Dimensionality Reduction for Mass Spectrometry Data

Authors:
Yihui Liu
Affiliations:
School of Computer Science and Information Technology, Shandong Institute of Light Industry, Jinan, Shandong, 250353, China
Venue:
ADMA '07 Proceedings of the 3rd international conference on Advanced Data Mining and Applications
Year:
2007

Citing 3
Cited 0

A Theory for Multiresolution Signal Decomposition: The Wavelet Representation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Microarrays for an Integrative Genomics

Microarrays for an Integrative Genomics
Ovarian cancer identification based on dimensionality reduction for high-throughput mass spectrometry data

Bioinformatics

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper multilevel wavelet analysis is performed for high dimensional mass spectrometry data. A set of wavelet approximation coefficients at different scale is used to characterize the features of mass spectrometry data. Approximation coefficients compress mass spectrometry data and act as "fingerprint" of mass spectrometry data. Support vector machine is used to classify the different tissue based on these wavelet features. 2 and 3 fold cross validation experiments are performed on 2 datasets based on approximation coefficients at 1st, 2ndand 3rdlevel decomposition respectively. A highly competitive accuracy in comparison to the best performance of other kinds of classification models is achieved.