Causal discovery approach with reinforcement learning for risk factors of type II diabetes mellitus.

BACKGROUND: Statistical correlation analysis is currently the most typically used approach for investigating the risk factors of type 2 diabetes mellitus (T2DM). However, this approach does not readily reveal the causal relationships between risk factors and rarely describes the causal relationships visually. RESULTS: Considering the superiority of reinforcement learning in prediction, a causal discovery approach with reinforcement learning for T2DM risk factors is proposed herein. First, a reinforcement learning model is constructed for T2DM risk factors. Second, the process involved in the causal discovery method for T2DM risk factors is detailed. Finally, several experiments are designed based on diabetes datasets and used to verify the proposed approach. CONCLUSIONS: The experimental results show that the proposed approach improves the accuracy of causality mining between T2DM risk factors and provides new evidence to researchers engaged in T2DM prevention and treatment research.

[Comparison of three methods for preparation of bacterial ghosts from avian pathogenic Escherichia coli].

Bacterial ghosts are bacterial cell envelopes devoid of cytoplasmic contents while maintaining their cellular morphology, which can be used as a new vaccine and delivery vector. In this study, a clinical isolate of avian pathogenic Escherichia coli (APEC) strain DE17 was used to prepare bacterial ghost through three different ways. The results showed that the cleavage efficiency of DE17 bacterial ghost was 99.9% with the lysis plasmid containing the PhiX174 lysis gene E. Scanning electron microscopy showed that transmembrane tunnels were formed in the middle or both ends of the cell envelope of DE17. Furthermore, the DE17 bacterial ghost was prepared with one of cell penetrating peptides (CPPs) named MAP (KLALKLALKALKAALKLA), which will completely inactivate DE17 (OD600=0.1) by 10 µmol/L MAP. The cell envelope showed a gully-like structure and obvious transmembrane tunnels were not found through the SEM. However, the DE17 could not be lysed by importing the lysis plasmid (pBV220-MAP), which was used to express MAP. The present study will benefit for research on bacterial ghost preparation methods and provide a reference for biosafety of bacterial ghost vaccines.