Graph Convolutional Network-Enhanced Model for Screening Persistent, Mobile, and Toxic and Very Persistent and Very Mobile Substances.

The global management for persistent, mobile, and toxic (PMT) and very persistent and very mobile (vPvM) substances has been further strengthened with the rapid increase of emerging contaminants. The development of a ready-to-use and publicly available tool for the high-throughput screening of PMT/vPvM substances is thus urgently needed. However, the current model building with the coupling of conventional algorithms, small-scale data set, and simplistic features hinders the development of a robust model for screening PMT/vPvM with wide application domains. Here, we construct a graph convolutional network (GCN)-enhanced model with feature fusion of a molecular graph and molecular descriptors to effectively utilize the significant correlation between critical descriptors and PMT/vPvM substances. The model is built with 213,084 substances following the latest PMT classification criteria. The application domains of the GCN-enhanced model assessed by kernel density estimation demonstrate the high suitability for high-throughput screening PMT/vPvM substances with both a high accuracy rate (86.6%) and a low false-negative rate (6.8%). An online server named PMT/vPvM profiler is further developed with a user-friendly web interface (http://www.pmt.zj.cn/). Our study facilitates a more efficient evaluation of PMT/vPvM substances with a globally accessible screening platform.

Impaired barrier integrity of endothelial cells induced by PEGylated black phosphorus nanosheets.

PEGylated black phosphorus nanosheets (PEG-BPNSs) have shown promising applications in biomedicine and potentially interact with the vasculature following iatrogenic exposures. Whether the exposure to PEG-BPNSs could induce toxic effects on endothelial cells that line the blood vessels remains largely unknown. Herein, we investigate the cellular response and transcriptional profiling of human umbilical vein endothelial cells (HUVECs) after the exposure to BPNSs and PEG-BPNSs. BPNSs and PEG-BPNSs induce cellular elongation and cause significant cytotoxicity to HUVECs at 0.8 µg/mL, with viabilities of 87.8% and 87.7% respectively. The transcriptome analysis indicates that BPNSs and PEG-BPNSs at 0.4 µg/mL cause marked alterations in the expression of genes associated with detection of stimulus, ion transmembrane transport and components of plasma membrane. BPNSs and PEG-BPNSs at 0.4 µg/mL decrease the transendothelial electrical resistance (TEER) across monolayers of HUVECs by 22.8% and 20.3% compared to the control, respectively. The disturbance of tight junctions (TJs) after 24 h exposure to 0.4 µg/mL BPNSs and PEG-BPNSs is indicated with the downregulated mRNA expression of zona occluden-1 (ZO-1) by respective 16.5% and 29.9%, which may be involved in the impairment of endothelial barrier integrity. Overall, the response of HUVECs to PEG-BPNSs and BPNSs has no statistical difference, suggesting that PEGylation does not attenuate the BPNSs-induced endothelial injury. This study demonstrates the detrimental effects of BPNSs and PEG-BPNSs on barrier integrity of HUVECs, contributing to our understanding on the potential toxicological mechanisms.

Improving kitchen waste composting maturity by optimizing the processing parameters based on machine learning model.

As a novel analytical method based on big data, machine learning model can explore the relationship between different parameters and draw universal conclusions, which was used to predict composting maturity and identify key parameters in this study. The results showed that the Stacking model exhibited excellent prediction accuracy. SHapley Additive exPlanations (SHAP) and Partial Dependence Analysis (PDA) were performed to evaluate the importance of different parameters as well as their optimal interval. Optimal starting conditions should be maintained in the mesophilic state (temperature: 30-45℃, moisture content: 55-65%, pH: 6.3-8.0), and nutrients (total nitrogen > 2.3%, total organic carbon > 35%) should be adjusted in the thermophilic state. Experiments revealed that model-based optimization strategies could improve composting maturity because they could optimize compost microbial flora and perform complex carbon cycle functions. In conclusion, this study provides new insights into the enhancement of the composting process.