Improving the prediction accuracy in classification using the combined data sets by ranks of gene expressions

BackgroundThe information from different data sets experimented under different conditions may be inconsistent even though they are performed with the same research objectives. More than that, even when the data sets were generated from the same platform, the data agreement may be affected by the technical variation among the laboratories. In this case, it is necessary to use the combined data set after adjusting the differences between such data sets, for detecting the more reliable information.ResultsThe proposed method combines data sets posterior to the discretization of data sets based on the ranks of the gene expression ratios, and the statistical method is applied to the combined data set for predictive gene selection. The efficiency of the proposed method was evaluated using five colon cancer related data sets, which were experimented using cDNA microarrays with different RNA sources, and one experiment utilized oligonucleotide arrays. NCI-60 cell lines data sets were used, which were performed with two different platforms of cDNA microarrays and Affymetrix HU6800 oligonucleotide arrays. The combined data set by the proposed method predicted the test data sets more accurately than the separated data sets did. The biological significant genes were detected from the combined data set, which were missed on the separated data sets.ConclusionBy transforming gene expressions using ranks, the proposed method is not influenced by systematic bias among chips and normalization method. The method may be especially more useful to find predictive genes from data sets which have different scale in gene expressions.

[1]  Usama M. Fayyad,et al.  Multi-Interval Discretization of Continuous-Valued Attributes for Classification Learning , 1993, IJCAI.

[2]  C. Pipper,et al.  [''R"--project for statistical computing]. , 2008, Ugeskrift for laeger.

[3]  U. Alon,et al.  Transcriptional gene expression profiles of colorectal adenoma, adenocarcinoma, and normal tissue examined by oligonucleotide arrays. , 2001, Cancer research.

[4]  Ron Kohavi,et al.  Supervised and Unsupervised Discretization of Continuous Features , 1995, ICML.

[5]  A. Markham,et al.  Expression of the antiapoptosis gene,Survivin, predicts death from recurrent colorectal carcinoma , 2000, Gut.

[6]  J. Rissanen Stochastic Complexity and Modeling , 1986 .

[7]  Huan Liu,et al.  Discretization: An Enabling Technique , 2002, Data Mining and Knowledge Discovery.

[8]  C. Bordi,et al.  Xq25 and Xq26 identify the common minimal deletion region in malignant gastroenteropancreatic endocrine carcinomas , 2006, Virchows Archiv.

[9]  Nikola Kasabov,et al.  Gene Expression Proé ling of Metastatic and Nonmetastatic Colorectal Cancer Cell Lines , 2002 .

[10]  Daniel R. Rhodes,et al.  CIT: identification of differentially expressed clusters of genes from microarray data , 2002, Bioinform..

[11]  Taesung Park,et al.  Combining multiple microarrays in the presence of controlling variables , 2006, Bioinform..

[12]  Jason Catlett,et al.  On Changing Continuous Attributes into Ordered Discrete Attributes , 1991, EWSL.

[13]  F. Ramsey,et al.  The statistical sleuth : a course in methods of data analysis , 2002 .

[14]  E. Rieber,et al.  Antibody response to the tumor-associated inhibitor of apoptosis protein survivin in cancer patients. , 2000, Cancer research.

[15]  Raymond B. Nagle,et al.  Erratum: Identification of differentially expressed genes in pancreatic cancer cells using cDNA microarray (Cancer Research (May 15, 2002) (2890-2896)) , 2002 .

[16]  Stephen H. Friend,et al.  A human DNA segment with properties of the gene that predisposes to retinoblastoma and osteosarcoma , 1986, Nature.

[17]  Ki-Yeol Kim,et al.  Novel and simple transformation algorithm for combining microarray data sets , 2007, BMC Bioinformatics.

[18]  Randy Kerber,et al.  ChiMerge: Discretization of Numeric Attributes , 1992, AAAI.

[19]  B. De Moor,et al.  Comparison and meta-analysis of microarray data: from the bench to the computer desk. , 2003, Trends in genetics : TIG.

[20]  Wolfgang Huber,et al.  Systematic analysis of T7 RNA polymerase based in vitro linear RNA amplification for use in microarray experiments , 2004, BMC Genomics.

[21]  S K Libutti,et al.  Advantages of mRNA amplification for microarray analysis. , 2002, BioTechniques.

[22]  Jun Chen,et al.  Joint analysis of two microarray gene-expression data sets to select lung adenocarcinoma marker genes , 2004, BMC Bioinformatics.

[23]  Lucila Ohno-Machado,et al.  Analysis of matched mRNA measurements from two different microarray technologies , 2002, Bioinform..

[24]  H. Kamiyama,et al.  Analysis of the Relationship between Sex and Chromosomal Aberrations in Colorectal Cancer by Comparative Genomic Hybridization , 2006, The Journal of international medical research.

[25]  George Potamias,et al.  Gene Selection via Discretized Gene-Expression Profiles and Greedy Feature-Elimination , 2004, SETN.

[26]  Peter J. Park,et al.  A Nonparametric Scoring Algorithm for Identifying Informative Genes from Microarray Data , 2000, Pacific Symposium on Biocomputing.

[27]  Lei Liu,et al.  A study of inter-lab and inter-platform agreement of DNA microarray data , 2005, BMC Genomics.

[28]  S. Thorgeirsson,et al.  Application of comparative functional genomics to identify best-fit mouse models to study human cancer , 2004, Nature Genetics.

[29]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[30]  Fuad G. Gwadry,et al.  Comparing cDNA and oligonucleotide array data: concordance of gene expression across platforms for the NCI-60 cancer cells , 2003, Genome Biology.

[31]  K. Nowak,et al.  BMI1 is a target gene of E2F-1 and is strongly expressed in primary neuroblastomas , 2006, Nucleic acids research.

[32]  Y. Baba,et al.  Comparison of gene expression measurements from cDNA and 60-mer oligonucleotide microarrays. , 2005, Genomics.

[33]  Haiyong Han,et al.  Identification of differentially expressed genes in pancreatic cancer cells using cDNA microarray. , 2002, Cancer research.

[34]  Petri Auvinen,et al.  Are data from different gene expression microarray platforms comparable? , 2004, Genomics.

[35]  Ki-Yeol Kim,et al.  Reuse of imputed data in microarray analysis increases imputation efficiency , 2004, BMC Bioinformatics.

[36]  Inyoung Kim,et al.  Statistical methods of translating microarray data into clinically relevant diagnostic information in colorectal cancer , 2005, Bioinform..

[37]  L. Hedges,et al.  Statistical Methods for Meta-Analysis , 1987 .