海南医科大学学报2025，Vol.31Issue(2)：109-117,9.DOI:10.13210/j.cnki.jhmu.20240717.001
基于系统性硬化症溶酶体相关基因的人工神经网络模型的构建及实验验证
Construction and experimental verification of artificial neural network model based on lysosome related genes in systemic sclerosis
摘要
Abstract
Objective:To establish a combined random forest and artificial neural network diagnosis model of lysosome related genes in scleroderma based on GEO database and evaluate its effect.Method:Four scleroderma chips were obtained from GEO da-tabase.GSE95065 and GSE76807 were combined as training data set,and random forest algorithm was used to screen scleroder-ma lysosome-related characteristic genes.The artificial neural network model was constructed with characteristic genes,and the ac-curacy of the model was verified by 10-fold crossover.Then the verification data set GSE32413 and GSE59787 are used to further verify the model,and the product value under the ROC curve is used to evaluate the accuracy of the model.Finally,RT-qPCR was used for experimental verification.Result:The results showed a total of 46 differentially expressed genes were identified,in-cluding 16 genes that were up-regulated and 30 genes that were down-regulated.Furthermore,the six most relevant characteristic genes(LYN,TNFAIP3,RNF128,MCOLN3,ANKFY1,PLD3)were screened by random forest,and the artificial neural net-work diagnosis model was constructed.Using this model,the ROC curves of training group and verification group were drawn,and the AUC value was 0.999.The AUC of the verification group was 0.740 and 0.732,respectively.The average AUC of 10%discount cross-validation is greater than 0.980.RT-qPCR results showed that compared with the control group,the expressions of LYN(P=0.004)and TNFAIP3(P=0.000 1)were significantly up-regulated in scleroderma,while the expressions of RNF128(P=0.000 2),MCOLN3(P=0.001),ANKFY1(P=0.02)and PLD3(P<0.000 1)were significantly down-regulated in scleroderma.Consistent with machine learning results.Conclusion:An artificial neural network diagnosis model of lysosome-related characteristic genes in scleroderma was constructed,which provides a new perspective for exploring the patho-genesis of scleroderma.关键词
系统性硬化症/溶酶体/人工神经网络/随机森林/诊断模型Key words
Systemic sclerosis/Lysosome/Artificial neural network/Random forest/Diagnostic model分类
信息技术与安全科学引用本文复制引用
左志威,卞博,崔家康,耿玉鑫,王一晨,郭克磊,孟庆良,卞华..基于系统性硬化症溶酶体相关基因的人工神经网络模型的构建及实验验证[J].海南医科大学学报,2025,31(2):109-117,9.基金项目
National Natural Science Foundation of China(82074415) （82074415）
Zhongyuan Talent Program-Zhongyuan Science and Technology Innovation Leading Talent Project(234200510006) （234200510006）
Science and Technology Plan Project of Henan Province(232102311201) （232102311201）
Key Project of Nanyang Basic and Frontier Technology Research Special Plan(23JCQY1006) 国家自然科学基金项目(82074415) （23JCQY1006）
中原英才计划-中原科技创新领军人才项目(234200510006) （234200510006）
河南省科技计划项目(232102311201) （232102311201）
南阳市基础与前沿技术研究专项计划重点项目(23JCQY1006) （23JCQY1006）
