Prediction of Nuclear Localization Signals by HMM

The transport of nuclear proteins is a very important step for the maintenance of life. Most proteins that function in the nucleus are moved through the nuclear envelope that is penetrated by the nuclear pores. The nuclear pore is formed by a large, complex structure known as the nuclear pore complex (NPC). The NPC is a major gateway for mediating ions, small molecules, proteins, RNAs, and ribonucleoprotein particles in and out of the nucleus. The nuclear proteins are transported to the nucleus via the NPC, if they contain nuclear localization signals (NLSs). NLS was first found in SV40 T antigen as a short cluster of five contiguous positively charged residues in the sequence 126Pro-Lys-Lys-Lys-Arg-Lys-Val132. A family of simple NLSs of this type was generally characterized by one short basic stretch of sequence (4-8 residues) containing several lysine and arginine residues. Another typical NLS, known as bipartite NLS motif contains two interdependent positively charged clusters separated by a mutation tolerant linker region of 10-12 amino acids (Table 1). Both variants of the NLS are recognized by importin alpha family. The precise locations of NLSs within the amino acid sequence of the nuclear proteins are not regular unlike other localization signal peptides.