From informatics to bioinformatics
APBC '03 Proceedings of the First Asia-Pacific bioinformatics conference on Bioinformatics 2003 - Volume 19
On the prediction of genes based on the asymptotic local approach
International Journal of Systems Science
Research Article: Search of regular sequences in promoters from eukaryotic genomes
Computational Biology and Chemistry
Promoter prediction based on a multiple instance learning scheme
Proceedings of the First ACM International Conference on Bioinformatics and Computational Biology
Hi-index | 0.00 |
The Dragon Promoter Finder is an advanced system for promoter recognition in vertebrates. It uses a collection of models based on multisensor integration, signal processing, and artificial neural networks. The system uses newly developed sensors based on the statistical concept of oligonucleotide positional distributions in specific functional regions of DNA. These distributions are modeled as a set of position weight matrices of the most significant oligonucleotides. The authors calibrated the system to minimize the number of false-positive predictions for various prespecified sensitivity levels. When evaluated on a large and diverse human sequence set, it exhibited several times higher accuracy than several other publicly available general promoter recognition systems.