Classifying genes to the correct Gene Ontology Slim term in Saccharomyces cerevisiae using neighbouring genes with classification learning

Abstract

BackgroundThere is increasing evidence that gene location and surrounding genes influence the functionality of genes in the eukaryotic genome. Knowing the Gene Ontology Slim terms associated with a gene gives us insight into a gene's functionality by informing us how its gene product behaves in a cellular context using three different ontologies: molecular function, biological process, and cellular component. In this study, we analyzed if we could classify a gene in Saccharomyces cerevisiae to its correct Gene Ontology Slim term using information about its location in the genome and information from its nearest-neighbouring genes using classification learning.ResultsWe performed experiments to establish that the MultiBoostAB algorithm using the J48 classifier could correctly classify Gene Ontology Slim terms of a gene given information regarding the gene's location and information from its nearest-neighbouring genes for training. Different neighbourhood sizes were examined to determine how many nearest neighbours should be included around each gene to provide better classification rules. Our results show that by just incorporating neighbour information from each gene's two-nearest neighbours, the percentage of correctly classified genes to their correct Gene Ontology Slim term for each ontology reaches over 80% with high accuracy (reflected in F-measures over 0.80) of the classification rules produced.ConclusionsWe confirmed that in classifying genes to their correct Gene Ontology Slim term, the inclusion of neighbour information from those genes is beneficial. Knowing the location of a gene and the Gene Ontology Slim information from neighbouring genes gives us insight into that gene's functionality. This benefit is seen by just including information from a gene's two-nearest neighbouring genes.

The evolution and pathogenic mechanisms of the rice sheath blight pathogen

“…Moreover, using Gene Ontology Slim17, the largest values for genes were also detected in R. solani AG1 IA (Supplementary Fig. S4, Supplementary Note 4).…”

The challenge of improved secretory production of active pharmaceutical ingredients in Saccharomyces cerevisiae: A case study on human insulin analogs

“…It has been suggested that, although the co‐regulation of genes mediated by TFs would potentially be sufficient, an even more efficient co‐regulation of such functionally related genes would be more efficient when being co‐localized in the same region of a chromosome, reducing the burden of unpacking the DNA from its histone‐wrapped state prior to transcription. A recent study has further underlined this hypothesis, as over 80% of S. cerevisiae genes have been successfully assigned to their correct Gene Ontology Slim term by using information about the localization of each gene's two‐nearest neighbors, highlighting the extensive use of co‐localization of functionally related gene clusters in this host system (Amthauer and Tsatsoulis, ). Considering the similar fold change ranges of the significantly up‐regulated genes in C.U17 EWK which were pinpointed within the designated chromosome IV locus, our data suggest the existence of a physical cluster of genes which are related to protein maturation.…”

A visual spreadsheet using HTML5 for whole genome display

“…In this project, she has to identify some of unknown genes functions. She focused on an experiment that states the gene function can be identified by knowing the gene location and the Gene Ontology Slim information from neighbouring genes [Amthauer and Tsatsoulis, 2010]. Since getting information from images is less time-consuming than looking through numbers and texts, she needs software that helps her to visualize the genes location in the chromosome and shows the GO Slims distribution in the chromosome.…”