps can offer to the practicing chemist are approaching those of conventional desktop-based software, but apps tend to be focused on a relatively small range of tasks. To overcome this, chemistry apps must be able to seamlessly transfer data to other apps, and through the network to other devices, as well as to other platforms, such as desktops and servers, using documented file formats and protocols whenever possible. This article describes the development and state of the art with regard to chemistry-aware apps that make use of facile data interchange, and some of the scenarios in which these apps can be inserted into a chemical information workflow to increase productivity. A selection of contemporary apps is used to demonstrate their relevance to pharmaceutical research. Mobile apps represent a novel approach for delivery of cheminformatics tools to chemists and other scientists, and indications suggest that mobile devices represent a disruptive technology for drug discovery, as they have been to many other industries.