Abstract
BackgroundAlthough numerous methods of using microarray data analysis for cancer classification have been proposed, most utilize many genes to achieve accurate classification. This can hamper interpretability of the models and ease of translation to other assay platforms. We explored the use of single genes to construct classification models. We first identified the genes with the most powerful univariate class discrimination ability and then constructed simple classification rules for class prediction using the single genes.ResultsWe applied our model development algorithm to eleven cancer gene expression datasets and compared classification accuracy to that for standard methods including Diagonal Linear Discriminant Analysis, k-Nearest Neighbor, Support Vector Machine and Random Forest. The single gene classifiers provided classification accuracy comparable to or better than those obtained by existing methods in most cases. We analyzed the factors that determined when simple single gene classification is effective and when more complex modeling is warranted.ConclusionsFor most of the datasets examined, the single-gene classification methods appear to work as well as more standard methods, suggesting that simple models could perform well in microarray-based cancer prediction.
Highlights
Numerous methods of using microarray data analysis for cancer classification have been proposed, most utilize many genes to achieve accurate classification
We explored the usefulness of very simple single gene classification models for molecular classification of cancer
The classification results based on split-sample rather than leave-one-out cross validation (LOOCV) evaluation are presented in Table S1 and Table S2 (Additional file 1)
Summary
Numerous methods of using microarray data analysis for cancer classification have been proposed, most utilize many genes to achieve accurate classification This can hamper interpretability of the models and ease of translation to other assay platforms. Recent advances in microarray technology have made it feasible to rapidly measure the expression levels of tens of thousands of genes in a single experiment at a reasonable expense [1]. This technology has facilitated the molecular exploration of cancer [2,3,4,5,6,7,8,9]. Several authors have suggested that simple models could perform well in some cases of microarraybased cancer prediction [17,18,19,20,21,22,23]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.