Document Detail

Simple rules underlying gene expression profiles of more than six subtypes of acute lymphoblastic leukemia (ALL) patients.
MedLine Citation:
PMID:  12499295     Owner:  NLM     Status:  MEDLINE    
MOTIVATIONS AND RESULTS: For classifying gene expression profiles or other types of medical data, simple rules are preferable to non-linear distance or kernel functions. This is because rules may help us understand more about the application in addition to performing an accurate classification. In this paper, we discover novel rules that describe the gene expression profiles of more than six subtypes of acute lymphoblastic leukemia (ALL) patients. We also introduce a new classifier, named PCL, to make effective use of the rules. PCL is accurate and can handle multiple parallel classifications. We evaluate this method by classifying 327 heterogeneous ALL samples. Our test error rate is competitive to that of support vector machines, and it is 71% better than C4.5, 50% better than Naive Bayes, and 43% better than k-nearest neighbour. Experimental results on another independent data sets are also presented to show the strength of our method.
AVAILABILITY: Under, click on Supplementary Information.
Jinyan Li; Huiqing Liu; James R Downing; Allen Eng-Juh Yeoh; Limsoon Wong
Related Documents :
10935455 - How good are support vector machines?
9990165 - Development and application of a work-process classification.
20013155 - Classification of leukemia blood samples using neural networks.
20858575 - Driver drowsiness classification using fuzzy wavelet-packet-based feature-extraction al...
18965735 - The determination of molybdenum in a sea water candidate reference material by inductiv...
279385 - Metaphyseal multifocal osteosarcoma.
Publication Detail:
Type:  Comparative Study; Evaluation Studies; Journal Article; Validation Studies    
Journal Detail:
Title:  Bioinformatics (Oxford, England)     Volume:  19     ISSN:  1367-4803     ISO Abbreviation:  Bioinformatics     Publication Date:  2003 Jan 
Date Detail:
Created Date:  2002-12-24     Completed Date:  2003-07-22     Revised Date:  2013-05-20    
Medline Journal Info:
Nlm Unique ID:  9808944     Medline TA:  Bioinformatics     Country:  England    
Other Details:
Languages:  eng     Pagination:  71-8     Citation Subset:  IM    
Laboratories for Information Technology, 21 Heng Mui Keng Terrace, Singapore 119613, Singapore.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Cluster Analysis
DNA, Neoplasm / classification*,  genetics*
Gene Expression Profiling / methods*
Gene Expression Regulation, Neoplastic / genetics
Genetic Markers / genetics
Models, Genetic
Models, Statistical
Pattern Recognition, Automated
Precursor Cell Lymphoblastic Leukemia-Lymphoma / classification,  genetics*
Tumor Markers, Biological / classification,  genetics
Reg. No./Substance:
0/DNA, Neoplasm; 0/Genetic Markers; 0/Tumor Markers, Biological

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  Prediction of biologically significant components from microarray data: Independently Consistent Exp...
Next Document:  Mining gene expression databases for association rules.