k-Nearest neighbor models for microarray gene expression analysis and clinical outcome prediction

Parry, R. Mitchell; Jones, Wendell; Stokes, Todd H.; Phan, John H.; Moffitt, Richard A.; Fang, Hong; Shi, Leming; Oberthuer, André; Fischer, Matthias; Tong, Weida; Wang, May D.

doi:10.1038/tpj.2010.56

Cited by 111 publications

(73 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The most common metric used in Bioinformatics is the absolute Pearson coefficient. For clinical end points and controls from breast cancer, neuroblastoma, and multiple myeloma, authors in [38] generated 463,320 kNN models by varying feature ranking method, a number of features, distance metric, a number of neighbors, vote weighting and decision threshold. They identified factors that contribute to the MAQC-II project performance variation.…”

Section: Classification Techniquesmentioning

confidence: 99%

A Review of Various Methods Used in the Analysis of Functional Gene Expression Data

Fyad¹,

Barigou²,

Bouamrane³

et al. 2017

IJITCS

View full text Add to dashboard Cite

show abstract

Section: Classification Techniquesmentioning

confidence: 99%

A Review of Various Methods Used in the Analysis of Functional Gene Expression Data

Fyad¹,

Barigou²,

Bouamrane³

et al. 2017

IJITCS

View full text Add to dashboard Cite

show abstract

“…Since Parry et al (2010) showed that their three feature ranking methods−significance analysis of microarrays (SAM) d-value, fold change ranking with Pvalue threshold of 0.05, and P-value ranking with fold change threshold of 1.5−performed similarly well in the research of KNN modeling strategy, and our main interest is to find a classifier which predicts well in the cross platform classification, only one method, SAM, is applied to rank the differentiability of genes.…”

Section: Prediction Performance Of the Classifiersmentioning

confidence: 99%

Cross platform classification of microarrays by rank comparison

Lee¹

2015

Journal of the Korean Data and Information Science Society

View full text Add to dashboard Cite

Mining the microarray data accumulated in the public data repositories can save experimental cost and time and provide valuable biomedical information. Big data analysis pooling multiple data sets increases statistical power, improves the reliability of the results, and reduces the specific bias of the individual study. However, integrating several data sets from different studies is needed to deal with many problems. In this study, I limited the focus to the cross platform classification that the platform of a testing sample is different from the platform of a training set, and suggested a simple classification method based on rank. This method is compared with the diagonal linear discriminant analysis, k nearest neighbor method and support vector machine using the cross platform real example data sets of two cancers.

show abstract

“…The first one called the Training set is meant to be used for the classifier training, while the second one is named Validation set and it is to be used as an independent test set to validate the prediction performance. An additional advantage when analyzing the MAQC data is that a diverse collection of analysis teams has worked on the same data, following the same evaluation procedure and publishing their results 24,22,19 . An accurate benchmark of a new algorithm can be done to understand how well it performs when compared to a considerable number of state of the art alternatives.…”

Section: Datamentioning

confidence: 99%

Gene Expression Data Classification Combining Hierarchical Representation and Efficient Feature Selection

et al. 2012

View full text Add to dashboard Cite

A general framework for microarray data classification is proposed in this paper. It produces precise and reliable classifiers through a two-step approach. At first, the original feature set is enhanced by a new set of features called metagenes. These new features are obtained through a hierarchical clustering process on the original data. Two different metagene generation rules have been analyzed, called Treelets clustering and Euclidean clustering. Metagenes creation is attractive for several reasons: first, they can improve the classification since they broaden the available feature space and capture the common behavior of similar genes reducing the residual measurement noise. Furthermore, by analyzing some of the chosen metagenes for classification with gene set enrichment analysis algorithms, it is shown how metagenes can summarize the behavior of functionally related probe sets. Additionally, metagenes can point out, still undocumented, highly discriminant probe sets numerically related to other probes endowed with prior biological information in order to contribute to the knowledge discovery process.The second step of the framework is the feature selection which applies the Improved Sequential Floating Forward Selection algorithm (IFFS) to properly choose a subset from the available feature set for classification composed of genes and metagenes. Considering the microarray sample scarcity problem, besides the classical error rate, a reliability measure is introduced to improve the feature selection process. Different scoring schemes are studied to choose the best one using both error rate and reliability. The Linear Discriminant Analysis classifier (LDA) has been used throughout this work, due to its good characteristics, but the proposed framework can be used with almost any classifier. The potential of the proposed framework has been evaluated analyzing all the publicly available datasets offered by the Micro Array Quality Control Study, phase II (MAQC). The comparative results showed that the proposed framework can compete with a wide variety of state of the art alternatives and it can obtain the best mean performance if a particular setup is chosen. A Monte Carlo simulation confirmed that the proposed framework obtains stable and repeatable results.

show abstract

k-Nearest neighbor models for microarray gene expression analysis and clinical outcome prediction

Cited by 111 publications

References 45 publications

A Review of Various Methods Used in the Analysis of Functional Gene Expression Data

A Review of Various Methods Used in the Analysis of Functional Gene Expression Data

Cross platform classification of microarrays by rank comparison

Gene Expression Data Classification Combining Hierarchical Representation and Efficient Feature Selection

Contact Info

Product

Resources

About