Enhanced analytical power of SDS-PAGE using machine learning algorithms

We aim to demonstrate that a complex plant tissue protein mixture can be reliably "fingerprinted" by running conventional 1-D SDS-PAGE in bulk and analyzing gel banding patterns using machine learning methods. An unsupervised approach to filter noise and systemic biases (principal component analysis) was coupled to state-of-the-art supervised methods for classification (support vector machines) and attribute ranking (ReliefF) to improve tissue discrimination, visualization, and recognition of important gel regions.