Oversampling to Overcome Overfitting: Exploring the Relationship between Data Set Composition, Molecular Descriptors, and Predictive Modeling Methods

Predicting Free Energies of Exfoliation and Solvation for Graphitic Carbon Nitrides Using Machine Learning

As a metal-free and visible-light-responsive photocatalyst, graphitic carbon nitride (g-C3N4) has emerged as a new research hotspot and has attracted broad attention in the field of solar energy conversion and thin-film transistors. Liquid-phase exfoliation (LPE) is the best-known method for the synthesis of 2D g-C3N4 nanosheets. In LPE, bulk g-C3N4 is exfoliated in a solvent via high-shear mixing or sonication in order to produce a stable suspension of individual nanosheets. Two parameters of importance in gauging the performance of a solvent in LPE are the free energy required to exfoliate a unit area of layered materials into individual sheets in the solvent (ΔGexf) and the solvation free energy per unit area of a nanosheet (ΔGsol). While approximations for the free energies exist, they are shown in our previous work to be inaccurate and incapable of capturing the experimentally observed efficacy of LPE. Molecular dynamics (MD) simulations can provide accurate free-energy calculations, but doing so for every single solvent is time- and resource-consuming. Herein, machine learning (ML) algorithms are used to predict ΔGexf and ΔGsol for g-C3N4. First, a database for ΔGexf and ΔGsol is created based on a series of MD simulations involving 49 different solvents with distinct chemical structures and properties. The data set also includes values of critical descriptors for the solvents, including density, surface tension, dielectric constant, etc. Different ML methods are compared, accompanied by descriptor selection, to develop the most accurate model for predicting ΔGexf and ΔGsol. The extra tree regressor is shown to be the best performer among the six ML methods studied. Experimental validation of the model is conducted by performing dispersibility tests in several solvents for which the free energies are predicted. Finally, the influence of the selected descriptors on the free energies is analyzed, and strategies for solvent selection in LPE are proposed.

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.

Property Prediction and Structural Feature Extraction of Polyimide Materials Based on Machine Learning

The construction of material prediction models using machine learning algorithms can aid in the polyimide structural design and screening of materials as well as accelerate the development of new materials. There is a lack of research on predicting the optical properties of polyimide materials and the interpretation of the structural features. Here, we collected 652 polyimide molecular structures and used seven popular machine learning algorithms to predict the glass transition temperature and cut-off wavelength of polyimide materials and extract key feature information of repeating unit structures. The results showed that the root mean square error of the glass transition temperature prediction model was 33.92 °C, and the correlation coefficient was 0.861. The root mean square error of the cut-off wavelength prediction model was 17.18 nm, and the correlation coefficient was 0.837. The elasticity of the molecular structure was also found to be the key factor affecting glass transition temperature, and the presence and location of heterogeneous atoms had a significant effect on the cut-off wavelengths. Finally, eight polyimide materials were synthesized to test the accuracy of the prediction models, and the experimental characterization values agreed with the predicted values. The results would contribute to the development of polyimide structural design and materials preparation for flexible display.

Ensemble modeling with machine learning and deep learning to provide interpretable generalized rules for classifying CNS drugs with high prediction power

The trade-off between a machine learning (ML) and deep learning (DL) model's predictability and its interpretability has been a rising concern in central nervous system-related quantitative structure-activity relationship (CNS-QSAR) analysis. Many state-of-the-art predictive modeling failed to provide structural insights due to their black box-like nature. Lack of interpretability and further to provide easy simple rules would be challenging for CNS-QSAR models. To address these issues, we develop a protocol to combine the power of ML and DL to generate a set of simple rules that are easy to interpret with high prediction power. A data set of 940 market drugs (315 CNS-active, 625 CNS-inactive) with support vector machine and graph convolutional network algorithms were used. Individual ML/DL modeling methods were also constructed for comparison. The performance of these models was evaluated using an additional external dataset of 117 market drugs (42 CNS-active, 75 CNS-inactive). Fingerprint-split validation was adopted to ensure model stringency and generalizability. The resulting novel hybrid ensemble model outperformed other constituent traditional QSAR models with an accuracy of 0.96 and an F1 score of 0.95. With the power of the interpretability provided with this protocol, our model laid down a set of simple physicochemical rules to determine whether a compound can be a CNS drug using six sub-structural features. These rules displayed higher classification ability than classical guidelines, with higher specificity and more mechanistic insights than just for blood-brain barrier permeability. This hybrid protocol can potentially be used for other drug property predictions.

Machine Learning in Prediction of Bladder Cancer on Clinical Laboratory Data

Bladder cancer has been increasing globally. Urinary cytology is considered a major screening method for bladder cancer, but it has poor sensitivity. This study aimed to utilize clinical laboratory data and machine learning methods to build predictive models of bladder cancer. A total of 1336 patients with cystitis, bladder cancer, kidney cancer, uterus cancer, and prostate cancer were enrolled in this study. Two-step feature selection combined with WEKA and forward selection was performed. Furthermore, five machine learning models, including decision tree, random forest, support vector machine, extreme gradient boosting (XGBoost), and light gradient boosting machine (GBM) were applied. Features, including calcium, alkaline phosphatase (ALP), albumin, urine ketone, urine occult blood, creatinine, alanine aminotransferase (ALT), and diabetes were selected. The lightGBM model obtained an accuracy of 84.8% to 86.9%, a sensitivity 84% to 87.8%, a specificity of 82.9% to 86.7%, and an area under the curve (AUC) of 0.88 to 0.92 in discriminating bladder cancer from cystitis and other cancers. Our study provides a demonstration of utilizing clinical laboratory data to predict bladder cancer.

GPCR_LigandClassify.py; a rigorous machine learning classifier for GPCR targeting compounds

The current study describes the construction of various ligand-based machine learning models to be used for drug-repurposing against the family of G-Protein Coupled Receptors (GPCRs). In building these models, we collected > 500,000 data points, encompassing experimentally measured molecular association data of > 160,000 unique ligands against > 250 GPCRs. These data points were retrieved from the GPCR-Ligand Association (GLASS) database. We have used diverse molecular featurization methods to describe the input molecules. Multiple supervised ML algorithms were developed, tested and compared for their accuracy, F scores, as well as for their Matthews' correlation coefficient scores (MCC). Our data suggest that combined with molecular fingerprinting, ensemble decision trees and gradient boosted trees ML algorithms are on the accuracy border of the rather sophisticated deep neural nets (DNNs)-based algorithms. On a test dataset, these models displayed an excellent performance, reaching a ~ 90% classification accuracy. Additionally, we showcase a few examples where our models were able to identify interesting connections between known drugs from the Drug-Bank database and members of the GPCR family of receptors. Our findings are in excellent agreement with previously reported experimental observations in the literature. We hope the models presented in this paper synergize with the currently ongoing interest of applying machine learning modeling in the field of drug repurposing and computational drug discovery in general.

Comparison of Cellular Morphological Descriptors and Molecular Fingerprints for the Prediction of Cytotoxicity- and Proliferation-Related Assays

Cell morphology features, such as those from the Cell Painting assay, can be generated at relatively low costs and represent versatile biological descriptors of a system and thereby compound response. In this study, we explored cell morphology descriptors and molecular fingerprints, separately and in combination, for the prediction of cytotoxicity- and proliferation-related in vitro assay endpoints. We selected 135 compounds from the MoleculeNet ToxCast benchmark data set which were annotated with Cell Painting readouts, where the relatively small size of the data set is due to the overlap of required annotations. We trained Random Forest classification models using nested cross-validation and Cell Painting descriptors, Morgan and ErG fingerprints, and their combinations. While using leave-one-cluster-out cross-validation (with clusters based on physicochemical descriptors), models using Cell Painting descriptors achieved higher average performance over all assays (Balanced Accuracy of 0.65, Matthews Correlation Coefficient of 0.28, and AUC-ROC of 0.71) compared to models using ErG fingerprints (BA 0.55, MCC 0.09, and AUC-ROC 0.60) and Morgan fingerprints alone (BA 0.54, MCC 0.06, and AUC-ROC 0.56). While using random shuffle splits, the combination of Cell Painting descriptors with ErG and Morgan fingerprints further improved balanced accuracy on average by 8.9% (in 9 out of 12 assays) and 23.4% (in 8 out of 12 assays) compared to using only ErG and Morgan fingerprints, respectively. Regarding feature importance, Cell Painting descriptors related to nuclei texture, granularity of cells, and cytoplasm as well as cell neighbors and radial distributions were identified to be most contributing, which is plausible given the endpoint considered. We conclude that cell morphological descriptors contain complementary information to molecular fingerprints which can be used to improve the performance of predictive cytotoxicity models, in particular in areas of novel structural space.

Poverty Classification Using Machine Learning: The Case of Jordan

The scope of this paper is focused on the multidimensional poverty problem in Jordan. Household expenditure and income surveys provide data that are used for identifying and measuring the poverty status of Jordanian households. However, carrying out such surveys is hard, time consuming, and expensive. Machine learning could revolutionize this process. The contribution of this work is the proposal of an original machine learning approach to assess and monitor the poverty status of Jordanian households. This approach takes into account all the household expenditure and income surveys that took place since the early beginning of the new millennium. This approach is accurate, inexpensive, and makes poverty identification cheaper and much closer to real-time. Data preprocessing and handling imbalanced data are major parts of this work. Various machine learning classification models are applied. The LightGBM algorithm has achieved the best performance with 81% F1-Score. The final machine learning classification model could transform efforts to track and target poverty across the country. This work demonstrates how powerful and versatile machine learning can be, and hence, it promotes for adoption across many domains in both the private sector and government.

Handling Imbalance Classification Virtual Screening Big Data Using Machine Learning Algorithms

Virtual screening is the most critical process in drug discovery, and it relies on machine learning to facilitate the screening process. It enables the discovery of molecules that bind to a specific protein to form a drug. Despite its benefits, virtual screening generates enormous data and suffers from drawbacks such as high dimensions and imbalance. This paper tackles data imbalance and aims to improve virtual screening accuracy, especially for a minority dataset. For a dataset identified without considering the data’s imbalanced nature, most classification methods tend to have high predictive accuracy for the majority category. However, the accuracy was significantly poor for the minority category. The paper proposes a K-mean algorithm coupled with Synthetic Minority Oversampling Technique (SMOTE) to overcome the problem of imbalanced datasets. The proposed algorithm is named as KSMOTE. Using KSMOTE, minority data can be identified at high accuracy and can be detected at high precision. A large set of experiments were implemented on Apache Spark using numeric PaDEL and fingerprint descriptors. The proposed solution was compared to both no-sampling method and SMOTE on the same datasets. Experimental results showed that the proposed solution outperformed other methods.

Effective Feature Selection Method for Class-Imbalance Datasets Applied to Chemical Toxicity Prediction

During the drug development process, it is common to carry out toxicity tests and adverse effect studies, which are essential to guarantee patient safety and the success of the research. The use of in silico quantitative structure-activity relationship (QSAR) approaches for this task involves processing a huge amount of data that, in many cases, have an imbalanced distribution of active and inactive samples. This is usually termed the class-imbalance problem and may have a significant negative effect on the performance of the learned models. The performance of feature selection (FS) for QSAR models is usually damaged by the class-imbalance nature of the involved datasets. This paper proposes the use of an FS method focused on dealing with the class-imbalance problems. The method is based on the use of FS ensembles constructed by boosting and using two well-known FS methods, fast clustering-based FS and the fast correlation-based filter. The experimental results demonstrate the efficiency of the proposal in terms of the classification performance compared to standard methods. The proposal can be extended to other FS methods and applied to other problems in cheminformatics.

Current development of integrated web servers for preclinical safety and pharmacokinetics assessments in drug development

In drug development, preclinical safety and pharmacokinetics assessments of candidate drugs to ensure the safety profile are a must. While in vivo and in vitro tests are traditionally used, experimental determinations have disadvantages, as they are usually time-consuming and costly. In silico predictions of these preclinical endpoints have each been developed in the past decades. However, only a few web-based tools have integrated different models to provide a simple one-step platform to help researchers thoroughly evaluate potential drug candidates. To efficiently achieve this approach, a platform for preclinical evaluation must not only predict key ADMET (absorption, distribution, metabolism, excretion and toxicity) properties but also provide some guidance on structural modifications to improve the undesired properties. In this review, we organized and compared several existing integrated web servers that can be adopted in preclinical drug development projects to evaluate the subject of interest. We also introduced our new web server, Virtual Rat, as an alternative choice to profile the properties of drug candidates. In Virtual Rat, we provide not only predictions of important ADMET properties but also possible reasons as to why the model made those structural predictions. Multiple models were implemented into Virtual Rat, including models for predicting human ether-a-go-go-related gene (hERG) inhibition, cytochrome P450 (CYP) inhibition, mutagenicity (Ames test), blood-brain barrier penetration, cytotoxicity and Caco-2 permeability. Virtual Rat is free and has been made publicly available at https://virtualrat.cmdm.tw/.

Testing Novel Portland Cement Formulations with Carbon Nanotubes and Intrinsic Properties Revelation: Nanoindentation Analysis with Machine Learning on Microstructure Identification

Nanoindentation was utilized as a non-destructive technique to identify Portland Cement hydration phases. Artificial Intelligence (AI) and semi-supervised Machine Learning (ML) were used for knowledge gain on the effect of carbon nanotubes to nanomechanics in novel cement formulations. Data labelling is performed with unsupervised ML with k-means clustering. Supervised ML classification is used in order to predict the hydration products composition and 97.6% accuracy was achieved. Analysis included multiple nanoindentation raw data variables, and required less time to execute than conventional single component probability density analysis (PDA). Also, PDA was less informative than ML regarding information exchange and re-usability of input in design predictions. In principle, ML is the appropriate science for predictive modeling, such as cement phase identification and facilitates the acquisition of precise results. This study introduces unbiased structure-property relations with ML to monitor cement durability based on cement phases nanomechanics compared to PDA, which offers a solution based on local optima of a multidimensional space solution. Evaluation of nanomaterials inclusion in composite reinforcement using semi-supervised ML was proved feasible. This methodology is expected to contribute to design informatics due to the high prediction metrics, which holds promise for the transfer learning potential of these models for studying other novel cement formulations.

DeepSnap-Deep Learning Approach Predicts Progesterone Receptor Antagonist Activity With High Performance

The progesterone receptor (PR) is important therapeutic target for many malignancies and endocrine disorders due to its role in controlling ovulation and pregnancy via the reproductive cycle. Therefore, the modulation of PR activity using its agonists and antagonists is receiving increasing interest as novel treatment strategy. However, clinical trials using the PR modulators have not yet been found conclusive evidences. Recently, increasing evidence from several fields shows that the classification of chemical compounds, including agonists and antagonists, can be done with recent improvements in deep learning (DL) using deep neural network. Therefore, we recently proposed a novel DL-based quantitative structure-activity relationship (QSAR) strategy using transfer learning to build prediction models for agonists and antagonists. By employing this novel approach, referred as DeepSnap-DL method, which uses images captured from 3-dimension (3D) chemical structure with multiple angles as input data into the DL classification, we constructed prediction models of the PR antagonists in this study. Here, the DeepSnap-DL method showed a high performance prediction of the PR antagonists by optimization of some parameters and image adjustment from 3D-structures. Furthermore, comparison of the prediction models from this approach with conventional machine learnings (MLs) indicated the DeepSnap-DL method outperformed these MLs. Therefore, the models predicted by DeepSnap-DL would be powerful tool for not only QSAR field in predicting physiological and agonist/antagonist activities, toxicity, and molecular bindings; but also for identifying biological or pathological phenomena.

Applying Machine Learning to Nanoindentation Data of (Nano-) Enhanced Composites

Carbon fiber reinforced polymers (CFRPs) are continuously gaining attention in aerospace and space applications, and especially their multi-scale reinforcement with nanoadditives. Carbon nanotubes (CNTs), graphene, carbon nanofibers (CNFs), and their functionalized forms are often incorporated into interactive systems to engage specific changes in the environment of application to a smart response. Structural integrity of these nanoscale reinforced composites is assessed with advanced characterization techniques, with the most prominent being nanoindentation testing. Nanoindentation is a well-established technique, which enables quantitative mapping of nanomechanical properties with the μm surficial and nm indentation resolution scale and high precision characterization. This feature enables the characterization of the interface in a statistical and quantitative manner and the correlation of (nano-) reinforcement to interface properties of CFRPs. Identification of reinforcement is performed with k-Nearest Neighbors and Support Vector Machine classification algorithms. Expertise is necessary to describe the physical problem and create representative training/testing datasets. Development of open source Machine Learning algorithms can have an influential impact on uniformity of nanometry data creation and management. The statistical character of nanoindentation is a key factor to supply information on heterogeneity of multiscale reinforced composites. Both the identification of (nano-) reinforcement and quality assessment of composites are provided by involving artificial intelligence.

A Way towards Reliable Predictive Methods for the Prediction of Physicochemical Properties of Chemicals Using the Group Contribution and other Methods

Physicochemical properties of chemicals as referred to in this review include, for example, thermodynamic properties such as heat of formation, boiling point, toxicity of molecules and the fate of molecules whenever undergoing or accelerating (catalytic) a chemical reaction and therewith about chemical equilibrium, that is, the equilibrium in chemical reactions. All such properties have been predicted in literature by a variety of methods. However, for the experimental scientist for whom such predictions are of relevance, the accuracies are often far from sufficient for reliable application We discuss current practices and suggest how one could arrive at better, that is sufficiently accurate and reliable, predictive methods. Some recently published examples have shown this to be possible in practical cases. In summary, this review focuses on methodologies to obtain the required accuracies for the chemical practitioner and process technologist designing chemical processes. Finally, something almost never explicitly mentioned is the fact that whereas for some practical cases very accurate predictions are required, for other cases a qualitatively correct picture with relatively low correlation coefficients can be sufficient as a valuable predictive tool. Requirements for acceptable predictive methods can therefore be significantly different depending on the actual application, which are illustrated using real-life examples, primarily with industrial relevance. Furthermore, for specific properties such as the octanol-water partition coefficient more close collaboration between research groups using different methods would greatly facilitate progress in the field of predictive modelling.

Advancing Computational Toxicology in the Big Data Era by Artificial Intelligence: Data-Driven and Mechanism-Driven Modeling for Chemical Toxicity

In 2016, the Frank R. Lautenberg Chemical Safety for the 21st Century Act became the first US legislation to advance chemical safety evaluations by utilizing novel testing approaches that reduce the testing of vertebrate animals. Central to this mission is the advancement of computational toxicology and artificial intelligence approaches to implementing innovative testing methods. In the current big data era, the terms volume (amount of data), velocity (growth of data), and variety (the diversity of sources) have been used to characterize the currently available chemical, in vitro, and in vivo data for toxicity modeling purposes. Furthermore, as suggested by various scientists, the variability (internal consistency or lack thereof) of publicly available data pools, such as PubChem, also presents significant computational challenges. The development of novel artificial intelligence approaches based on public massive toxicity data is urgently needed to generate new predictive models for chemical toxicity evaluations and make the developed models applicable as alternatives for evaluating untested compounds. In this procedure, traditional approaches (e.g., QSAR) purely based on chemical structures have been replaced by newly designed data-driven and mechanism-driven modeling. The resulting models realize the concept of adverse outcome pathway (AOP), which can not only directly evaluate toxicity potentials of new compounds, but also illustrate relevant toxicity mechanisms. The recent advancement of computational toxicology in the big data era has paved the road to future toxicity testing, which will significantly impact on the public health.

Predicting the cytotoxicity of chemicals using ensemble learning methods and molecular fingerprints

The prediction of compound cytotoxicity is an important part of the drug discovery process. However, it usually appears as poor predictive performance because the datasets are high-throughput and have a class-imbalance problem. In this study, several strategies of performing a structure-activity relationship study for a cytotoxic endpoint in the AID364 dataset were explored to solve the class-imbalance problem. Random forest adaboost was used as the base learners for 10 types of molecular fingerprints and an ensemble method and six data-balancing methods were applied to balance the classes. As a result, the ensemble model using MACCS fingerprint was found to be the best, giving area under the curve of 85.2% ± 0.35%, sensitivity of 81.8% ± 0.65%, and specificity of 76.0% ± 0.12% in fivefold cross-validation and area under the curve of 78.8%, sensitivity of 55.5% and specificity of 78.5% in external validation. Good performance also appeared on other datasets with different sizes/degrees of imbalance. To explore the structural commonality of cytotoxic compounds, several substructures were identified as an important reference for substructure alerts. The convincing results indicate that the proposed models are helpful in predicting the cytotoxicity of chemicals.

Predicting reference soil groups using legacy data: A data pruning and Random Forest approach for tropical environment (Dano catchment, Burkina Faso)

Predicting taxonomic classes can be challenging with dataset subject to substantial irregularities due to the involvement of many surveyors. A data pruning approach was used in the present study to reduce such source errors by exploring whether different data pruning methods, which result in different subsets of a major reference soil groups (RSG) – the Plinthosols – would lead to an increase in prediction accuracy of the minor soil groups by using Random Forest (RF). This method was compared to the random oversampling approach. Four datasets were used, including the entire dataset and the pruned dataset, which consisted of 80% and 90% respectively, and standard deviation core range of the Plinthosols data while cutting off all data points belonging to the outer range. The best prediction was achieved when RF was used with recursive feature elimination along with the non-oversampled 90% core range dataset. This model provided a substantial agreement to observation, with a kappa value of 0.57 along with 7% to 35% increase in prediction accuracy for smaller RSG. The reference soil groups in the Dano catchment appeared to be mainly influenced by the wetness index, a proxy for soil moisture distribution.

Naïve Bayesian Models for Vero Cell Cytotoxicity

PURPOSE

To advance translational research of potential therapeutic small molecules against infectious microbes, the compounds must display a relative lack of mammalian cell cytotoxicity. Vero cell cytotoxicity (CC₅₀) is a common initial assay for this metric. We explored the development of naïve Bayesian models that can enhance the probability of identifying non-cytotoxic compounds.

METHODS

Vero cell cytotoxicity assays were identified in PubChem, reformatted, and curated to create a training set with 8741 unique small molecules. These data were used to develop Bayesian classifiers, which were assessed with internal cross-validation, external tests with a set of 193 compounds from our laboratory, and independent validation with an additional diverse set of 1609 unique compounds from PubChem.

RESULTS

Evaluation with independent, external test and validation sets indicated that cytotoxicity Bayesian models constructed with the ECFP_6 descriptor were more accurate than those that used FCFP_6 fingerprints. The best cytotoxicity Bayesian model displayed predictive power in external evaluations, according to conventional and chance-corrected statistics, as well as enrichment factors.

CONCLUSIONS

The results from external tests demonstrate that our novel cytotoxicity Bayesian model displays sufficient predictive power to help guide translational research. To assist the chemical tool and drug discovery communities, our curated training set is being distributed as part of the Supplementary Material. Graphical Abstract Naive Bayesian models have been trained with publically available data and offer a useful tool for chemical biology and drug discovery to select for small molecules with a high probability of exhibiting acceptably low Vero cell cytotoxicity.

ADMET Evaluation in Drug Discovery. Part 17: Development of Quantitative and Qualitative Prediction Models for Chemical-Induced Respiratory Toxicity

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 (q²_ext = 0.707), and the XGBoost classification model achieves the most accurate qualitative predictions for the test set (MCC of 0.644, AUC of 0.893, and global accuracy of 82.62%). The application domains were analyzed, and all of the tested compounds fall within the application domain coverage. We also examined the structural features of the compounds and important fragments with large prediction errors. In conclusion, the SVM regression model and the XGBoost classification model can be employed as accurate prediction tools for respiratory toxicity.

Modelling compound cytotoxicity using conformal prediction and PubChem HTS data

The assessment of compound cytotoxicity is an important part of the drug discovery process. Accurate predictions of cytotoxicity have the potential to expedite decision making and save considerable time and effort. In this work we apply class conditional conformal prediction to model the cytotoxicity of compounds based on 16 high throughput cytotoxicity assays from PubChem. The data span 16 cell lines and comprise more than 440 000 unique compounds. The data sets are heavily imbalanced with only 0.8% of the tested compounds being cytotoxic. We trained one classification model for each cell line and validated the performance with respect to validity and accuracy. The generated models deliver high quality predictions for both toxic and non-toxic compounds despite the imbalance between the two classes. On external data collected from the same assay provider as one of the investigated cell lines the model had a sensitivity of 74% and a specificity of 65% at the 80% confidence level among the compounds assigned to a single class. Compared to previous approaches for large scale cytotoxicity modelling, this represents a balanced performance in the prediction of the toxic and non-toxic classes. The conformal prediction framework also allows the modeller to control the error frequency of the predictions, allowing predictions of cytotoxicity outcomes with confidence.

Getting the most out of PubChem for virtual screening

INTRODUCTION

With the emergence of the 'big data' era, the biomedical research community has great interest in exploiting publicly available chemical information for drug discovery. PubChem is an example of public databases that provide a large amount of chemical information free of charge.

AREAS COVERED

This article provides an overview of how PubChem's data, tools, and services can be used for virtual screening and reviews recent publications that discuss important aspects of exploiting PubChem for drug discovery.

EXPERT OPINION

PubChem offers comprehensive chemical information useful for drug discovery. It also provides multiple programmatic access routes, which are essential to build automated virtual screening pipelines that exploit PubChem data. In addition, PubChemRDF allows users to download PubChem data and load them into a local computing facility, facilitating data integration between PubChem and other resources. PubChem resources have been used in many studies for developing bioactivity and toxicity prediction models, discovering polypharmacologic (multi-target) ligands, and identifying new macromolecule targets of compounds (for drug-repurposing or off-target side effect prediction). These studies demonstrate the usefulness of PubChem as a key resource for computer-aided drug discovery and related area.

Modern approaches to accelerate discovery of new antischistosomal drugs

INTRODUCTION

The almost exclusive use of only praziquantel for the treatment of schistosomiasis has raised concerns about the possible emergence of drug-resistant schistosomes. Consequently, there is an urgent need for new antischistosomal drugs. The identification of leads and the generation of high quality data are crucial steps in the early stages of schistosome drug discovery projects.

AREAS COVERED

Herein, the authors focus on the current developments in antischistosomal lead discovery, specifically referring to the use of automated in vitro target-based and whole-organism screens and virtual screening of chemical databases. They highlight the strengths and pitfalls of each of the above-mentioned approaches, and suggest possible roadmaps towards the integration of several strategies, which may contribute for optimizing research outputs and led to more successful and cost-effective drug discovery endeavors.

EXPERT OPINION

Increasing partnerships and access to funding for drug discovery have strengthened the battle against schistosomiasis in recent years. However, the authors believe this battle also includes innovative strategies to overcome scientific challenges. In this context, significant advances of in vitro screening as well as computer-aided drug discovery have contributed to increase the success rate and reduce the costs of drug discovery campaigns. Although some of these approaches were already used in current antischistosomal lead discovery pipelines, the integration of these strategies in a solid workflow should allow the production of new treatments for schistosomiasis in the near future.

Discovery of Influenza A virus neuraminidase inhibitors using support vector machine and Naïve Bayesian models

Neuraminidase (NA) is a critical enzyme in the life cycle of influenza virus, which is known as a successful paradigm in the design of anti-influenza agents. However, to date there are no classification models for the virtual screening of NA inhibitors. In this work, we built support vector machine and Naïve Bayesian models of NA inhibitors and non-inhibitors, with different ratios of active-to-inactive compounds in the training set and different molecular descriptors. Four models with sensitivity or Matthews correlation coefficients greater than 0.9 were chosen to predict the NA inhibitory activities of 15,600 compounds in our in-house database. We combined the results of four optimal models and selected 60 representative compounds to assess their NA inhibitory profiles in vitro. Nine NA inhibitors were identified, five of which were oseltamivir derivatives with large C-5 substituents exhibiting potent inhibition against H1N1 NA with IC50 values in the range of 12.9-185.0 nM, and against H3N2 NA with IC50 values between 18.9 and 366.1 nM. The other four active compounds belonged to novel scaffolds, with IC50 values ranging 39.5-63.8 μM against H1N1 NA and 44.5-114.1 μM against H3N2 NA. This is the first time that classification models of NA inhibitors and non-inhibitors are built and their prediction results validated experimentally using in vitro assays.

Rule-based classification models of molecular autofluorescence

Fluorescence-based detection has been commonly used in high-throughput screening (HTS) assays. Autofluorescent compounds, which can emit light in the absence of artificial fluorescent markers, often interfere with the detection of fluorophores and result in false positive signals in these assays. This interference presents a major issue in fluorescence-based screening techniques. In an effort to reduce the time and cost that will be spent on prescreening of autofluorescent compounds, in silico autofluorescence prediction models were developed for selected fluorescence-based assays in this study. Five prediction models were developed based on the respective fluorophores used in these HTS assays, which absorb and emit light at specific wavelengths (excitation/emission): Alexa Fluor 350 (A350) (340 nm/450 nm), 7-amino-4-trifluoromethyl-coumarin (AFC) (405 nm/520 nm), Alexa Fluor 488 (A488) (480 nm/540 nm), Rhodamine (547 nm/598 nm), and Texas Red (547 nm/618 nm). The C5.0 rule-based classification algorithm and PubChem 2D chemical structure fingerprints were used to develop prediction models. To optimize the accuracies of these prediction models despite the highly imbalanced ratio of fluorescent versus nonfluorescent compounds presented in the collected data sets, oversampling and undersampling strategies were applied. The average final accuracy achieved for the training set was 97%, and that for the testing set was 92%. In addition, five external data sets were used to further validate the models. Ultimately, 14 representative structural features (or rules) were determined to efficiently predict autofluorescence in data sets containing both fluorescent and nonfluorescent compounds. Several cases were illustrated in this study to demonstrate the applicability of these rules.

Predictive modeling studies for the ecotoxicity of ionic liquids towards the green algae Scenedesmus vacuolatus

Hazardous potential of ionic liquids is becoming an issue of high concern with increasing application of these compounds in various industrial processes. Predictive toxicological modeling on ionic liquids provides a rational assessment strategy and aids in developing suitable guidance for designing novel analogues. The present study attempts to explore the chemical features of ionic liquids responsible for their ecotoxicity towards the green algae Scenedesmus vacuolatus by developing mathematical models using extended topochemical atom (ETA) indices along with other categories of chemical descriptors. The entire study has been conducted with reference to the OECD guidelines for QSAR model development using predictive classification and regression modeling strategies. The best models from both the analyses showed that ecotoxicity of ionic liquids can be decreased by reducing chain length of cationic substituents and increasing hydrogen bond donor feature in cations, and replacing bulky unsaturated anions with simple saturated moiety having less lipophilic heteroatoms.

An efficient algorithm coupled with synthetic minority over-sampling technique to classify imbalanced PubChem BioAssay data

It is common that imbalanced datasets are often generated from high-throughput screening (HTS). For a given dataset without taking into account the imbalanced nature, most classification methods tend to produce high predictive accuracy for the majority class, but significantly poor performance for the minority class. In this work, an efficient algorithm, GLMBoost, coupled with Synthetic Minority Over-sampling TEchnique (SMOTE) is developed and utilized to overcome the problem for several imbalanced datasets from PubChem BioAssay. By applying the proposed combinatorial method, those data of rare samples (active compounds), for which usually poor results are generated, can be detected apparently with high balanced accuracy (Gmean). As a comparison with GLMBoost, Random Forest (RF) combined with SMOTE is also adopted to classify the same datasets. Our results show that the former (GLMBoost+SMOTE) not only exhibits higher performance as measured by the percentage of correct classification for the rare samples (Sensitivity) and Gmean, but also demonstrates greater computational efficiency than the latter (RF+SMOTE). Therefore, we hope that the proposed combinatorial algorithm based on GLMBoost and SMOTE could be extensively used to tackle the imbalanced classification problem.