Toxicity-guided assessment of disinfection by-products via machine learning and network toxicology.

Machine Learning Applied to Aquatic Toxicity and Chemical Reactions of Xenobiotic Compounds

Environmental toxicity, especially in aquatic ecosystems, is an extremely relevant topic in the current global scenario due to the increased contamination caused by human activities and industrial processes. Chemical substances, such as pesticides, industrial waste, cosmetics, and microplastics, are frequently released into water bodies, endangering aquatic biodiversity and human health. These pollutants can cause cumulative and synergistic effects, amplifying the reach and severity of the environmental impact. In this work, machine learning and chemoinformatics tools were used in conjunction with the RDKit library to study OH radical chemical reactions in an aquatic environment. Bond change type plots were generated for 17 chemical reactions, testing approximately 1500 xenobiotic reagents, identifying the main changes between products and reagents. The quantitative structure-activity relationship (QSAR) was used as the basis for a toxicity prediction model, using ExtraTreeRegressor, for (lethal dose 50% (LD50)) values obtained from the US EPA Ecotox database. An R2 score of 0.6134 for the validation set was obtained. The three most important QSAR descriptors was identified in this prediction model using variable selection tools from the Scikit-learn library.

Species-aware prediction of fish acute toxicity improves hazard screening and prioritization of environmentally detected pharmaceuticals.

Widespread contamination of surface waters by active pharmaceutical ingredients (APIs) leads to ubiquitous exposure in fish, critical sentinels in aquatic food webs. However, ecotoxicity assessment remains constrained by pronounced interspecies differences in sensitivity and by the scarcity of toxicity data for fish species representative of distinct ecoregions. To support hazard screening of environmentally detected APIs, we developed an ensemble model integrating Deep Neural Networks (DNN) with six other machine learning models. Trained on 10,054 acute toxicity data points (4190 groups, 1651 organic compounds, 24 freshwater fish species), the model achieved a test-set R2 of 0.72 and an RMSE of 0.83. Ablation analysis showed that the model trained on a feature space integrating chemical, biological, and exposure-related descriptors outperformed the model based solely on chemical descriptors, indicating that biological and experimental factors provide complementary information for predicting fish acute toxicity. Feature interaction analysis revealed that Salmoniformes exhibited heightened sensitivity to lower-MW compounds, whereas under static exposure conditions, higher MW was associated with attenuated toxicity. Applied to 714 environmentally detected APIs lacking experimental fish acute toxicity data, the framework showed that applicability-domain definitions strongly influenced scenario coverage and downstream species sensitivity distribution construction. This work provides a predictive strategy that helps address the limitations of disparate and ecologically unrepresentative testing data that compromise regional relevance, thereby enabling proactive and ecologically grounded chemical prioritization in freshwater ecosystems.

Prediction and mechanistic insights into drug-induced reproductive toxicity through integrated machine learning, FAERS-based signal comparison, and network toxicology analyses.

ToxiVerse: chemical bioprofiling, toxicity data sharing and customizable predictive modeling.

MOTIVATION Chemical toxicity assessment is critical for drug development and environmental safety. Computational models have emerged as a promising alternative to animal testing and now play a significant role in efficiently evaluating new chemicals. To address the urgent need for user-friendly machine learning tools in computational toxicology, we developed ToxiVerse, a public web-based platform. RESULTS ToxiVerse provides automatic chemical bioprofiling, curated toxicity datasets, and a predictive modeling interface designed for researchers who lack programming expertise. The platform comprises three integrated modules: (i) Bioprofiler, which provides chemical descriptors by combining chemical-bioactivity data from PubChem assays with a machine learning-based data gap-filling procedure; (ii) Database, which hosts ∼50 000 curated chemicals covering diverse toxicity endpoints; and (iii) Cheminformatics, which enables dataset upload, chemical curation, and automatic generation of quantitative structure-activity relationship models for toxicity prediction. AVAILABILITY The tool is accessible at www.toxiverse.com, and source code is available at https://github.com/zhu-research-group/toxiverse. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.

Machine learning models for prediction of emerging pollutants' risk in Daphnia magna.

Emerging pollutants may threaten aquatic ecosystems, yet the limited toxicity data for many compounds significantly restrict high-throughput screening of these contaminants. Because Daphnia magna is a sensitive standard test organism and an important link in aquatic food webs, reliable prediction of its acute toxicity response is critical for ecological risk assessment. Here, we curated a Daphnia magna acute toxicity (EC50) database for 170 compounds across several classes of emerging pollutants, including per- and polyfluoroalkyl substances (PFASs) and organophosphate esters (OPEs), using public databases and literature. We developed machine learning models to predict 1-4 day EC50 values and found that eXtreme Gradient Boosting (XGB) performed best (QLOO2 = 0.95, QEXT2 = 0.85), followed by Random Forest (RF; QLOO2 = 0.89, QEXT2 = 0.77). An eight-compound case-study validation showed that predicted and empirical Daphnia magna acute-effect values were generally within one order of magnitude, but the small sample size and high leverage of extreme values require cautious interpretation. Model interpretation identified molecular topology and electronic distribution as key toxicity drivers. The predicted Daphnia magna EC50 values were then combined with empirical toxicity data from other aquatic species to construct Species Sensitivity Distribution (SSD) curves. This framework provides a high-throughput tool for filling toxicity data gaps and supporting ecological risk assessment of emerging pollutants.

Toxic Mechanisms Underlying Prostate Cancer Induction by Water Pollutants: Based on Network Toxicology, Molecular Docking, and Molecular Dynamics Simulations.

INTRODUCTION Addressing water pollutants remains a key priority in contemporary environmental governance, as waterborne pollutants pose significant risks to human health. We focus on four major classes of environmentally persistent water pollutants, namely volatile organic compounds (VOCs), polycyclic aromatic hydrocarbons (PAHs), organochlorine pesticides (OCPs), and polybrominated diphenyl ethers (PBDEs), due to their widespread occurrence and potential carcinogenicity. Integrating network toxicology, molecular docking, and molecular dynamics simulations, this study elucidates the molecular mechanisms by which these pollutants may contribute to prostate carcinogenesis. METHODS We initially employed ProTox-3.0 and ADMETLAB 3.0 to predict the toxicity of the selected water pollutants. Potential targets for compounds representing four major classes of water pollutants were retrieved from the ChEMBL and SwissTargetPrediction databases. Disease genes related to prostate cancer were collected from the GeneCards, OMIM, and TTD databases. Utilizing the STRING database and Cytoscape software, a molecular regulatory network of toxicological targets and a protein-protein interaction (PPI) network associated with water pollutant-induced prostate cancer were constructed. Then, core genes were screened. Subsequently, Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis were performed, followed by molecular docking. Finally, molecular dynamics (MD) simulations were conducted based on the molecular docking results. RESULTS Enrichment analysis revealed that multiple pathways associated with water pollutant exposure were significantly enriched among prostate cancer-related genes, indicating a potential link between pollutant carcinogenicity and prostate carcinogenesis. Molecular docking results indicated that 80 % of the 75 tested protein-ligand complexes exhibited binding energies lower than -5.0 kcal/mol. MD simulation results demonstrated that all four selected protein-ligand complexes maintained remarkable structural stability throughout the simulation trajectory. DISCUSSION The integration of network toxicology, molecular docking, and MD simulations in this study provides a systematic framework for deciphering the molecular toxicological mechanisms by which water pollutants contribute to the development of prostate cancer. By integrating target information from multiple authoritative databases, we identified five core targets (TP53, EGFR, MYC, STAT3, and TNF) that play pivotal roles in mediating the carcinogenic effects of water pollutants. These targets offer key molecular anchors for understanding the pathogenic link between water pollution and prostate cancer. GO and KEGG enrichment analyses further elucidated the critical biological processes and signaling pathways involved (including the hypoxic response and the PI3K-Akt signaling pathway), which are closely associated with cell proliferation, apoptosis, inflammation, and angiogenesis, all of which are hallmarks of prostate cancer progression. Collectively, these findings suggest that the identified pollutant compounds form highly stable interactions with key prostate cancer targets, supporting their potential role in disease progression. CONCLUSION This study suggests that specific compounds within the four classes of typical water pollutants may exert potential carcinogenic effects on prostate cancer. Furthermore, these findings provide a theoretical framework and methodological reference for future investigations into the impact of water pollutants on other malignancies and chronic diseases.