Protein Folding Class Predictor for SCOP: Approach Based on Global Descriptors

This workdemonstrates newtechniques developed for the prediction of protein folding class in the context of the most comprehensiveStructural Classification of Proteins (SCOP). The prediction method uses global descriptors of a protein in terms of the physical, chemical and structural properties of its constituent aminoacids. Neural networksare utilized to combine these descriptors in a specific wayto discriminate membersof a given folding class from membersof all other classes. It is shownthat a specific amino acid’s properties workcompletely differently on different folding classes. This creates the possibility of finding an individual set of descriptors that works best on a particular folding class.

• Type: Conference
• Year: 1997
• Where: ISMB
• Authors: Inna Dubchak, Ilya B. Muchnik, Sung-Hou Kim
• Keywords: Computational Biology, Folding Class, ISMB 1997, Particular Folding Class, Protein Folding Class