Pertinent background knowledge for learning protein grammars

Authors:
Christopher H. Bryant;Daniel C. Fredouille;Alex Wilson;Channa K. Jayawickreme;Steven Jupe;Simon Topp
Affiliations:
School of Computing, The Robert Gordon University, Aberdeen, UK;School of Computing, The Robert Gordon University, Aberdeen, UK;School of Computing, Division of Mathematics and Statistics, The Robert Gordon University, Aberdeen, UK;Discovery Research Biology, Durham;Department of Bioinformatics, Stevenage, UK;Department of Bioinformatics, Harlow, UK
Venue:
ECML'06 Proceedings of the 17th European conference on Machine Learning
Year:
2006

Citing 5
Cited 2

Theories for mutagenicity: a study in first-order and feature-based induction

Artificial Intelligence - Special volume on empirical methods
Discovering Patterns and Subfamilies in Biosequences

Proceedings of the Fourth International Conference on Intelligent Systems for Molecular Biology
Verbumculus and the discovery of unusual words

Journal of Computer Science and Technology - Special issue on bioinformatics
Applying inductive logic programming to predicting gene function

AI Magazine
Prediction of the coupling specificity of GPCRs to four families of G-proteins using hidden Markov models and artificial neural networks

Bioinformatics

An ILP Refinement Operator for Biological Grammar Learning

Inductive Logic Programming
L-Modified ILP Evaluation Functions for Positive-Only Biological Grammar Learning

ILP '08 Proceedings of the 18th international conference on Inductive Logic Programming

Quantified Score

Hi-index	0.00

Visualization

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.