Effect of training-sample size and classification difficulty on the accuracy of genomic predictors.
Details
State: Public
Version: author
Serval ID
serval:BIB_0C25CFF6BFCD
Type
Article: article from journal or magazin.
Collection
Publications
Institution
Title
Effect of training-sample size and classification difficulty on the accuracy of genomic predictors.
Journal
Breast Cancer Research
ISSN
1465-542X[electronic], 1465-5411[linking]
Publication state
Published
Issued date
2010
Peer-reviewed
Oui
Volume
12
Number
1
Pages
R5
Language
english
Abstract
Introduction: As part of the MicroArray Quality Control (MAQC)-II project, this analysis examines how the choice of univariate feature-selection methods and classification algorithms may influence the performance of genomic predictors under varying degrees of prediction difficulty represented by three clinically relevant endpoints.
Methods: We used gene-expression data from 230 breast cancers (grouped into training and independent validation sets), and we examined 40 predictors (five univariate feature-selection methods combined with eight different classifiers) for each of the three endpoints. Their classification performance was estimated on the training set by using two different resampling methods and compared with the accuracy observed in the independent validation set.
Results: A ranking of the three classification problems was obtained, and the performance of 120 models was estimated and assessed on an independent validation set. The bootstrapping estimates were closer to the validation performance than were the cross-validation estimates. The required sample size for each endpoint was estimated, and both gene-level and pathway-level analyses were performed on the obtained models.
Conclusions: We showed that genomic predictor accuracy is determined largely by an interplay between sample size and classification difficulty. Variations on univariate feature-selection methods and choice of classification algorithm have only a modest impact on predictor performance, and several statistically equally good predictors can be developed for any given classification problem.
Methods: We used gene-expression data from 230 breast cancers (grouped into training and independent validation sets), and we examined 40 predictors (five univariate feature-selection methods combined with eight different classifiers) for each of the three endpoints. Their classification performance was estimated on the training set by using two different resampling methods and compared with the accuracy observed in the independent validation set.
Results: A ranking of the three classification problems was obtained, and the performance of 120 models was estimated and assessed on an independent validation set. The bootstrapping estimates were closer to the validation performance than were the cross-validation estimates. The required sample size for each endpoint was estimated, and both gene-level and pathway-level analyses were performed on the obtained models.
Conclusions: We showed that genomic predictor accuracy is determined largely by an interplay between sample size and classification difficulty. Variations on univariate feature-selection methods and choice of classification algorithm have only a modest impact on predictor performance, and several statistically equally good predictors can be developed for any given classification problem.
Keywords
Algorithms, Area Under Curve, Breast Neoplasms/chemistry, Breast Neoplasms/genetics, Female, Gene Expression Profiling/methods, Humans, Receptors, Estrogen/analysis, Sample Size
Pubmed
Web of science
Open Access
Yes
Create date
25/02/2011 15:37
Last modification date
20/08/2019 13:33