Cheminformatics-aided pharmacovigilance: application to Stevens-Johnson Syndrome

Abstract Objective Quantitative Structure-Activity Relationship (QSAR) models can predict adverse drug reactions (ADRs), and thus provide early warnings of potential hazards. Timely identification of potential safety concerns could protect patients and aid early diagnosis of ADRs among the exposed. Our objective was to determine whether global spontaneous reporting patterns might allow chemical substructures associated with Stevens-Johnson Syndrome (SJS) to be identified and utilized for ADR prediction by QSAR models. Materials and Methods Using a reference set of 364 drugs having positive or negative reporting correlations with SJS in the VigiBase global repository of individual case safety reports (Uppsala Monitoring Center, Uppsala, Sweden), chemical descriptors were computed from drug molecular structures. Random Forest and Support Vector Machines methods were used to develop QSAR models, which were validated by external 5-fold cross validation. Models were employed for virtual screening of DrugBank to predict SJS actives and inactives, which were corroborated using knowledge bases like VigiBase, ChemoText, and MicroMedex (Truven Health Analytics Inc, Ann Arbor, Michigan). Results We developed QSAR models that could accurately predict if drugs were associated with SJS (area under the curve of 75%–81%). Our 10 most active and inactive predictions were substantiated by SJS reports (or lack thereof) in the literature. Discussion Interpretation of QSAR models in terms of significant chemical descriptors suggested novel SJS structural alerts. Conclusions We have demonstrated that QSAR models can accurately identify SJS active and inactive drugs. Requiring chemical structures only, QSAR models provide effective computational means to flag potentially harmful drugs for subsequent targeted surveillance and pharmacoepidemiologic investigations.

Download Full-text

A Toxicity Prediction Tool for Potential Agonist/Antagonist Activities in Molecular Initiating Events Based on Chemical Structures

International Journal of Molecular Sciences ◽

10.3390/ijms21217853 ◽

2020 ◽

Vol 21 (21) ◽

pp. 7853

Author(s):

Kota Kurosaki ◽

Raymond Wu ◽

Yoshihiro Uesawa

Keyword(s):

Web Application ◽

Endocrine Disrupting Chemicals ◽

Three Dimensional ◽

Quantitative Structure Activity Relationship ◽

Molecular Structures ◽

Adverse Outcome Pathway ◽

Toxicity Prediction ◽

Practical Applications ◽

Chemical Structures ◽

Qsar Models

Because the health effects of many compounds are unknown, regulatory toxicology must often rely on the development of quantitative structure–activity relationship (QSAR) models to efficiently discover molecular initiating events (MIEs) in the adverse-outcome pathway (AOP) framework. However, the QSAR models used in numerous toxicity prediction studies are publicly unavailable, and thus, they are challenging to use in practical applications. Approaches that simultaneously identify the various toxic responses induced by a compound are also scarce. The present study develops Toxicity Predictor, a web application tool that comprehensively identifies potential MIEs. Using various chemicals in the Toxicology in the 21st Century (Tox21) 10K library, we identified potential endocrine-disrupting chemicals (EDCs) using a machine-learning approach. Based on the optimized three-dimensional (3D) molecular structures and XGBoost algorithm, we established molecular descriptors for QSAR models. Their predictive performances and applicability domain were evaluated and applied to Toxicity Predictor. The prediction performance of the constructed models matched that of the top model in the Tox21 Data Challenge 2014. These advanced prediction results for MIEs are freely available on the Internet.

Download Full-text

Open-source QSAR models for pKa prediction using multiple machine learning approaches

Journal of Cheminformatics ◽

10.1186/s13321-019-0384-1 ◽

2019 ◽

Vol 11 (1) ◽

Cited By ~ 10

Author(s):

Kamel Mansouri ◽

Neal F. Cariello ◽

Alexandru Korotcov ◽

Valery Tkachenko ◽

Chris M. Grulke ◽

...

Keyword(s):

Machine Learning ◽

Open Source ◽

Acid Dissociation ◽

Support Vector ◽

Learning Approaches ◽

Data Set ◽

Pka Prediction ◽

Chemical Structures ◽

Extreme Gradient Boosting ◽

Qsar Models

Abstract Background The logarithmic acid dissociation constant pKa reflects the ionization of a chemical, which affects lipophilicity, solubility, protein binding, and ability to pass through the plasma membrane. Thus, pKa affects chemical absorption, distribution, metabolism, excretion, and toxicity properties. Multiple proprietary software packages exist for the prediction of pKa, but to the best of our knowledge no free and open-source programs exist for this purpose. Using a freely available data set and three machine learning approaches, we developed open-source models for pKa prediction. Methods The experimental strongest acidic and strongest basic pKa values in water for 7912 chemicals were obtained from DataWarrior, a freely available software package. Chemical structures were curated and standardized for quantitative structure–activity relationship (QSAR) modeling using KNIME, and a subset comprising 79% of the initial set was used for modeling. To evaluate different approaches to modeling, several datasets were constructed based on different processing of chemical structures with acidic and/or basic pKas. Continuous molecular descriptors, binary fingerprints, and fragment counts were generated using PaDEL, and pKa prediction models were created using three machine learning methods, (1) support vector machines (SVM) combined with k-nearest neighbors (kNN), (2) extreme gradient boosting (XGB) and (3) deep neural networks (DNN). Results The three methods delivered comparable performances on the training and test sets with a root-mean-squared error (RMSE) around 1.5 and a coefficient of determination (R2) around 0.80. Two commercial pKa predictors from ACD/Labs and ChemAxon were used to benchmark the three best models developed in this work, and performance of our models compared favorably to the commercial products. Conclusions This work provides multiple QSAR models to predict the strongest acidic and strongest basic pKas of chemicals, built using publicly available data, and provided as free and open-source software on GitHub.

Download Full-text

Evolution of Multivariate Image Analysis in QSAR

Quantitative Structure-Activity Relationships in Drug Design, Predictive Toxicology, and Risk Assessment - Advances in Chemical and Materials Engineering ◽

10.4018/978-1-4666-8136-1.ch003 ◽

2015 ◽

pp. 84-122

Author(s):

Matheus P. Freitas ◽

Mariene H. Duarte

Keyword(s):

Image Analysis ◽

Biological Activities ◽

Quantitative Structure Activity Relationship ◽

Simple Method ◽

Multivariate Image Analysis ◽

Chemical Structures ◽

Qsar Models ◽

Chemical Descriptors ◽

Multivariate Image

Multivariate Image Analysis applied in Quantitative Structure-Activity Relationship (MIA-QSAR) is a simple method to achieve, at least in a variety of examples, QSAR models with predictive abilities comparable to those of sophisticated tridimensional methodologies. MIA-QSAR is based on the correlation between properties (e.g. biological activities) and chemical descriptors, which are pixels of images representing chemical structures in a congeneric series of molecules. The MIA-QSAR approach has been improved since its creation, in 2005, both in terms of data analysis and development of more descriptive information. This chapter reports the MIA-QSAR method, including its augmented version, named aug-MIA-QSAR because of the introduction of new dimensions to better encode atomic properties. In addition, the application to a case study illustrates the main practical differences between traditional and augmented MIA-QSAR. The use of a neglected disease as example represents a challenge in QSAR, which is particularly focused on diseases with higher economical appearance.

Download Full-text

G96 Stevens-Johnson syndrome and toxic epidermal necrolysis associated with lamotrigine treatment in children: A review of 486 individual case safety reports

Archives of Disease in Childhood ◽

10.1136/archdischild-2016-310863.93 ◽

2016 ◽

Vol 101 (Suppl 1) ◽

pp. A56.1-A56

Author(s):

O Egunsola ◽

K Star ◽

K Juhlin ◽

I Choonara ◽

H Sammons

Keyword(s):

Toxic Epidermal Necrolysis ◽

Individual Case ◽

Stevens Johnson Syndrome ◽

Johnson Syndrome

Download Full-text

Investigation of NMDA Receptor Channel Blockers in a Series of Methylene Blue Conjugates Using QSAR and Molecular Modeling

Biomedical Chemistry Research and Methods ◽

10.18097/bmcrm00091 ◽

2019 ◽

Vol 2 (2) ◽

pp. e00091

Author(s):

V.Y. Grigorev ◽

K.A. Shcherbakov ◽

D.E. Polianczyk ◽

А.N. Razdolsky ◽

A.V. Veselovsky ◽

...

Keyword(s):

Methylene Blue ◽

Nmda Receptor ◽

Support Vector ◽

Channel Blockers ◽

Receptor Binding Site ◽

Chemical Structures ◽

Qsar Models ◽

Derivatives Of ◽

Nmda Receptor Channel

29 conjugates of methylene blue and four chemical structures, including derivatives of carbazole, tetrahydrocarbazole, substituted indoles and γ-carboline, combined with a 1-oxopropylene spacer have been studied as channel blockers of the NMDA receptor (binding site of MK-801) by using four QSAR methods (multiple linear regression, random forest, support vector machine, Gaussian process) and molecular docking. QSAR models have satisfactory characteristics. The analysis of regression models at the statistical level revealed an important role of the hydrogen bond in the complex formation. This was also confirmed by the study of modeled by docking complexes. It was found that the increase in the inhibitory activity of the part of compounds could be attributed to appearance of additional H bonds between the ligands and the receptor.

Download Full-text