Towards integrative gene functional similarity measurement

Abstract

BackgroundIn Gene Ontology, the "Molecular Function" (MF) categorization is a widely used knowledge framework for gene function comparison and prediction. Its structure and annotation provide a convenient way to compare gene functional similarities at the molecular level. The existing gene similarity measures, however, solely rely on one or few aspects of MF without utilizing all the rich information available including structure, annotation, common terms, lowest common parents.ResultsWe introduce a rank-based gene semantic similarity measure called InteGO by synergistically integrating the state-of-the-art gene-to-gene similarity measures. By integrating three GO based seed measures, InteGO significantly improves the performance by about two-fold in all the three species studied (yeast, Arabidopsis and human).ConclusionsInteGO is a systematic and novel method to study gene functional associations. The software and description are available at http://www.msu.edu/~jinchen/InteGO.

InteGO2: a web tool for measuring and visualizing gene semantic similarities using Gene Ontology

“…), we recently proposed two integrative measurements successively to unite the advantage of the existing measures [9, 10]. Our measurements automatically select and integrate seed measurements with a meta-heuristic search based method.…”

WDNfinder: A method for minimum driver node set detection and analysis in directed and weighted biological network

“…3,21,22 Among these methods, we respectively use 5 most-cited methods to calculate simðg 1 ; g 2 Þ, which are from Resnik et al, 26 Lin et al, 12 Schlicker(Relevant) et al, 27 Jiang et al 7 and Wang et al 33 In comparison with gene-gene similarity weight, the fraction weight and exponent weight are proposed. Both of these two weights are based on attaching higher priority to the matching path with less branches in a directed network.…”

Classification by integrating plant stress response gene expression data with biological knowledge

“…[27], and Liu et al [28] introduced 110 another new method called weighted multipath measurement. 111 An integrative approach, InteGO [29] was proposed, which is a 112 gene functional similarity measurement which integrates three state-113 of-the-art gene semantic similarity measures, and the performance Q2 114 got a significant improvement on yeast, Arabidopsis and human. 115 However, limitations still exist in InteGO method, because it is 116 sensitive to the selection of low performance measures, and its in-117 tegration strategy may not be suitable for all gene pairs.…”

“…Recently, Shreem 26 et al [6] introduced a measure which is a hybrid of harmony search 27 and Markov blanket for gene selection. Although those methods are 28 efficient and the results were prominent, it is far from satisfactory 29 in the view of biology, because of the poor biological significance in 30 results [7]. 31 Some previous researches for genomic analysis have successfully 32 used prior biological knowledge in data mining methods, which make 33 the result more acceptable to biologist.…”