Gene selection for tumor classification using a novel bio-inspired multi-objective approach

M. Dashtban; Mohammadali Balafar; Prashanth Suravajhala

首页> 外文期刊>Genomics >Gene selection for tumor classification using a novel bio-inspired multi-objective approach

【24h】

Gene selection for tumor classification using a novel bio-inspired multi-objective approach

机译：使用新的生物启发的多目标方法进行肿瘤分类的基因选择

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

Abstract Identifying the informative genes has always been a major step in microarray data analysis. The complexity of various cancer datasets makes this issue still challenging. In this paper, a novel Bio-inspired Multi-objective algorithm is proposed for gene selection in microarray data classification specifically in the binary domain of feature selection. The presented method extends the traditional Bat Algorithm with refined formulations, effective multi-objective operators, and novel local search strategies employing social learning concepts in designing random walks. A hybrid model using the Fisher criterion is then applied to three widely-used microarray cancer datasets to explore significant biomarkers which reveal the effectiveness of the proposed method for genomic analysis. Experimental results unveil new combinations of informative biomarkers have association with other studies. Highlights ? Multi-objective version of bat algorithm for binary feature selection ? Advanced local search strategies employing social learning concepts ? Specific random walks well-suited for local search in binary domain ? Novel Integration of genetic operators in local searches of bat algorithm ? Simplified multi-objective procedure without generating multiple population

机译：摘要识别信息基因一直是微阵列数据分析的重要步骤。各种癌症数据集的复杂性使这个问题仍然具有挑战性。本文提出了一种新的生物启发多目标算法，用于小阵列数据分类中的基因选择，具体在特征选择的二进制域中。该方法扩展了传统的BAT算法，具有精致的配方，有效的多目标运营商以及在设计随机散步时使用社会学习概念的新型本地搜索策略。然后将使用Fisher标准的混合模型应用于三种广泛使用的微阵列癌数据集，以探讨显着的生物标志物，揭示了基因组分析方法的有效性。实验结果揭示了新型信息生物标志物的新组合与其他研究有关。强调？二进制特征选择BAT算法的多目标版本？雇用社会学习概念的高级本地搜索策略？特定的随机步行适合在二进制域中的本地搜索？遗传算子在蝙蝠算法本地搜索中的新融合？简化的多目标程序而不产生多种群体

著录项

来源
《Genomics》 |2018年第1期|共8页
作者
M. Dashtban; Mohammadali Balafar; Prashanth Suravajhala;
展开▼
作者单位

Department of Computer Engineering Faculty of Electrical &

Computer Engineering University of;

Department of Computer Engineering Faculty of Electrical &

Computer Engineering University of;

Birla Institute of Scientific Research;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类医学遗传学;
关键词
Cancer classification; Gene selection; Bat algorithm; Feature selection; Evolutionary algorithms; Microarray data analysis;

机译：癌症分类;基因选择;BAT算法;特征选择;进化算法;微阵列数据分析;

相似文献

外文文献
中文文献
专利

1. Gene selection for tumor classification using a novel bio-inspired multi-objective approach [J] . M.Dashtban, MohammadaliBalafar, PrashanthSuravajhala Genomics . 2018,第1期

机译：使用新型生物启发多目标方法进行肿瘤分类的基因选择
2. Gene selection for tumor classification using a novel bio-inspired multi-objective approach [J] . M. Dashtban, Mohammadali Balafar, Prashanth Suravajhala Genomics . 2018,第1期

机译：使用新的生物启发的多目标方法进行肿瘤分类的基因选择
3. A consensus multi-view multi-objective gene selection approach for improved sample classification [J] . Sudipta Acharya, Laizhong Cui, Yi Pan BMC Bioinformatics . 2020,第S13期

机译：改进样本分类的共识多视图多目标基因选择方法
4. Gene Selection Approach Utilizing Data Clustering Based Technique Optimization for Tumor Classification [C] . Kefaya Qaddoum International Conference on Intelligent Informatics and Biomedical Sciences . 2018

机译：利用基于数据聚类的技术优化进行肿瘤分类的基因选择方法
5. Multi-objective genetic programming for data visualization and classification [D] . Icke, Ilknur 2011

机译：用于数据可视化和分类的多目标遗传规划
6. A consensus multi-view multi-objective gene selection approach for improved sample classification [O] . Sudipta Acharya, Laizhong Cui, Yi Pan 2020

机译：改进样本分类的共识多视图多目标基因选择方法
7. Optimization of Multi-objective ENORA and NSGA-II based on Bio-Inspired Algorithms for Classification Problem [O] . Mohammad Aizat Basir 2020

机译：基于生物启发算法的多目标enora和NSGA-II的优化

Gene selection for tumor classification using a novel bio-inspired multi-objective approach

摘要

著录项

相似文献

相关主题

期刊订阅