New approach based on fuzzy logic and principal component analysis for the classification of two-dimensional maps in health and disease. Application to lymphomas.

摘要: Two-dimensional (2D) electrophoresis is the most wide spread technique for separation of proteins in biological systems. This produces 2D maps high complexity, which creates difficulties comparison different samples. The method proposed this paper can be summarised four steps: (a) digitalisation image; (b) fuzzyfication digitalised map order to consider variability two-dimensional electrophoretic separation; (c) decoding by principal component analysis previously obtained fuzzy maps, reduce system dimensionality; (d) classification (linear discriminant analysis), separate samples contained dataset according classes present said dataset. was applied a constituted eight samples: belonging healthy human lymph-nodes and deriving from non-Hodgkin lymphomas. amount original governed s parameter. larger value, more resulting transformed map. effect parameter investigated, optimal results being 5 1.75 2.25. Principal linear allowed two without any misclassification.  2003 Elsevier B.V. All rights reserved.