当前位置： SCI文献检索 > NUCLEIC ACIDS RESEARCH期刊下所有文献 > PreCisIon: PREdiction of CIS-regulatory elements improved by gene's positION.

PreCisIon: PREdiction of CIS-regulatory elements improved by gene's positION.

Abstract：

:Conventional approaches to predict transcriptional regulatory interactions usually rely on the definition of a shared motif sequence on the target genes of a transcription factor (TF). These efforts have been frustrated by the limited availability and accuracy of TF binding site motifs, usually represented as position-specific scoring matrices, which may match large numbers of sites and produce an unreliable list of target genes. To improve the prediction of binding sites, we propose to additionally use the unrelated knowledge of the genome layout. Indeed, it has been shown that co-regulated genes tend to be either neighbors or periodically spaced along the whole chromosome. This study demonstrates that respective gene positioning carries significant information. This novel type of information is combined with traditional sequence information by a machine learning algorithm called PreCisIon. To optimize this combination, PreCisIon builds a strong gene target classifier by adaptively combining weak classifiers based on either local binding sequence or global gene position. This strategy generically paves the way to the optimized incorporation of any future advances in gene target prediction based on local sequence, genome layout or on novel criteria. With the current state of the art, PreCisIon consistently improves methods based on sequence information only. This is shown by implementing a cross-validation analysis of the 20 major TFs from two phylogenetically remote model organisms. For Bacillus subtilis and Escherichia coli, respectively, PreCisIon achieves on average an area under the receiver operating characteristic curve of 70 and 60%, a sensitivity of 80 and 70% and a specificity of 60 and 56%. The newly predicted gene targets are demonstrated to be functionally consistent with previously known targets, as assessed by analysis of Gene Ontology enrichment or of the relevant literature and databases.

journal_name

Nucleic Acids Res

journal_title

Nucleic acids research

authors

Elati M,Nicolle R,Junier I,Fernández D,Fekih R,Font J,Képès F

doi

10.1093/nar/gks1286

subject

Has Abstract

pub_date

2013-02-01 00:00:00

pages

1406-15

issue

eissn

0305-1048

issn

1362-4962

pii

gks1286

journal_volume

pub_type

杂志文章

在线工具

PreCisIon: PREdiction of CIS-regulatory elements improved by gene's positION.