Skip to main content
SpringerLink
Log in

Studying Peptides Biological Activities Based on Multidimensional Descriptors (E) Using Support Vector Regression

  • Published:
International Journal of Peptide Research and Therapeutics Aims and scope Submit manuscript

Abstract

A quantitative multidimensional amino acids descriptors E (E1–E5) has been introduced in bioactive peptides Quantitative Structure–Activity Relationship (QSAR) study. These descriptors correlate well with hydrophobicity, size, preferences for amino acids to occur in α-helices, composition and the net charge, respectively. They were then applied to construct characterization and QSAR analysis on 48 angiotensin-converting enzyme (ACE) inhibitors dipeptides, 55 ACE inhibitors tripeptides and 48 bitter tasting dipeptides by support vector regression (SVR). The leave one out cross validation Q 2(CV) were 0.886, 0.985 and 0.912, the root mean square error (RMSE) were 0.250, 0.021 and 0.123, respectively. The results showed that, in comparison with the conventional descriptors, the new descriptor (E) is a useful structure characterization method for peptide QSAR analysis. The importance of each parameter or property at each position in peptides is estimated by the value of the model RMSE obtained using leave-one-parameter-out (LOPO) approach in the SVR model. This will be provided with certain guidance meaning to design and exploit peptide analogues. The results also indicate that SVR can be used as an alternative powerful modeling tool for peptide QSAR studies, and give one advice (LOPO) about evaluating the importance of parameter in SVR model. Moreover, it also offered an idea about nonlinear relation between bioactive of peptides and their structural descriptors E. The establishment of such methods will be a very meaningful work to peptide bioactive investigation in peptide analogue drug design.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Abbreviations

QSAR:

Quantitative structure–activity relationship

ACE:

Angiotensin-converting enzyme

LOPO:

Leave-one-parameter-out

SVR:

Support vector regression

MLR:

Multiple linear regression

PLS:

Partial least square

PCR:

Princupal component regression

RMSE:

Root mean square error

BA:

Biological activities

LOOCV:

Leave-one-out cross-validation

References

  • Alex JS, Bernhrd S (2004) A tutorial on support vector regression. Stat Comput 14:199–222

    Article  Google Scholar 

  • Asao M, Iwamara H, Akamatsu M, Fujita T (1987) Quantitative structure–activity relationships of bitter thresholds of amino acids, peptides and their derivatives. J Med Chem 30(10):1873–1879

    Article  CAS  PubMed  Google Scholar 

  • Cocchi M, Johansson E (1993) Amino acids characterization by GRID and multivariate data analysis. Quant Struct-Act Relat 12:1–8

    Article  CAS  Google Scholar 

  • Collantes ER, Dunn WJ (1995) Amino acid side chain descriptors for quantitative structure-activity relationship studies of peptide analogues. J Med Chem 38:2705–2713

    Article  CAS  PubMed  Google Scholar 

  • Cushman DW, Cheung HS, Sabo EF, Ondetti MA (1981) Angiotensin converting enzyme inhibitors: evolution of a new class of antihypertensive drugs. In: Horovitz ZP (ed) Angiotensin converting enzyme inhibitors, mechanisms of action and clinical implications. Urban and Schwarzenberg, Baltimore, pp 3–25

    Google Scholar 

  • Eriksson L, Johansson E, Kettaneh-Wold N, Trygg J, Wikström C, Wold S (2001) Multi- and megavariate data analysis: principle and application. Umetrics AB, Umea, Sweden

    Google Scholar 

  • Fan RE, Chen PH, Lin CJ (2005) Working set selection using the second order information for training SVM. J Mach Learn Res 6:1889–1918 or http://www.csie.ntu.edu.tw/~cjlin/libsvm/

    Google Scholar 

  • Fang Y, Guo Y, Feng Y, Li M (2008) Predicting DNA-binding proteins: approached from Chou’s pseudo amino acid composition and other specific sequence features. Amino Acids 34(1):103–109

    Article  CAS  PubMed  Google Scholar 

  • Guo Y, Yu L, Wen Z, Li M (2008) Using support vector machine combined with auto covariance to predict protein-protein interactions from protein sequences. Nucleic Acids Res 36(9):3025–3030

    Article  CAS  PubMed  Google Scholar 

  • Hellberg S, Sjostrom M, Wold S (1986) The prediction of bradykinin potentiating potency of pentapeptides: an example of a peptide quantitative structure-activity relationship. Acta Chem Scand 40:135–140

    Article  CAS  Google Scholar 

  • Hellberg S, Sjostrom M, Skagerberg B, Wold S (1987) Peptide quantitative structure-activity relationships, a multivariate approach. J Med Chem 30:1126–1135

    Article  CAS  PubMed  Google Scholar 

  • Hellberg S, Eriksson L, Jonsson J, Lindgren F, Sjostrom M, Skagerberg B, Wold S, Andrews P (1991) Minimum analogue peptide sets (MAPS) for quantitative structure-activity relationships. Int J Pept Protein Res 37:414–424

    Article  CAS  PubMed  Google Scholar 

  • Jonsson J, Eriksson L, Hellberg S, Sjostrom M, Wold S (1989) Multivariate parameterization of 55 coded and non-coded amino acids. Quant Struct-Act Relat 8:204–209

    Article  CAS  Google Scholar 

  • Kidera A, Konishi Y, Oka M, Ooi T, Scheraga HA (1985) A statistical analysis of the physical properties of the 20 naturally occurring amino acids. J Protein Chem 4:23–55

    Article  CAS  Google Scholar 

  • Li SZ, Fu BH, Wang YQ, Liu SS (2001) On structural parameterization and molecular modeling of peptide analogues by molecular electronegativity-edge vector (VMEE): estimation and prediction for biological activity of pentapeptides. J Chin Chem Soc 48:937–944

    CAS  Google Scholar 

  • Liang GZ, Zhou P, Zhou Y, Zhang QX, Li ZL (2006) New descriptors of amino acids and their applications to peptide quantitative structure activity relationship. Acta Chim Sinica 64(5):393–396

    CAS  Google Scholar 

  • Lin ZH, Long HX, Bo Z, Wang YQ, Wu YZ (2008) New descriptors of amino acids and their application to peptide QSAR study. Peptides 28:1798–1805

    Article  CAS  Google Scholar 

  • Liu SS, Yin CS, Cai SX, Li ZL (2001) A novel MHDV descriptor for dipeptide QSAR studies. J Chin Chem Soc 48:253–260

    CAS  Google Scholar 

  • Liu SS, Yin CS, Wang LS (2002) Combined MEDV-GA-MLR method for QSAR of three panels of steroids, dipeptides, and COX-2 indihibitors. J Chem Inf Comput Sci 42:749–756

    CAS  PubMed  Google Scholar 

  • Mei H, Zhou Y, Sun LL, Li ZL (2004) A new descriptors of amino acid and its application in peptide QSAR. Acta Phys Chim Sin 20:821–825

    CAS  Google Scholar 

  • Mei H, Liao ZH, Zhou Y, Li SSZ (2005) A new set of amino acid descriptors and its application in peptide QSARs. Biopolymers (peptide science) 80(6):775–786

    Article  CAS  Google Scholar 

  • Niu B, Lu WC, Yang SS, Cai YD, Li GZ (2007) Support vector machine for SAR/QSAR of phenethyl-amines. Acta Pharmacol Sin 28:1075–1086

    Article  CAS  PubMed  Google Scholar 

  • Ramos De Armas R, Gonzalez-Diaz H, Molina R, Perez-Gonzalez M, Uriarte E (2004) Stochastic-based descriptors studying peptides biological properties: modeling the bitter tasting threshold of dipeptides. Bioorg Med Chem 12:4815–4822

    Article  CAS  PubMed  Google Scholar 

  • Raychaudhury C, Banerjee A, Bag P, Roy S (1999) Topological shape and size of peptides: identification of potential allele specific helper T cell antigenic sites. J Chem Inf Comput Sci 39:248–254

    CAS  PubMed  Google Scholar 

  • Sandberg M, Eriksson L, Jonsson J, Sjostrom M, Wold S (1998) New chemical descriptors relevant for the design of biologically active peptides. A multivariate characterization of 87 amino acids. J Med Chem 41:2481–2491

    Article  CAS  PubMed  Google Scholar 

  • Sewald N, Jakubke HD (2002) Peptides: chemistry and biology. Wiley-Vch Verlag GmbH & Co. KGaA, Weinheim

    Google Scholar 

  • Sneath PH (1966) Relations between chemical structure and biological activity in peptides. J Theor Biol 12:157–195

    Article  CAS  PubMed  Google Scholar 

  • Tian FF, Zhou P, Li ZL (2007) T-Scale as a novel vector of topological descriptors for amino acids and its application in QSARs of peptides. J Mol Struct (Theochem) 830:106–115

    CAS  Google Scholar 

  • Tong J, Liu S, Zhou P, Wu B, Li Z (2008) A novel descriptor of amino acids and its application in peptide QSAR. J Theor Biol 253:90–97

    Article  CAS  PubMed  Google Scholar 

  • Vapnik VN (2004) Statistical learning theory. Publishing House of Electronics Industry, Beijing

    Google Scholar 

  • Venkatarajan MS, Braun W (2001) New quantitative descriptors of amino acids based on multidimensional scaling of a large number of physical–chemical properties. J Mol Model 7:445–453

    Article  CAS  Google Scholar 

  • Wold S, Eriksson L, Hellberg S, Jonsson J, Sjostrom M, Skagerberg B, Wikstrom C (1987) Principal property values for six non-natural amino acids and their application to a structure-activity relationship for oxytocin peptide analogues. Can J Chem 65:1814–1820

    Article  CAS  Google Scholar 

  • Wu J, Aluko RE, Nakai S (2006) Structural requirements of angiotensin I-converting enzyme inhibitory peptides: quantitative structure–and–activity relationship study of di- and tri-peptides. J Agric Food Chem 54:732–738

    Article  CAS  PubMed  Google Scholar 

  • Yin JJ, Diao YB, Wen ZN, Wang ZM, Li ML (2009) Study of peptides quantitative structure-activity relationship base on E descriptors by multiple linear regression. Interdiscip Sci Comput Life Sci (submitted)

  • Zaliani A, Gancia E (1999) MS-WHIM scores for amino acids: a new 3D description for peptide QSAR and QSPR studies. J Chem Inf Comput Sci 39:525–533

    CAS  Google Scholar 

  • Zhou P, Zhou Y, Wu SR, Li B, Tian FF, Li ZL (2006) A new descriptor of amino acids based on the three-dimensional vector of atomic interaction field. Chin Sci Bull 51(5):524–529

    Article  CAS  Google Scholar 

Download references

Acknowledgment

This work was supported by the National Natural Science Foundation of China (No. 20775052) and by the “211 Engineering Double Support Plan” Foundation of Sichuan Agricultural University (Yaan, China).

Author information

Authors and Affiliations

  1. College of Life and Science, Sichuan Agriculture University, Ya’an, 625014, People’s Republic of China

    Jiajian Yin

  2. College of Chemistry, Sichuan University, Chengdu, 610064, People’s Republic of China

    Yuanbo Diao, Zhining Wen, Zhimeng Wang & Menglong Li

Authors
  1. Jiajian Yin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yuanbo Diao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhining Wen
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Zhimeng Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Menglong Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Menglong Li.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Yin, J., Diao, Y., Wen, Z. et al. Studying Peptides Biological Activities Based on Multidimensional Descriptors (E) Using Support Vector Regression. Int J Pept Res Ther 16, 111–121 (2010). https://doi.org/10.1007/s10989-010-9210-3

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10989-010-9210-3

Keywords

Search

Navigation