An inductive logic programming approach to validate Hexose binding biochemical knowledge

Authors:
Houssam Nassif;Hassan Al-Ali;Sawsan Khuri;Walid Keirouz;David Page
Affiliations:
Department of Computer Sciences and Department of Biostatistics and Medical Informatics, University of Wisconsin-Madison;Department of Biochemistry and Molecular Biology, University of Miami Miller School of Medicine, Florida;Center for Computational Science, University of Miami and The Dr. John T. Macdonald Foundation Department of Human Genetics, University of Miami Miller School of Medicine, Florida;Department of Computer Science, American University of Beirut, Lebanon;Department of Computer Sciences and Department of Biostatistics and Medical Informatics, University of Wisconsin-Madison
Venue:
ILP'09 Proceedings of the 19th international conference on Inductive logic programming
Year:
2009

Citing 6
Cited 2

Pharmacophore Discovery Using the Inductive Logic Programming System PROGOL

Machine Learning - Special issue on applications of machine learning and the knowledge discovery process
Machine Learning

Machine Learning
Carcinogenesis Predictions Using ILP

ILP '97 Proceedings of the 7th International Workshop on Inductive Logic Programming
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
View learning for statistical relational learning: with an application to mammography

IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
An integrated approach to learning bayesian networks of rules

ECML'05 Proceedings of the 16th European conference on Machine Learning

Uncovering age-specific invasive and DCIS breast cancer rules using inductive logic programming

Proceedings of the 1st ACM International Health Informatics Symposium
Reducing examples in relational learning with bounded-treewidth hypotheses

NFMCP'12 Proceedings of the First international conference on New Frontiers in Mining Complex Patterns

Quantified Score

Hi-index	0.00

Visualization

Abstract

Hexoses are simple sugars that play a key role inmany cellular pathways, and in the regulation of development and disease mechanisms. Current protein-sugar computational models are based, at least partially, on prior biochemical findings and knowledge. They incorporate different parts of these findings in predictive black-box models. We investigate the empirical support for biochemical findings by comparing Inductive Logic Programming (ILP) induced rules to actual biochemical results.We mine the Protein DataBank for a representative data set of hexose binding sites, non-hexose binding sites and surface grooves. We build an ILP model of hexose-binding sites and evaluate our results against several baseline machine learning classifiers. Our method achieves an accuracy similar to that of other black-box classifiers while providing insight into the discriminating process. In addition, it confirms wet-lab findings and reveals a previously unreported Trp-Glu amino acids dependency.