郑州大学学报（工学版）2025，Vol.46Issue(6)：58-65,8.DOI:10.13705/j.issn.1671-6833.2025.06.013
预测ICI治疗响应的凹惩罚Logistic回归模型
A Concave-penalized Logistic Regression Model for Predicting ICI Treatment Respense
摘要
Abstract
To improve the accuracy of predicting the response of melanoma patients to immune checkpoint inhibitor(ICI)therapy,a new method integrating bulk RNA-seq and single-cell RNA-seq data was proposed.Firstly,a pa-tient-cell correlation matrix was constructed through Pearson correlation analysis,and the Louvain algorithm was used to classify single-cell RNA-seq data into cell groups.The importance of cell groups in immune response relat-ed pathways was quantified using the CellChat tool.On this basis,a double group minimax concave penalty logistic regression model(DMCPLR)was proposed by introducing the cell group importance evaluation criterion construc-ted based on the cell-cell communication network and combining with the group minimax concave penalty.The ex-periments on the GSE35640 dataset showed that the prediction accuracy of the DMCPLR model reached 80.18%,with precision,recall,and F1 score of 82.24%,89.71%,and 85.11%,respectively,significantly better than the performance of 14 comparison methods including Lasso regression and random forest,while reducing the fatal error rate to 8.30%.The ablation analysis experiment confirmed that the introduction of cell group weight mechanism and L2 regularization term can improve the performance of the model.关键词
黑色素瘤/免疫检查点抑制剂/批量RNA测序和单细胞RNA测序数据/数据整合/细胞间通信Key words
melanoma/immune checkpoint inhibitor/bulk RNA-seq and single-cell RNA-seq data/data integra-tion/cell-cell communication分类
医药卫生引用本文复制引用
穆晓霞,张红梅,宋学坤,李钧涛..预测ICI治疗响应的凹惩罚Logistic回归模型[J].郑州大学学报（工学版）,2025,46(6):58-65,8.基金项目
国家自然科学基金资助项目(61203293) （61203293）
河南省科技攻关项目(242102211023) （242102211023）
