Image-Based Human Protein Subcellular Location Prediction Using Local Tetra Patterns Descriptor

Protein subcellular location has a huge positive influence on understanding protein function. In the past decades, many image-based automated approaches have been published for predicting protein subcellular location. However, in the reported literatures, there is a common deficiency for diverse prediction models in capturing local information of interest region of image. It motivates us to propose a novel approach by employing local feature descriptor named the Local Tetra Patterns (LTrP). In this paper, local features together with global features were fed to support vector machine to train chain classifiers, which can deal with multi-label datasets by using problem transformation pattern. To verify the validity of our approach, three different experiments were conducted based on the same benchmark dataset. The results show that the performance of the classification with LTrP descriptor not only captured more local information in interest region of images but also contributed to the improvement of prediction precision since the local descriptor is encoded along horizontal and vertical directions by LTrP. By applying the new approach, a more accurate classifier of protein subcellular location can be modeled, which is crucial to screen cancer biomarkers and research pathology mechanisms.