Multiclass cancer classification and biomarker discovery using GA-based algorithms

• Published in: Bioinformatics Vol. 21; no. 11; pp. 2691 - 2697
• Main Authors: Liu, Jane Jijun, Cutler, Gene, Li, Wuxiong, Pan, Zheng, Peng, Sihua, Hoey, Tim, Chen, Liangbiao, Ling, Xuefeng Bruce
• Format: Journal Article
• Language: English
• Published: Oxford Oxford University Press 01.06.2005; Oxford Publishing Limited (England)
• Subjects: Algorithms; Artificial Intelligence; Bioinformatics; Biological and medical sciences; Biomarkers, Tumor - classification; Biomarkers, Tumor - genetics; Biomarkers, Tumor - metabolism; Data mining; Diagnosis, Computer-Assisted - methods; Fundamental and applied biological sciences. Psychology; Gene Expression Profiling - methods; General aspects; Humans; Mathematics in biology. Statistical analysis. Models. Metrology. Data processing in biology (general aspects); Neoplasm Proteins - classification; Neoplasm Proteins - genetics; Neoplasm Proteins - metabolism; Neoplasms - classification; Neoplasms - diagnosis; Neoplasms - genetics; Neoplasms - metabolism; Oligonucleotide Array Sequence Analysis - methods; Pattern Recognition, Automated - methods; Reproducibility of Results; Sensitivity and Specificity; Tumors; High throughput screening; Treatment; Gene; Genetic algorithm; Classification; DNA chip; Development; Biological marker; Malignant tumor; Microarray
• ISSN: 1367-4803; 0266-7061; 1460-2059; 1460-2059; 1367-4811
• DOI: 10.1093/bioinformatics/bti419

Motivation: The development of microarray-based high-throughput gene profiling has led to the hope that this technology could provide an efficient and accurate means of diagnosing and classifying tumors, as well as predicting prognoses and effective treatments. However, the large amount of data generated by microarrays requires effective reduction of discriminant gene features into reliable sets of tumor biomarkers for such multiclass tumor discrimination. The availability of reliable sets of biomarkers, especially serum biomarkers, should have a major impact on our understanding and treatment of cancer. Results: We have combined genetic algorithm (GA) and all paired (AP) support vector machine (SVM) methods for multiclass cancer categorization. Predictive features can be automatically determined through iterative GA/SVM, leading to very compact sets of non-redundant cancer-relevant genes with the best classification performance reported to date. Interestingly, these different classifier sets harbor only modest overlapping gene features but have similar levels of accuracy in leave-one-out cross-validations (LOOCV). Further characterization of these optimal tumor discriminant features, including the use of nearest shrunken centroids (NSC), analysis of annotations and literature text mining, reveals previously unappreciated tumor subclasses and a series of genes that could be used as cancer biomarkers. With this approach, we believe that microarray-based multiclass molecular analysis can be an effective tool for cancer biomarker discovery and subsequent molecular cancer diagnosis. Contact: xuefeng_ling@yahoo.com Supplementary information: http://www.fishgenome.org/publication/Liu/bioinformatics/