[1]黄鹏杰,林勇,张梦欢,等.基于集成学习的肿瘤药物敏感性预测研究[J].中国医学物理学杂志,2021,38(4):511-517.[doi:DOI:10.3969/j.issn.1005-202X.2021.04.021]
　HUANG Pengjie,LIN Yong,et al.Predicting anti-tumor drug sensitivity based on ensemble learning[J].Chinese Journal of Medical Physics,2021,38(4):511-517.[doi:DOI:10.3969/j.issn.1005-202X.2021.04.021]
点击复制

基于集成学习的肿瘤药物敏感性预测研究()
分享到：

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

卷:
38卷
期数:
2021年第4期
页码:
511-517
栏目:
医学人工智能
出版日期:
2021-04-29

文章信息/Info

Title:
Predicting anti-tumor drug sensitivity based on ensemble learning
文章编号:
1005-202X（2021）04-0511-07
作者:
黄鹏杰1; 2; 林勇1; 张梦欢3; 吕琳1; 刘振浩2; 裴潇倜1; 许林锋1; 2; 谢鹭2
1.上海理工大学医疗器械与食品学院， 上海 200093； 2.上海生物信息技术研究中心， 上海 201203； 3.中国科学院分子细胞科学卓越创新中心， 上海 200031
Author(s):
HUANG Pengjie1;  2;  LIN Yong1;  ZHANG Menghuan3;  L?Lin1;  LIU Zhenhao2;  PEI Xiaoti1;  XU Linfeng1;  2;  XIE Lu2
1. School of Medical Instrument and Food Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China 2. Shanghai Center for Bioinformation Technology, Shanghai 201203, China 3. Center for Excellence in Molecular Cell Science, Chinese Academy of Sciences, Shanghai 200031, China
关键词:
集成学习; 肿瘤; 药物敏感性预测; AdaBoost; 富集分析
Keywords:
Keywords: ensemble learning tumor drug sensitivity prediction AdaBoost enrichment analysis
分类号:
R318；R917
DOI:
DOI:10.3969/j.issn.1005-202X.2021.04.021
文献标志码:
A
摘要:
肿瘤药物敏感性预测对个性化精准用药具有重要意义。本文基于GDSC数据库通过Boosting集成学习构建了面向RNA-seq基因表达和癌症药物敏感性数据的预测模型。先将183种药物集分别做归一化处理和基因特征降维，接着用AdaBoost集成SVM的方法建模，并采用十折交叉验证。实验结果表明构建的预测模型具有较高的预测精度，13种药物的AUC大于0.95，108种大于0.9，174种大于0.8。对比验证实验中，AdaBoost+SVM相比单学习器模型在整体药物集的综合评价指标中约提高4%，与其他集成模型相比提高2%。同时本文探讨了药物特异性，通过特征选择和富集分析对药物作用通路进行验证，从生物学角度提供了模型可解释性，证明其应用于临床用药指导的价值。
Abstract:
Abstract: The prediction of anti-tumor drug sensitivity is of great significance for personalized and precise medication. Herein a prediction model for RNA-seq gene expression and anti-cancer drug sensitivity data is established based on GDSC database through Boosting ensemble learning. A total of 183 drug sets are normalized, and gene feature dimensionality is reduced. Then, AdaBoost+SVM is used for modeling, and 10-fold cross validation for verifying. The experimental results show that the established prediction model has a high prediction accuracy. The AUC of 13, 108 and 174 drugs are greater than 0.95, 0.90 and 0.80, respectively. AdaBoost+SVM improves the comprehensive evaluation index of the overall drug set by about 4% and 2%, compared with the models based on a learner only and other ensemble models. Meanwhile, drug specificity is also discussed and the signal pathway of specific drug is verified through feature selection and enrichment analysis and the interpretability of the established model is confirmed from a biological perspective. In sum, the value of the established model in clinical medication guidance is proved in the study.

相似文献/References:

[1]杜永兴,桑路路,秦岭,等.一种基于图像匹配的微波热疗方法[J].中国医学物理学杂志,2016,33(10):1026.[doi:10.3969/j.issn.1005-202X.2016.10.011]
　[J].Chinese Journal of Medical Physics,2016,33(4):1026.[doi:10.3969/j.issn.1005-202X.2016.10.011]
[2]杜永兴,冯路平,张令泽,等.基于序列温度匹配方法的肿瘤微波治疗[J].中国医学物理学杂志,2016,33(12):1257.[doi:10.3969/j.issn.1005-202X.2016.12.017]
　[J].Chinese Journal of Medical Physics,2016,33(4):1257.[doi:10.3969/j.issn.1005-202X.2016.12.017]
[3]朱翔宇,葛中芹,张冰清,等.基于图像处理的医学影像处理平台系统设计[J].中国医学物理学杂志,2017,34(4):388.[doi:DOI:10.3969/j.issn.1005-202X.2017.04.014]
[4]洪文松,张力,陈兵锋,等. 基于Gompertz模型肿瘤放疗分析与模拟[J].中国医学物理学杂志,2018,35(1):5.[doi:DOI:10.3969/j.issn.1005-202X.2018.01.002]
　HONG Wensong,ZHANG Li,CHEN Bingfeng,et al. Gompertz model-based tumor radiotherapy analysis and simulation[J].Chinese Journal of Medical Physics,2018,35(4):5.[doi:DOI:10.3969/j.issn.1005-202X.2018.01.002]
[5]于松茂,杨敬贤,康加阜,等. 不同部位肿瘤患者模拟机复位误差的对比分析[J].中国医学物理学杂志,2018,35(2):141.[doi:DOI:10.3969/j.issn.1005-202X.2018.02.004]
　YU Songmao,YANG Jingxian,KANG Jiafu,et al. Comparison of reset errors in simulator for patients with tumors in different locations[J].Chinese Journal of Medical Physics,2018,35(4):141.[doi:DOI:10.3969/j.issn.1005-202X.2018.02.004]
[6]李双双,侯震,刘娟,等.影像组学分析与建模工具综述[J].中国医学物理学杂志,2018,35(9):1043.[doi:10.3969/j.issn.1005-202X.2018.09.010]
　LI Shuangshuang,HOU Zhen,LIU Juan,et al.Review of radiomic analysis and modeling tools[J].Chinese Journal of Medical Physics,2018,35(4):1043.[doi:10.3969/j.issn.1005-202X.2018.09.010]
[7]吴先想,郭红博,费振乐,等. CT值相对电子密度转换关系影响因素及其对剂量计算的影响分析[J].中国医学物理学杂志,2019,36(2):157.[doi:DOI:10.3969/j.issn.1005-202X.2019.02.007]
　WU Xianxiang,GUO Hongbo,FEI Zhenle,et al. Influence factors of CT value-relative electron density conversion and its effects on dose calculation[J].Chinese Journal of Medical Physics,2019,36(4):157.[doi:DOI:10.3969/j.issn.1005-202X.2019.02.007]
[8]杨华,龚明福,邹利光,等. CL-PEG-MnFe2O4纳米胶束介导的肿瘤微血管和微淋巴管双重靶向MR成像[J].中国医学物理学杂志,2019,36(9):1034.[doi:DOI:10.3969/j.issn.1005-202X.2019.09.008]
　YANG Hua,GONG Mingfu,ZOU Liguang,et al. Magnetic resonance imaging of angiogenesis and lymphangiogenesis in tumor using dual-targeted CL-PEG-MnFe2O4 nanomicelles[J].Chinese Journal of Medical Physics,2019,36(4):1034.[doi:DOI:10.3969/j.issn.1005-202X.2019.09.008]
[9]李义伟,王建国.静磁场生物效应的研究进展[J].中国医学物理学杂志,2020,37(11):1459.[doi:DOI:10.3969/j.issn.1005-202X.2020.11.021]
　[J].Chinese Journal of Medical Physics,2020,37(4):1459.[doi:DOI:10.3969/j.issn.1005-202X.2020.11.021]
[10]陈婉琦,林勇.基于集成学习的骨质疏松性骨折预测研究[J].中国医学物理学杂志,2021,38(2):254.[doi:DOI:10.3969/j.issn.1005-202X.2021.02.023]
　CHEN Wanqi,LIN Yong.Prediction of osteoporotic fracture based on ensemble learning[J].Chinese Journal of Medical Physics,2021,38(4):254.[doi:DOI:10.3969/j.issn.1005-202X.2021.02.023]

备注/Memo

备注/Memo:
【收稿日期】2020-09-15 【基金项目】国家自然科学基金青年科学基金（31800700）；上海市卫计委协同创新集群项目（2019CXJQ02）；国家自然科学基金（31301092） 【作者简介】黄鹏杰，硕士研究生，研究方向：医学信息工程，E-mail: sl_pagelhuang@163.com 【通信作者】谢鹭，研究员，研究方向：生物信息学，E-mail: luxiex2017@outlook.com
更新日期/Last Update: 2021-04-29