Using machine learning to classify the immunosuppressive activity of per- and polyfluoroalkyl substances.

Per- and polyfluoroalkyl substances (PFASs), one of the persistent organic pollutants, have immunosuppressive effects. The evaluation of this effect has been the focus of regulatory toxicology. In this investigation, 146 PFASs (immunosuppressive or nonimmunosuppressive) and corresponding concentration gradients were collected from literature, and their structures were characterized by using Dragon descriptors. Feature importance analysis and stepwise feature elimination are used for feature selection. Three machine learning (ML) methods, namely Random Forest (RF), Extreme Gradient Boosting Machine (XGB), and Categorical Boosting Machine (CB), were utilized for model development. The model interpretability was explored by feature importance analysis and correlation analysis. The findings indicated that the three models developed have exhibited excellent performance. Among them, the best-performing RF model has an average AUC score of 0.9720 for the testing set. The results of the feature importance analysis demonstrated that concentration, SpPosA_X, IVDE, R2s, and SIC2 were the crucial molecular features. Applicability domain analysis was also performed to determine reliable prediction boundaries for the model. In conclusion, this study is the first application of ML models to investigate the immunosuppressive activity of PFASs. The variables used in the models can help understand the mechanism of the immunosuppressive activity of PFASs, allow researchers to more effectively assess the immunosuppressive potential of a large number of PFASs, and thus better guide environmental and health risk assessment efforts.

HNF4A as a potential target of PFOA and PFOS leading to hepatic steatosis: Integrated molecular docking, molecular dynamic and transcriptomic analyses.

Perfluorooctanoic acid (PFOA) and perfluorooctane sulfonate (PFOS) are indeed among the most well known and extensively studied Per- and polyfluoroalkyl substances (PFASs), and increasing evidence confirm their effects on human health, especially liver steatosis. Nonetheless, the molecular mechanisms of their initiation of hepatic steatosis is still elusive. Therefore, potential targets of PFOA/PFOS must be explored to ameliorate its adverse consequences. This research aims to investigate the molecular mechanisms of PFOA and PFOS-induced liver steatosis, with emphasis on identifying a potential target that links these PFASs to liver steatosis. The potential target that causes PFOA and PFOS-induced liver steatosis have been explored and determined based on molecular docking, molecular dynamics (MD) simulation, and transcriptomics analysis. In silico results show that PFOA/PFOS can form a stable binding conformation with HNF4A, and PFOA/PFOS may interact with HNF4A to affect the downstream conduction mechanism. Transcriptome data from PFOA/PFOS-induced human stem cell spheres showed that HNF4A was inhibited, suggesting that PFOA/PFOS may constrain its function. PFOS mainly down-regulated genes related to cholesterol synthesis while PFOA mainly up-regulated genes related to fatty acid ß-oxidation. This study explored the toxicological mechanism of liver steatosis caused by PFOA/PFOS. These compounds might inhibit and down-regulate HNF4A, which is the molecular initiation events (MIE) that induces liver steatosis.

Prediction of the Endocrine disruption profile of fluorinated biphenyls and analogues: An in silico study.

Fluorinated biphenyls and their analogues (FBAs) are considered new persistent organic pollutants, but their endocrine-disrupting effects are still unknown. To fill this gap, the binding probability of 44 FBAs to different nuclear hormone receptors (NHRs) was predicted using Endocrine Disruptome. And molecular similarity and network toxicology analysis were used to strengthen the docking screening. The docking results showed that FBAs could have high binding potential for various NHRs, such as estrogen receptors ß antagonism (ERß an), liver X receptors α (LXRα), estrogen receptors α (ERα), and liver X receptors ß (LXRß). The similarity analysis found that the degree of overlap of the NHR repertoire was related to the Tanimoto coefficient of FBAs. Network toxicology verified a part of docking screening results and identified endocrine-disrupting pathways worthy of attention. This study found out potential endocrine-disrupting FBAs and their vulnerable, and developed a workflow that would leverage in silico approaches including molecular docking, similarity, and network toxicology for risk prioritization of potential endocrine-disrupting compounds.

Prediction of the endocrine-disrupting ability of 49 per- and polyfluoroalkyl substances: In silico and epidemiological evidence.

The toxic effects of per- and polyfluoroalkyl substances (PFASs) on humans are mediated by nuclear hormone receptors (NHRs). However, data on the interaction of PFASs and NHRs is limited. Endocrine Disruptome, an inverse docking tool, was used in this study to simulate the docking of 49 common PFASs with 14 different types of human NHRs. According to the findings, 25 PFASs have a high or moderately high probability of binding to more than five NHRs, with androgen receptor (AR) and mineralocorticoid receptor (MR) being the most likely target NHRs. Molecular docking analyses revealed that the binding modes of PFASs with the two NHRs were similar to those of their corresponding co-crystallized ligands. PFASs, in particular, may disrupt the endocrine system by binding to MR. This finding is consistent with epidemiological research that has linked PFASs to MR-related diseases. Our findings may contribute to a better understanding of the health risks posed by PFASs.