[Prediction of Cadmium Uptake Factor in Wheat Based on Machine Learning].

Applying machine learning methods to resolve the cadmium (Cd) uptake characteristics of regional soil-wheat systems can contribute to the accuracy and rationality of risk decisions. Based on a regional survey, we constructed a Freundlich-type transfer equation, random forest (RF) model, and neural network (BPNN) model to predict wheat Cd enrichment factor (BCF-Cd); verified the prediction accuracy; and assessed the uncertainty of different models. The results showed that both RF (R2=0.583) and BPNN (R2=0.490) were better than the Freundlich transfer equation (R2=0.410). The RF and BPNN were further trained repeatedly, and the results showed that the mean absolute error (MAE) and root mean square error (RMSE) of RF and BPNN were close to each other. Additionally, the accuracy and stability of RF (R2=0.527-0.601) was higher than that of BPNN (R2=0.432-0.661). Feature importance analysis showed that multiple factors led to the heterogeneity of wheat BCF-Cd, in which soil phosphorus (P) and zinc (Zn) were the key variables affecting the change in wheat BCF-Cd. Parameter optimization can further improve the accuracy, stability, and generalization ability of the model.

[Streptococcus pneumoniae induces SPLUNC1 and the regulatory effects of resveratrol].

OBJECTIVE: To investigate the host-defense role of short palate, lung, and nasal epithelium clone 1 (SPLUNC1) in Streptococcus pneumoniae (SP) infection and the effect of resveratrol (Res) on SPLUNC1 expression, and to provide new thoughts for the treatment of diseases caused by SP infection. METHODS: According to the multiplicity of infection (MOI), BEAS-2B cells with SP infection were divided into control group, MOI20 SP group, and MOI50 SP group. According to the different concentrations of Res, the BEAS-2B cells with MOI20 SP infection pretreated by Res were divided into 12.5Res+SP group, 25Res+SP group, and 50Res+SP group (the final concentrations of Res were 12.5, 25, and 50 µmol/L, respectively). Cell Counting Kit-8 was used to measure cell activity and determine the optimal concentration and action time of SP and Res. In the formal experiment, the cells were divided into control group, Res group, SP group, and Res+SP group. Real-time PCR and ELISA were used to measure the mRNA and protein expression of SPLUNC1. RESULTS: Over the time of SP infection, cell activity tended to decrease. Compared with the control group and the MOI20 SP group, the MOI50 SP group had a reduction in cell activity. Compared with the MOI20 SP group, the 25Res+SP group had increased cell activity and the 50Res+SP group had reduced cell activity (P<0.05). MOI20 SP bacterial suspension and 25 µmol/L Res were used for the formal experiment. Over the time of SP infection, the mRNA expression of SPLUNC1 in BEAS-2B cells firstly increased and then decreased in the SP group and the Res+SP group (P<0.05). Compared with the SP group, the Res+SP group had significant increases in the mRNA and protein expression of SPLUNC1 at all time points (P<0.05). Compared with the control group, the Res group had no significant changes in the mRNA and protein expression of SPLUNC1 (P>0.05). CONCLUSIONS: SP infection can induce SPLUNC1 expression and the host-defense role of SPLUNC1. Res can upregulate SPLUNC1 expression during the development of infection and enhance cell protection in a concentration- and time-dependent manner.