A network toxicology and machine learning approach to uncover the molecular machinery of bisphenol A-induced colorectal cancer

Integration of network toxicology, machine learning and single-cell sequencing identifies candidate molecular links between air pollutants and hepatocellular carcinoma.

BACKGROUND Epidemiological studies link long-term air pollution to an increased risk of hepatocellular carcinoma (HCC), but the underlying toxicological targets remain poorly understood. We used an integrative computational framework to identify and prioritize candidate molecular mediators potentially linking pollutant-associated gene signatures with hepatocarcinogenesis. METHODS We retrieved pollutant-responsive genes associated with seven toxicants from the Comparative Toxicogenomics Database and intersected them with HCC-associated genes. We used protein-protein interaction (PPI) network analysis to identify hub nodes. An optimized machine learning pipeline (glmBoost and Ridge regression) was trained on GSE36376 and validated in three independent cohorts. We mapped gene program activity within the tumor microenvironment using single-cell RNA sequencing (scRNA-seq) and modeled perturbations with scTenifoldKnk. Finally, we assessed structural compatibility between pollutants and protein targets. RESULTS We identified 240 genes at the intersection of pollutant and HCC sets. Enrichment analysis highlighted innate immune signaling and chronic inflammation, specifically the IL-17, TNF, and NF-κB pathways. Hub nodes included IL6, TNF, MMP9, and AKT1. The machine learning model prioritized five candidate transcriptomic markers: FOS (AUC = 0.944), PARP1 (AUC = 0.929), MMP9 (AUC = 0.813), CCL5 (AUC = 0.747), and JUN (AUC = 0.733), all validated across cohorts. scRNA-seq module scoring showed the highest activity in T cells, monocytes, and macrophages. However, these data lack individual-level pollutant exposure documentation. In silico MMP9 knockout perturbed genes involved in angiogenesis and the extracellular matrix. Molecular docking suggested preliminary structural compatibility between toluene and MMP9 (-5.2 kcal/mol). CONCLUSION This analysis outlines a potential "pollutant-immune/inflammation-HCC" framework and identifies five transcriptomic signatures for further validation. These findings support a hypothesis that air pollutant-associated molecular programs may be linked to HCC pathobiology and warrant experimental validation.

Integrated multi-omics, machine learning, network toxicology, and molecular docking reveal potential mechanisms underlying methyl 4-hydroxybenzoate-associated breast cancer.

Integrated network toxicology, bioinformatics, and molecular docking reveal the potential molecular mechanisms linking bisphenol A to glioma progression

Glioma is a highly aggressive central nervous system malignancy with poor clinical outcomes, and increasing attention has focused on whether environmental endocrine-disrupting chemicals contribute to its progression. This study aimed to systematically investigate the molecular mechanisms linking bisphenol A (BPA) to glioma using an integrated network toxicology and bioinformatics strategy. BPA-related targets were collected from public databases and intersected with glioma-associated genes to identify shared targets. A protein–protein interaction network was then constructed to screen hub genes, followed by transcriptomic validation using the GSE41031 dataset. Functional enrichment analyses were performed to characterize the biological processes and signaling pathways involved, and molecular docking was used to assess the binding potential of BPA with representative core targets. A total of 696 common targets were identified between BPA and glioma. Network analysis highlighted 20 hub genes, among which STAT3, AKT1, TNF, IL6, and TP53 showed the highest topological importance. Most hub genes were significantly dysregulated in glioma stem cells relative to normal neural stem cells. Enrichment analyses indicated that the shared targets were mainly associated with oxidative stress, hypoxia, xenobiotic response, steroid hormone signaling, apoptosis, focal adhesion, and the PI3K-Akt pathway. Molecular docking suggested moderate predicted binding compatibility between BPA and the five selected hub proteins. These in silico findings suggest that BPA-related targets are potentially associated with glioma-relevant inflammatory, stress-response, and survival-related signaling networks. This study provides a systems-level framework for understanding the potential contribution of BPA to glioma biology and identifies candidate molecular targets for future mechanistic and translational investigations.

Plasticizers and prostate cancer: unraveling the link through network toxicology and machine learning

Background Plasticizers, as widespread environmental endocrine disruptors, are increasingly linked to an elevated risk of prostate cancer (PCa). However, the specific molecular mechanisms by which they drive PCa initiation and progression remain incompletely elucidated. Addressing this knowledge gap is crucial for assessing environmental health risks and identifying potential intervention targets. Methods This study employed a multi-level integrated research strategy. First, the toxicological profiles of target plasticizers were predicted using ADMETlab and ProTox platforms. Second, plasticizer-related targets were identified by integrating multiple databases and then cross-referenced with differentially expressed genes in PCa from TCGA and GEO cohorts to obtain shared targets. Subsequently, a protein-protein interaction (PPI) network was constructed and analyzed topologically. GO and KEGG enrichment analyses were performed to explore underlying biological processes and pathways. A total of 98 combination prediction models based on 10 machine learning algorithms were developed and evaluated to identify core prognostic genes. Furthermore, single-cell and spatial transcriptomics data were utilized to examine the expression localization of core genes within the tumor microenvironment. Molecular docking simulations were conducted to validate the binding affinity between plasticizers and core target proteins. Finally, in vitro experiments demonstrated the pro-tumorigenic effects of DMP and its regulatory role in PLK1 expression in prostate cancer cells. Results Toxicity predictions confirmed the carcinogenic potential of DEP, DMP, and DOP. A total of 183 bridging genes connecting plasticizers and PCa were identified. Enrichment analysis revealed their significant involvement in key pathways including inflammatory response, cell cycle, p53 signaling, and chemical carcinogenesis. PPI network analysis preliminarily screened hub genes such as ALB and MMP9. Through systematic machine learning modeling and prognostic analysis, the core targets were further narrowed down to PLK1, ALB, and CCNA2. Among these, high expression of PLK1 was significantly associated with shorter disease-free survival in multiple independent cohorts. Molecular docking results indicated that all three plasticizers could bind stably to the PLK1 protein with high affinity (binding free energy < -5.0 kcal/mol). Single-cell and spatial transcriptomic analyses showed high expression of PLK1 in tumor epithelial cells. In vitro experiments confirmed that DMP promotes the proliferation, migration, and invasion of PCa cells, as well as upregulates PLK1 expression. Pan-cancer analysis further indicated that PLK1 is commonly overexpressed in various cancers and associated with poor prognosis. Conclusion This study integrates computational toxicology, bioinformatics, machine learning, and experimental validation to reveal that common plasticizer exposure may promote PCa progression through dysregulation of cell cycle and inflammatory pathways, with PLK1 identified as a central molecular target. These findings establish a multi-omics evidence chain supporting the carcinogenic potential of environmental endocrine disruptors and provide a scientific basis for considering PLK1 as both a biomarker for risk assessment and a therapeutic target in plasticizer-associated PCa.

Multi-omics and network toxicology prioritize ADAMTS13 as a candidate gene computationally linked to TDCPP targets in hepatocellular carcinoma.

BACKGROUND Tris(1,3-dichloro-2-propyl) phosphate (TDCPP), a widely used organophosphate flame retardant, has been increasingly recognized as a potential environmental risk factor for human cancers. However, its potential association with hepatocellular carcinoma (HCC) and the underlying molecular mechanisms remain largely unclear. METHODS An integrative network toxicology and multi-omics approach was employed to explore the potential computational link between TDCPP‑related targets and HCC transcriptomic changes. TDCPP-associated targets were collected from public databases and intersected with differentially expressed genes from The Cancer Genome Atlas (TCGA). Weighted gene co-expression network analysis (WGCNA) and machine learning algorithms were applied to identify candidate genes. Functional enrichment, immune infiltration, single-cell RNA sequencing, and molecular docking analyses were subsequently performed. RESULTS A total of six candidate genes were identified, among which ADAMTS13 exhibited strong discriminative performance in the predictive models. Functional analyses suggested that these genes may be involved in pathways related to extracellular matrix organization, immune regulation, and tumor microenvironment remodeling. Immune infiltration and single-cell analyses indicated a potential association between ADAMTS13 expression and tumor microenvironment characteristics. Molecular docking analysis further suggested a potential interaction between TDCPP and ADAMTS13 at the structural level. CONCLUSIONS These findings suggest a computational association between TDCPP-related targets and HCC transcriptomic changes, with ADAMTS13 emerging as a computationally prioritized candidate gene for further experimental investigation. This study provides a hypothesis-generating framework for understanding possible molecular links between environmental contaminants and hepatocarcinogenesis, but does not establish causality or confirm actual TDCPP exposure in the analyzed patient cohorts.

Toxicological impact of benzo[a]pyrene on esophageal cancer: an integrated analysis via network toxicology, machine learning, and molecular docking

Background To investigate the mechanisms underlying benzo[a]pyrene-induced esophageal cancer (EC), and to screen and identify the key targets and biomarkers associated with benzo[a]pyrene-related EC. Methods Potential targets of benzo[a]pyrene (BaP) were predicted using PharmMapper, SwissTargetPrediction, and ChEMBL databases, and were intersected with differentially expressed genes (DEGs) from the GEO database to screen candidate key genes. Subsequently, diagnostic models were constructed using 14 machine learning algorithms based on the identified key genes. Meanwhile, a prognostic model of key genes was constructed based on the TCGA esophageal cancer cohort, and the correlation between these key genes and tumor immune infiltration was further explored. Additional explainability was provided via SHAP analysis by determining the contributions of key features. Molecular docking was performed to verify the binding between BaP and core targets. Results A total of 82 genes were identified as potential targets of EC induced by BaP. These key genes were found to be mainly involved in core tumor-related pathways, cell cycle regulation, MAPK signaling, and immune-inflammatory pathways, covering the crucial biological processes underlying malignant transformation of EC. Subsequently, 12 core genes (ACOT9、ACOX3、AURKA、HMGCR、INHBA、MMP3、MSR1、SHC1、SORT1、MAOB、MMP13、CDK4) were identified as key regulators by machine learning analysis. Among them, SORT1 and ACOX3 were significantly down-regulated, while AURKA and MMP13 were markedly up-regulated (P < 0.05). The 12-gene prognostic model enables efficient prognostic stratification of esophageal cancer patients, and core genes are implicated in the remodeling of the esophageal cancer immunosuppressive microenvironment through the regulation of immune cell infiltration. Molecular docking revealed strong binding ability between BaP and target proteins. Conclusions Bioinformatics analysis and molecular docking results revealed significant associations between BaP and 12 core esophageal cancer-related genes. BaP could stably bind to core proteins including AURKA, CDK4, MMP13 and INHBA, which is potentially correlated with altered cell cycle, metabolic disorders and dysregulated tumor immune microenvironment in esophageal cancer. 12 core genes were identified via machine learning, which offers new perspectives for the interdisciplinary field of environmental toxicology and precision oncology and provides a foundation for the development of individualized therapeutic strategies.