Premium
Multivariate analysis approach to the plasma protein profile of patients with advanced colorectal cancer
Author(s) -
Ragazzi Eugenio,
Pucciarelli Salvatore,
Seraglia Roberta,
Molin Laura,
Agostini Marco,
Lise Mario,
Traldi Pietro,
Nitti Donato
Publication year - 2006
Publication title -
journal of mass spectrometry
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.475
H-Index - 121
eISSN - 1096-9888
pISSN - 1076-5174
DOI - 10.1002/jms.1113
Subject(s) - linear discriminant analysis , chemistry , multivariate analysis , principal component analysis , colorectal cancer , multivariate statistics , medicine , mass spectrometry , matrix assisted laser desorption/ionization , cluster (spacecraft) , cancer , gastroenterology , oncology , chromatography , desorption , artificial intelligence , statistics , adsorption , mathematics , organic chemistry , computer science , programming language
The aim of the present study was to identify the pattern of plasma protein species of interest as markers of colorectal cancer (CRC). Using matrix‐assisted laser desorption/ionization‐mass spectrometry (MALDI‐MS), the plasma protein profile was determined in nine stage IV CRC patients (study group) and nine clean‐colon healthy subjects (control group). Multivariate analysis methods were employed to identify distinctive disease patterns at protein spectrum. In the study and control groups, cluster analysis (CA) on the complete MALDI‐MS spectra plasma protein profile showed a distinction between CRC patients and healthy subjects, thus allowing the identification of the most discriminating ionic species. Principal component analysis (PCA) and linear discriminant analysis (LDA) yielded similar grouping results. LDA with leave‐one‐out cross validation achieved a correct classification rate of 89% in both the patients and the healthy subjects. Copyright © 2006 John Wiley & Sons, Ltd.