Quantitative analysis of dose interval effect of Pb-Cd interaction on Oryza sativa L. root

Exploring pollutant joint effects in disease through interpretable machine learning

Identifying the impact of pollutants on diseases is crucial. However, assessing the health risks posed by the interplay of multiple pollutants is challenging. This study introduces the concept of Pollutants Outcome Disease, integrating multidisciplinary knowledge and employing explainable artificial intelligence (AI) to explore the joint effects of industrial pollutants on diseases. Using lung cancer as a representative case study, an extreme gradient boosting predictive model that integrates meteorological, socio-economic, pollutants, and lung cancer statistical data is developed. The joint effects of industrial pollutants on lung cancer are identified and analyzed by employing the SHAP (Shapley Additive exPlanations) interpretable machine learning technique. Results reveal substantial spatial heterogeneity in emissions from CPG and ILC, highlighting pronounced nonlinear relationships among variables. The model yielded strong predictions (an R of 0.954, an RMSE of 4283, and an R2 of 0.911) and emphasized the impact of pollutant emission amounts on lung cancer responses. Diverse joint effects patterns were observed, varying in terms of patterns, regions (frequency), and the extent of antagonistic and synergistic effects among pollutants. The study provides a new perspective for exploring the joint effects of pollutants on diseases and demonstrates the potential of AI technology to assist scientific discovery.

Physiological tolerance of black locust (Robinia pseudoacacia L.) and changes of rhizospheric bacterial communities in response to Cd and Pb in the contaminated soil

Woody plants possess great potential for phytoremediation of heavy metal-contaminated soil. A pot trial was conducted to study growth, physiological response, and Cd and Pb uptake and distribution in black locust (Robinia pseudoacacia L.), as well as the rhizosphere bacterial communities in Cd and Pb co-contaminated soil. The results showed that R. pseudoacacia L. had strong physiological regulation ability in response to Cd and Pb stress in contaminated soil. The total chlorophyll, malondialdehyde (MDA), soluble protein, and sulfhydryl contents, as well as antioxidant enzymes (superoxide dismutase, peroxidase, catalase) activities in R. pseudoacacia L. leaves under the 40 mg·kg-1 Cd and 1000 mg·kg-1 Pb co-contaminated soil were slightly altered. Cd uptake in R. pseudoacacia L. roots and stems increased, while the Pb content in the shoots of R. pseudoacacia L. under the combined Cd and Pb treatments decreased in relative to that in the single Pb treatments. The bacterial α-diversity indices (e.g., Sobs, Shannon, Simpson, Ace, and Chao) of R. pseudoacacia L. rhizosphere soil under Cd and Pb stress were changed slightly relative to the CK treatment. However, Cd and Pb stress could significantly (p < 0.05) alter the rhizosphere soil microbial communities. According to heat map and LEfSe (Linear discriminant analysis Effect Size) analysis, Bacillus, Sphingomonas, Terrabacter, Roseiflexaceae, Paenibacillus, and Myxococcaceae at the genus level were notably (p < 0.05) accumulated in the Cd- and/or Pb-contaminated soil. Furthermore, the MDA content was notably (p < 0.05) negatively correlated with the relative abundances of Isosphaeraceae, Gaiellales, and Gemmatimonas. The total biomass of R. pseudoacacia L. was positively (p < 0.05) correlated with the relative abundances of Xanthobacteraceae and Vicinamibacreraceae. Network analysis showed that Cd and Pb combined stress might enhance the modularization of bacterial networks in the R. pseudoacacia L. rhizosphere soil. Thus, the assembly of the soil bacterial communities in R. pseudoacacia L. rhizosphere may improve the tolerance of plants in response to Cd and/or Pb stress.