- Probabilistic protein function prediction from heterogeneous genome-wide dataNaoki Nariai
Bioinformatics Program, Boston University, Boston, Massachusetts, United States of America
PLoS ONE 2:e337. 2007..Surprisingly, in some contexts integration hurts overall prediction accuracy. Lastly, we provide a comprehensive assignment of putative GO terms to 463 proteins that currently have no assigned function...
- Context specific protein function predictionNaoki Nariai
Boston University, Boston, MA 02215, USA
Genome Inform 18:173-82. 2007..Finally, we predicted 57 unknown genes as "ribosome biogenesis" proteins...
- Integration of relational and hierarchical network information for protein function predictionXiaoyu Jiang
Department of Mathematics and Statistics, Boston University, Boston, MA 02215, USA
BMC Bioinformatics 9:350. 2008..Currently, the most common approach to imposing these hierarchical constraints on network-based classifiers is through the use of transitive closure to predictions...
- Estimating gene regulatory networks and protein-protein interactions of Saccharomyces cerevisiae from multiple genome-wide dataNaoki Nariai
Human Genome Center, Institute of Medical Science, University of Tokyo, Shirokanedai, Minato ku, Tokyo, Japan
Bioinformatics 21:ii206-12. 2005....