Probabilistic Inference of Biological Networks via Data Integration.
There is significant interest in inferring the structure of subcellular networks of interaction. Here we consider supervised interactive network inference in which a reference set of known network links and nonlinks is used to train a classifier for predicting new links. Many types of data are relev...
| Publicado en: | BioMed Research International Vol. 2015; pp. 1 - 10 |
|---|---|
| Autores principales: | , , |
| Formato: | equations & formulas research tables/charts Journal Article |
| Publicado: |
Wiley-Blackwell
3/22/2015
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=109273742&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 109273742 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 23146133 FT2T jtl: BioMed Research International issn: 23146133 maglogo: N pubinfo: dt: 3/22/2015 vid: 2015 pid: 480 pub: Wiley-Blackwell place: Malden, Massachusetts artinfo: ui: 109273742 109273742 109273742 10.1155/2015/707453 109273742 ppf: 1 ppct: 9 formats: fmt: @attributes: type: P tig: atl: Probabilistic Inference of Biological Networks via Data Integration. aug: au: Rogers, Mark F. Campbell, Colin Ying, Yiming affil: Intelligent Systems Laboratory, University of Bristol, Merchant Venturers Building, Bristol BS8 1UB, UK sug: subj: Data Analysis, Statistical Genes Data Management Mathematics Descriptive Statistics Data Analysis Software Odds Ratio Confidence Intervals Data Collection Computer Input Devices Funding Source ab: There is significant interest in inferring the structure of subcellular networks of interaction. Here we consider supervised interactive network inference in which a reference set of known network links and nonlinks is used to train a classifier for predicting new links. Many types of data are relevant to inferring functional links between genes, motivating the use of data integration. We use pairwise kernels to predict novel links, along with multiple kernel learning to integrate distinct sources of data into a decision function. We evaluate various pairwise kernels to establish which are most informative and compare individual kernel accuracies with accuracies for weighted combinations. By associating a probability measure with classifier predictions, we enable cautious classification, which can increase accuracy by restricting predictions to high-confidence instances, and data cleaning that can mitigate the influence of mislabeled training instances. Although one pairwise kernel (the tensor product pairwise kernel) appears to work best, different kernels may contribute complimentary information about interactions: experiments in S. cerevisiae (yeast) reveal that a weighted combination of pairwise kernels applied to different types of data yields the highest predictive accuracy. Combined with cautious classification and data cleaning, we can achieve predictive accuracies of up to 99.6%. pubtype: Academic Journal doctype: equations & formulas research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|