Current studentsExisting staffContact us
 

Classification of MALDI-MS imaging data of tissue microarrays using canonical correlation analysis based variable selection

Simple item page
dc.contributor.authorWinderbaum, L.
dc.contributor.authorKoch, I.
dc.contributor.authorMittal, P.
dc.contributor.authorHoffmann, P.
dc.date.issued2016
dc.descriptionFirst published: 9 May 2016 Link to a related website: https://digital.library.adelaide.edu.au/dspace/bitstream/2440/100545/2/hdl_100545.pdf, Open Access via Unpaywall
dc.description.abstractApplying MALDI-MS imaging to tissue microarrays (TMAs) provides access to proteomics data from large cohorts of patients in a cost- and time-efficient way, and opens the potential for applying this technology in clinical diagnosis. The complexity of these TMA data—high-dimensional low sample size—provides challenges for the statistical analysis, as classical methods typically require a nonsingular covariance matrix that cannot be satisfied if the dimension is greater than the sample size. We use TMAs to collect data from endometrial primary carcinomas from 43 patients. Each patient has a lymph node metastasis (LNM) status of positive or negative, which we predict on the basis of the MALDI-MS imaging TMA data. We propose a variable selection approach based on canonical correlation analysis that explicitly uses the LNM information. We apply LDA to the selected variables only. Our method misclassifies 2.3–20.9% of patients by leave-one-out cross-validation and strongly outperforms LDA after reduction of the original data with principle component analysis.
dc.description.statementofresponsibilityLyron Winderbaum, Inge Koch, Parul Mittal and Peter Hoffmann
dc.identifier.citationProteomics, 2016; 16(11-12):1731-1735
dc.identifier.doi10.1002/pmic.201500451
dc.identifier.issn1615-9853
dc.identifier.issn1615-9861
dc.identifier.orcidMittal, P. [0000-0003-0139-9757]
dc.identifier.orcidHoffmann, P. [0000-0002-6573-983X]
dc.identifier.urihttp://hdl.handle.net/2440/100545
dc.language.isoen
dc.publisherWiley-VCH Verlag
dc.rights© 2016 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim
dc.source.urihttp://dx.doi.org/10.1002/pmic.201500451
dc.subjectBioinformatics; Canonical correlation analysis; Classification; Endometrial cancer; MALDI-MS imaging; Variable ranking
dc.titleClassification of MALDI-MS imaging data of tissue microarrays using canonical correlation analysis based variable selection
dc.typeJournal article
pubs.publication-statusPublished

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
hdl_100545.pdf
Size:
818.61 KB
Format:
Adobe Portable Document Format
Description:
Accepted version
Download

Collections

IPAS publications