A Protocol to Detect Local Affinities Involved in Proteins Distant Interactions

The tridimensional structure of a protein is constrained or stabilized by some local interactions between distant residues of the protein, such as disulfide bonds, electrostatic interactions, hydrogen links, Wan Der Waals forces, etc. The correct prediction of such contacts should be an important step towards the whole challenge of tridimensional structure prediction. The in silico prediction of the disulfide connectivity has been widely studied: most results were based on few amino-acids around bonded and non-bonded cysteines, which we call local environments of bonded residues. In order to evaluate the impact of such local information onto residue pairing, we propose a machine learning based protocol, independent from the type of contact, to detect affinities between local environments which would contribute to residues pairing. This protocol requires that learning methods are able to learn from examples corrupted by class-conditional classification noise. To this end, we propose an...

• Type: Conference
• Year: 2007
• Where: BIBM
• Authors: Christophe Nicolas Magnan, Cécile Capponi, François Denis
• Keywords: BIBM 2007, Bioinformatics, Disulfide, Local Environments, Tridimensional Structure