C3dg and MAC complement depositions in the renal histopathology of patients with lupus nephropathy.

Background: Childhood-onset systemic lupus erythematosus (SLE) refers to SLE with an onset before 18 years old. The key to the pathogenesis of SLE tissue inflammation and injury is complement activation. The presence of complement split C3dg and membrane attack complex (MAC) may indicate a worse prognosis for lupus nephritis (LN). This study investigated whether complement split C3dg and MAC depositions in the pathogenesis of LN are potential biomarkers of disease severity and tissue injury. Methods: The data on patients with LN were retrospectively analyzed in our center between April 2018 and December 2020. The depositions of C3dg and MAC were detected by immunofluorescence staining. Results: C3dg and MAC were both detected in specimens from 61.5% of patients. Patients with MAC depositions had a greater proportion of neurological disorders than those without MAC depositions (22.9% vs. 3.3%; P=0.044). We found significant differences in serum creatinine, urinary protein, and estimated glomerular filtration rate (eGFR) in all four groups of patients with differing degrees of C3dg and MAC depositions. Conclusions: This study suggests that C3dg and MAC depositions may be potential biomarkers for disease severity and tissue injury in LN. MAC and C3dg staining may be useful in routine studies of lupus biopsies to identify patients who need more aggressive treatment.

Prediction for odor gas generation from domestic waste based on machine learning.

Domestic waste is prone to produce a variety of volatile organic compounds (VOCs), which often has unpleasant odors. A key process in treating odor gases is predicting the production of odors from domestic waste. In this study, four factors of domestic waste (weight, wet composition, temperature, and fermentation time) were adopted to be the prediction indicators in the prediction for domestic waste odor gases. Machine learning models (Random Forest, XGBoost, LightGBM) were established using the odor intensity values of 512 odor gases from domestic waste. Based on these data, the regression prediction with supervised machine learning was achieved, in which three different algorithmic models were evaluated for prediction performance. A Random Forest model with a R2 value of 0.8958 demonstrated the most accurate prediction of the production of domestic waste odor gas based on our data. Furthermore, the prediction results in the Random Forest model were further discussed based on the microbial fermentation of domestic waste. In addition to enhancing our knowledge of the production of odor from domestic waste, we also explore the application of machine learning to odor pollution in our study.