Functional discrimination of gene expression patterns using ILP

Liviu Badea. In Stan Matwin, editor, Work-in-Progress Track at the 12th International Conference on Inductive Logic Programming, July 2002.

Abstract

The ever-growing amount of experimental data in molecular biology and genetics requires more and more sophisticated knowledge discovery tools. We argue that the complexity of the domain makes ILP an ideal candidate, due to its ability to deal with expressive background theories. We illustrate our claim by using an ILP learner to induce functional discrimination rules between genes studied using microarrays and found to by differentially expressed in three recently discovered subtypes of adenocarcinoma (AC) of the lung [Garber et al. 2001]. The dis-crimination rules involve functional annotations in terms of the Gene Ontology (GO). While most of the lower levels of gene expression data (pre)processing have been automated, our work can be seen as a step toward automating the higher level functional analysis of the data. In fact, ILP could play an even more important role in gene expression analysis, as the existing functional annotations will become more sophisticated.

BibTeX entry.

Functional discrimination of gene expression patterns using ILP

Abstract

Other publications