In Silico Estimation of Chemical Carcinogenicity with Binary and Ternary Classification Methods

Unlocking the potential of AI: Machine learning and deep learning models for predicting carcinogenicity of chemicals

The escalating apprehension surrounding the carcinogenic potential of chemicals emphasizes the imperative need for efficient methods of assessing carcinogenicity. Conventional experimental approaches such as in vitro and in vivo assays, albeit effective, suffer from being costly and time-consuming. In response to this challenge, new alternative methodologies, notably machine learning and deep learning techniques, have attracted attention for their potential in developing carcinogenicity prediction models. This article reviews the progress in predicting carcinogenicity using various machine learning and deep learning algorithms. A comparative analysis on these developed models reveals that support vector machine, random forest, and ensemble learning are commonly preferred for their robustness and effectiveness in predicting chemical carcinogenicity. Conversely, models based on deep learning algorithms, such as feedforward neural network, convolutional neural network, graph convolutional neural network, capsule neural network, and hybrid neural networks, exhibit promising capabilities but are limited by the size of available carcinogenicity datasets. This review provides a comprehensive analysis of current machine learning and deep learning models for carcinogenicity prediction, underscoring the importance of high-quality and large datasets. These observations are anticipated to catalyze future advancements in developing effective and generalizable machine learning and deep learning models for predicting chemical carcinogenicity.

Recent progress in machine learning approaches for predicting carcinogenicity in drug development

INTRODUCTION

This review explores the transformative impact of machine learning (ML) on carcinogenicity prediction within drug development. It discusses the historical context and recent advancements, emphasizing the significance of ML methodologies in overcoming challenges related to data interpretation, ethical considerations, and regulatory acceptance.

AREAS COVERED

The review comprehensively examines the integration of ML, deep learning, and diverse artificial intelligence (AI) approaches in various aspects of drug development safety assessments. It explores applications ranging from early-phase compound screening to clinical trial optimization, highlighting the versatility of ML in enhancing predictive accuracy and efficiency.

EXPERT OPINION

Through the analysis of traditional approaches such as in vivo rodent bioassays and in vitro assays, the review underscores the limitations and resource intensity associated with these methods. It provides expert insights into how ML offers innovative solutions to address these challenges, revolutionizing safety assessments in drug development.

Review of machine learning and deep learning models for toxicity prediction

The ever-increasing number of chemicals has raised public concerns due to their adverse effects on human health and the environment. To protect public health and the environment, it is critical to assess the toxicity of these chemicals. Traditional in vitro and in vivo toxicity assays are complicated, costly, and time-consuming and may face ethical issues. These constraints raise the need for alternative methods for assessing the toxicity of chemicals. Recently, due to the advancement of machine learning algorithms and the increase in computational power, many toxicity prediction models have been developed using various machine learning and deep learning algorithms such as support vector machine, random forest, k-nearest neighbors, ensemble learning, and deep neural network. This review summarizes the machine learning- and deep learning-based toxicity prediction models developed in recent years. Support vector machine and random forest are the most popular machine learning algorithms, and hepatotoxicity, cardiotoxicity, and carcinogenicity are the frequently modeled toxicity endpoints in predictive toxicology. It is known that datasets impact model performance. The quality of datasets used in the development of toxicity prediction models using machine learning and deep learning is vital to the performance of the developed models. The different toxicity assignments for the same chemicals among different datasets of the same type of toxicity have been observed, indicating benchmarking datasets is needed for developing reliable toxicity prediction models using machine learning and deep learning algorithms. This review provides insights into current machine learning models in predictive toxicology, which are expected to promote the development and application of toxicity prediction models in the future.

In-vitro antiviral activity and in-silico targeted study of quinoline-3-carboxylate derivatives against SARS-Cov-2 isolate

In recent years, the viral outbreak named COVID-19 showed that infectious diseases have a huge impact on both global health and the financial and economic sectors. The lack of efficacious antiviral drugs worsened the health problem. Based on our previous experience, we investigated in vitro and in silico a series of quinoline-3-carboxylate derivatives against a SARS-CoV-2 isolate. In the present study, the in-vitro antiviral activity of a series of quinoline-3-carboxylate compounds and the in silico target-based molecular dynamics (MD) and metabolic studies are reported. The compounds' activity against SARS-CoV-2 was evaluated using plaque assay and RT-qPCR. Moreover, from the docking scores, it appears that the most active compounds (1j and 1o) exhibit stronger binding affinity to the primary viral protease (NSP5) and the exoribonuclease domain of non structural protein 14 (NSP14). Additionally, the in-silico metabolic analysis of 1j and 1o defines CYP2C9 and CYP3A4 as the major P450 enzymes involved in their metabolism.

Application of a developed triple-classification machine learning model for carcinogenic prediction of hazardous organic chemicals to the US, EU, and WHO based on Chinese database

Cancer, the second largest human disease, has become a major public health problem. The prediction of chemicals' carcinogenicity before their synthesis is crucial. In this paper, seven machine learning algorithms (i.e., Random Forest (RF), Logistic Regression (LR), Support Vector Machines (SVM), Complement Naive Bayes (CNB), K-Nearest Neighbor (KNN), XGBoost, and Multilayer Perceptron (MLP)) were used to construct the carcinogenicity triple classification prediction (TCP) model (i.e., 1A, 1B, Category 2). A total of 1444 descriptors of 118 hazardous organic chemicals were calculated by Discovery Studio 2020, Sybyl X-2.0 and PaDEL-Descriptor software. The constructed carcinogenicity TCP model was evaluated through five model evaluation indicators (i.e., Accuracy, Precision, Recall, F1 Score and AUC). The model evaluation results show that Accuracy, Precision, Recall, F1 Score and AUC evaluation indicators meet requirements (greater than 0.6). The accuracy of RF, LR, XGBoost, and MLP models for predicting carcinogenicity of Category 2 is 91.67%, 79.17%, 100%, and 100%, respectively. In addition, the constructed machine learning model in this study has potential for error correction. Taking XGBoost model as an example, the predicted carcinogenicity level of 1,2,3-Trichloropropane (96-18-4) is Category 2, but the actual carcinogenicity level is 1B. But the difference between Category 2 and 1B is only 0.004, indicating that the XGBoost is one optimum model of the seven constructed machine learning models. Besides, results showed that functional groups like chlorine and benzene ring might influence the prediction of carcinogenic classification. Therefore, considering functional group characteristics of chemicals before constructing the carcinogenicity prediction model of organic chemicals is recommended. The predicted carcinogenicity of the organic chemicals using the optimum machine leaning model (i.e., XGBoost) was also evaluated and verified by the toxicokinetics. The RF and XGBoost TCP models constructed in this paper can be used for carcinogenicity detection before synthesizing new organic substances. It also provides technical support for the subsequent management of organic chemicals.

Predicting Chemical Carcinogens Using a Hybrid Neural Network Deep Learning Method

Determining environmental chemical carcinogenicity is urgently needed as humans are increasingly exposed to these chemicals. In this study, we developed a hybrid neural network (HNN) method called HNN-Cancer to predict potential carcinogens of real-life chemicals. The HNN-Cancer included a new SMILES feature representation method by modifying our previous 3D array representation of 1D SMILES simulated by the convolutional neural network (CNN). We developed binary classification, multiclass classification, and regression models based on diverse non-congeneric chemicals. Along with the HNN-Cancer model, we developed models based on the random forest (RF), bootstrap aggregating (Bagging), and adaptive boosting (AdaBoost) methods for binary and multiclass classification. We developed regression models using HNN-Cancer, RF, support vector regressor (SVR), gradient boosting (GB), kernel ridge (KR), decision tree with AdaBoost (DT), KNeighbors (KN), and a consensus method. The performance of the models for all classifications was assessed using various statistical metrics. The accuracy of the HNN-Cancer, RF, and Bagging models were 74%, and their AUC was ~0.81 for binary classification models developed with 7994 chemicals. The sensitivity was 79.5% and the specificity was 67.3% for the HNN-Cancer, which outperforms the other methods. In the case of multiclass classification models with 1618 chemicals, we obtained the optimal accuracy of 70% with an AUC 0.7 for HNN-Cancer, RF, Bagging, and AdaBoost, respectively. In the case of regression models, the correlation coefficient (R) was around 0.62 for HNN-Cancer and RF higher than the SVM, GB, KR, DTBoost, and NN machine learning methods. Overall, the HNN-Cancer performed better for the majority of the known carcinogen experimental datasets. Further, the predictive performance of HNN-Cancer on diverse chemicals is comparable to the literature-reported models that included similar and less diverse molecules. Our HNN-Cancer could be used in identifying potentially carcinogenic chemicals for a wide variety of chemical classes.

Artificial intelligence uncovers carcinogenic human metabolites

The genome of a eukaryotic cell is often vulnerable to both intrinsic and extrinsic threats owing to its constant exposure to a myriad of heterogeneous compounds. Despite the availability of innate DNA damage responses, some genomic lesions trigger malignant transformation of cells. Accurate prediction of carcinogens is an ever-challenging task owing to the limited information about bona fide (non-)carcinogens. We developed Metabokiller, an ensemble classifier that accurately recognizes carcinogens by quantitatively assessing their electrophilicity, their potential to induce proliferation, oxidative stress, genomic instability, epigenome alterations, and anti-apoptotic response. Concomitant with the carcinogenicity prediction, Metabokiller is fully interpretable and outperforms existing best-practice methods for carcinogenicity prediction. Metabokiller unraveled potential carcinogenic human metabolites. To cross-validate Metabokiller predictions, we performed multiple functional assays using Saccharomyces cerevisiae and human cells with two Metabokiller-flagged human metabolites, namely 4-nitrocatechol and 3,4-dihydroxyphenylacetic acid, and observed high synergy between Metabokiller predictions and experimental validations.

Highly accurate machine learning prediction of crystal point groups for ternary materials from chemical formula

One of the most challenging problems in condensed matter physics is to predict crystal structure just from the chemical formula of the material. In this work, we present a robust machine learning (ML) predictor for the crystal point group of ternary materials (A\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$_l$$\end{document}lB\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$_m$$\end{document}mC\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$_n$$\end{document}n) - as first step to predict the structure - with very small set of ionic and positional fundamental features. From ML perspective, the problem is strenuous due to multi-labelity, multi-class, and data imbalance. The resulted prediction is very reliable as high balanced accuracies are obtained by different ML methods. Many similarity-based approaches resulted in a balanced accuracy above 95% indicating that the physics is well captured by the reduced set of features; namely, stoichiometry, ionic radii, ionization energies, and oxidation states for each of the three elements in the ternary compound. The accuracy is not limited by the approach; but rather by the limited data points and we should expect higher accuracy prediction by having more reliable data.

Machine learning models for classification tasks related to drug safety

In this review, we outline the current trends in the field of machine learning-driven classification studies related to ADME (absorption, distribution, metabolism and excretion) and toxicity endpoints from the past six years (2015-2021). The study focuses only on classification models with large datasets (i.e. more than a thousand compounds). A comprehensive literature search and meta-analysis was carried out for nine different targets: hERG-mediated cardiotoxicity, blood-brain barrier penetration, permeability glycoprotein (P-gp) substrate/inhibitor, cytochrome P450 enzyme family, acute oral toxicity, mutagenicity, carcinogenicity, respiratory toxicity and irritation/corrosion. The comparison of the best classification models was targeted to reveal the differences between machine learning algorithms and modeling types, endpoint-specific performances, dataset sizes and the different validation protocols. Based on the evaluation of the data, we can say that tree-based algorithms are (still) dominating the field, with consensus modeling being an increasing trend in drug safety predictions. Although one can already find classification models with great performances to hERG-mediated cardiotoxicity and the isoenzymes of the cytochrome P450 enzyme family, these targets are still central to ADMET-related research efforts.

Mining Toxicity Information from Large Amounts of Toxicity Data

Safety is a main reason for drug failures, and therefore, the detection of compound toxicity and potential adverse effects in the early stage of drug development is highly desirable. However, accurate prediction of many toxicity endpoints is extremely challenging due to low accessibility of sufficient and reliable toxicity data, as well as complicated and diversified mechanisms related to toxicity. In this study, we proposed the novel multitask graph attention (MGA) framework to learn the regression and classification tasks simultaneously. MGA has shown excellent predictive power on 33 toxicity data sets and has the capability to extract general toxicity features and generate customized toxicity fingerprints. In addition, MGA provides a new way to detect structural alerts and discover the relationship between different toxicity tasks, which will be quite helpful to mine toxicity information from large amounts of toxicity data.

Machine Learning in Predictive Toxicology: Recent Applications and Future Directions for Classification Models

In recent times, machine learning has become increasingly prominent in predictive toxicology as it has shifted from in vivo studies toward in silico studies. Currently, in vitro methods together with other computational methods such as quantitative structure-activity relationship modeling and absorption, distribution, metabolism, and excretion calculations are being used. An overview of machine learning and its applications in predictive toxicology is presented here, including support vector machines (SVMs), random forest (RF) and decision trees (DTs), neural networks, regression models, naïve Bayes, k-nearest neighbors, and ensemble learning. The recent successes of these machine learning methods in predictive toxicology are summarized, and a comparison of some models used in predictive toxicology is presented. In predictive toxicology, SVMs, RF, and DTs are the dominant machine learning methods due to the characteristics of the data available. Lastly, this review describes the current challenges facing the use of machine learning in predictive toxicology and offers insights into the possible areas of improvement in the field.

Prediction of potential inhibitors for RNA-dependent RNA polymerase of SARS-CoV-2 using comprehensive drug repurposing and molecular docking approach

The pandemic prevalence of COVID-19 has become a very serious global health issue. Scientists all over the world have been seriously attempting in the discovery of a drug to combat SARS-CoV-2. It has been found that RNA-dependent RNA polymerase (RdRp) plays a crucial role in SARS-CoV-2 replication, and thus could be a potential drug target. Here, comprehensive computational approaches including drug repurposing and molecular docking were employed to predict an effective drug candidate targeting RdRp of SARS-CoV-2. This study revealed that Rifabutin, Rifapentine, Fidaxomicin, 7-methyl-guanosine-5'-triphosphate-5'-guanosine and Ivermectin have a potential inhibitory interaction with RdRp of SARS-CoV-2 and could be effective drugs for COVID-19. In addition, virtual screening of the compounds from ZINC database also allowed the prediction of two compounds (ZINC09128258 and ZINC09883305) with pharmacophore features that interact effectively with RdRp of SARS-CoV-2, indicating their potentiality as effective inhibitors of the enzyme. Furthermore, ADME analysis along with analysis of toxicity was also undertaken to check the pharmacokinetics and drug-likeness properties of the two compounds. Comparative structural analysis of protein-inhibitor complexes revealed that the amino acids Y32, K47, Y122, Y129, H133, N138, D140, T141, S709 and N781 are crucial for drug surface hotspot in the RdRp of SARS-CoV-2.

Antiviral activity of astragaloside II, astragaloside III and astragaloside IV compounds against dengue virus: Computational docking and in vitro studies

This study was aimed to identify the phytocompounds possessing anti-dengue virus activity using in silico and in vitro approaches. A total of 7000 phytocompounds were virtually screened against protein targets (envelope, NS2b/NS3, and NS5) of dengue virus using iGEMDOCK and individually docked using Maestro 10.7 module of Schrödinger software. In vitro cytotoxicity and antiviral studies were performed using vero cell line. Finally, three phytocompounds namely astragaloside II, astragaloside III, and astragaloside IV were screened based on their highest binding energy values against protein targets. Astragaloside III exhibited the highest interaction energy value of -8.718 kcal/mol and -8.447 kcal/mol against envelope, and NS2b/NS3 targets, respectively. Astragaloside IV exhibited -7.244 kcal/mol against SAM site, and -9.179 kcal/mol against RNA cap site of NS5 targets. In silico ADMET analysis revealed that astragaloside II, III, and IV were non-mutagenic and non-carcinogenic in nature and these compounds were also non-toxic to vero cells upto 1000 μg/mL. Against dengue virus serotype 3, astragaloside II exhibited substantial antiviral activity at the concentration of 1.56 μg/mL followed by astragaloside III at 6.25 μg/mL and astragaloside IV at 12.5 μg/mL. Also, against dengue serotype 1, astragaloside II showed the maximum antiviral activity at 1.56 μg/mL followed by astragaloside III and IV at 3.125 μg/mL. This study concludes that astragaloside II, III, and IV compounds had potential in vitro anti-dengue virus activity.

Neural network activation similarity: a new measure to assist decision making in chemical toxicology

Deep learning neural networks, constructed for the prediction of chemical binding at 79 pharmacologically important human biological targets, show extremely high performance on test data (accuracy 92.2 ± 4.2%, MCC 0.814 ± 0.093 and ROC-AUC 0.96 ± 0.04). A new molecular similarity measure, Neural Network Activation Similarity, has been developed, based on signal propagation through the network. This is complementary to standard Tanimoto similarity, and the combined use increases confidence in the computer's prediction of activity for new chemicals by providing a greater understanding of the underlying justification. The in silico prediction of these human molecular initiating events is central to the future of chemical safety risk assessment and improves the efficiency of safety decision making.

Antitumor Cannabinoid Chemotypes: Structural Insights

Cannabis has long been known to limit or prevent nausea and vomiting, lack of appetite, and pain. For this reason, cannabinoids have been successfully used in the treatment of some of the unwanted side effects caused by cancer chemotherapy. Besides their palliative effects, research from the past two decades has demonstrated their promising potential as antitumor agents in a wide variety of tumors. Cannabinoids of endogenous, phytogenic, and synthetic nature have been shown to impact the proliferation of cancer through the modulation of different proteins involved in the endocannabinoid system such as the G protein-coupled receptors CB1, CB2, and GRP55, the ionotropic receptor TRPV1, or the fatty acid amide hydrolase (FAAH). In this article, we aim to structurally classify the antitumor cannabinoid chemotypes described so far according to their targets and types of cancer. In a drug discovery approach, their in silico pharmacokinetic profile has been evaluated in order to identify appropriate drug-like profiles, which should be taken into account for further progress toward the clinic. This analysis may provide structural insights into the selection of specific cannabinoid scaffolds for the development of antitumor drugs for the treatment of particular types of cancer.

ADMET-score - a comprehensive scoring function for evaluation of chemical drug-likeness

Chemical absorption, distribution, metabolism, excretion, and toxicity (ADMET), play key roles in drug discovery and development. A high-quality drug candidate should not only have sufficient efficacy against the therapeutic target, but also show appropriate ADMET properties at a therapeutic dose. A lot of in silico models are hence developed for prediction of chemical ADMET properties. However, it is still not easy to evaluate the drug-likeness of compounds in terms of so many ADMET properties. In this study, we proposed a scoring function named the ADMET-score to evaluate drug-likeness of a compound. The scoring function was defined on the basis of 18 ADMET properties predicted via our web server admetSAR. The weight of each property in the ADMET-score was determined by three parameters: the accuracy rate of the model, the importance of the endpoint in the process of pharmacokinetics, and the usefulness index. The FDA-approved drugs from DrugBank, the small molecules from ChEMBL and the old drugs withdrawn from the market due to safety concerns were used to evaluate the performance of the ADMET-score. The indices of the arithmetic mean and p-value showed that the ADMET-score among the three data sets differed significantly. Furthermore, we learned that there was no obvious linear correlation between the ADMET-score and QED (quantitative estimate of drug-likeness). These results suggested that the ADMET-score would be a comprehensive index to evaluate chemical drug-likeness, and might be helpful for users to select appropriate drug candidates for further development.

In Silico Prediction of Chemical Toxicity for Drug Design Using Machine Learning Methods and Structural Alerts

During drug development, safety is always the most important issue, including a variety of toxicities and adverse drug effects, which should be evaluated in preclinical and clinical trial phases. This review article at first simply introduced the computational methods used in prediction of chemical toxicity for drug design, including machine learning methods and structural alerts. Machine learning methods have been widely applied in qualitative classification and quantitative regression studies, while structural alerts can be regarded as a complementary tool for lead optimization. The emphasis of this article was put on the recent progress of predictive models built for various toxicities. Available databases and web servers were also provided. Though the methods and models are very helpful for drug design, there are still some challenges and limitations to be improved for drug safety assessment in the future.

The development and application of in silico models for drug induced liver injury

Drug-induced liver injury (DILI), caused by drugs, herbal agents or nutritional supplements, is a major issue for patients and the pharmaceutical industry. It has been a leading cause of clinical trials failure and withdrawal of FDA approval. In this research, we focused on in silico estimation of chemical DILI potential on humans based on structurally diverse organic chemicals. We developed a series of binary classification models using five different machine learning methods and eight different feature reduction methods. The model, developed with the support vector machine (SVM) and the MACCS fingerprint, performed best both on the test set and external validation. It achieved a prediction accuracy of 80.39% on the test set and 82.78% on external validation. We made this model available at http://opensource.vslead.com/. The user can freely predict the DILI potential of molecules. Furthermore, we analyzed the difference of distributions of 12 key physical-chemical properties between DILI-positive and DILI-negative compounds and 20 privileged substructures responsible for DILI were identified from the Klekota-Roth fingerprint. Moreover, since traditional Chinese medicine (TCM)-induced liver injury is also one of the major concerns among the toxic effects, we evaluated the DILI potential of TCM ingredients using the MACCS_SVM model developed in this study. We hope the model and privileged substructures could be useful complementary tools for chemical DILI evaluation.

Combining machine learning models of in vitro and in vivo bioassays improves rat carcinogenicity prediction

In vitro genotoxicity bioassays are cost-efficient methods of assessing potential carcinogens. However, many genotoxicity bioassays are inappropriate for detecting chemicals eliciting non-genotoxic mechanisms, such as tumour promotion, this necessitates the use of in vivo rodent carcinogenicity (IVRC) assays. In silico IVRC modelling could potentially address the low throughput and high cost of this assay. We aimed to develop and combine computational QSAR models of novel bioassays for the prediction of IVRC results and compare with existing software. QSAR models were generated from existing Ames (n = 6512), Syrian Hamster Embryonic (SHE, n = 410), ISSCAN rodent carcinogenicity (ISC, n = 834) and GreenScreen GADD45a-GFP (n = 1415) chemical datasets. These models mapped the molecular descriptors of each compound to their respective assay result using machine learning algorithms (adaboost, k-Nearest Neighbours, C.45 Decision Tree, Multilayer Perceptron, Random Forest). The best performing models were combined with k-Nearest Neighbours to create a cascade model for IVRC prediction. High QSAR model performance was observed from ten time 10-fold cross-validation with above 80% accuracy and 0.85 AUC for each assay dataset. The cascade model predicted rat carcinogenicity with 69.3% accuracy and 0.700 AUC. This study demonstrates the novelty of a combined approach for IVRC prediction, with higher performance than existing software.

Insights into the Molecular Basis of the Acute Contact Toxicity of Diverse Organic Chemicals in the Honey Bee

Use of chemical pollutants, including pesticides and other industrial chemicals, has resulted in significant risks to the whole ecosystem. Therefore, ecological risk assessment of chemicals is vital and necessary. Since the honey bee (Apis mellifera) is probably among the most exposed species to the polluting chemicals, we focused on the in silico estimation of honey bee toxicity (HBT) of chemicals and the analysis of the relevance of chemical HBT and several key physical-chemical properties and structural characteristics. A total of 40 classification models were developed by combination of five machine learning methods along with seven kinds of fingerprints and a set of molecular descriptors. After 5-fold cross validation and external validation, several models showed good predictive power. The relevance of 12 key physical-chemical properties and chemical HBT was also investigated. Five properties, including AlogP, logD, molecular weight (MW), molecular surface area (MSA), and the number of rotatable bonds (nRTB), indicated positive correlation coefficients with HBT, while molecular solubility (logS) and the number of hydrogen bond donors (nHBD) indicated negative correlation coefficients. Finally, seven privileged substructures responsible for chemical HBT were identified from KRFP and SubFP fingerprints. The results of this study should provide critical information and useful tools for chemical HBT estimation in environmental risk assessment.

In silico prediction of pesticide aquatic toxicity with chemical category approaches

Aquatic toxicity is an important issue in pesticide development. In this study, using nine molecular fingerprints to describe pesticides, binary and ternary classification models were constructed to predict aquatic toxicity of pesticides via six machine learning methods: Naïve Bayes (NB), Artificial Neural Network (ANN), k-Nearest Neighbor (kNN), Classification Tree (CT), Random Forest (RF) and Support Vector Machine (SVM). For the binary models, local models were obtained with 829 pesticides on rainbow trout (RT) and 151 pesticides on lepomis (LP), and global models were constructed on the basis of 1258 diverse pesticides on RT and LP and 278 on other fish species. After analyzing the local binary models, we found that fish species caused influence in terms of accuracy. Considering the data size and predictive range, the 1258 pesticides were also used to build global ternary models. The best local binary models were Maccs_ANN for RT and Maccs_SVM for LP, which exhibited accuracies of 0.90 and 0.90, respectively. For global binary models, the best model was Graph_SVM with an accuracy of 0.89. Accuracy of the best global ternary model Graph_SVM was 0.81, which was a little lower than that of the best global binary model. In addition, several substructural alerts were identified including nitrobenzene, chloroalkene and nitrile, which could significantly correlate with pesticide aquatic toxicity. This study provides a useful tool for an early evaluation of pesticide aquatic toxicity in environmental risk assessment.

Modeling of the hERG K+ Channel Blockage Using Online Chemical Database and Modeling Environment (OCHEM)

Human ether-a-go-go related gene (hERG) K+ channel plays an important role in cardiac action potential. Blockage of hERG channel may result in long QT syndrome (LQTS), even cause sudden cardiac death. Many drugs have been withdrawn from the market because of the serious hERG-related cardiotoxicity. Therefore, it is quite essential to estimate the chemical blockage of hERG in the early stage of drug discovery. In this study, a diverse set of 3721 compounds with hERG inhibition data was assembled from literature. Then, we make full use of the Online Chemical Modeling Environment (OCHEM), which supplies rich machine learning methods and descriptor sets, to build a series of classification models for hERG blockage. We also generated two consensus models based on the top-performing individual models. The consensus models performed much better than the individual models both on 5-fold cross validation and external validation. Especially, consensus model II yielded the prediction accuracy of 89.5 % and MCC of 0.670 on external validation. This result indicated that the predictive power of consensus model II should be stronger than most of the previously reported models. The 17 top-performing individual models and the consensus models and the data sets used for model development are available at https://ochem.eu/article/103592.

In silico prediction of chemical subcellular localization via multi-classification methods

Chemical subcellular localization is closely related to drug distribution in the body and hence important in drug discovery and design. Although many in vivo and in vitro methods have been developed, in silico methods play key roles in the prediction of chemical subcellular localization due to their low costs and high performance. For that purpose, machine learning-based methods were developed here. At first, 614 unique compounds localized in the lysosome, mitochondria, nucleus and plasma membrane were collected from the literature. 80% of the compounds were used to build the models and the rest as the external validation set. Both fingerprints and molecular descriptors were used to describe the molecules, and six machine learning methods were applied to build the multi-classification models. The performance of the models was measured by 5-fold cross-validation and external validation. We further detected key substructures for each localization and analyzed potential structure-localization relationships, which could be very helpful for molecular design and modification. The key substructures can also be used as features complementary to fingerprints to improve the performance of the models.

CarcinoPred-EL: Novel models for predicting the carcinogenicity of chemicals using molecular fingerprints and ensemble learning methods

Carcinogenicity refers to a highly toxic end point of certain chemicals, and has become an important issue in the drug development process. In this study, three novel ensemble classification models, namely Ensemble SVM, Ensemble RF, and Ensemble XGBoost, were developed to predict carcinogenicity of chemicals using seven types of molecular fingerprints and three machine learning methods based on a dataset containing 1003 diverse compounds with rat carcinogenicity. Among these three models, Ensemble XGBoost is found to be the best, giving an average accuracy of 70.1 ± 2.9%, sensitivity of 67.0 ± 5.0%, and specificity of 73.1 ± 4.4% in five-fold cross-validation and an accuracy of 70.0%, sensitivity of 65.2%, and specificity of 76.5% in external validation. In comparison with some recent methods, the ensemble models outperform some machine learning-based approaches and yield equal accuracy and higher specificity but lower sensitivity than rule-based expert systems. It is also found that the ensemble models could be further improved if more data were available. As an application, the ensemble models are employed to discover potential carcinogens in the DrugBank database. The results indicate that the proposed models are helpful in predicting the carcinogenicity of chemicals. A web server called CarcinoPred-EL has been built for these models (http://ccsipb.lnu.edu.cn/toxicity/CarcinoPred-EL/).

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.

Classification of the fragrant styles and evaluation of the aromatic quality of flue-cured tobacco leaves by machine-learning methods

During commercial transactions, the quality of flue-cured tobacco leaves must be characterized efficiently, and the evaluation system should be easily transferable across different traders. However, there are over 3000 chemical compounds in flue-cured tobacco leaves; thus, it is impossible to evaluate the quality of flue-cured tobacco leaves using all the chemical compounds. In this paper, we used Support Vector Machine (SVM) algorithm together with 22 chemical compounds selected by ReliefF-Particle Swarm Optimization (R-PSO) to classify the fragrant style of flue-cured tobacco leaves, where the Accuracy (ACC) and Matthews Correlation Coefficient (MCC) were 90.95% and 0.80, respectively. SVM algorithm combined with 19 chemical compounds selected by R-PSO achieved the best assessment performance of the aromatic quality of tobacco leaves, where the PCC and MSE were 0.594 and 0.263, respectively. Finally, we constructed two online tools to classify the fragrant style and evaluate the aromatic quality of flue-cured tobacco leaf samples. These tools can be accessed at http://bioinformatics.fafu.edu.cn/tobacco .