Simple consensus procedures are effective and sufficient in secondary structure prediction |
| |
Authors: | Albrecht Mario Tosatto Silvio C E Lengauer Thomas Valle Giorgio |
| |
Affiliation: | Max-Planck-Institute for Informatics, Stuhlsatzenhausweg 85, 66123 Saarbrücken, Germany. mario.albrecht@mpi-sb.mpg.de |
| |
Abstract: | We have analyzed the performance of majority voting on minimal combination sets of three state-of-the-art secondary structure prediction methods in order to obtain a consensus prediction. Using three large benchmark sets from the EVA server, our results show a significant improvement in the average Q3 prediction accuracy of up to 1.5 percentage points by consensus formation. The application of an additional trivial filtering procedure for predicted secondary structure elements that are too short, does not significantly affect the prediction accuracy. Our analysis also provides valuable insight into the similarity of the results of the prediction methods that we combine as well as the higher confidence in consistently predicted secondary structure. |
| |
Keywords: | |
本文献已被 PubMed 等数据库收录! |
|