Genetic algorithm-optimized backpropagation neural network establishes a diagnostic prediction model for diabetic nephropathy:Combined machine learning and experimental validation in mice

Background:Diabetic nephropathy(DN)is the most common complication of type 2 diabetes mellitus and the main cause of end-stage renal disease worldwide.Diagnostic biomarkers may allow early diagnosis and treatment of DN to reduce the prevalence and delay the development of DN.Kidney biopsy is the gold standard for diagnosing DN;however,its invasive character is its primary limitation.The machine learning approach provides a non-invasive and specific criterion for diagnosing DN,although traditional machine learning algorithms need to be improved to enhance diagnostic performance.Methods:We applied high-throughput RNA sequencing to obtain the genes related to DN tubular tissues and normal tubular tissues of mice.Then machine learning algorithms,random forest,LASSO logistic regression,and principal component analysis were used to identify key genes(CES1G,CYP4A14,NDUFA4,ABCC4,ACE).Then,the genetic algorithm-optimized backpropagation neural network(GA-BPNN)was used to improve the DN diagnostic model.Results:The AUC value of the GA-BPNN model in the training dataset was 0.83,and the AUC value of the model in the validation dataset was 0.81,while the AUC values of the SVM model in the training dataset and external validation dataset were 0.756 and 0.650,respectively.Thus,this GA-BPNN gave better values than the traditional SVM model.This diagnosis model may aim for personalized diagnosis and treatment of patients with DN.Immunohistochemical staining further confirmed that the tissue and cell expression of NADH dehydrogenase(ubiquinone)1 alpha subcomplex,4-like 2(NDUFA4L2)in tubular tissue in DN mice were decreased.Conclusion:The GA-BPNN model has better accuracy than the traditional SVM model and may provide an effective tool for diagnosing DN.

A Swarm Intelligence Networking Framework for Small Satellite Systems

Recent development of technologies and methodologies on distributed spacecraft systems enable the small satellite network systems by supporting integrated navigation, communications and control tasks. The distributed sensing data can be communicated and processed autonomously among the network systems. Due to the size, density and dynamic factors of small satellite networks, the traditional network communication framework is not well suited for distributed small satellites. The paper proposes a novel swarm intelligence based networking framework by using Ant colony optimization. The proposed network framework enables self-adaptive routing, communications and network reconstructions among small satellites. The simulation results show our framework is suitable for dynamic factors in distributed small satellite systems. The proposed schemes are adaptive and scalable to network topology and achieve good performance in different network scenarios.

Self-sufficient nanoparticles with dual-enzyme activity trigger radical storms and activate cascade-amplified antitumor immunologic responses

Radiotherapy(RT) can potentially induce systemic immune responses by initiating immunogenic cell death(ICD) of tumor cells.However,RT-induced antitumor immunologic responses are sporadic and insufficient against cancer metastases.Herein,we construct multifunctional self-sufficient nanoparticles(MARS) with dual-enzyme activity(GOx and peroxidase-like) to trigger radical storms and activate the cascade-amplified systemic immune responses to suppress both local tumors and metastatic relapse.In addition to limiting the Warburg effect to actualize starvation therapy,MARS catalyzes glucose to produce hydrogen peroxide(H_(2)O_(2)),which is then used in the Cu^(+)-mediated Fenton-like reaction and RT sensitization.RT and chemodynamic therapy produce reactive oxygen species in the form of radical storms,which have a robust ICD impact on mobilizing the immune system.Thus,when MARS is combined with RT,potent systemic antitumor immunity can be generated by activating antigen-presenting cells,promoting dendritic cells maturation,increasing the infiltration of cytotoxic T lymphocytes,and reprogramming the immuno suppre ssive tumor microenvironment.Furthermore,the synergistic therapy of RT and MARS effectively suppresses local tumor growth,increases mouse longevity,and results in a 90% reduction in lung metastasis and postoperative recurrence.Overall,we provide a viable approach to treating cancer by inducing radical storms and activating cascade-amplified systemic immunity.