Improved technique for automated classification of protein Subcellular Location patterns in fluorescence microscope images

The genomic revolution promises a complete understanding of the mechanisms by which cells and tissues carry out their functions. As proteins are integral components of cell function, it is critical to understand their properties such as structure and localization. Knowledge of a protein's subcellular distribution can contribute to a complete understanding of its function. Processing of subcellular image sets is still mostly manual and it causes the process inefficient and error-prone. But in recent years, try to perform high-resolution; high-throughput analysis for ten thousands of expressed proteins in the many cell types and cellular conditions under which they may be found creates. In this review, we describe a systematic approach for interpreting protein subcellular distributions using modified threshold adjacency statistics (MTAS) set of Subcellular Location Features (SLF). Previous work that uses threshold adjacency statistics (TAS), introduces a set of Subcellular Location Features which are computed by counting the number of threshold pixels adjacent. But here a novel method has been used that determines a modified features set, to improve the recognition of protein subcellular location patterns in 2D fluorescence microscope images with high accuracy and high speed.