Accurately predicting transcription start sites using logitlinear model and local oligonucleotide frequencies

Authors:
Jia Wang;Chuang Ma;Dao Zhou;Libin Zhang;Yanhong Zhou
Affiliations:
Hubei Bioinformatics and Molecular Imaging Key Laboratory, Huazhong University of Science and Technology, Wuhan, Hubei, China;Hubei Bioinformatics and Molecular Imaging Key Laboratory, Huazhong University of Science and Technology, Wuhan, Hubei, China;Hubei Bioinformatics and Molecular Imaging Key Laboratory, Huazhong University of Science and Technology, Wuhan, Hubei, China;Hubei Bioinformatics and Molecular Imaging Key Laboratory, Huazhong University of Science and Technology, Wuhan, Hubei, China;Hubei Bioinformatics and Molecular Imaging Key Laboratory, Huazhong University of Science and Technology, Wuhan, Hubei, China
Venue:
ICIC'11 Proceedings of the 7th international conference on Intelligent Computing: bio-inspired computing and applications
Year:
2011

Citing 7
Cited 0

ARTS

Bioinformatics
PromoterExplorer: an effective promoter identification method based on the AdaBoost algorithm

Bioinformatics
ProSOM

Bioinformatics
Toward a gold standard for promoter prediction evaluation

Bioinformatics
Accurate Prediction of Alternatively Spliced Cassette Exons Using Evolutionary Conservation Information and Logitlinear Model

IJCBS '09 Proceedings of the 2009 International Joint Conference on Bioinformatics, Systems Biology and Intelligent Computing
Computational modeling of oligonucleotide positional densities for human promoter prediction

Artificial Intelligence in Medicine
SCS: Signal, Context, and Structure Features for Genome-Wide Human Promoter Recognition

IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this study, we construct a transcription start site (TSS) prediction model using the logitlinear model and the genomic context features mined in promoter regions. We also develop a computational program named ProKey that is able to accurately predict TSSs in long DNA sequences. Performance evaluation results on the whole human genome show that ProKey could achieve 71.2% sensitivity and 76.3% specificity at the resolution level of 2000bp. Further comparison results exhibit that the correlation coefficient (CC) value of ProKey is higher than that of DragonGSF and Eponine.