A multivariate spot filtering model for two‐dimensional gel electrophoresis

Abstract

Image segmentation plays an important role in the automatic analysis of protein spots in 2-DE. Using image segments representing protein spots, the amount of protein in each segment can be quantified, and corresponding segments can be matched and compared for multiple gels. However, the common presence of image segments caused by noise and unwanted artefacts highly disturb the analysis and comparison of the gels. Common sources of such artefacts are cracks in the gel surface, fingerprints, dust and other pollutions. It would be advantageous to remove these unwanted artefacts during or after the segmentation procedure. To achieve this task a multivariate spot filtering model is developed using image segments from a gel segmentation. Parameters in the model are based on texture, shape and intensity measurements of the image segments. The model successfully managed to separate segments caused by noise, artefacts and cracks from image segments representing true protein spots. The classification method used is discriminant partial least squares regression.

Impulse noise removal in two-dimensional electrophoresis images based on dome recognition

“…The wavelet filter (WF) we used is the undecimated discrete wavelet transform (UDWT), as implemented in the Rice Wavelet Toolbox (RWT, which is freely available from the web site http://dsp.rice.edu/software/rice-wavelet-toolbox) [6]. The parameters for the contourlet filter (CF) are set according to the work [7]. The results obtained by the proposed method are compared with that of the existing methods.…”

“…In common sense, impulse noise means salt-and-pepper noise and random-valued noise. In the traditional preprocess pipeline, they are preprocessed in advance and then other artifacts were dealt with in the next step [7]. In 2009, Cannistraci et al [3] states the following three goals of 2DE image denoising: i) to improve the identification of low intensity, yet significant spots; ii) to prevent the identification of misleading spots (artifacts), improving spot matching; ;iii) to estimate spot properties, like spot volume, more accurately.…”

Texture Classification of Proteins Using Support Vector Machines and Bio-inspired Metaheuristics

“…With respect to related work, the authors were not able to find any other work in the literature dealing with evolutionary computation in combination with texture analysis in 2D-electrophoresis images, while we did find one article describing a discriminant partial least squares regression (PLSR) method for spot filtering in 2D-electrophoresis [26]. The authors use a set of parameters to build a model based on texture, shape and intensity measurements using image segments from gel segmentation.…”

2D-PAGE Texture Classification using Support Vector Machines and Genetic Algorithms - An Hybrid Approach for Texture Image Analysis

“…With respect to related work, the authors were not able to find any other work in the literature handling with evolutionary computation in combination with texture analysis in 2Delectrophoresis images; however, one article describes a discriminant partial least squares regression (PLSR) method for spot filtering in 2Delectrophoresis (Rye and Alsberg, 2008). They use a set of parameters to build a model based on texture, shape and intensity measurements using image segments from gel segmentation.…”