File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Classification between normal and tumor tissues based on the pair-wise gene expression ratio

TitleClassification between normal and tumor tissues based on the pair-wise gene expression ratio
Authors
KeywordsAdipsin
Colon cancer
Hepsin
Monocyte-derived neutrophil-activating protein
Prostate cancer
Issue Date2004
PublisherBioMed Central Ltd. The Journal's web site is located at http://www.biomedcentral.com/bmccancer/
Citation
Bmc Cancer, 2004, v. 4 How to Cite?
AbstractBackground: Precise classification of cancer types is critically important for early cancer diagnosis and treatment. Numerous efforts have been made to use gene expression profiles to improve precision of tumor classification. However, reliable cancer-related signals are generally lacking. Method: Using recent datasets on colon and prostate cancer, a data transformation procedure from single gene expression to pair-wise gene expression ratio is proposed. Making use of the internal consistency of each expression profiling dataset this transformation improves the signal to noise ratio of the dataset and uncovers new relevant cancer-related signals (features). The efficiency in using the transformed dataset to perform normal/tumor classification was investigated using feature partitioning with informative features (gene annotation) as discriminating axes (single gene expression or pair-wise gene expression ratio). Classification results were compared to the original datasets for up to 10-feature model classifiers. Results: 82 and 262 genes that have high correlation to tissue phenotype were selected from the colon and prostate datasets respectively. Remarkably, data transformation of the highly noisy expression data successfully led to lower the coefficient of variation (CV) for the within-class samples as well as improved the correlation with tissue phenotypes. The transformed dataset exhibited lower CV when compared to that of single gene expression. In the colon cancer set, the minimum CV decreased from 45.3% to 16.5%. In prostate cancer, comparable CV was achieved with and without transformation. This improvement in CV, coupled with the improved correlation between the pair-wise gene expression ratio and tissue phenotypes, yielded higher classification efficiency, especially with the colon dataset - from 87.1% to 93.5%. Over 90% of the top ten discriminating axes in both datasets showed significant improvement after data transformation. The high classification efficiency achieved suggested that there exist some cancer-related signals in the form of pair-wise gene expression ratio. Conclusion: The results from this study indicated that: 1) in the case when the pair-wise expression ratio transformation achieves lower CV and higher correlation to tissue phenotypes, a better classification of tissue type will follow. 2) the comparable classification accuracy achieved after data transformation suggested that pair-wise gene expression ratio between some pairs of genes can identify reliable markers for cancer. © 2004 Yap et al; licensee BioMed Central Ltd.
Persistent Identifierhttp://hdl.handle.net/10722/44574
ISSN
2021 Impact Factor: 4.638
2020 SCImago Journal Rankings: 1.358
PubMed Central ID
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorYap, YLen_HK
dc.contributor.authorZhang, XWen_HK
dc.contributor.authorLing, MTen_HK
dc.contributor.authorWang, XHen_HK
dc.contributor.authorWong, YCen_HK
dc.contributor.authorDanchin, Aen_HK
dc.date.accessioned2007-10-30T06:04:41Z-
dc.date.available2007-10-30T06:04:41Z-
dc.date.issued2004en_HK
dc.identifier.citationBmc Cancer, 2004, v. 4en_HK
dc.identifier.issn1471-2407en_HK
dc.identifier.urihttp://hdl.handle.net/10722/44574-
dc.description.abstractBackground: Precise classification of cancer types is critically important for early cancer diagnosis and treatment. Numerous efforts have been made to use gene expression profiles to improve precision of tumor classification. However, reliable cancer-related signals are generally lacking. Method: Using recent datasets on colon and prostate cancer, a data transformation procedure from single gene expression to pair-wise gene expression ratio is proposed. Making use of the internal consistency of each expression profiling dataset this transformation improves the signal to noise ratio of the dataset and uncovers new relevant cancer-related signals (features). The efficiency in using the transformed dataset to perform normal/tumor classification was investigated using feature partitioning with informative features (gene annotation) as discriminating axes (single gene expression or pair-wise gene expression ratio). Classification results were compared to the original datasets for up to 10-feature model classifiers. Results: 82 and 262 genes that have high correlation to tissue phenotype were selected from the colon and prostate datasets respectively. Remarkably, data transformation of the highly noisy expression data successfully led to lower the coefficient of variation (CV) for the within-class samples as well as improved the correlation with tissue phenotypes. The transformed dataset exhibited lower CV when compared to that of single gene expression. In the colon cancer set, the minimum CV decreased from 45.3% to 16.5%. In prostate cancer, comparable CV was achieved with and without transformation. This improvement in CV, coupled with the improved correlation between the pair-wise gene expression ratio and tissue phenotypes, yielded higher classification efficiency, especially with the colon dataset - from 87.1% to 93.5%. Over 90% of the top ten discriminating axes in both datasets showed significant improvement after data transformation. The high classification efficiency achieved suggested that there exist some cancer-related signals in the form of pair-wise gene expression ratio. Conclusion: The results from this study indicated that: 1) in the case when the pair-wise expression ratio transformation achieves lower CV and higher correlation to tissue phenotypes, a better classification of tissue type will follow. 2) the comparable classification accuracy achieved after data transformation suggested that pair-wise gene expression ratio between some pairs of genes can identify reliable markers for cancer. © 2004 Yap et al; licensee BioMed Central Ltd.en_HK
dc.format.extent474069 bytes-
dc.format.extent2104 bytes-
dc.format.extent2603 bytes-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypetext/plain-
dc.format.mimetypetext/plain-
dc.languageengen_HK
dc.publisherBioMed Central Ltd. The Journal's web site is located at http://www.biomedcentral.com/bmccancer/en_HK
dc.relation.ispartofBMC Canceren_HK
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.subjectAdipsinen_HK
dc.subjectColon canceren_HK
dc.subjectHepsinen_HK
dc.subjectMonocyte-derived neutrophil-activating proteinen_HK
dc.subjectProstate canceren_HK
dc.subject.meshColonic Neoplasms - genetics - pathologyen_HK
dc.subject.meshGene Expressionen_HK
dc.subject.meshGene Expression Profiling - methodsen_HK
dc.subject.meshOligonucleotide Array Sequence Analysis - methodsen_HK
dc.subject.meshProstatic Neoplasms - genetics - pathologyen_HK
dc.titleClassification between normal and tumor tissues based on the pair-wise gene expression ratioen_HK
dc.typeArticleen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=1471-2407&volume=4&spage=72&epage=&date=2004&atitle=Classification+between+normal+and+tumor+tissues+based+on+the+pair-wise+gene+expression+ratioen_HK
dc.identifier.emailLing, MT:patling@hkucc.hku.hken_HK
dc.identifier.emailWong, YC:ycwong@hkucc.hku.hken_HK
dc.identifier.authorityLing, MT=rp00449en_HK
dc.identifier.authorityWong, YC=rp00316en_HK
dc.description.naturepublished_or_final_versionen_HK
dc.identifier.doi10.1186/1471-2407-4-72en_HK
dc.identifier.pmid15469618-
dc.identifier.pmcidPMC524507-
dc.identifier.scopuseid_2-s2.0-13144300125en_HK
dc.identifier.hkuros95163-
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-13144300125&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume4en_HK
dc.identifier.isiWOS:000224939000001-
dc.publisher.placeUnited Kingdomen_HK
dc.identifier.scopusauthoridYap, YL=7005551975en_HK
dc.identifier.scopusauthoridZhang, XW=7410270641en_HK
dc.identifier.scopusauthoridLing, MT=7102229780en_HK
dc.identifier.scopusauthoridWang, XH=7501854829en_HK
dc.identifier.scopusauthoridWong, YC=7403041798en_HK
dc.identifier.scopusauthoridDanchin, A=7103235597en_HK
dc.identifier.citeulike1077496-
dc.identifier.issnl1471-2407-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats