Two‐stage support vector regression approach for predicting accessible surface areas of amino acids
- 2 February 2006
- journal article
- research article
- Published by Wiley in Proteins-Structure Function and Bioinformatics
- Vol. 63 (3) , 542-550
- https://doi.org/10.1002/prot.20883
Abstract
We address the problem of predicting solvent accessible surface area (ASA) of amino acid residues in protein sequences, without classifying them into buried and exposed types. A two‐stage support vector regression (SVR) approach is proposed to predict real values of ASA from the position‐specific scoring matrices generated from PSI‐BLAST profiles. By adding SVR as the second stage to capture the influences on the ASA value of a residue by those of its neighbors, the two‐stage SVR approach achieves improvements of mean absolute errors up to 3.3%, and correlation coefficients of 0.66, 0.68, and 0.67 on the Manesh dataset of 215 proteins, the Barton dataset of 502 nonhomologous proteins, and the Carugo dataset of 338 proteins, respectively, which are better than the scores published earlier on these datasets. A Web server for protein ASA prediction by using a two‐stage SVR method has been developed and is available ( http://birc.ntu.edu.sg/∼pas0186457/asa.html). Proteins 2006.Keywords
This publication has 38 references indexed in Scilit:
- Solvent accessibility in native and isolated domain environments: general features and implications to interface predictabilityBiophysical Chemistry, 2005
- Protein‐protein interactions as a target for drugs in proteomicsProteomics, 2003
- Real value prediction of solvent accessibility from amino acid sequenceProteins-Structure Function and Bioinformatics, 2003
- Quantifying the accessible surface area of protein residues in their local environmentProtein Engineering, Design and Selection, 2002
- Prediction of protein solvent accessibility using support vector machinesProteins-Structure Function and Bioinformatics, 2002
- New methods for accurate prediction of protein secondary structureProteins-Structure Function and Bioinformatics, 1999
- Adaptation of protein surfaces to subcellular location 1 1Edited by F. E. CohenJournal of Molecular Biology, 1998
- Prediction of protein hydration sites from sequence by modular neural networksProtein Engineering, Design and Selection, 1998
- Conservation and prediction of solvent accessibility in protein familiesProteins-Structure Function and Bioinformatics, 1994
- Origins of structure in globular proteins.Proceedings of the National Academy of Sciences, 1990