Pertinent background knowledge for learning protein grammars

Bryant, CH; Fredouille, DC; Wilson, A; Jayawickreme, CK; Jupe, S; Topp, S

Abstract

We are interested in using Inductive Logic Programming(ILP) to infer grammars representing sets of protein sequences. ILP takes as input both examples and background knowledge predicates. This work is a first step in optimising the choice of background knowledge predicates for predicting the function of proteins. We propose methods to obtain different sets of background knowledge. We then study the impact of these sets on inference results through a hard protein function inference task: the prediction of the coupling preference of GPCR proteins. All but one of the proposed sets of background knowledge are statistically shown to have positive impacts on the predictive power of inferred rules, either directly or through interactions with other sets. In addition, this work provides further confirmation, after the work of Muggleton et al. (2001) that ILP can help to predict protein functions.

Citation

Bryant, C., Fredouille, D., Wilson, A., Jayawickreme, C., Jupe, S., & Topp, S. (2006). Pertinent background knowledge for learning protein grammars. In J. Fürnkranz, T. Scheffer, & M. Spiliopoulou (Eds.), Machine learning: ECML 2006 (54-65). Berlin / Heidelberg, Germany: Springer. https://doi.org/10.1007/11871842_10

• Start Date: Sep 18, 2006
• End Date: Sep 22, 2006
• Publication Date: Sep 1, 2006
• Deposit Date: Feb 16, 2009
• Publicly Available Date: Feb 16, 2009
• Publisher: Springer
• Pages: 54-65
• Series Title: Lecture notes in artificial intelligence (subseries of Lecture notes in computer science)
• Series Number: 4212
• Book Title: Machine learning: ECML 2006
• ISBN: 9783540453758
• DOI: https://doi.org/10.1007/11871842_10
• Publisher URL: http://dx.doi.org/10.1007/11871842_10
• Additional Information: Paper originally presented at the 17th European Conference on Machine Learning in Berlin, Germany, September 18-22 2006