Feature Selection on High Throughput SELDI-TOF Mass-Spectrometry Data for Identifying Biomarker Candidates in Ovarian and Prostate Cancer

Author

Plant, Claudia ; Osl, Melanie ; Tilg, Bernhard ; Baumgartner, Christian

Author_Institution

Inst. of Biomed. Eng., Univ. of Health Sci., Biomed. Informatics & Technol., Tirol

fYear

2006

fDate

Dec. 2006

Firstpage

174

Lastpage

179

Abstract

High-throughput mass-spectrometry screening has the potential of superior results in detecting early stage cancer than traditional biomarkers. Proteomic data poses novel challenges for data mining, especially concerning the curse of dimensionality. In this paper, we present a 3-step feature selection framework combining the advantages of efficient filter and effective wrapper techniques. We demonstrate the performance of our framework on two SELDI-TOF-MS data sets for identifying biomarker candidates in ovarian and prostate cancer

Keywords

biology computing; cancer; data mining; feature extraction; mass spectroscopy; proteins; SELDI-TOF mass-spectrometry data; biomarker candidates; data mining; early stage cancer detection; feature selection; high-throughput mass-spectrometry screening; ovarian cancer; prostate cancer; proteomic data; Algorithm design and analysis; Biomarkers; Cancer detection; Data mining; Filters; Prostate cancer; Proteins; Proteomics; Robotics and automation; Throughput;

fLanguage

English

Publisher

ieee

Conference_Titel

Data Mining Workshops, 2006. ICDM Workshops 2006. Sixth IEEE International Conference on

Conference_Location

Hong Kong

Print_ISBN

0-7695-2702-7

Type

conf

DOI

10.1109/ICDMW.2006.80

Filename

4063620