ECCB 2002 Poster sorted by: Author | Number

Next | Previous poster (in order of the view you have selected)
Title: Generating Rules to Predict P. gingivalis Protein Functional Class from Sequence
P5
Al-Shahib, A. (1); Gilbert, David (1); Saqi, M. (2)

alshahib@dcs.gla.ac.uk, drg@brc.dcs.gla.ac.uk, saqi@qmul.ac.uk
(1) Bioinformatics Research Center, Department of Computing Science, University of Glasgow, Scotland UK; (2) St. Bartholemews and the Royal London School of Medicine and Dentistry, University of London, UK

One of the most exciting challenges in bioinformatics today is annotation of biochemical functions of organisms. In humans it is reported that approximately 30% of our genes are orphans, which is somewhat worrying for scientists. One of the main obstacles in attempting to annotate these genes ist the appearance of uncertainty and low confidence levels in the sequence comparison methods. There is therefore a need to computationally lower this level of uncertainty and thus provide a higher confidence level for gene annotation.

Here, we have used machine learning approach to predict protein functional class from sequence. Our database consists of data from the gum disease causing bacterial pathogen: P. gingivalis. We have used inductive logic programming and decision trees (ACE) to reason over the P. gingivalis data. Our rules have provided biologically important information regarding the P. gingivalis bacterium as well as providing an insight to further experiment in this data mining technique on other organisms. The machine learning approach for predicting protein functional classes from sequences is only the first step towards tacking the obstacle of uncertainty in functional genomics.
This work is part of a PhD project funded by the EPSRC.
[1] Marcotte, M., Pellegrine, M., Thompson, M.J., Yeates, T.O., Eisenberg, D. (1999). A combined algorithm for genome wide prediction of protein function. Nature, 402, 83-86.
[2] Blockeel, H., Dahaspe, L., Demoen, B., Janssens, G., Ramon, J., Vandecasteele, H.. Executing Query Packs in ILP. Proceedings of the 10th International Conference on Inductive Logic Programming, Lecture Notes in Artificial Intelligence Vol. 1866, Springer, pp. 60-77.