A new method for class prediction based on signed-rank algorithms applied to Affymetrix microarray experiments.

Publisher: BioMed Central Country of Publication: England NLM ID: 100965194 Publication Model: Electronic Cited Medium: Internet ISSN: 1471-2105 (Electronic) Linking ISSN: 14712105 NLM ISO Abbreviation: BMC Bioinformatics Subsets: MEDLINE

Original Publication: [London] : BioMed Central, 2000-

Algorithms* ; Data Interpretation, Statistical*; Gene Expression Profiling/*methods ; Oligonucleotide Array Sequence Analysis/*methods; Europe ; Oligonucleotide Array Sequence Analysis/standards ; Quality Control ; Reproducibility of Results ; Sensitivity and Specificity

Background: The huge amount of data generated by DNA chips is a powerful basis to classify various pathologies. However, constant evolution of microarray technology makes it difficult to mix data from different chip types for class prediction of limited sample populations. Affymetrix(R) technology provides both a quantitative fluorescence signal and a decision (detection call: absent or present) based on signed-rank algorithms applied to several hybridization repeats of each gene, with a per-chip normalization. We developed a new prediction method for class belonging based on the detection call only from recent Affymetrix chip type. Biological data were obtained by hybridization on U133A, U133B and U133Plus 2.0 microarrays of purified normal B cells and cells from three independent groups of multiple myeloma (MM) patients.
Results: After a call-based data reduction step to filter out non class-discriminative probe sets, the gene list obtained was reduced to a predictor with correction for multiple testing by iterative deletion of probe sets that sequentially improve inter-class comparisons and their significance. The error rate of the method was determined using leave-one-out and 5-fold cross-validation. It was successfully applied to (i) determine a sex predictor with the normal donor group classifying gender with no error in all patient groups except for male MM samples with a Y chromosome deletion, (ii) predict the immunoglobulin light and heavy chains expressed by the malignant myeloma clones of the validation group and (iii) predict sex, light and heavy chain nature for every new patient. Finally, this method was shown powerful when compared to the popular classification method Prediction Analysis of Microarray (PAM).
Conclusion: This normalization-free method is routinely used for quality control and correction of collection errors in patient reports to clinicians. It can be easily extended to multiple class prediction suitable with clinical groups, and looks particularly promising through international cooperative projects like the "Microarray Quality Control project of US FDA" MAQC as a predictive classifier for diagnostic, prognostic and response to treatment. Finally, it can be used as a powerful tool to mine published data generated on Affymetrix systems and more generally classify samples with binary feature values.

N Engl J Med. 2006 Jun 8;354(23):2463-72. (PMID: 16760446)
BMC Bioinformatics. 2006;7:49. (PMID: 16448562)
Proc Natl Acad Sci U S A. 2000 Jan 4;97(1):262-7. (PMID: 10618406)
Nature. 2000 Feb 3;403(6769):503-11. (PMID: 10676951)
Nature. 2000 Jun 15;405(6788):827-36. (PMID: 10866209)
Nat Med. 2001 Jun;7(6):673-9. (PMID: 11385503)
Proc Natl Acad Sci U S A. 2001 Jun 5;98(12):6730-5. (PMID: 11381113)
Genetica. 2000;109(3):183-97. (PMID: 11430482)
Nat Med. 2002 Jan;8(1):68-74. (PMID: 11786909)
Blood. 2002 Mar 1;99(5):1745-57. (PMID: 11861292)
Proc Natl Acad Sci U S A. 2002 May 14;99(10):6567-72. (PMID: 12011421)
Bioinformatics. 2002 Jul;18(7):961-70. (PMID: 12117794)
Genome Biol. 2002 Jun 14;3(7):RESEARCH0033. (PMID: 12184807)
Oncogene. 2002 Oct 3;21(44):6848-57. (PMID: 12360412)
Proc Natl Acad Sci U S A. 2002 Oct 29;99(22):14031-6. (PMID: 12388780)
Bioinformatics. 2002 Dec;18(12):1593-9. (PMID: 12490443)
J Natl Cancer Inst. 2003 Jan 1;95(1):14-8. (PMID: 12509396)
Bioinformatics. 2003 Jan 22;19(2):185-93. (PMID: 12538238)
Br J Haematol. 2003 Mar;120(6):960-9. (PMID: 12648065)
Mol Cancer Res. 2003 Mar;1(5):346-61. (PMID: 12651908)
Blood. 2003 Jul 15;102(2):592-600. (PMID: 12663452)
Proc Natl Acad Sci U S A. 2003 Aug 19;100(17):9991-6. (PMID: 12900505)
Oncogene. 2003 Sep 29;22(42):6497-507. (PMID: 14528274)
Bioinformatics. 2003 Oct;19 Suppl 2:ii238-44. (PMID: 14534196)
Bioinformatics. 2003 Nov 1;19(16):2072-8. (PMID: 14594712)
Blood. 2003 Dec 1;102(12):3871-9. (PMID: 12933571)
N Engl J Med. 2004 Apr 15;350(16):1605-16. (PMID: 15084693)
N Engl J Med. 2004 Apr 15;350(16):1617-28. (PMID: 15084694)
N Engl J Med. 2004 Apr 29;350(18):1828-37. (PMID: 15115829)
N Engl J Med. 2004 Aug 5;351(6):533-42. (PMID: 15295046)
Br J Haematol. 1992 Jun;81(2):223-30. (PMID: 1643019)
Science. 1999 Oct 15;286(5439):531-7. (PMID: 10521349)
N Engl J Med. 2004 Nov 18;351(21):2159-69. (PMID: 15548776)
N Engl J Med. 2004 Dec 30;351(27):2817-26. (PMID: 15591335)
Lancet. 2005 Feb 5-11;365(9458):488-92. (PMID: 15705458)
BMC Bioinformatics. 2005;6:80. (PMID: 15799785)
Bioinformatics. 2005 May 1;21(9):1971-8. (PMID: 15677704)
Bioinformatics. 2005 May 1;21(9):1987-94. (PMID: 15691856)
Oncogene. 2005 May 12;24(21):3512-24. (PMID: 15735670)
Blood. 2005 Aug 1;106(3):1021-30. (PMID: 15827134)
BMC Bioinformatics. 2005;6:166. (PMID: 15992406)
BMC Bioinformatics. 2005;6:214. (PMID: 16124883)
Leukemia. 2005 Nov;19(11):2002-5. (PMID: 16121219)
Oncogene. 2006 Nov 16;25(54):7180-91. (PMID: 16732320)

Date Created: 20080115 Date Completed: 20080310 Latest Revision: 20181113

20231215

PMC2248160

10.1186/1471-2105-9-16

18190711