Extracting Discriminant Patterns in Two-Dimensional Gel Images:An Application to Neuroproteomics

The proteomic approach may be extremely useful when searching for the causes of variations in the protein content of cells and of biological fluids associated with the development of various diseases such as neurodegenerative disorders. Today, two-dimensional gel electrophoresis (2DE) is still widely used as method of choice in proteomics for its ability to analyze many proteins simultaneously yielding a global view of protein expression. However, the automatic extraction of information from gel images is still a challenging task. In this paper, we propose a computational strategy to the aim of identifying patterns that are representative of a clinical status. The method was applied to an experimental protocol including two different clinical groups of amyotrophic lateral sclerosis (ALS) and peripheral neuropathy patients: 32 2DE maps generated from cerebrospinal fluid (24 pathological and 8 control subjects) were processed. Quantitative image descriptors were extracted to describe each image and dealt with the dimension reduction technique of local tangent space alignment (LTSA). The discovered low-dimensional structure reveals clear discrimination between diseased and control subjects, showing the informativeness of the adopted descriptors and providing the bases for classification of this kind of samples.BioMed@POLIMI Proc 1st Workshop on the Life Sciences at Politecnico di Milano, Milano, Nov. 2010