Gene Expression Profiles for Predicting Metastasis in Breast Cancer: a Cross-study Comparison of Classification Methods

Overview

Journal ScientificWorldJournal

Publisher Wiley

Specialty Biology

Date 2012 Dec 20

PMID 23251101

Citations 10

Authors

Mark Burton

Mads Thomassen

Qihua Tan

Torben A Kruse

Affiliations

Soon will be listed here.

Abstract

Machine learning has increasingly been used with microarray gene expression data and for the development of classifiers using a variety of methods. However, method comparisons in cross-study datasets are very scarce. This study compares the performance of seven classification methods and the effect of voting for predicting metastasis outcome in breast cancer patients, in three situations: within the same dataset or across datasets on similar or dissimilar microarray platforms. Combining classification results from seven classifiers into one voting decision performed significantly better during internal validation as well as external validation in similar microarray platforms than the underlying classification methods. When validating between different microarray platforms, random forest, another voting-based method, proved to be the best performing method. We conclude that voting based classifiers provided an advantage with respect to classifying metastasis outcome in breast cancer patients.

Citing Articles

Ensemble-based classification using microRNA expression identifies a breast cancer patient subgroup with an ultralow long-term risk of metastases.

Block I, Burton M, Sorensen K, Larsen M, Do T, Bak M Cancer Med. 2024; 13(9):e7089.

PMID: 38676390 PMC: 11053369. DOI: 10.1002/cam4.7089.

Identification of Breast Cancer Metastasis Markers from Gene Expression Profiles Using Machine Learning Approaches.

Jung J, Yoo S Genes (Basel). 2023; 14(9).

PMID: 37761960 PMC: 10530902. DOI: 10.3390/genes14091820.

Computational approaches in rheumatic diseases - Deciphering complex spatio-temporal cell interactions.

Hegarty C, Neto N, Cahill P, Floudas A Comput Struct Biotechnol J. 2023; 21:4009-4020.

PMID: 37649712 PMC: 10462794. DOI: 10.1016/j.csbj.2023.08.005.

Identification of biomarkers predictive of metastasis development in early-stage colorectal cancer using network-based regularization.

Peixoto C, Lopes M, Martins M, Casimiro S, Sobral D, Grosso A BMC Bioinformatics. 2023; 24(1):17.

PMID: 36647008 PMC: 9841719. DOI: 10.1186/s12859-022-05104-z.

Development and Validation of Machine Learning Models for Predicting Occult Nodal Metastasis in Early-Stage Oral Cavity Squamous Cell Carcinoma.

Farrokhian N, Holcomb A, Dimon E, Karadaghy O, Ward C, Whiteford E JAMA Netw Open. 2022; 5(4):e227226.

PMID: 35416990 PMC: 9008495. DOI: 10.1001/jamanetworkopen.2022.7226.

References

Hoshida Y . Nearest template prediction: a single-sample-based flexible class prediction with confidence assessment. PLoS One. 2010; 5(11):e15543. PMC: 2990751. DOI: 10.1371/journal.pone.0015543. View

Sewak M, Reddy N, Duan Z . Gene expression based leukemia sub-classification using committee neural networks. Bioinform Biol Insights. 2010; 3:89-98. PMC: 2808175. DOI: 10.4137/bbi.s2908. View

Zucknick M, Richardson S, Stronach E . Comparing the characteristics of gene expression profiles derived by univariate and multivariate classification methods. Stat Appl Genet Mol Biol. 2008; 7(1):Article7. PMC: 2496885. DOI: 10.2202/1544-6115.1307. View

Zervakis M, Blazadonakis M, Tsiliki G, Danilatou V, Tsiknakis M, Kafetzopoulos D . Outcome prediction based on microarray analysis: a critical perspective on methods. BMC Bioinformatics. 2009; 10:53. PMC: 2667512. DOI: 10.1186/1471-2105-10-53. View

Thomassen M, Tan Q, Kruse T . Gene expression meta-analysis identifies metastatic pathways and transcription factors in breast cancer. BMC Cancer. 2009; 8:394. PMC: 2642844. DOI: 10.1186/1471-2407-8-394. View

Thomassen M, Tan Q, Kruse T . Gene expression meta-analysis identifies chromosomal regions and candidate genes involved in breast cancer metastasis. Breast Cancer Res Treat. 2008; 113(2):239-49. DOI: 10.1007/s10549-008-9927-2. View

Statnikov A, Aliferis C, Tsamardinos I, Hardin D, Levy S . A comprehensive evaluation of multicategory classification methods for microarray gene expression cancer diagnosis. Bioinformatics. 2004; 21(5):631-43. DOI: 10.1093/bioinformatics/bti033. View

van Vliet M, Reyal F, Horlings H, van de Vijver M, Reinders M, Wessels L . Pooling breast cancer datasets has a synergetic effect on classification performance and improves signature stability. BMC Genomics. 2008; 9:375. PMC: 2527336. DOI: 10.1186/1471-2164-9-375. View

Peng Y . A novel ensemble machine learning for robust microarray data classification. Comput Biol Med. 2005; 36(6):553-73. DOI: 10.1016/j.compbiomed.2005.04.001. View

10.

Huang E, Cheng S, Dressman H, Pittman J, Tsou M, Horng C . Gene expression predictors of breast cancer outcomes. Lancet. 2003; 361(9369):1590-6. DOI: 10.1016/S0140-6736(03)13308-9. View

11.

Chen M, Shi L, Kelly R, Perkins R, Fang H, Tong W . Selecting a single model or combining multiple models for microarray-based classifier development?--a comparative analysis based on large and diverse datasets generated from the MAQC-II project. BMC Bioinformatics. 2011; 12 Suppl 10:S3. PMC: 3236846. DOI: 10.1186/1471-2105-12-S10-S3. View

12.

Zeng T, Liu J . Mixture classification model based on clinical markers for breast cancer prognosis. Artif Intell Med. 2009; 48(2-3):129-37. DOI: 10.1016/j.artmed.2009.07.008. View

13.

Sotiriou C, Wirapati P, Loi S, Harris A, Fox S, Smeds J . Gene expression profiling in breast cancer: understanding the molecular basis of histologic grade to improve prognosis. J Natl Cancer Inst. 2006; 98(4):262-72. DOI: 10.1093/jnci/djj052. View

14.

Kim S . Effects of sample size on robustness and prediction accuracy of a prognostic gene signature. BMC Bioinformatics. 2009; 10:147. PMC: 2689196. DOI: 10.1186/1471-2105-10-147. View

15.

Miller L, Smeds J, George J, Vega V, Vergara L, Ploner A . An expression signature for p53 status in human breast cancer predicts mutation status, transcriptional effects, and patient survival. Proc Natl Acad Sci U S A. 2005; 102(38):13550-5. PMC: 1197273. DOI: 10.1073/pnas.0506230102. View

16.

Huynh H, Kim J, Won Y . Performance comparison of SLFN training algorithms for DNA microarray classification. Adv Exp Med Biol. 2011; 696:135-43. DOI: 10.1007/978-1-4419-7046-6_14. View

17.

Sotiriou C, Neo S, McShane L, Korn E, Long P, Jazaeri A . Breast cancer classification and prognosis based on gene expression profiles from a population-based study. Proc Natl Acad Sci U S A. 2003; 100(18):10393-8. PMC: 193572. DOI: 10.1073/pnas.1732912100. View

18.

Statnikov A, Aliferis C . Are random forests better than support vector machines for microarray-based cancer classification?. AMIA Annu Symp Proc. 2008; :686-90. PMC: 2655823. View

19.

Taylor S, Kim K . A jackknife and voting classifier approach to feature selection and classification. Cancer Inform. 2011; 10:133-47. PMC: 3091410. DOI: 10.4137/CIN.S7111. View

20.

Karlsson E, Delle U, Danielsson A, Olsson B, Abel F, Karlsson P . Gene expression variation to predict 10-year survival in lymph-node-negative breast cancer. BMC Cancer. 2008; 8:254. PMC: 2559847. DOI: 10.1186/1471-2407-8-254. View