Abstract
In recent years, pattern recognition methods have been applied to determine the activity of biological molecules, including the prediction of antimicrobial activity of synthetic and natural peptides where Quantitative Structure-Activity Relationship methodologies are widely used. Traditionally, works focused on designing descriptors for sequences to yield better correlations with the biological activity and improve predictors performance. Albeit there have been remarkable results, the small size of available datasets leave large room for improvement. In this work, rather than hand-crafting new descriptors, our approach consists in automatically learning them from existing ones. We use stacked autoencoders (a class of unsupervised neural networks), and the descriptors learnt are fed to a support vector regression task to predict biological activity. This method improves results in existing literature by roughly 12 % simultaneously in different metrics, providing interesting insights into the nature of descriptors learnt and suggesting its applicability in other areas in protein properties prediction.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Amábile-Cuevas, C.F.: Antimicrobial resistance in developing countries. In: Sosa, A.d.J., Byarugaba, D.K., Amábile-Cuevas, C.F., Hsueh, P.R., Kariuki, S., Okeke, I.N. (eds.) Antimicrobial Resistance in Develoving Countries, Chap. 1, pp. 15–27. Springer, New York (2010)
Projan, S.J.: Why is big Pharma getting out of antibacterial drug discovery? Curr. Opin. Microbiol. 6(5), 427–430 (2003)
Fjell, C.D., Hiss, J., Hancock, R.E.W., Schneider, G.: Designing antimicrobial peptides: form follows function. Nature Rev. Drug Discov. 11(1), 37–51 (2012)
Zhou, X., Li, Z., Dai, Z., Zou, X.: QSAR modeling of peptide biological activity by coupling support vector machine with particle swarm optimization algorithm and genetic algorithm. J. Mol. Graph. Model. 29(2), 188–196 (2010)
Borkar, M.R., Pissurlenkar, R.R.S., Coutinho, E.C.: HomoSAR: bridging comparative protein modeling with quantitative structural activity relationship to design new peptides. J. Comput. Chem. 34(30), 2635–2646 (2013)
Cherkasov, A., Jankovic, B.: Application of ‘inductive’ QSAR descriptors for quantification of antibacterial activity of cationic polypeptides. Molecules 9(12), 1034–1052 (2004). (Basel, Switzerland)
Taboureau, O.: Methods for building quantitative structure-activity relationship (QSAR) descriptors and predictive models for computer-aided design of antimicrobial peptides. In: Giuliani, A., Rinaldi, A.C. (eds.) Antimicrobial Peptides, Methods in Molecular Biology, Methods in Molecular Biology, Chap. 6, vol. 618, pp. 77–86. Humana Press, Totowa (2010)
Shu, M., Yu, R., Zhang, Y., Wang, J., Yang, L., Wang, L., Lin, Z.: Predicting the activity of antimicrobial peptides with amino acid topological information. Med. Chem. 9(1), 32–44 (2013)
Hemmateenejad, B., Yousefinejad, S., Mehdipour, A.R.: Novel amino acids indices based on quantum topological molecular similarity and their application to QSAR study of peptides. Amino Acids 40(4), 1169–1183 (2011)
Lin, Z., Long, H., Bo, Z., Wang, Y., Wu, Y.: New descriptors of amino acids and their application to peptide QSAR study. Peptides 29(10), 1798–1805 (2008)
Li, Z.R., Lin, H.H., Han, L.Y., Jiang, L., Chen, X., Chen, Y.Z.: PROFEAT: a web server for computing structural and physicochemical features of proteins and peptides from amino acid sequence. Nucleic Acids Res. 34(Web Server issue), W32–W37 (2006)
Cao, D.S., Xu, Q.S., Liang, Y.Z.: propy: a tool to generate various models of Chous PseAAC. Bioinform. Appl. Note 29(7), 960–962 (2013)
Shin, H., Orton, M.R., Collins, D.J., Doran, S.J., Leach, M.O.: Stacked autoencoders for unsupervised feature learning and multiple organ detection in a pilot study using 4D patient data. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1930–1943 (2013)
Wold, S., Esbensen, K., Geladi, P.: Principal component analysis. Chemometr. Intell. Lab. Syst. 2(1–3), 37–52 (1987)
Liu, D.C., Nocedal, J.: On the limited memory BFGS method for large scale optimization. Math. Program. 45, 503–528 (1989)
Kiralj, R., Ferreira, M.M.C.: Basic validation procedures for regression models in QSAR and QSPR studies: theory and application. J. Braz. Chem. Soc. 20(4), 770–787 (2009)
Ng, A., Ngiam, J., Foo, C.Y., Mai, Y., Suen, C.: Unsupervised feature learning and deep learning. http://ufldl.stanford.edu/wiki/index.php/UFLDL_Tutorial
Wang, Y., Ding, Y., Wen, H., Lin, Y., Hu, Y., Zhang, Y., Xia, Q., Lin, Z.: QSAR modeling and design of cationic antimicrobial peptides based on structural properties of amino acids. Comb. Chem. High Throughput Screen. 15(4), 347–353 (2012)
Torrent, M., Andreu, D., Nogués, V.M., Boix, E.: Connecting peptide physicochemical and antimicrobial properties by a rational prediction model. PLoS One 6(2), e16968 (2011)
Acknowledgments
The authors thank the support of the High Performance and Scientific Computing Centre at Universidad Industrial de Santander (www.sc3.uis.edu.co). This project was funded by COLCIENCIAS (Project number: 1102-5453-1671) and Vicerrectoría de Investigación y Extensión (VIE) from UIS.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Camacho, F., Torres, R., Ramos-Pollán, R. (2015). Feature Learning Using Stacked Autoencoders to Predict the Activity of Antimicrobial Peptides. In: Roux, O., Bourdon, J. (eds) Computational Methods in Systems Biology. CMSB 2015. Lecture Notes in Computer Science(), vol 9308. Springer, Cham. https://doi.org/10.1007/978-3-319-23401-4_11
Download citation
DOI: https://doi.org/10.1007/978-3-319-23401-4_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-23400-7
Online ISBN: 978-3-319-23401-4
eBook Packages: Computer ScienceComputer Science (R0)