Learning Rules for Protein Exposure (KUL)

Application domain: Protein Engineering
Further specification: Data set
Pointers: Contact Hendrik Blockeel Hendrik.Blockeel@cs.kuleuven.ac.be
Data complexity: 860 KB
Data format: interpretations (ICL/Claudien)


This application is very similar to the well-known protein secondary structure prediction problem. A protein is a long sequence of amino acids, that is somehow folded in 3-D space. Some parts of the sequence will be located at the surface of the 3-D shape formed by the protein (these are exposed), others are located at the inside (buried). The aim of the learning process is to predict which parts of a protein are exposed.

The background information is the same as the one available for the secondary structure prediction problem. The data themselves are the same as used in previous experiments by Holbrook et al. (1990).


  1. S.R. Holbrook, S.M. Muskal and S.H. Kim. Predicting surface exposure of amino acids from protein sequence. Protein Engineering, 3, 289-294. 1990.

back to index