Machine Learnable Fold Space Representation based on Residue Cluster Classes

• We implemented a vectorial representation of residues contacts
• We implemented an efficient statistical test for machine-learnable data
• Our vectorial model reproduces protein packing
• A predictor is trained to effectively reproduce CATH and SCOP classifications
• Our predictor automatically identified inconsistent classification in CATH and SCOP

MotivationProtein fold space is a conceptual framework where all possible protein folds exist and ideas about protein structure, function and evolution may be analyzed. Classification of protein folds in this space is commonly achieved by using similarity indexes and/or machine learning approaches, each with different limitations.ResultsWe propose a method for constructing a compact vector space model of protein fold space by representing each protein structure by its residues local contacts. We developed an efficient method to statistically test for the separability of points in a space and showed that our protein fold space representation is learnable by any machine-learning algorithm.AvailabilityAn API is freely available at https://code.google.com/p/pyrcc/.

Figure optionsDownload as PowerPoint slide