Applications of the SDL Global Optimization Method in DNA Microarray Data Analysis - DNA Microarray Technology and Data Analysis in Cancer Research - page 65

Table 5.5. Top hits in P210.

GenBankID NCBI Hyperlink Foldchange.Ref.relative.to.Treatment

NM_023279 NM_023279 −2.26

S60870 S60870 −2.56

NM_008495 NM_008495 −2.52

X89686 X89686 2.23

NM_011224 NM_011224 −2.45

M92334 M92334 −2.55

NM_016866 NM_016866 2.58

BC011154 BC011154 2.50

NM_011313 NM_011313 −7.97

U26473 U26473 −2.67

AY043479 AY043479 3.30

AF263458 AF263458 −3.90

NM_009638 NM_009638 −2.39

X00496 X00496 −3.65

NM_009801 NM_009801 −3.25

NM_010735 NM_010735 −3.90

L46814 L46814 −2.21

NM_009829 NM_009829 −3.80

NM_021611 NM_021611 −4.88

AK011429 AK011429 −3.09

NM_008581 NM_008581 8.89

X80951 X80951 −2.32

their classes. The classification processes are automated after the gene
expression data are inputted. Instead of examining a single gene at a time,
the SDL method can find the global optimal solutions and construct a
multi-subset pyramidal hierarchy class predictor containing up to 23 gene
subsets based on a given microarray gene expression data collection
within a period of several hours. Such an automatically derived class pre-
dictor makes reliable cancer classification and accurate tumor diagnosis in
clinical practice possible.
DNA chip technology enables the study of gene expression on a large
scale (Barrett, 2005; Churchill, 2002; Enright et al ., 1999; Hacia, 1999).
Large-scale gene expressions are used to determine drug targets, identify
coregulated genes, and study the response to environmental conditions