[1]穆晓霞,张红梅,宋学坤,等.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(06):58-65.[doi:10.13705/j.issn.1671-6833.2025.06.013]
　MU Xiaoxia,ZHANG Hongmei,SONG Xuekun,et al.A Concave-penalized Logistic Regression Model for Predicting ICI Treatment Respense[J].Journal of Zhengzhou University (Engineering Science),2025,46(06):58-65.[doi:10.13705/j.issn.1671-6833.2025.06.013]
点击复制

预测ICI治疗响应的凹惩罚Logistic回归模型()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
46
期数:
2025年06期
页码:
58-65
栏目:
出版日期:
2025-10-22

文章信息/Info

Title:
A Concave-penalized Logistic Regression Model for Predicting ICI Treatment Respense
文章编号:
1671-6833(2025)06-0058-08
作者:
穆晓霞1;  张红梅2;  宋学坤3;  李钧涛4
1.河南师范大学 计算机与信息工程学院,河南 新乡 453007;2.东北林业大学 生命科学学院,黑龙江 哈尔滨 150006;3.河南中医药大学 信息技术学院,河南 郑州 450046;4.河南师范大学 数学与统计学院,河南 新乡 453007
Author(s):
MU Xiaoxia1;  ZHANG Hongmei2;  SONG Xuekun3;  LI Juntao4
1.College of Computer and Information Engineering, Henan Normal University, Xinxiang 453007, China; 2.College of Life Sciences, Northeast Forestry University, Harbin 150006, China; 3.College of Information Technology, Henan University of Chinese Medicine, Zhengzhou 450046, China; 4.School of Mathematics and Statistics, Henan Normal University, Xinxiang 453007, China
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
Keywords:
melanoma;  immune checkpoint inhibitor;  bulk RNA-seq and single-cell RNA-seq data;  data integration;  cell-cell communication
分类号:
R739.5TP181
DOI:
10.13705/j.issn.1671-6833.2025.06.013
文献标志码:
A
摘要:
为提升黑色素瘤患者对免疫检查点抑制剂(ICI)治疗响应的预测准确性,提出了一种整合批量RNA测序和单细胞RNA测序数据的新方法。首先,通过皮尔逊相关性分析构建患者-细胞相关性矩阵,采用Louvain算法对单细胞RNA测序数据进行细胞分群;其次利用CellChat工具量化细胞群在免疫响应相关通路中的重要性;最后,通过引入基于细胞间通信网络构建的细胞群重要性评价准则,并结合群极小极大凹惩罚,提出了二重群极小极大凹惩罚Logistic回归模型(DMCPLR)。在GSE35640数据集上的实验表明,DMCPLR模型的预测准确率达到80.18%,精确率、召回率和F1分数分别为82.24%,89.71%和85.11%,显著优于包括Lasso回归和随机森林在内的14种对比方法的性能,同时,将致命错误率降至8.30%。消融分析实验证实,细胞群权重机制和L2正则化项的引入能够提高模型的性能。
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 patient-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 related 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 constructed based on the cell-cell communication network and combining with the group minimax concave penalty. The experiments 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.

参考文献/References:

[1]ARNOLD M, SINGH D, LAVERSANNE M, et al. Global burden of cutaneous melanoma in 2020 and projections to 2040[J]. JAMA Dermatology, 2022, 158(5): 495503. 

[2]GUO W N, WANG H N, LI C Y. Signal pathways of melanoma and targeted therapy[J]. Signal Transduction and Targeted Therapy, 2021, 6(1): 424. 
[3]YIN X M, LIAO H, YUN H, et al. Artificial intelligence-based prediction of clinical outcome in immunotherapy and targeted therapy of lung cancer[J]. Seminars in Cancer Biology, 2022, 86: 146-159. 
[4]CONROY J M, PABLA S, NESLINE M K, et al. Next generation sequencing of PD-L1 for predicting response to immune checkpoint inhibitors[J]. Journal for Immunotherapy of Cancer, 2019, 7(1): 18. 
[5]ANAGNOSTOU V, NIKNAFS N, MARRONE K, et al. Multimodal genomic features predict outcome of immune checkpoint blockade in non-small-cell lung cancer[J]. Nature Cancer, 2020, 1(1): 99-111. 
[6]LITCHFIELD K, READING J L, PUTTICK C, et al. Meta-analysis of tumor- and T cell-intrinsic mechanisms of sensitization to checkpoint inhibition[J]. Cell, 2021, 184(3): 596-614.e14. 
[7]TABARI A, COX M, D′AMORE B, et al. Machine learning improves the prediction of responses to immune checkpoint inhibitors in metastatic melanoma[J]. Cancers, 2023, 15(10): 2700. 
[8]GUO Q H, XIANG S, LI J T. Second-order polynomial regularized logistic regression for predicting melanoma patients response to immune checkpoint inhibitors[C]∥ Proceedings of 2024 Chinese Intelligent Systems Conference. Cham: Springer, 2024: 610-617. 
[9]LIGERO M, GARCIA-RUIZ A, VIAPLANA C, et al. Artificial intelligence combining radiomics and clinical data for predicting response to immunotherapy[J]. Annals of Oncology, 2019, 30: 476. 
[10] CHOWELL D, YOO S K, VALERO C, et al. Improved prediction of immune checkpoint blockade efficacy across multiple cancer types[J]. Nature Biotechnology, 2022, 40(4): 499-506. 
[11] ZHANG S N, LI M Y, TAN Y L, et al. Identification of mutational signature for lung adenocarcinoma prognosis and immunotherapy prediction[J]. Journal of Molecular Medicine, 2022, 100(12): 1755-1769. 
[12] KONG J, HA D, LEE J H, et al. Network-based machine learning approach to predict immunotherapy response in cancer patients[J]. Nature Communications, 2022, 13(1): 3703. 
[13] VALDES-MORA F, HANDLER K, LAW AMK, et al. Single-cell transcriptomics in cancer immunobiology: the future of precision oncology[J]. Frontiers in Immunology, 2018, 9: 2582. 
[14] ZHANG Z, WANG Z X, CHEN Y X, et al. Integrated analysis of single-cell and bulk RNA sequencing data reveals a pan-cancer stemness signature predicting immunotherapy response[J]. Genome Medicine, 2022, 14 (1): 45.
[15] SUN D C, GUAN X N, MORAN A E, et al. Identifying phenotype-associated subpopulations by integrating bulk and single-cell sequencing data[J]. Nature Biotechnology, 2022, 40(4): 527-538. 
[16] LI J T, ZHANG H M, MU B Y, et al. Identifying phenotype-associated subpopulations through LP_SGL[J]. Briefings in Bioinformatics, 2023, 25(1): bbad424. 
[17] BARRETT T, TROUP D B, WILHITE S E, et al. NCBI GEO: archive for high-throughput functional genomic data [J]. Nucleic Acids Research, 2009, 37(Database issue): D885-D890. 
[18] ULLOA-MONTOYA F, LOUAHED J, DIZIER B, et al. Predictive gene signature in MAGE-A3 antigen-specific cancer immunotherapy[J]. Journal of Clinical Oncology, 2013, 31(19): 2388-2395. 
[19] BREHENY P, HUANG J. Penalized methods for bi-level variable selection[J]. Statistics and Its Interface, 2009, 2(3): 369-380. 
[20] CHEN M, LI Y X, ZHOU S M, et al. Establishment of a risk prediction model for olfactory disorders in patients with transnasal pituitary tumors by machine learning[J]. Scientific Reports, 2024, 14(1): 12514. 
[21] SARKAR J P, SAHA I, SARKAR A, et al. Machine learning integrated ensemble of feature selection methods followed by survival analysis for predicting breast cancer subtype specific miRNA biomarkers[J]. Computers in Biology and Medicine, 2021, 131: 104244.

更新日期/Last Update: 2025-10-21