PLpred              Identification and Classification of PLASTID proteins
PLASTIDS are characteristic plant cell organelles that perform essential biosynthetic and metabolic functions. These include photosynthetic carbon fixation, and the synthesis of amino acids, fatty acids, starch and secondary metabolites such as pigments. On the basis of their structure, pigment composition (colour), metabolism and function, PLASTIDS are classified as chloroplasts in photosynthetically active tissues, chromoplasts in fruits and petals, amyloplasts in roots, etioplasts in dark-grown seedlings and elaioplasts that are found in the seed endosperm.
Although plastids are of significant biological interest, our current understanding of the metabolite functions and capacities of different plastid types is still limited. However, Proteomics is a powerful approach to map the complete set of plastid proteins and to infer plastid-type specific metabolite functions, only a few proteomic approaches have been reported. Besides time consuming, the experimental approaches face several other constraints, for example, the chloroplast proteome analysis is nearing saturation because the detection of new proteins is constrained by highly abundant photosynthetic proteins that dominate the proteome of photosynthetically active chloroplasts. To circumvent these constraints and to increase proteome coverage, the development of highly efficient computational prediction tools is another complementary approach to provide useful global information about the possible evolution of the plastid proteome. PLpred is an attempt in this direction which is a Support Vector Machine (SVM) based two-phase prediction tool for identifying as well as classifying the plastid proteins.
Various features of a protein sequence viz. Amino acid composition, Dipeptide composition and Pseudo Amino Acid Composition were exploited in the development of this prediction method. Secondly, the similarity search-based PSI-BLAST module was also developed (See paper for details.). Conclusively, these modules have been made available on this server to the research community for real time identification and classification of plastid proteins.