Selection of optimal models for predicting growth stress in Artemisia desertorum by comparison of linear regression and multiple neural networks: Take the construction of a green mine in the Bayan Obo mine as an example.

In recent years, more and more countries are focusing on the control of mining sites and the surrounding ecological environment, and the new environmental concept of green mines has been proposed. By investigating the ecological background of a mine site, pollution and ecological imbalances in the mine can be predicted, managed or transformed. This study investigated the effects of rare earth elements on plant growth in the Baotou Bayan Obo Rare Earth Mine and evaluated soil contamination and subsequent remediation through the measured plant height. Using linear regression, BP(Back Propagation) neural networks, GA-BP(Genetic Algorithm- Back Propagation) neural networks, ELM(Extreme Learning Machine) and GA-ELM(Genetic Algorithm- Extreme Learning Machine) model prediction instruments, the different rare earth solution concentrations were set as input values and the heights of Artemisia desertorum, which as the model plant, were set as output values in the prediction. The results showed that the linear regression predicted the standard error of single La(III), Ce(III) solution and compound La(III) + Ce(III) solution for Artemisia desertorum growth stress was on the high side, 7.02%- 8.92%; the efficiency range of each group of models under BP neural network, GA-BP neural network and ELM neural network were 1.15%- 2.53%, 0.85%- 1.28%, 1.76%- 3.53%; while the efficiency range under GA-ELM neural network was 0.59%- 0.68%, with average error values and predicted values close to the true values. Among them, the MAPE of GA-ELM neural network are significantly lower than other models, and the error decreases with increasing concentration of the compound solution. So GA-ELM neural network can be used as an efficient, fast and reasonable optimal model for predicting the growth stress of Artemisia desertorum in Bayan Obo mining area. The experimental results can provide a theoretical basis for assessing the risk of soil rare earth contamination in the area, evaluating the expectation of later remediation, and provide a degree of new ideas for the construction of green mines.

Proteomic analysis of apoptosis induction by lariciresinol in human HepG2 cells.

Lariciresinol (LA) is a traditional Chinese medicine possessing anticancer activity, but its mechanism of action remains unclear. The present study explored the effects of LA on human HepG2 cells and the underlying mechanism. Our data indicated that LA inhibited cell proliferation and induced cell cycle arrest in S phase, subsequently resulting in apoptosis in HepG2 cells. Using a proteomics approach, eight differentially expressed proteins were identified. Among them, three proteins, glyceraldehyde-3-phosphate, UDP-glucose 4-epimerase, and annexin A1, were upregulated, while the other five proteins, heat shock protein 27, haptoglobin, tropomodulin-2, tubulin alpha-1A chain, and brain acid soluble protein 1, were downregulated; all of these proteins are involved in cell proliferation, metabolism, cytoskeletal organization, and movement. Network analysis of these proteins suggested that the ubiquitin-conjugating enzyme (UBC) plays an important role in the mechanism of LA. Western blotting confirmed downregulation of heat shock protein 27 and upregulation of ubiquitin and UBC expression levels in LA-treated cells, consistent with the results of two-dimensional electrophoresis and a STRING software-based analysis. Overall, LA is a multi-target compound with anti-cancer effects potentially related to the ubiquitin-proteasome pathway. This study will increase our understanding of the anticancer mechanisms of LA.