| DOI | Resolve DOI: https://doi.org/10.1016/j.jmb.2012.10.014 |
|---|
| Author | Search for: Sternberg, M.J.E.; Search for: Tamaddoni-Nezhad, A.; Search for: Lesk, V.I.; Search for: Kay, E.; Search for: Hitchen, P.G.; Search for: Cootes, A.; Search for: Van Alphen, L.B.; Search for: Lamoureux, M.P.1; Search for: Jarrell, H.C.1; Search for: Rawlings, C.J.; Search for: Soo, E.C.2; Search for: Szymanski, C.M.; Search for: Dell, A.; Search for: Wren, B.W.; Search for: Muggleton, S.H. |
|---|
| Affiliation | - National Research Council of Canada. NRC Institute for Biological Sciences
- National Research Council of Canada. NRC Institute for Marine Biosciences
|
|---|
| Format | Text, Article |
|---|
| Subject | glucuronosyltransferase; heptose guanosyltransferase; heptose kinase; methyltransferase; sedoheptulose isomerase; sugar transferase; unclassified drug; Campylobacter jejuni; DNA microarray; gene expression; gene function; knockout gene; machine learning; serotype; Artificial Intelligence; Bacterial Capsules; Biosynthetic Pathways; Campylobacter jejuni; Gene Knockout Techniques; Genes, Bacterial; Glycomics; Logic; Metabolomics; Models, Biological; Molecular Sequence Annotation; Mutation; Oligonucleotide Array Sequence Analysis; Phenotype; Polysaccharides, Bacterial; Systems Biology; Campylobacter jejuni |
|---|
| Abstract | Increasingly, experimental data on biological systems are obtained from several sources and computational approaches are required to integrate this information and derive models for the function of the system. Here, we demonstrate the power of a logic-based machine learning approach to propose hypotheses for gene function integrating information from two diverse experimental approaches. Specifically, we use inductive logic programming that automatically proposes hypotheses explaining the empirical data with respect to logically encoded background knowledge. We study the capsular polysaccharide biosynthetic pathway of the major human gastrointestinal pathogen Campylobacter jejuni. We consider several key steps in the formation of capsular polysaccharide consisting of 15 genes of which 8 have assigned function, and we explore the extent to which functions can be hypothesised for the remaining 7. Two sources of experimental data provide the information for learning - the results of knockout experiments on the genes involved in capsule formation and the absence/presence of capsule genes in a multitude of strains of different serotypes. The machine learning uses the pathway structure as background knowledge. We propose assignments of specific genes to five previously unassigned reaction steps. For four of these steps, there was an unambiguous optimal assignment of gene to reaction, and to the fifth, there were three candidate genes. Several of these assignments were consistent with additional experimental results. We therefore show that the logic-based methodology provides a robust strategy to integrate results from different experimental approaches and propose hypotheses for the behaviour of a biological system. © 2012 Elsevier Ltd. |
|---|
| Publication date | 2013 |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| NPARC number | 21269810 |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | c567c96c-e878-4326-b202-05390750300b |
|---|
| Record created | 2013-12-13 |
|---|
| Record modified | 2020-04-22 |
|---|
