Find Key m/z Values in Predication of Mass Spectrometry Cancer Data

Authors:
Yihui Liu;Li Bai
Affiliations:
School of Computer Science and Information Technology, Shandong Institute of Light Industry, Jinan, China 250353;School of Computer Science, University of Nottingham, Nottingham, UK NG8 1BB
Venue:
ICIC '08 Proceedings of the 4th international conference on Intelligent Computing: Advanced Intelligent Computing Theories and Applications - with Aspects of Theoretical and Methodological Issues
Year:
2008

Citing 7
Cited 0

A Theory for Multiresolution Signal Decomposition: The Wavelet Representation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Adaptation in natural and artificial systems

Adaptation in natural and artificial systems
Tackling Real-Coded Genetic Algorithms: Operators and Tools for Behavioural Analysis

Artificial Intelligence Review
A real-coded genetic algorithm for training recurrent neural networks

Neural Networks
Ovarian cancer identification based on dimensionality reduction for high-throughput mass spectrometry data

Bioinformatics
Cancer Classification Based on Mass Spectrometry

WILF '07 Proceedings of the 7th international workshop on Fuzzy Logic and Applications: Applications of Fuzzy Sets Theory
Feature extraction for mass spectrometry data

LSMS'07 Proceedings of the 2007 international conference on Life System Modeling and Simulation

Quantified Score

Hi-index	0.00

Visualization

Abstract

To find the significant biomarker is very important in detecting protein patterns associated with diseases. In this study multilevel wavelet analysis is performed on high dimensional mass spectrometry data to extract the detail coefficients, which are used to detect the difference between cancer tissue and normal tissue. In order to find the key m/z values of mass spectra, wavelet detail information is reconstructed based on orthogonal wavelet detail coefficients, and genetic algorithm is further employed to select best features from the reconstructed detail information. Finally the corresponding significant m/z values of mass spectra are identified using the optimized detail features.