Discovering 3-d Protein Structures for Optimal Structure Alignment

Analyzing three dimensional protein structures is a very important task in molecular biology. Nowadays, the solution for protein structures often stems from the use of the state-of-the-art technologies such as nuclear magnetic resonance (NMR) spectroscopy techniques or X-Ray crystallography etc. as seen in the increasing number of PDB [34] entries. Protein Data Bank is a database of 3D structural data of large biological molecules, such as proteins and nucleic acids. It was proved that structurally similar proteins tend to have similar functions even if their amino acid sequences are not similar to one another. Thus, it is very important to find proteins with similar structures (even in part) from the growing database to analyze protein functions. Yang et al. [47] exploited machine learning techniques including variants of Self-Organizing Global Ranking, a decision tree, and support vector machine (SVM) algorithms to predict the tertiary structure of transmembrane proteins. Hecker et al. [14] developed a state of the art protein disorder predictor and tested it on a large protein disorder dataset