The shape-descriptor for automated classification of binding-site geometries can be used as an additional tool complementing elaborate manual inspections.
In the next step, we will attempt to classify protein DNA complexes by using the conventional motif-based classification and the structural and functional properties-based classification of DNA binding proteins, and then predict their DNA-binding sites in proteins and identify common properties and rules that govern protein DNA recognition.
Tonikian et al. performed a large-scale characterization of PDZ binding specificities for 54 human and 28 worm PDZ domains [ 14], which allowed for an extended classification of their binding specificities.
These classification methods were primarily developed for the classification of odorant binding proteins in the mosquito genome.
The algorithm described here uses a scheme for the classification of odorant binding proteins on the basis of functional residues and Cys-pairing.
(C ) Classification of all binding models into non-repetitive sites (monomer), and sites with two, three or four similar subsequences (dimer, trimer and dimer of dimers, respectively).
In this work, we have used a pre-existing classification of protein protein binding modes provided by SCOPPI.
The classification of AR binding sites relative to genomic annotations (promoter/exomic/intronic/intergenic) and calculation of associated enrichment statistics were performed with RegionMiner tool and ElDorado database (Genomatix).
This demonstrated that a combination of amino acid periodicities as a feature vector optimizes the system for the classification of DNA/RNA-binding proteins.
By using the same method, one finds that, in order of prominence, the polarity, hydrophobicity, amino acid composition, and solvent accessibility play more prominent roles than other feature properties in the classification of lipid-binding protein (Lin et al. 2006c).
