3D protein model assessment using geometric and biological features

Automatic prediction of protein three-dimensional structures from its amino acid sequence has become one of the most important researched fields in bioinformatics. With that increases the importance of determining the quality of these protein models. Protein three-dimensional structure evaluation is a complex problem in computational structure biology. We attempt to solve this problem using SVM and information from both sequence and structure of the protein. The goal is to generate a machine that understands structures from PDB and when given a new model, predicts whether it belongs to the same class as the PDB structures or not (correct or incorrect protein model). Here we show one such machine; results appear promising for further analysis. For the purpose of reducing computational overhead multiprocessor environment and basic feature selection method is used.