Feature extraction for cancer prediction by tensor decomposition of 1D protein expression levels

Ivica Kopriva, Ante Jukić, Andrzej Cichocki

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)

Abstract

Tensor decomposition approach to feature extraction from one-dimensional data samples is presented. One-dimensional data samples are transformed into matrices of appropriate dimensions that are further concatenated into a third order tensor. This tensor is factorized according to the Tucker-2 model by means of the higher-order-orthogonal iteration (HOOI) algorithm. Derived method is validated on publicly available and well known datasets comprised of low-resolution mass spectra of cancerous and non-cancerous samples related to ovarian and prostate cancers. The method respectively achieved, in 200 independent two-fold cross-validations, average sensitivity of 96.8% (sd 2.9%) and 99.6% (sd 1.2%) and average specificity of 95.4% (sd 3.5%) and 98.7% (sd 2.9%). Due to the widespread significance of mass spectrometry for monitoring protein expression levels and cancer prediction it is conjectured that presented feature extraction scheme can be of practical importance.

Original languageEnglish
Title of host publicationProceedings of the 2nd IASTED International Conference on Computational Bioscience, CompBio 2011
Pages277-283
Number of pages7
DOIs
Publication statusPublished - 2011
Externally publishedYes
Event2nd International Conference on Computational Bioscience, CompBio 2011 - Cambridge, United Kingdom
Duration: 11 Jul 201113 Jul 2011

Publication series

NameProceedings of the 2nd IASTED International Conference on Computational Bioscience, CompBio 2011

Conference

Conference2nd International Conference on Computational Bioscience, CompBio 2011
Country/TerritoryUnited Kingdom
CityCambridge
Period11/07/1113/07/11

Keywords

  • Cancer prediction
  • Feature extraction
  • Mass spectrometry
  • Pattern recognition
  • Tensor decomposition

Fingerprint

Dive into the research topics of 'Feature extraction for cancer prediction by tensor decomposition of 1D protein expression levels'. Together they form a unique fingerprint.

Cite this