Identifying gene functions using functional expression profiles obtained by voxelation

An, Li; Smith, Desmond J.; Xie, Hongbo; Megalooikonomou, Vasileios; Obradović, Zoran

doi:10.1145/1854776.1854805

Cited by 2 publications

(3 citation statements)

References 16 publications

(18 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The similarity (distance) between any two gene functions was obtained by Lin's method based on GO structures. We also built the MFEP specific subset using multiple functional profiles [ 24 ] so that the genes in the subset had strong relationship between gene functions and gene expression maps. Based on the MFEP specific subsets, we applied AdaBoost and proposed a weak classifier to fit the characteristics of the dataset.…”

Section: Discussionmentioning

confidence: 99%

“…The relationship between the gene functions and gene expression maps does not hold for all genes but only for a certain set of genes. For this reason, we take advantage of previous results obtained [ 24 ] using multiple functional expression profiles (MFEPs) to perform the boosting analysis. For a given gene function or a set of gene functions, there might be a specific gene expression map (profile) associated with it.…”

Section: Methodsmentioning

confidence: 99%

“…Genes associated to an MFEP have the same set of gene functions and also have very similar gene expression maps. The detected MFEPs can be used to predict gene functions with high accuracy [ 24 ]. In order to explore the strong relationship between gene functions and expression maps, we use a subset of genes instead of the whole dataset.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Learning pair-wise gene functional similarity by multiplex gene expression maps

Ling

Obradović

et al. 2012

BMC Bioinformatics

Self Cite

View full text Add to dashboard Cite

Background: The relationships between the gene functional similarity and gene expression profile, and between gene function annotation and gene sequence have been studied extensively. However, not much work has considered the connection between gene functions and location of a gene's expression in the mammalian tissues. On the other hand, although unsupervised learning methods have been commonly used in functional genomics, supervised learning cannot be directly applied to a set of normal genes without having a target (class) attribute.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%