In silico prediction of toxicity of non-congeneric industrial chemicals using ensemble learning based modeling approaches

Prediction model of in-hospital mortality in intensive care unit patients with heart failure: machine learning-based, retrospective analysis of the MIMIC-III database

OBJECTIVE

The predictors of in-hospital mortality for intensive care units (ICUs)-admitted heart failure (HF) patients remain poorly characterised. We aimed to develop and validate a prediction model for all-cause in-hospital mortality among ICU-admitted HF patients.

DESIGN

A retrospective cohort study.

SETTING AND PARTICIPANTS

Data were extracted from the Medical Information Mart for Intensive Care (MIMIC-III) database. Data on 1177 heart failure patients were analysed.

METHODS

Patients meeting the inclusion criteria were identified from the MIMIC-III database and randomly divided into derivation (n=825, 70%) and a validation (n=352, 30%) group. Independent risk factors for in-hospital mortality were screened using the extreme gradient boosting (XGBoost) and the least absolute shrinkage and selection operator (LASSO) regression models in the derivation sample. Multivariate logistic regression analysis was used to build prediction models in derivation group, and then validated in validation cohort. Discrimination, calibration and clinical usefulness of the predicting model were assessed using the C-index, calibration plot and decision curve analysis. After pairwise comparison, the best performing model was chosen to build a nomogram according to the regression coefficients.

RESULTS

Among the 1177 admissions, in-hospital mortality was 13.52%. In both groups, the XGBoost, LASSO regression and Get With the Guidelines-Heart Failure (GWTG-HF) risk score models showed acceptable discrimination. The XGBoost and LASSO regression models also showed good calibration. In pairwise comparison, the prediction effectiveness was higher with the XGBoost and LASSO regression models than with the GWTG-HF risk score model (p<0.05). The XGBoost model was chosen as our final model for its more concise and wider net benefit threshold probability range and was presented as the nomogram.

CONCLUSIONS

Our nomogram enabled good prediction of in-hospital mortality in ICU-admitted HF patients, which may help clinical decision-making for such patients.

Study of the Gastrointestinal Heat Retention Syndrome in Children: From Diagnostic Model to Biological Basis

Gastrointestinal heat retention syndrome (GHRS) refers to a condition that is associated with increased gastrointestinal heat caused by a metabolic block in energy. It is common in children and is closely related to the occurrence and development of recurrent respiratory tract infection, pneumonia, recurrent functional abdominal pain, etc. However, there are no standardized diagnostic criteria to differentiate the GHRS. Therefore, this study is aimed to establish a diagnostic model for children's GHRS and explore the possible biological basis by using systems biology to achieve. Furthermore, Delphi method and the clinical data of Lasso analysis were used to screen out the core symptoms. Nineteen core symptoms of GHRS in children were screened including digestive symptoms such as dry stool, poor appetite, vomiting, and some nervous system symptoms such as night restlessness and irritability. Based on the core symptoms, a GHRS diagnosis model was established using the eXtreme Gradient Boosting (XGBoost) method, and the accuracy of internal verification reached 93.03%. Relevant targets of the core symptoms in the Human Phenotype Ontology (HPO) were retrieved, and target interactions were linked through the Search Tool for the Retrieval of Interacting Genes/Proteins (STRING) database, and core targets were selected after topological analysis using Cytoscape. Relevant biological processes and pathways were analyzed by applying the DAVID and KEGG databases. The enriched biological processes focused on the cell proliferation, differentiation, apoptosis, and mitochondrial metabolism, which were mainly associated with PI3K-AKT, MAPK network pathways, and the Wnt signaling pathway. In conclusion, we established a diagnosis model of GHRS in children based on the core symptoms and provided an objective standard for its clinical diagnosis. And, the Wnt signaling pathway and the estrogen receptor-activated PI3K-AKT and MAPK network pathways may play important roles in the GHRS processing.

Ranking and prioritizing pharmaceuticals in the aquatic environment of China

Pharmaceuticals have become "persistent" pollutants in the aquatic environment, due to their wide usage in daily life and their continuous release into the aquatic environment. Hence, prioritization and ranking lists are required to screen for target compounds as part of risk assessments. A ranking system based on three criteria, such as occurrence, exposure potential and ecological effects, was developed in this study for specific application to China. A total of 100 pharmaceuticals were selected as candidates based on the ranking system and available consumption data. These pharmaceuticals have been previously reported by wastewater treatment plants (WWTPs) in China. 13 pharmaceuticals were classified as priority pharmaceuticals, among which diclofenac, erythromycin, and penicillin G were highly prioritized. Due to their abuse, antibiotics contributed a majority to the priority pharmaceuticals among all therapeutic classes, indicating that antibiotics should be considered based on their behaviors in WWTPs. The pharmaceuticals ranking list achieved good applicability and will help to establish a focus for future monitoring and management of pharmaceuticals. It will also provide an important basis for both ecological risk assessment and pollution control of pharmaceuticals in the aquatic environment.

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.

In silico prediction of toxicity of phenols to Tetrahymena pyriformis by using genetic algorithm and decision tree-based modeling approach

Risk assessment of chemicals is an important issue in environmental protection; however, there is a huge lack of experimental data for a large number of end-points. The experimental determination of toxicity of chemicals involves high costs and time-consuming process. In silico tools such as quantitative structure-toxicity relationship (QSTR) models, which are constructed on the basis of computational molecular descriptors, can predict missing data for toxic end-points for existing or even not yet synthesized chemicals. Phenol derivatives are known to be aquatic pollutants. With this background, we aimed to develop an accurate and reliable QSTR model for the prediction of toxicity of 206 phenols to Tetrahymena pyriformis. A multiple linear regression (MLR)-based QSTR was obtained using a powerful descriptor selection tool named Memorized_ACO algorithm. Statistical parameters of the model were 0.72 and 0.68 for R_training² and R_test², respectively. To develop a high-quality QSTR model, classification and regression tree (CART) was employed. Two approaches were considered: (1) phenols were classified into different modes of action using CART and (2) the phenols in the training set were partitioned to several subsets by a tree in such a manner that in each subset, a high-quality MLR could be developed. For the first approach, the statistical parameters of the resultant QSTR model were improved to 0.83 and 0.75 for R_training² and R_test², respectively. Genetic algorithm was employed in the second approach to obtain an optimal tree, and it was shown that the final QSTR model provided excellent prediction accuracy for the training and test sets (R_training² and R_test² were 0.91 and 0.93, respectively). The mean absolute error for the test set was computed as 0.1615.

In Silico Prediction of Gamma-Aminobutyric Acid Type-A Receptors Using Novel Machine-Learning-Based SVM and GBDT Approaches

Gamma-aminobutyric acid type-A receptors (GABA_ARs) belong to multisubunit membrane spanning ligand-gated ion channels (LGICs) which act as the principal mediators of rapid inhibitory synaptic transmission in the human brain. Therefore, the category prediction of GABA_ARs just from the protein amino acid sequence would be very helpful for the recognition and research of novel receptors. Based on the proteins' physicochemical properties, amino acids composition and position, a GABA_AR classifier was first constructed using a 188-dimensional (188D) algorithm at 90% cd-hit identity and compared with pseudo-amino acid composition (PseAAC) and ProtrWeb web-based algorithms for human GABA_AR proteins. Then, four classifiers including gradient boosting decision tree (GBDT), random forest (RF), a library for support vector machine (libSVM), and k-nearest neighbor (k-NN) were compared on the dataset at cd-hit 40% low identity. This work obtained the highest correctly classified rate at 96.8% and the highest specificity at 99.29%. But the values of sensitivity, accuracy, and Matthew's correlation coefficient were a little lower than those of PseAAC and ProtrWeb; GBDT and libSVM can make a little better performance than RF and k-NN at the second dataset. In conclusion, a GABA_AR classifier was successfully constructed using only the protein sequence information.

Molecular mechanisms of endocrine and metabolic disruption: An in silico study on antitrypanosomal natural products and some derivatives

The VirtualToxLab is an in silico technology for estimating the toxic potential - endocrine and metabolic disruption, as well as aspects of carcinogenicity and cardiotoxicity - of drugs, chemicals and natural products. The technology is based on an automated protocol that simulates and quantifies the binding of small molecules towards a series of currently 16 proteins, known or suspected to trigger adverse effects. The simulations are conducted at the atomic level and explicitly allow for a mechanistic interpretation of the results (in real-time 3D/4D), thereby complying with the Setubal principles put forward in 2002 for computational approaches to toxicology. Moreover, the underlying "ab-initio" protocol is independent from any training data and makes the approach universal with respect to the applicability domain. The VirtualToxLab runs in client-server mode and is freely available to academic and non-profit organizations. As the underlying technology yields a thermodynamic estimate of the binding affinity, the associated ligand-protein complexes have been challenged by molecular-dynamics simulations to probe their kinetic stability. Human African trypanosomiasis is a neglected tropical disease caused by two subspecies of Trypanosoma brucei. The control of this parasitic infection relies on a few chemotherapeutic agents, most of which were discovered decades ago and pose many challenges including adverse side effects, poor efficacy, and the occurrence of drug resistances. Natural products, on the other hand, offer a high potential for the discovery of new drug leads due to their chemical diversity. In this in silico study, we analyze a series of 89 natural products and derivatives displaying anti-trypanosomal activity for their potential to trigger adverse effects. Our results indicate a moderate potential for a number of those compounds to bind to nuclear receptors and thereby ease the development of endocrine disregulation. A few others would seem to inhibit enzymes of the cytochrome P450 family and, hence, sustain drug-drug interactions.

ADMET evaluation in drug discovery: 15. Accurate prediction of rat oral acute toxicity using relevance vector machine and consensus modeling

Background

Determination of acute toxicity, expressed as median lethal dose (LD₅₀), is one of the most important steps in drug discovery pipeline. Because in vivo assays for oral acute toxicity in mammals are time-consuming and costly, there is thus an urgent need to develop in silico prediction models of oral acute toxicity.

Results

In this study, based on a comprehensive data set containing 7314 diverse chemicals with rat oral LD₅₀ values, relevance vector machine (RVM) technique was employed to build the regression models for the prediction of oral acute toxicity in rate, which were compared with those built using other six machine learning approaches, including k-nearest-neighbor regression, random forest (RF), support vector machine, local approximate Gaussian process, multilayer perceptron ensemble, and eXtreme gradient boosting. A subset of the original molecular descriptors and structural fingerprints (PubChem or SubFP) was chosen by the Chi squared statistics. The prediction capabilities of individual QSAR models, measured by q_ext² for the test set containing 2376 molecules, ranged from 0.572 to 0.659.

Conclusion

Considering the overall prediction accuracy for the test set, RVM with Laplacian kernel and RF were recommended to build in silico models with better predictivity for rat oral acute toxicity. By combining the predictions from individual models, four consensus models were developed, yielding better prediction capabilities for the test set (q_ext² = 0.669–0.689). Finally, some essential descriptors and substructures relevant to oral acute toxicity were identified and analyzed, and they may be served as property or substructure alerts to avoid toxicity. We believe that the best consensus model with high prediction accuracy can be used as a reliable virtual screening tool to filter out compounds with high rat oral acute toxicity. Graphical abstract

Predicting aquatic toxicities of chemical pesticides in multiple test species using nonlinear QSTR modeling approaches

In this study, we established nonlinear quantitative-structure toxicity relationship (QSTR) models for predicting the toxicities of chemical pesticides in multiple aquatic test species following the OECD (Organization for Economic Cooperation and Development) guidelines. The decision tree forest (DTF) and decision tree boost (DTB) based QSTR models were constructed using a pesticides toxicity dataset in Selenastrum capricornutum and a set of six descriptors. Other six toxicity data sets were used for external validation of the constructed QSTRs. Global QSTR models were also constructed using the combined dataset of all the seven species. The diversity in chemical structures and nonlinearity in the data were evaluated. Model validation was performed deriving several statistical coefficients for the test data and the prediction and generalization abilities of the QSTRs were evaluated. Both the QSTR models identified WPSA1 (weighted charged partial positive surface area) as the most influential descriptor. The DTF and DTB QSTRs performed relatively better than the single decision tree (SDT) and support vector machines (SVM) models used as a benchmark here and yielded R(2) of 0.886 and 0.964 between the measured and predicted toxicity values in the complete dataset (S. capricornutum). The QSTR models applied to six other aquatic species toxicity data yielded R(2) of >0.92 (DTF) and >0.97 (DTB), respectively. The prediction accuracies of the global models were comparable with those of the S. capricornutum models. The results suggest for the appropriateness of the developed QSTR models to reliably predict the aquatic toxicity of chemicals and can be used for regulatory purpose.

Predicting the hazardous dose of industrial chemicals in warm-blooded species using machine learning-based modelling approaches

The hazardous dose of a chemical (HD50) is an emerging and acceptable test statistic for the safety/risk assessment of chemicals. Since it is derived using the experimental toxicity values of the chemical in several test species, it is highly cumbersome, time and resource intensive. In this study, three machine learning-based QSARs were established for predicting the HD50 of chemicals in warm-blooded species following the OECD guidelines. A data set comprising HD50 values of 957 chemicals was used to develop SDT, DTF and DTB QSAR models. The diversity in chemical structures and nonlinearity in the data were verified. Several validation coefficients were derived to test the predictive and generalization abilities of the constructed QSARs. The chi-path descriptors were identified as the most influential in three QSARs. The DTF and DTB performed relatively better than SDT model and yielded r(2) values of 0.928 and 0.959 between the measured and predicted HD50 values in the complete data set. Substructure alerts responsible for the toxicity of the chemicals were identified. The results suggest the appropriateness of the developed QSARs for reliably predicting the HD50 values of chemicals, and they can be used for screening of new chemicals for their safety/risk assessment for regulatory purposes.

Estimating sensory irritation potency of volatile organic chemicals using QSARs based on decision tree methods for regulatory purpose

Volatile organic compounds (VOCs) are among the priority atmospheric pollutants that have high indoor and outdoor exposure potential. The toxicity assessment of VOCs to living ecosystems has received considerable attention in recent years. Development of computational methods for safety assessment of chemicals has been advocated by various regulatory agencies. The paper proposes robust and reliable quantitative structure-activity relationships (QSARs) for estimating the sensory irritation potency and screening of the VOCs. Here, decision tree (DT) based classification and regression QSARs models, such as single DT, decision tree forest (DTF), and decision tree boost (DTB) were developed using the sensory irritation data on VOCs in mice following the OECD principles. Structural diversity and nonlinearity in the data were evaluated through the Euclidean distance and Brock-Dechert-Scheinkman statistics. The constructed QSAR models were validated with external test data and the predictive performance of these models was established through a set of coefficients recommended in QSAR literature. The performance of all three classification and regression QSAR models was satisfactory, but DTF and DTB performed relatively better. The classification and regression QSAR models (DTF, DTB) rendered classification accuracies of 98.59 and 100 %, and yielded correlations (R(2)) of 0.950 and 0.971, respectively in complete data. The lipoaffinity index and SwHBa were identified as the most influential descriptors in proposed QSARs. The developed QSARs performed better than the previous studies. The developed models exhibited high statistical confidence and identified the structural properties of the VOCs responsible for their sensory irritation, and hence could be useful tools in screening of chemicals for regulatory purpose.

QSTR modeling for predicting aquatic toxicity of pharmacological active compounds in multiple test species for regulatory purpose

High concentrations of pharmacological active compounds (PACs) detected in global drinking water resources and their toxicological implications in aquatic life has become a matter of concern compelling for the development of reliable QSTRs (qualitative/quantitative structure-toxicity relationships) for their risk assessment. Robust QSTRs, such as decision treeboost (DTB) and decision tree forest (DTF) models implementing stochastic gradient boosting and bagging algorithms were established by experimental toxicity data of structurally diverse PACs in daphnia using molecular descriptors for predicting toxicity of new untested compounds in multiple test species. Developed models were rigorously validated using OECD recommended internal and external validation procedures and predictive power tested with external data of different trophic level test species (algae and fish). Classification QSTRs (DTB, DTF) rendered accuracy of 98.73% and 97.47%, respectively in daphnia and 84.38%, 85.94% (algae), 78.46% and 79.23% (fish). On the other hand, the regression QSTRs (DTB, DTF) yielded squared correlation coefficient values of 0.831, 0.852 (daphnia), 0.534, 0.556 (algae) and 0.620, 0.637 (fish). QSTRs developed in this study passed the OECD validation criteria and performed better than reported earlier for predicting toxicity of PACs, and can be used for screening the new untested compounds for regulatory purpose.

Qualitative and quantitative structure-activity relationship modelling for predicting blood-brain barrier permeability of structurally diverse chemicals

In this study, structure-activity relationship (SAR) models have been established for qualitative and quantitative prediction of the blood-brain barrier (BBB) permeability of chemicals. The structural diversity of the chemicals and nonlinear structure in the data were tested. The predictive and generalization ability of the developed SAR models were tested through internal and external validation procedures. In complete data, the QSAR models rendered ternary classification accuracy of >98.15%, while the quantitative SAR models yielded correlation (r(2)) of >0.926 between the measured and the predicted BBB permeability values with the mean squared error (MSE) <0.045. The proposed models were also applied to an external new in vitro data and yielded classification accuracy of >82.7% and r(2) > 0.905 (MSE < 0.019). The sensitivity analysis revealed that topological polar surface area (TPSA) has the highest effect in qualitative and quantitative models for predicting the BBB permeability of chemicals. Moreover, these models showed predictive performance superior to those reported earlier in the literature. This demonstrates the appropriateness of the developed SAR models to reliably predict the BBB permeability of new chemicals, which can be used for initial screening of the molecules in the drug development process.

OpenVirtualToxLab--a platform for generating and exchanging in silico toxicity data

The VirtualToxLab is an in silico technology for estimating the toxic potential--endocrine and metabolic disruption, some aspects of carcinogenicity and cardiotoxicity--of drugs, chemicals and natural products. The technology is based on an automated protocol that simulates and quantifies the binding of small molecules towards a series of currently 16 proteins, known or suspected to trigger adverse effects: 10 nuclear receptors (androgen, estrogen α, estrogen β, glucocorticoid, liver X, mineralocorticoid, peroxisome proliferator-activated receptor γ, progesterone, thyroid α, thyroid β), four members of the cytochrome P450 enzyme family (1A2, 2C9, 2D6, 3A4), a cytosolic transcription factor (aryl hydrocarbon receptor) and a potassium ion channel (hERG). The toxic potential of a compound--its ability to trigger adverse effects--is derived from its computed binding affinities toward these very proteins: the computationally demanding simulations are executed in client-server model on a Linux cluster of the University of Basel. The graphical-user interface supports all computer platforms, allows building and uploading molecular structures, inspecting and downloading the results and, most important, rationalizing any prediction at the atomic level by interactively analyzing the binding mode of a compound with its target protein(s) in real-time 3D. Access to the VirtualToxLab is available free of charge for universities, governmental agencies, regulatory bodies and non-profit organizations.