模式识别与人工智能
2025年4月4日 星期五   首 页     期刊简介     编委会     投稿指南     伦理声明     联系我们                                                                English
模式识别与人工智能  2022, Vol. 35 Issue (4): 323-332    DOI: 10.16451/j.cnki.issn1003-6059.202204003
论文与报告 最新目录| 下期目录| 过刊浏览| 高级检索 |
基于多尺度局部累积特征和神经网络的抗肿瘤药物反应预测
韩睿1, 郭成安1
1.大连理工大学 信息与通信工程学院 大连 116024
Prediction of Antitumor Drug Response Based on Multiscale Local Cumulative Features and Neural Networks
HAN Rui1, GUO Cheng'an1
1. School of Information and Communication Engineering, Dalian University of Technology, Dalian 116024

全文: PDF (623 KB)   HTML (1 KB) 
输出: BibTeX | EndNote (RIS)      
摘要 目前已有的研究结果表明现有抗肿瘤药物的有效性高度依赖于患者的基因组学特征.如何为每位肿瘤患者量身定制最佳的治疗方案是重要又富有挑战性的前沿课题.针对该课题,文中提出抗肿瘤药物反应预测方法,运用机器学习技术,对患者肿瘤基因测序数据进行处理、特征提取及建模,预测各种不同抗肿瘤药物的疗效反应.首先,提出基于多尺度关联规则的数据挖掘方法,对基因组学数据进行不同尺度的特征挑选.进而通过累积窗函数对挑选后的基因组学数据进行局部累积,进一步执行数据压缩,提取具有较强整体表达性的基因特征信息.然后,以多层全连接神经网络为模型、以提取的多尺度累积基因特征为输入样本,进行训练和建模.最后,分别采用特征融合和决策融合,实现某一肿瘤基因测序数据对于各种不同抗肿瘤药物反应结果的预测.在COSMIC、GDSC数据库上的仿真实验表明,文中方法在敏感性、特异性、准确率、特性曲线面积值等关键性能指标上均取得较优值.
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
韩睿
郭成安
关键词 药物反应预测神经网络多尺度关联规则局部累积特征融合决策融合    
Abstract:Medical research results show that the effectiveness of an antitumor drug is highly dependent on the genomic characteristics of patients. How to customize an optimal medical treatment for each tumor patient is an extremely important and challenging research topic. Aiming at this subject, a set of methods to predict the efficacy response of various antitumor drugs is proposed by machine learning technology for data processing, feature extraction and modeling of the tumor gene sequences of patients. Firstly, a data mining algorithm based on multiscale association rules is proposed for feature selection at different scales of genomics data. Then, the selected genomics data are locally accumulated by the cumulative window function to further compress the data and extract the gene feature information with stronger overall expression. Based on the above, a fully connected multi-layer neural network is designed and the extracted multiscale cumulative gene features are treated as input samples to train the network. Finally, two fusion methods, including feature fusion and decision fusion, are utilized to predict the responses of a tumor gene sequence to different antitumor drugs, respectively. Results of simulation experiments show that the proposed approach is superior in key performance indexes, such as sensitivity, specificity, accuracy and the area under characteristic curve.
Key wordsDrug Response Prediction    Neural Network    Multiscale Association Rules    Local Accumulation    Feature Fusion    Decision Fusion   
收稿日期: 2021-08-30     
ZTFLH: TP183  
通讯作者: 郭成安,博士,教授.主要研究方向为信号与信息处理、智能计算,生物医学信号处理、医学智能.E-mail:cguo@dlut.edu.cn.   
作者简介: 韩 睿,博士研究生,主要研究方向为生物信息处理、医学智能.E-mail:tracyhan@mail.dlut.edu.cn.
引用本文:   
韩睿, 郭成安. 基于多尺度局部累积特征和神经网络的抗肿瘤药物反应预测[J]. 模式识别与人工智能, 2022, 35(4): 323-332. HAN Rui, GUO Cheng'an. Prediction of Antitumor Drug Response Based on Multiscale Local Cumulative Features and Neural Networks. Pattern Recognition and Artificial Intelligence, 2022, 35(4): 323-332.
链接本文:  
http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.202204003      或     http://manu46.magtech.com.cn/Jweb_prai/CN/Y2022/V35/I4/323
版权所有 © 《模式识别与人工智能》编辑部
地址:安微省合肥市蜀山湖路350号 电话:0551-65591176 传真:0551-65591176 Email:bjb@iim.ac.cn
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn