结合reliefF和mRMR的基因选择算法。
Gene selection algorithm by combining reliefF and mRMR.
作者信息
Zhang Yi, Ding Chris, Li Tao
机构信息
School of Computer Science, Florida International University, 11200 SW 8th Street, Miami, FL 33199, USA.
出版信息
BMC Genomics. 2008 Sep 16;9 Suppl 2(Suppl 2):S27. doi: 10.1186/1471-2164-9-S2-S27.
Abstract
BACKGROUND
Gene expression data usually contains a large number of genes, but a small number of samples. Feature selection for gene expression data aims at finding a set of genes that best discriminate biological samples of different types. In this paper, we present a two-stage selection algorithm by combining ReliefF and mRMR: In the first stage, ReliefF is applied to find a candidate gene set; In the second stage, mRMR method is applied to directly and explicitly reduce redundancy for selecting a compact yet effective gene subset from the candidate set.
RESULTS
We perform comprehensive experiments to compare the mRMR-ReliefF selection algorithm with ReliefF, mRMR and other feature selection methods using two classifiers as SVM and Naive Bayes, on seven different datasets. And we also provide all source codes and datasets for sharing with others.
CONCLUSION
The experimental results show that the mRMR-ReliefF gene selection algorithm is very effective.
摘要
背景
基因表达数据通常包含大量基因，但样本数量较少。基因表达数据的特征选择旨在找到一组能最佳区分不同类型生物样本的基因。在本文中，我们提出了一种结合ReliefF和mRMR的两阶段选择算法：在第一阶段，应用ReliefF找到候选基因集；在第二阶段，应用mRMR方法直接且明确地减少冗余，以便从候选集中选择一个紧凑而有效的基因子集。
结果
我们进行了全面的实验，使用支持向量机（SVM）和朴素贝叶斯这两种分类器，在七个不同数据集上，将mRMR-ReliefF选择算法与ReliefF、mRMR及其他特征选择方法进行比较。并且我们还提供所有源代码和数据集以供他人共享。
结论
实验结果表明，mRMR-ReliefF基因选择算法非常有效。
相似文献
1
Gene selection algorithm by combining reliefF and mRMR.结合reliefF和mRMR的基因选择算法。
BMC Genomics. 2008 Sep 16;9 Suppl 2(Suppl 2):S27. doi: 10.1186/1471-2164-9-S2-S27.
2
Minimum redundancy feature selection from microarray gene expression data.从微阵列基因表达数据中进行最小冗余特征选择。
J Bioinform Comput Biol. 2005 Apr;3(2):185-205. doi: 10.1142/s0219720005001004.
3
Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy.基于互信息的特征选择：最大依赖、最大相关和最小冗余准则。
IEEE Trans Pattern Anal Mach Intell. 2005 Aug;27(8):1226-38. doi: 10.1109/TPAMI.2005.159.
4
An entropy-based gene selection method for cancer classification using microarray data.一种基于熵的利用微阵列数据进行癌症分类的基因选择方法。
BMC Bioinformatics. 2005 Mar 24;6:76. doi: 10.1186/1471-2105-6-76.
5
SVM-RFE with MRMR filter for gene selection.基于 MRMR 滤波器的 SVM-RFE 基因选择方法。
IEEE Trans Nanobioscience. 2010 Mar;9(1):31-7. doi: 10.1109/TNB.2009.2035284. Epub 2009 Oct 30.
6
Development of two-stage SVM-RFE gene selection strategy for microarray expression data analysis.用于微阵列表达数据分析的两阶段支持向量机-递归特征消除基因选择策略的开发。
IEEE/ACM Trans Comput Biol Bioinform. 2007 Jul-Sep;4(3):365-81. doi: 10.1109/TCBB.2007.70224.
7
A Cancer Gene Selection Algorithm Based on the K-S Test and CFS.一种基于K-S检验和CFS的癌症基因选择算法
Biomed Res Int. 2017;2017:1645619. doi: 10.1155/2017/1645619. Epub 2017 May 8.
8
A Hybrid Gene Selection Method Based on ReliefF and Ant Colony Optimization Algorithm for Tumor Classification.基于 ReliefF 和蚁群优化算法的混合基因选择方法在肿瘤分类中的应用。
Sci Rep. 2019 Jun 20;9(1):8978. doi: 10.1038/s41598-019-45223-x.
9
Hybrid Feature Selection Algorithm mRMR-ICA for Cancer Classification from Microarray Gene Expression Data.用于从微阵列基因表达数据进行癌症分类的混合特征选择算法mRMR-ICA
Comb Chem High Throughput Screen. 2018;21(6):420-430. doi: 10.2174/1386207321666180601074349.
10
Gene selection algorithms for microarray data based on least squares support vector machine.基于最小二乘支持向量机的微阵列数据基因选择算法
BMC Bioinformatics. 2006 Feb 27;7:95. doi: 10.1186/1471-2105-7-95.
引用本文的文献
1
Machine Learning and Computed Tomography Radiomics to Predict Disease Progression to Upfront Pembrolizumab Monotherapy in Advanced Non-Small-Cell Lung Cancer: A Pilot Study.机器学习与计算机断层扫描影像组学预测晚期非小细胞肺癌一线帕博利珠单抗单药治疗疾病进展的初步研究
Cancers (Basel). 2024 Dec 28;17(1):58. doi: 10.3390/cancers17010058.
2
A retrospective prognostic evaluation using unsupervised learning in the treatment of COVID-19 patients with hypertension treated with ACEI/ARB drugs.使用无监督学习对 COVID-19 合并高血压患者应用 ACEI/ARB 类药物治疗的回顾性预后评估。
PeerJ. 2024 May 13;12:e17340. doi: 10.7717/peerj.17340. eCollection 2024.
3
Epidemiological Aspects of Opioid Poisoning in Northern Iran: A Registry-Based Clinical Study.伊朗北部阿片类药物中毒的流行病学特征：一项基于登记处的临床研究。
Health Serv Insights. 2024 Feb 22;17:11786329241232300. doi: 10.1177/11786329241232300. eCollection 2024.
4
The Relative Power of Structural Genomic Variation versus SNPs in Explaining the Quantitative Trait Growth in the Marine Teleost .结构基因组变异与单核苷酸多态性在解释海洋硬骨鱼类数量性状生长中的相对作用
Genes (Basel). 2022 Jun 23;13(7):1129. doi: 10.3390/genes13071129.
5
Screening of Gene Expression Markers for Corona Virus Disease 2019 Through Boruta_MCFS Feature Selection.通过 Boruta_MCFS 特征选择筛选 2019 年冠状病毒病的基因表达标志物。
Front Public Health. 2022 Jun 22;10:901602. doi: 10.3389/fpubh.2022.901602. eCollection 2022.
6
Roles of Physicochemical and Structural Properties of RNA-Binding Proteins in Predicting the Activities of Trans-Acting Splicing Factors with Machine Learning.基于物理化学和结构特性的 RNA 结合蛋白在机器学习预测反式剪接因子活性中的作用。
Int J Mol Sci. 2022 Apr 17;23(8):4426. doi: 10.3390/ijms23084426.
7
A bi-stage feature selection approach for COVID-19 prediction using chest CT images.一种使用胸部CT图像进行COVID-19预测的双阶段特征选择方法。
Appl Intell (Dordr). 2021;51(12):8985-9000. doi: 10.1007/s10489-021-02292-8. Epub 2021 Apr 19.
8
ILRC: a hybrid biomarker discovery algorithm based on improved L1 regularization and clustering in microarray data.ILRC：一种基于改进的L1正则化和微阵列数据聚类的混合生物标志物发现算法。
BMC Bioinformatics. 2021 Oct 22;22(1):514. doi: 10.1186/s12859-021-04443-7.
9
Gene Correlation Guided Gene Selection for Microarray Data Classification.基于基因相关性的基因选择在基因芯片数据分析分类中的应用。
Biomed Res Int. 2021 Aug 14;2021:6490118. doi: 10.1155/2021/6490118. eCollection 2021.
10
Screening for Core Genes Related to Pathogenesis of Alzheimer's Disease.阿尔茨海默病发病机制相关核心基因的筛选
Front Cell Dev Biol. 2021 Apr 22;9:668738. doi: 10.3389/fcell.2021.668738. eCollection 2021.
本文引用的文献
1
Iterative RELIEF for feature weighting: algorithms, theories, and applications.用于特征加权的迭代RELIEF：算法、理论与应用
IEEE Trans Pattern Anal Mach Intell. 2007 Jun;29(6):1035-51. doi: 10.1109/TPAMI.2007.1093.
2
Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy.基于互信息的特征选择：最大依赖、最大相关和最小冗余准则。
IEEE Trans Pattern Anal Mach Intell. 2005 Aug;27(8):1226-38. doi: 10.1109/TPAMI.2005.159.
3
Minimum redundancy feature selection from microarray gene expression data.从微阵列基因表达数据中进行最小冗余特征选择。
J Bioinform Comput Biol. 2005 Apr;3(2):185-205. doi: 10.1142/s0219720005001004.
4
A comparative study of feature selection and multiclass classification methods for tissue classification based on gene expression.基于基因表达的组织分类中特征选择与多类分类方法的比较研究
Bioinformatics. 2004 Oct 12;20(15):2429-37. doi: 10.1093/bioinformatics/bth267. Epub 2004 Apr 15.
5
RankGene: identification of diagnostic genes based on expression data.RankGene：基于表达数据的诊断基因鉴定
Bioinformatics. 2003 Aug 12;19(12):1578-9. doi: 10.1093/bioinformatics/btg179.
6
Genetic algorithms applied to multi-class prediction for the analysis of gene expression data.应用于基因表达数据分析的多类预测的遗传算法。
Bioinformatics. 2003 Jan;19(1):37-44. doi: 10.1093/bioinformatics/19.1.37.
7
Classification, subtype discovery, and prediction of outcome in pediatric acute lymphoblastic leukemia by gene expression profiling.通过基因表达谱分析对儿童急性淋巴细胞白血病进行分类、亚型发现及预后预测。
Cancer Cell. 2002 Mar;1(2):133-43. doi: 10.1016/s1535-6108(02)00032-6.
8
Multiclass cancer diagnosis using tumor gene expression signatures.利用肿瘤基因表达特征进行多类癌症诊断。
Proc Natl Acad Sci U S A. 2001 Dec 18;98(26):15149-54. doi: 10.1073/pnas.211566398. Epub 2001 Dec 11.
9
Gene-expression profiles in hereditary breast cancer.遗传性乳腺癌中的基因表达谱
N Engl J Med. 2001 Feb 22;344(8):539-48. doi: 10.1056/NEJM200102223440801.
10
Systematic variation in gene expression patterns in human cancer cell lines.人类癌细胞系中基因表达模式的系统性变化。
Nat Genet. 2000 Mar;24(3):227-35. doi: 10.1038/73432.
Zotero 插件