Explore the vast range of titles available.

Unexpected toxicity has become a significant obstacle to drug candidate development, accounting for 30% of drug discovery failures. Traditional toxicity assessment through animal testing is costly and time‐consuming. Big data and artificial intelligence (AI), especially machine learning (ML), are robustly contributing to innovation and progress in toxicology research. However, the optimal AI model for different types of toxicity usually varies, making it essential to conduct comparative analyses of AI methods across toxicity domains. The diverse data sources also pose challenges for researchers focusing on specific toxicity studies. In this review, 10 categories of drug‐induced toxicity is examined, summarizing the characteristics and applicable ML models, including both predictive and interpretable algorithms, striking a balance between breadth and depth. Key databases and tools used in toxicity prediction are also highlighted, including toxicology, chemical, multi‐omics, and benchmark databases, organized by their focus and function to clarify their roles in drug‐induced toxicity prediction. Finally, strategies to turn challenges into opportunities are analyzed and discussed. This review may provide researchers with a valuable reference for understanding and utilizing the available resources to bridge prediction and mechanistic insights, and further advance the application of ML in drugs‐induced toxicity prediction. Unexpected toxicity accounts for 30% of drug development failures. This review highlights ML innovations in predicting drug‐induced toxicity, emphasizing comparative analyses, interpretable algorithms, and multi‐source data integration. It categorizes toxicity types, summarizes ML models, and organizes key databases, offering strategies to address challenges. This work bridges prediction and mechanistic insights, advancing drug toxicity research.

Background Drug-induced liver injury (DILI) is a critical issue in drug development because DILI causes failures in clinical trials and the withdrawal of approved drugs from the market. There have been many attempts to predict the risk of DILI based on in vivo and in silico identification of hepatotoxic compounds. In the current study, we propose the in silico prediction model predicting DILI using weighted molecular fingerprints. Results In this study, we used 881 bits of molecular fingerprint and used as features describing presence or absence of each substructure of compounds. Then, the Bayesian probability of each substructure was calculated and labeled (positive or negative for DILI), and a weighted fingerprint was determined from the ratio of DILI-positive to DILI-negative probability values. Using weighted fingerprint features, the prediction models were trained and evaluated with the Random Forest (RF) and Support Vector Machine (SVM) algorithms. The constructed models yielded accuracies of 73.8% and 72.6%, AUCs of 0.791 and 0.768 in cross-validation. In independent tests, models achieved accuracies of 60.1% and 61.1% for RF and SVM, respectively. The results validated that weighted features helped increase overall performance of prediction models. The constructed models were further applied to the prediction of natural compounds in herbs to identify DILI potential, and 13,996 unique herbal compounds were predicted as DILI-positive with the SVM model. Conclusions The prediction models with weighted features increased the performance compared to non-weighted models. Moreover, we predicted the DILI potential of herbs with the best performed model, and the prediction results suggest that many herbal compounds could have potential to be DILI. We can thus infer that taking natural products without detailed references about the relevant pathways may be dangerous. Considering the frequency of use of compounds in natural herbs and their increased application in drug development, DILI labeling would be very important.

This chapter contains sections titled: Introduction Ionization Apparatus, Mechanisms, and General Performance Drug Analysis in Biological Matrices using DESI and DART High‐Throughput Analysis Chemical Imaging and Profiling Future Perspectives References

Microbial toxicity tests play an important role in various scientific and technical fields including the risk assessment of chemical compounds in the environment. There is a large battery of normalized tests available that have been standardized by ISO (International Organization for Standardization) and OECD (Organization for Economic Co-operation and Development) and which are worldwide accepted and applied. The focus of this review is to provide information on microbial toxicity tests, which are used to elucidate effects in other laboratory tests such as biodegradation tests, and for the prediction of effects in natural and technical aqueous compartments in the environment. The various standardized tests as well as not normalized methods are described and their advantages and disadvantages are discussed. In addition, the sensitivity and usefulness of such tests including a short comparison with other ecotoxicological tests is presented. Moreover, the far-reaching influence of microbial toxicity tests on biodegradation tests is also demonstrated. A new concept of the physiological potential of an inoculum (PPI) consisting of microbial toxicity tests whose results are expressed as a chemical resistance potential (CRP) and the biodegradation adaptation potential (BAP) of an inoculum is described that may be helpful to characterize inocula used for biodegradation tests. Key points • Microbial toxicity tests standardized by ISO and OECD have large differences in sensitivity and applicability. • Standardized microbial toxicity tests in combination with biodegradability tests open a new way to characterize inocula for biodegradation tests. • Standardized microbial toxicity tests together with ecotoxicity tests can form a very effective toolbox for the characterization of toxic effects of chemicals.

The ubiquitous use of pesticides has increased concerns over their direct and indirect effects on disease dynamics. While studies examining the effects of pesticides on host–parasite interactions have largely focused on how pesticides influence the host, few studies have considered the effects of pesticides on parasites. We investigated the toxicity of six common insecticides at six environmentally-relevant concentrations to cercariae of the trematode Echinoparyphium from two populations. All six insecticides reduced the survival of cercariae (overall difference between mortality in control vs pesticide exposure = 86·2 ± 8·7%) but not in a predictable dose-dependent manner. These results suggest that Echinoparyphium are sensitive to a broad range of insecticides commonly used in the USA. The lack of a clear dose-dependent response in Echinoparyphium highlights the potential limitations of toxicity assays in predicting pesticide toxicity to parasites. Finally, population-level variation in cercarial susceptibility to pesticides underscores the importance of accounting for population variation as overlooking this variation can limit our ability to predict toxicity in nature. Collectively, this work demonstrates that consideration of pesticide toxicity to parasites is important to understanding how pesticides ultimately shape disease dynamics in nature.

Generative models are becoming a tool of choice for exploring the molecular space. These models learn on a large training dataset and produce novel molecular structures with similar properties. Generated structures can be utilized for virtual screening or training semi-supervized predictive models in the downstream tasks. While there are plenty of generative models, it is unclear how to compare and rank them. In this work, we introduce a benchmarking platform called Molecular Sets (MOSES) to standardize training and comparison of molecular generative models. MOSES provides training and testing datasets, and a set of metrics to evaluate the quality and diversity of generated structures. We have implemented and compared several molecular generation models and suggest to use our results as reference points for further advancements in generative chemistry research. The platform and source code are available at https://github.com/molecularsets/moses .

Background The treatment of complex diseases by taking multiple drugs becomes increasingly popular. However, drug-drug interactions (DDIs) may give rise to the risk of unanticipated adverse effects and even unknown toxicity. DDI detection in the wet lab is expensive and time-consuming. Thus, it is highly desired to develop the computational methods for predicting DDIs. Generally, most of the existing computational methods predict DDIs by extracting the chemical and biological features of drugs from diverse drug-related properties, however some drug properties are costly to obtain and not available in many cases. Results In this work, we presented a novel method (namely DPDDI) to predict DDIs by extracting the network structure features of drugs from DDI network with graph convolution network (GCN), and the deep neural network (DNN) model as a predictor. GCN learns the low-dimensional feature representations of drugs by capturing the topological relationship of drugs in DDI network. DNN predictor concatenates the latent feature vectors of any two drugs as the feature vector of the corresponding drug pairs to train a DNN for predicting the potential drug-drug interactions. Experiment results show that, the newly proposed DPDDI method outperforms four other state-of-the-art methods; the GCN-derived latent features include more DDI information than other features derived from chemical, biological or anatomical properties of drugs; and the concatenation feature aggregation operator is better than two other feature aggregation operators (i.e., inner product and summation). The results in case studies confirm that DPDDI achieves reasonable performance in predicting new DDIs. Conclusion We proposed an effective and robust method DPDDI to predict the potential DDIs by utilizing the DDI network information without considering the drug properties (i.e., drug chemical and biological properties). The method should also be useful in other DDI-related scenarios, such as the detection of unexpected side effects, and the guidance of drug combination.

The development of inhaled drugs for respiratory diseases is frequently impacted by lung pathology in non-clinical safety studies. To enable design of novel candidate drugs with the right safety profile, predictive in vitro lung toxicity assays are required that can be applied during drug discovery for early hazard identification and mitigation. Here, we describe a novel high-content imaging-based screening assay that allows for quantification of the tight junction protein occludin in A549 cells, as a model for lung epithelial barrier integrity. We assessed a set of compounds with a known lung safety profile, defined by clinical safety or non-clinical in vivo toxicology data, and were able to correctly identify 9 of 10 compounds with a respiratory safety risk and 9 of 9 compounds without a respiratory safety risk (90% sensitivity, 100% specificity). The assay was sensitive at relevant compound concentrations to influence medicinal chemistry optimization programs and, with an accessible cell model in a 96-well plate format, short protocol and application of automated imaging analysis algorithms, this assay can be readily integrated in routine discovery safety screening to identify and mitigate respiratory toxicity early during drug discovery. Interestingly, when we applied physiologically-based pharmacokinetic (PBPK) modelling to predict epithelial lining fluid exposures of the respiratory tract after inhalation, we found a robust correlation between in vitro occludin assay data and lung pathology in vivo, suggesting the assay can inform translational risk assessment for inhaled small molecules.

Understanding mechanistic and cellular events underlying a toxicological outcome allows the prediction of impact of environmental stressors to organisms living in different habitats. A systems-based approach aids in characterizing molecular events, and thereby the cellular pathways that have been perturbed. However, mapping only adverse outcomes of a toxicant falls short of describing the stress or adaptive response that is mounted to maintain homeostasis on perturbations and may confer resistance to the toxic insult. Silver is a potential threat to aquatic organisms because of the increasing use of silver-based nanomaterials, which release free silver ions. The effects of silver were investigated at the transcriptome, proteome, and cellular levels of Chlamydomonas reinhardtii . The cells instigate a fast transcriptome and proteome response, including perturbations in copper transport system and detoxification mechanisms. Silver causes an initial toxic insult, which leads to a plummeting of ATP and photosynthesis and damage because of oxidative stress. In response, the cells mount a defense response to combat oxidative stress and to eliminate silver via efflux transporters. From the analysis of the perturbations of the cell’s functions, we derived a detailed mechanistic understanding of temporal dynamics of toxicity and adaptive response pathways for C. reinhardtii exposed to silver.

All areas of the modern society are affected by fluorine chemistry. In particular, fluorine plays an important role in medical, pharmaceutical and agrochemical sciences. Amongst various fluoro-organic compounds, trifluoromethyl (CF3) group is valuable in applications such as pharmaceuticals, agrochemicals and industrial chemicals. In the present study, following the strict OECD modelling principles, a quantitative structure–toxicity relationship (QSTR) modelling for the rat acute oral toxicity of trifluoromethyl compounds (TFMs) was established by genetic algorithm-multiple linear regression (GA-MLR) approach. All developed models were evaluated by various state-of-the-art validation metrics and the OECD principles. The best QSTR model included nine easily interpretable 2D molecular descriptors with clear physical and chemical significance. The mechanistic interpretation showed that the atom-type electro-topological state indices, molecular connectivity, ionization potential, lipophilicity and some autocorrelation coefficients are the main factors contributing to the acute oral toxicity of TFMs against rats. To validate that the selected 2D descriptors can effectively characterize the toxicity, we performed the chemical read-across analysis. We also compared the best QSTR model with public OPERA tool to demonstrate the reliability of the predictions. To further improve the prediction range of the QSTR model, we performed the consensus modelling. Finally, the optimum QSTR model was utilized to predict a true external set containing many untested/unknown TFMs for the first time. Overall, the developed model contributes to a more comprehensive safety assessment approach for novel CF3-containing pharmaceuticals or chemicals, reducing unnecessary chemical synthesis whilst saving the development cost of new drugs.