In silico prediction of the mutagenicity of nitroaromatic compounds using correlation weights of fragments of local symmetry

Most quantitative structure-property/activity relationships (QSPRs/QSARs) techniques involve using different programs separately for generating molecular descriptors and separately for building models based on available descriptors. Here, the capabilities of the CORAL program are evaluated. A user of the program should apply as the basis for models the representation of the molecular structure by means of the simplified molecular input-line entry system (SMILES) as well as experimental data on the endpoint of interest. The local symmetry of SMILES is a novel composition of symmetrically represented symbols, which are three 'xyx', four 'xyyx', or five symbols 'xyzyx'. We updated our CORAL software using this optimal, new flexible descriptor, sensitive to the symmetric composition of a specific part of the molecule. Computational experiments have shown that taking account of these attributes of SMILES can improve the predictive potential of models for the mutagenicity of nitroaromatic compounds. In addition, the above computational experiments have confirmed the advantage of using the index of ideality of correlation (IIC) and the correlation intensity index (CII) for Monte Carlo optimization of the correlation weights for various attributes of SMILES, including the local symmetry. The average value of the coefficient of determination for the validation set (five different models) without fragments of local symmetry is 0.8589 ± 0.025, whereas using fragments of local symmetry improves this criterion of the predictive potential up to 0.9055 ± 0.010.

Artificial Intelligence in Drug Toxicity Prediction: Recent Advances, Challenges, and Future Perspectives

Toxicity prediction is a critical step in the drug discovery process that helps identify and prioritize compounds with the greatest potential for safe and effective use in humans, while also reducing the risk of costly late-stage failures. It is estimated that over 30% of drug candidates are discarded owing to toxicity. Recently, artificial intelligence (AI) has been used to improve drug toxicity prediction as it provides more accurate and efficient methods for identifying the potentially toxic effects of new compounds before they are tested in human clinical trials, thus saving time and money. In this review, we present an overview of recent advances in AI-based drug toxicity prediction, including the use of various machine learning algorithms and deep learning architectures, of six major toxicity properties and Tox21 assay end points. Additionally, we provide a list of public data sources and useful toxicity prediction tools for the research community and highlight the challenges that must be addressed to enhance model performance. Finally, we discuss future perspectives for AI-based drug toxicity prediction. This review can aid researchers in understanding toxicity prediction and pave the way for new methods of drug discovery.

Chemical rules for optimization of chemical mutagenicity via matched molecular pairs analysis and machine learning methods

Chemical mutagenicity is a serious issue that needs to be addressed in early drug discovery. Over a long period of time, medicinal chemists have manually summarized a series of empirical rules for the optimization of chemical mutagenicity. However, given the rising amount of data, it is getting more difficult for medicinal chemists to identify more comprehensive chemical rules behind the biochemical data. Herein, we integrated a large Ames mutagenicity data set with 8576 compounds to derive mutagenicity transformation rules for reversing Ames mutagenicity via matched molecular pairs analysis. A well-trained consensus model with a reasonable applicability domain was constructed, which showed favorable performance in the external validation set with an accuracy of 0.815. The model was used to assess the generalizability and validity of these mutagenicity transformation rules. The results demonstrated that these rules were of great value and could provide inspiration for the structural modifications of compounds with potential mutagenic effects. We also found that the local chemical environment of the attachment points of rules was critical for successful transformation. To facilitate the use of these mutagenicity transformation rules, we integrated them into ADMETopt2 ( http://lmmd.ecust.edu.cn/admetsar2/admetopt2/ ), a free web server for optimization of chemical ADMET properties. The above-mentioned approach would be extended to the optimization of other toxicity endpoints.

Quo vadis blood protein adductomics?

Chemicals are measured regularly in air, food, the environment, and the workplace. Biomonitoring of chemicals in biological fluids is a tool to determine the individual exposure. Blood protein adducts of xenobiotics are a marker of both exposure and the biologically effective dose. Urinary metabolites and blood metabolites are short term exposure markers. Stable hemoglobin adducts are exposure markers of up to 120 days. Blood protein adducts are formed with many xenobiotics at different sites of the blood proteins. Newer methods apply the techniques developed in the field of proteomics. Larger adducted peptides with 20 amino acids are used for quantitation. Unfortunately, at present the methods do not reach the limits of detection obtained with the methods looking at single amino acid adducts or at chemically cleaved adducts. Therefore, to progress in the field new approaches are needed.

Predicting the Skin Sensitization Potential of Small Molecules with Machine Learning Models Trained on Biologically Meaningful Descriptors

In recent years, a number of machine learning models for the prediction of the skin sensitization potential of small organic molecules have been reported and become available. These models generally perform well within their applicability domains but, as a result of the use of molecular fingerprints and other non-intuitive descriptors, the interpretability of the existing models is limited. The aim of this work is to develop a strategy to replace the non-intuitive features by predicted outcomes of bioassays. We show that such replacement is indeed possible and that as few as ten interpretable, predicted bioactivities are sufficient to reach competitive performance. On a holdout data set of 257 compounds, the best model (“Skin Doctor CP:Bio”) obtained an efficiency of 0.82 and an MCC of 0.52 (at the significance level of 0.20). Skin Doctor CP:Bio is available free of charge for academic research. The modeling strategies explored in this work are easily transferable and could be adopted for the development of more interpretable machine learning models for the prediction of the bioactivity and toxicity of small organic compounds.

Machine Learning Strategies When Transitioning between Biological Assays

Machine learning is widely used in drug development to predict activity in biological assays based on chemical structure. However, the process of transitioning from one experimental setup to another for the same biological endpoint has not been extensively studied. In a retrospective study, we here explore different modeling strategies of how to combine data from the old and new assays when training conformal prediction models using data from hERG and Na_V assays. We suggest to continuously monitor the validity and efficiency of models as more data is accumulated from the new assay and select a modeling strategy based on these metrics. In order to maximize the utility of data from the old assay, we propose a strategy that augments the proper training set of an inductive conformal predictor by adding data from the old assay but only having data from the new assay in the calibration set, which results in valid (well-calibrated) models with improved efficiency compared to other strategies. We study the results for varying sizes of new and old assays, allowing for discussion of different practical scenarios. We also conclude that our proposed assay transition strategy is more beneficial, and the value of data from the new assay is higher, for the harder case of regression compared to classification problems.

Semisynthesis, Antiplasmodial Activity, and Mechanism of Action Studies of Isocoumarin Derivatives

In this study, eight natural isocoumarins (1-8) were isolated from a marine-derived Exserohilum sp. fungus. To explore their structure-activity relationship and discover potent antimalarial leads, a small library of 22 new derivatives (1a-1n, 2a, 3a-3c, 4a-4c, and 7a) were semisynthesized by varying the substituents of the aromatic ring and the aliphatic side chains. The natural compound (1) and three semisynthetic derivatives (1d, 1n, and 2a), possessing an all-cis stereochemistry, exhibited strong antiplasmodial activity with IC₅₀ values of 1.1, 0.8, 0.4, and 2.6 μM, respectively. Mechanism studies show that 1n inhibits hemozoin polymerization and decreases the mitochondrial membrane potential but also inhibits P. falciparum DNA gyrase. 1n not only combines different mechanisms of action but also exhibits a high therapeutic index (CC₅₀/IC₅₀ = 675), high selectivity, and a notable drug-like profile.

A deep neural network-based approach for prediction of mutagenicity of compounds

We are exposed to various chemical compounds present in the environment, cosmetics, and drugs almost every day. Mutagenicity is a valuable property that plays a significant role in establishing a chemical compound's safety. Exposure and handling of mutagenic chemicals in the environment pose a high health risk; therefore, identification and screening of these chemicals are essential. Considering the time constraints and the pressure to avoid laboratory animals' use, the shift to alternative methodologies that can establish a rapid and cost-effective detection without undue over-conservation seems critical. In this regard, computational detection and identification of the mutagens in environmental samples like drugs, pesticides, dyes, reagents, wastewater, cosmetics, and other substances is vital. From the last two decades, there have been numerous efforts to develop the prediction models for mutagenicity, and by far, machine learning methods have demonstrated some noteworthy performance and reliability. However, the accuracy of such prediction models has always been one of the major concerns for the researchers working in this area. The mutagenicity prediction models were developed using deep neural network (DNN), support vector machine, k-nearest neighbor, and random forest. The developed classifiers were based on 3039 compounds and validated on 1014 compounds; each of them encoded with 1597 molecular feature vectors. DNN-based prediction model yielded highest prediction accuracy of 92.95% and 83.81% with the training and test data, respectively. The area under the receiver's operating curve and precision-recall curve values were found to be 0.894 and 0.838, respectively. The DNN-based classifier not only fits the data with better performance as compared to traditional machine learning algorithms, viz., support vector machine, k-nearest neighbor, and random forest (with and without feature reduction) but also yields better performance metrics. In current work, we propose a DNN-based model to predict mutagenicity of compounds.

Skin Doctor CP: Conformal Prediction of the Skin Sensitization Potential of Small Organic Molecules

Skin sensitization potential or potency is an important end point in the safety assessment of new chemicals and new chemical mixtures. Formerly, animal experiments such as the local lymph node assay (LLNA) were the main form of assessment. Today, however, the focus lies on the development of nonanimal testing approaches (i.e., in vitro and in chemico assays) and computational models. In this work, we investigate, based on publicly available LLNA data, the ability of aggregated, Mondrian conformal prediction classifiers to differentiate between non- sensitizing and sensitizing compounds as well as between two levels of skin sensitization potential (weak to moderate sensitizers, and strong to extreme sensitizers). The advantage of the conformal prediction framework over other modeling approaches is that it assigns compounds to activity classes only if a defined minimum level of confidence is reached for the individual predictions. This eliminates the need for applicability domain criteria that often are arbitrary in their nature and less flexible. Our new binary classifier, named Skin Doctor CP, differentiates nonsensitizers from sensitizers with a higher reliability-to-efficiency ratio than the corresponding nonconformal prediction workflow that we presented earlier. When tested on a set of 257 compounds at the significance levels of 0.10 and 0.30, the model reached an efficiency of 0.49 and 0.92, and an accuracy of 0.83 and 0.75, respectively. In addition, we developed a ternary classification workflow to differentiate nonsensitizers, weak to moderate sensitizers, and strong to extreme sensitizers. Although this model achieved satisfactory overall performance (accuracies of 0.90 and 0.73, and efficiencies of 0.42 and 0.90, at significance levels 0.10 and 0.30, respectively), it did not obtain satisfying class-wise results (at a significance level of 0.30, the validities obtained for nonsensitizers, weak to moderate sensitizers, and strong to extreme sensitizers were 0.70, 0.58, and 0.63, respectively). We argue that the model is, in consequence, unable to reliably identify strong to extreme sensitizers and suggest that other ternary models derived from the currently accessible LLNA data might suffer from the same problem. Skin Doctor CP is available via a public web service at https://nerdd.zbh.uni-hamburg.de/skinDoctorII/.