The color of biodegradable mulch films is associated with differences in peanut yield and bacterial communities.

Biodegradable mulch films (BDMs) are increasingly used in agricultural production as desirable alternatives to the current widespread use of polyethylene (PE) mulch films in China. However, potential effects of different colors of BDMs on field crop production and microbiomes remain unexplored. Here, the differences in bacterial communities of peanut rhizosphere soil (RS) and bulk soil (BS) under non-mulching (CK), PE, and three different colors of BDMs were studied. The results indicated that all treatments could increase the soil temperature, which positively affected the growth of the peanut plants. Moreover, mulching affected the bacterial community structure in RS and BS compared to CK. Furthermore, certain BDM treatments significantly enriched N-fixing bacteria (Bradyrhizobium and Mesorhizobium) and functional groups, increased the closeness of bacterial networks, and harbored more beneficial bacteria as keystone taxa in the RS. This in turn facilitated the growth and development of the peanut plants under field conditions. Our study provides new insights into the micro-ecological effects of mulch films, which can be affected by both the mulch type and color. The observed effects are likely caused by temperature and prevalence of specific microbial functions under the employed films and could guide the development of optimized mulching materials.

Biodegradable mulch films significantly affected rhizosphere microbial communities and increased peanut yield.

Biodegradable mulch films are widely used to replace conventional plastic films in agricultural fields. However, their ecological effects on different microbial communities that naturally inhabit agricultural fields are scarcely explored. Herein, differences in bacterial communities recovered from biofilms, bulk soil, and rhizosphere soil were comparatively assessed for polyethylene film (PE) and biodegradable mulch film (BDM) application in peanut planted fields. The results showed that the plastic film type significantly influenced the bacterial community in different ecological niches of agricultural fields (P < 0.001). Specifically, BDMs significantly increased the diversity and abundance of bacteria in the rhizosphere soil. The bacterial communities in each ecological niche were distinguishable from each other; bacterial communities in the rhizosphere soil showed the most pronounced response among different treatments. Acidobacteria and Pseudomonas were significantly enriched in the rhizosphere soil when BDMs were used. BDMs also increased the rhizosphere soil bacterial network complexity and stability. The enrichment of beneficial bacteria in the rhizosphere soil under BDMs may also have implications for the observed increase in peanut yield. Deepening analyses indicated that Pseudoxanthomonas and Glutamicibacter are biomarkers in biofilms of PE and BDMs respectively. Our study provides new insights into the consequences of the application of different types of plastic films on microbial communities in different ecological niches of agricultural fields.

Classification Prediction of Breast Cancer Based on Machine Learning.

Breast cancer is the most common and deadly type of cancer in the world. Based on machine learning algorithms such as XGBoost, random forest, logistic regression, and K-nearest neighbor, this paper establishes different models to classify and predict breast cancer, so as to provide a reference for the early diagnosis of breast cancer. Recall indicates the probability of detecting malignant cancer cells in medical diagnosis, which is of great significance for the classification of breast cancer, so this article takes recall as the primary evaluation index and considers the precision, accuracy, and F1-score evaluation indicators to evaluate and compare the prediction effect of each model. In order to eliminate the influence of different dimensional concepts on the effect of the model, the data are standardized. In order to find the optimal subset and improve the accuracy of the model, 15 features were screened out as input to the model through the Pearson correlation test. The K-nearest neighbor model uses the cross-validation method to select the optimal k value by using recall as an evaluation index. For the problem of positive and negative sample imbalance, the hierarchical sampling method is used to extract the training set and test set proportionally according to different categories. The experimental results show that under different dataset division (8 : 2 and 7 : 3), the prediction effect of the same model will have different changes. Comparative analysis shows that the XGBoost model established in this paper (which divides the training set and test set by 8 : 2) has better effects, and its recall, precision, accuracy, and F1-score are 1.00, 0.960, 0.974, and 0.980, respectively.