[1]宋春晖,秦玉芳,陈明.基于部分DNA甲基化预测肿瘤浸润免疫细胞的比例[J].中国医学物理学杂志,2022,39(5):627-634.[doi:DOI:10.3969/j.issn.1005-202X.2022.05.018]
　SONG Chunhui,QIN Yufang,et al.Predicting the proportions of tumor-infiltrating immune cells based on partial DNA methylation[J].Chinese Journal of Medical Physics,2022,39(5):627-634.[doi:DOI:10.3969/j.issn.1005-202X.2022.05.018]
点击复制

基于部分DNA甲基化预测肿瘤浸润免疫细胞的比例()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
39卷
期数:
2022年第5期
页码:
627-634
栏目:
其他（激光医学等）
出版日期:
2022-05-27

文章信息/Info

Title:
Predicting the proportions of tumor-infiltrating immune cells based on partial DNA methylation
文章编号:
1005-202X（2022）05-0627-08
作者:
宋春晖1; 2; 秦玉芳1; 2; 陈明1; 2
1.上海海洋大学信息学院， 上海 201306； 2.农业农村部渔业信息重点实验室， 上海 201306
Author(s):
SONG Chunhui1;  2;  QIN Yufang1;  2;  CHEN Ming1;  2
1. College of Information Technology, Shanghai Ocean University, Shanghai 201306, China 2. Key Laboratory of Fisheries Information, Ministry of Agriculture and Rural Affairs of the Peoples Republic of China, Shanghai 201306, China
关键词:
癌症; DNA甲基化; 非负矩阵分解; 免疫细胞
Keywords:
Keywords: cancer DNA methylation non-negative matrix factorization immune cell
分类号:
R318；R730.2
DOI:
DOI:10.3969/j.issn.1005-202X.2022.05.018
文献标志码:
A
摘要:
了解肿瘤组织的免疫细胞比例对肿瘤患者的诊断和预后治疗具有重要意义，DNA甲基化可以作为一种细胞分子特征来量化复杂肿瘤混合物中的多种细胞类型。本研究基于非负矩阵分解算法并结合部分DNA甲基化建立肿瘤浸润免疫细胞比例预测模型。在预测肿瘤混合物中细胞类型的比例时，选择已知的对每种免疫细胞类型差异显著的DNA甲基化水平矩阵作为特征矩阵，将其和肿瘤混合物的DNA甲基化水平输入到非负矩阵分解算法进行细胞类型的比例预测。噪声和肿瘤含量不同设置下的模拟实验验证了该模型预测的免疫细胞比例与真实比例具有很高的一致性，且均方根误差较小。将该模型应用到4种真实的肿瘤样本上，得到每种样本中浸润水平最高的免疫细胞，结果与之前其他学者的生物学发现相一致。本研究的模型能准确预测组成肿瘤混合物的细胞类型比例，为肿瘤的免疫学研究提供了新的方法。
Abstract:
Abstract: Understanding the proportions of immune cells in tumor tissues has important implications for the diagnosis and prognostic treatment of tumor patients, and DNA methylation can be used as a cellular molecular signature to quantify multiple cell types in complex tumor mixtures. Herein a prediction model for the proportions of tumor-infiltrating immune cells is established based on a non-negative matrix factorization algorithm combined with partial DNA methylation. When predicting the proportions of cell types in tumor mixtures, the known DNA methylation level matrix that is significantly different for each immune cell type is selected as the feature matrix, and then the matrix and the DNA methylation level of tumor mixtures are input into the non-negative matrix factorization algorithm for predicting the proportions of cell types. Simulation experiments at different levels of noises and tumor contents verify that the proportions of immune cells predicted by the model are highly consistent with the real proportions, with small root-mean-square error. Applying the model to 4 kinds of real tumor samples yielded the highest levels of infiltrating immune cells in each sample, and the results are consistent with previous biological findings by other scholars. The proposed model can accurately predict the proportions of cell types that make up tumor mixtures, providing a new approach for tumor immunology research.

相似文献/References:

[1]辛学刚. 磁共振组织介电特性断层成像在癌症早期发现中的应用[J].中国医学物理学杂志,2016,33(12):1204.[doi:10.3969/j.issn.1005-202X.2016.12.004]
　[J].Chinese Journal of Medical Physics,2016,33(5):1204.[doi:10.3969/j.issn.1005-202X.2016.12.004]
[2]高冲,秦玉芳,陈明.基于通路活性的抗癌药物敏感性预测[J].中国医学物理学杂志,2021,38(12):1569.[doi:DOI:10.3969/j.issn.1005-202X.2021.12.020]
　GAO Chong,QIN Yufang,et al.Predicting anticancer drug sensitivity based on pathway activity[J].Chinese Journal of Medical Physics,2021,38(5):1569.[doi:DOI:10.3969/j.issn.1005-202X.2021.12.020]
[3]蒋芙蓉,赵静文,刘翔,等.基于病理图像的计算机辅助诊断进展[J].中国医学物理学杂志,2022,39(3):384.[doi:DOI:10.3969/j.issn.1005-202X.2022.03.020]
　JIANG Furong,ZHAO Jingwen,LIU Xiang,et al.Advances in computer-aided diagnosis based on pathological images[J].Chinese Journal of Medical Physics,2022,39(5):384.[doi:DOI:10.3969/j.issn.1005-202X.2022.03.020]

备注/Memo

备注/Memo:
【收稿日期】2021-12-10 【基金项目】国家自然科学基金（61702325）；国家重点研发计划项目（2018YFD0701003）；上海市科技创新计划项目（20dz1203800） 【作者简介】宋春晖，硕士在读，研究方向：机器学习、生物信息，E-mail: 641811576@qq.com 【通信作者】秦玉芳，博士，副教授，研究方向：机器学习、生物信息，E-mail: yfqin@shou.edu.cn
更新日期/Last Update: 2022-05-27