Accuracy of protein hydropathy predictions

Authors:
Satu Jaaskelainen;Pentti Riikonen;Tapio Salakoski;Mauno Vihinen
Affiliations:
Department of Information Technology, University of Turku, FI-/20014 Turku, Finland/ Bioinformatics Laboratory, Turku Centre for Computer Science, FI-/20520 Turku, Finland.;Department of Information Technology, University of Turku, FI-/20014 Turku, Finland/ Bioinformatics Laboratory, Turku Centre for Computer Science, FI-/20520 Turku, Finland.;Department of Information Technology, University of Turku, FI-/20014 Turku, Finland/ Bioinformatics Laboratory, Turku Centre for Computer Science, FI-/20520 Turku, Finland.;Institute of Medical Technology, FI-/33014 University of Tampere, Finland/ and Tampere University Hospital, FI-/33520 Tampere, Finland
Venue:
International Journal of Data Mining and Bioinformatics
Year:
2010

Citing 1
Cited 1

Improved prediction of MHC class I and class II epitopes using a novel Gibbs sampling approach

Bioinformatics

Protein crystallization prediction with AdaBoost

International Journal of Data Mining and Bioinformatics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Hydropathy is a dominant force in protein folding. Sequence-based hydropathy predictions are widely used, without knowledge about their accuracy and reliability. We investigated the prediction accuracy of 56 hydropathy scales by correlating predicted values with the accessible surface area in known protein structures. Results for different amino acids vary greatly within each scale. We also investigated prediction accuracies of amino acids separately in secondary structural elements and in protein fold families. Despite very low overall correlation, hydropathy predictions can still be used if the shape of the plot is important instead of the prediction values.