Establishment and Evaluation of Artificial Intelligence-Based Prediction Models for Chronic Kidney Disease under the Background of Big Data.

Objective: To establish a prediction model for the risk evaluation of chronic kidney disease (CKD) to guide the management and prevention of CKD. Methods: A total of 1263 patients with CKD and 1948 patients without CKD admitted to the Tongde Hospital of the Zhejiang Province from January 1, 2008, to December 31, 2018, were retrospectively analyzed. Spearman's correlation was used to analyze the relationship between CKD and laboratory parameters. XGBoost, random forest, Naive Bayes, support vector machine, and multivariate logistic regression algorithms were employed to establish prediction models for the risk evaluation of CKD. The accuracy, precision, recall, F1 score, and area under the receiver operating curve (AUC) of each model were compared. The new bidirectional encoder representations from transformers with light gradient boosting machine (MD-BERT-LGBM) model was used to process the unstructured data and transform it into researchable unstructured vectors, and the AUC was compared before and after processing. Results: Differences in laboratory parameters between CKD and non-CKD patients were observed. The neutrophil ratio and white blood cell count were significantly associated with the occurrence of CKD. The XGBoost model demonstrated the best prediction effect (accuracy = 0.9088, precision = 0.9175, recall = 0.8244, F1 score = 0.8868, AUC = 0.8244), followed by the random forest model (accuracy = 0.9020, precision = 0.9318, recall = 0.7905, F1 score = 0.581, AUC = 0.9519). Comparatively, the predictions of the Naive Bayes and support vector machine models were inferior to those of the logistic regression model. The AUC of all models was improved to some extent after processing using the new MD-BERT-LGBM model. Conclusion: The new MD-BERT-LGBM model with the inclusion of unstructured data has contributed to the higher accuracy, sensitivity, and specificity of the prediction models. Clinical features such as age, gender, urinary white blood cells, urinary red blood cells, thrombin time, serum creatinine, and total cholesterol were associated with CKD incidence.

Cytological and Proteomic Analysis of Wheat Pollen Abortion Induced by Chemical Hybridization Agent.

In plants, pollen grain transfers the haploid male genetic material from anther to stigma, both between flowers (cross-pollination) and within the same flower (self-pollination). In order to better understand chemical hybridizing agent (CHA) SQ-1-induced pollen abortion in wheat, comparative cytological and proteomic analyses were conducted. Results indicated that pollen grains underwent serious structural injury, including cell division abnormality, nutritional deficiencies, pollen wall defect and pollen grain malformations in the CHA-SQ-1-treated plants, resulting in pollen abortion and male sterility. A total of 61 proteins showed statistically significant differences in abundance, among which 18 proteins were highly abundant and 43 proteins were less abundant in CHA-SQ-1 treated plants. 60 proteins were successfully identified using MALDI-TOF/TOF mass spectrometry. These proteins were found to be involved in pollen maturation and showed a change in the abundance of a battery of proteins involved in multiple biological processes, including pollen development, carbohydrate and energy metabolism, stress response, protein metabolism. Interactions between these proteins were predicted using bioinformatics analysis. Gene ontology and pathway analyses revealed that the majority of the identified proteins were involved in carbohydrate and energy metabolism. Accordingly, a protein-protein interaction network involving in pollen abortion was proposed. These results provide information for the molecular events underlying CHA-SQ-1-induced pollen abortion and may serve as an additional guide for practical hybrid breeding.

Transcriptome-Wide Identification and Characterization of Potato Circular RNAs in Response to Pectobacterium carotovorum Subspecies brasiliense Infection.

Little information about the roles of circular RNAs (circRNAs) during potato-Pectobacterium carotovorum subsp. brasiliense (Pcb) interaction is currently available. In this study, we conducted the systematic identification of circRNAs from time series samples of potato cultivars Valor (susceptible) and BP1 (disease tolerant) infected by Pcb. A total of 2098 circRNAs were detected and about half (931, 44.38%) were intergenic circRNAs. And differential expression analysis detected 429 significantly regulated circRNAs. circRNAs play roles by regulating parental genes and sponging miRNAs. Gene Ontology (GO) enrichment of parental genes and miRNAs targeted mRNAs revealed that these differentially expressed (DE) circRNAs were involved in defense response (GO:0006952), cell wall (GO:0005199), ADP binding (GO:0043531), phosphorylation (GO:0016310), and kinase activity (GO:0016301), suggesting the roles of circRNAs in regulating potato immune response. Furthermore, weighted gene co-expression network analysis (WGCNA) found that circRNAs were closely related with coding-genes and long intergenic noncoding RNAs (lincRNAs). And together they were cultivar-specifically regulated to strengthen immune response of potato to Pcb infection, implying the roles of circRNAs in reprogramming disease responsive transcriptome. Our results will provide new insights into the potato-Pcb interaction and may lead to novel disease control strategy in the future.