Real value prediction of solvent accessibility in proteins using multiple sequence alignment and secondary structure - PubMed

Affiliations

• PMID: 16106377
• DOI: 10.1002/prot.20630

Real value prediction of solvent accessibility in proteins using multiple sequence alignment and secondary structure

Aarti Garg et al. Proteins. 2005.

Abstract

The present study is an attempt to develop a neural network-based method for predicting the real value of solvent accessibility from the sequence using evolutionary information in the form of multiple sequence alignment. In this method, two feed-forward networks with a single hidden layer have been trained with standard back-propagation as a learning algorithm. The Pearson's correlation coefficient increases from 0.53 to 0.63, and mean absolute error decreases from 18.2 to 16% when multiple-sequence alignment obtained from PSI-BLAST is used as input instead of a single sequence. The performance of the method further improves from a correlation coefficient of 0.63 to 0.67 when secondary structure information predicted by PSIPRED is incorporated in the prediction. The final network yields a mean absolute error value of 15.2% between the experimental and predicted values, when tested on two different nonhomologous and nonredundant datasets of varying sizes. The method consists of two steps: (1) in the first step, a sequence-to-structure network is trained with the multiple alignment profiles in the form of PSI-BLAST-generated position-specific scoring matrices, and (2) in the second step, the output obtained from the first network and PSIPRED-predicted secondary structure information is used as an input to the second structure-to-structure network. Based on the present study, a server SARpred (http://www.imtech.res.in/raghava/sarpred/) has been developed that predicts the real value of solvent accessibility of residues for a given protein sequence. We have also evaluated the performance of SARpred on 47 proteins used in CASP6 and achieved a correlation coefficient of 0.68 and a MAE of 15.9% between predicted and observed values.

Similar articles

• A neural network method for prediction of beta-turn types in proteins using evolutionary information.

  Kaur H, Raghava GP. Kaur H, et al. Bioinformatics. 2004 Nov 1;20(16):2751-8. doi: 10.1093/bioinformatics/bth322. Epub 2004 May 14. Bioinformatics. 2004. PMID: 15145798

• Role of evolutionary information in prediction of aromatic-backbone NH interactions in proteins.

  Kaur H, Raghava GP. Kaur H, et al. FEBS Lett. 2004 Apr 23;564(1-2):47-57. doi: 10.1016/S0014-5793(04)00305-9. FEBS Lett. 2004. PMID: 15094041

• Prediction of alpha-turns in proteins using PSI-BLAST profiles and secondary structure information.

  Kaur H, Raghava GP. Kaur H, et al. Proteins. 2004 Apr 1;55(1):83-90. doi: 10.1002/prot.10569. Proteins. 2004. PMID: 14997542

• BiRDS - Binding Residue Detection from Protein Sequences Using Deep ResNets.

  Chelur VR, Priyakumar UD. Chelur VR, et al. J Chem Inf Model. 2022 Apr 25;62(8):1809-1818. doi: 10.1021/acs.jcim.1c00972. Epub 2022 Apr 12. J Chem Inf Model. 2022. PMID: 35414182 Review.

• Protein secondary structure prediction.

  Barton GJ. Barton GJ. Curr Opin Struct Biol. 1995 Jun;5(3):372-6. doi: 10.1016/0959-440x(95)80099-9. Curr Opin Struct Biol. 1995. PMID: 7583635 Review.

Cited by

• Improving prediction of secondary structure, local backbone angles, and solvent accessible surface area of proteins by iterative deep learning.

  Heffernan R, Paliwal K, Lyons J, Dehzangi A, Sharma A, Wang J, Sattar A, Yang Y, Zhou Y. Heffernan R, et al. Sci Rep. 2015 Jun 22;5:11476. doi: 10.1038/srep11476. Sci Rep. 2015. PMID: 26098304 Free PMC article.

• Epitope Mapping of Rhi o 1 and Generation of a Hypoallergenic Variant: A CANDIDATE MOLECULE FOR FUNGAL ALLERGY VACCINES.

  Sircar G, Jana K, Dasgupta A, Saha S, Gupta Bhattacharya S. Sircar G, et al. J Biol Chem. 2016 Aug 19;291(34):18016-29. doi: 10.1074/jbc.M116.732032. Epub 2016 Jun 28. J Biol Chem. 2016. PMID: 27358405 Free PMC article.

• Protein-RNA interface residue prediction using machine learning: an assessment of the state of the art.

  Walia RR, Caragea C, Lewis BA, Towfic F, Terribilini M, El-Manzalawy Y, Dobbs D, Honavar V. Walia RR, et al. BMC Bioinformatics. 2012 May 10;13:89. doi: 10.1186/1471-2105-13-89. BMC Bioinformatics. 2012. PMID: 22574904 Free PMC article.

• Cytotoxic T lymphocyte antigen 4 (CTLA4) gene polymorphism with bladder cancer risk in North Indian population.

  Jaiswal PK, Singh V, Mittal RD. Jaiswal PK, et al. Mol Biol Rep. 2014 Feb;41(2):799-807. doi: 10.1007/s11033-013-2919-2. Epub 2014 Jan 4. Mol Biol Rep. 2014. PMID: 24390231

• Effective identification of Gram-negative bacterial type III secreted effectors using position-specific residue conservation profiles.

  Yang X, Guo Y, Luo J, Pu X, Li M. Yang X, et al. PLoS One. 2013 Dec 31;8(12):e84439. doi: 10.1371/journal.pone.0084439. eCollection 2013. PLoS One. 2013. PMID: 24391954 Free PMC article.

Publication types

MeSH terms

Substances

LinkOut - more resources

• Full Text Sources

  • Wiley

• Other Literature Sources

  • The Lens - Patent Citations Database

• Research Materials

  • NCI CPTC Antibody Characterization Program