De novo design of anticancer peptides by ensemble artificial neural networks

  • Francesca GrisoniEmail author
  • Claudia S. Neuhaus
  • Miyabi Hishinuma
  • Gisela Gabernet
  • Jan A. Hiss
  • Masaaki Kotera
  • Gisbert SchneiderEmail author
Original Paper
Part of the following topical collections:
  1. Tim Clark 70th Birthday Festschrift


Membranolytic anticancer peptides (ACPs) are drawing increasing attention as potential future therapeutics against cancer, due to their ability to hinder the development of cellular resistance and their potential to overcome common hurdles of chemotherapy, e.g., side effects and cytotoxicity. In this work, we present an ensemble machine learning model to design potent ACPs. Four counter-propagation artificial neural-networks were trained to identify peptides that kill breast and/or lung cancer cells. For prospective application of the ensemble model, we selected 14 peptides from a total of 1000 de novo designs, for synthesis and testing in vitro on breast cancer (MCF7) and lung cancer (A549) cell lines. Six de novo designs showed anticancer activity in vitro, five of which against both MCF7 and A549 cell lines. The novel active peptides populate uncharted regions of ACP sequence space.


Artificial intelligence Cancer Counterpropagation Machine learning Membranolysis Peptide design 



The authors thank Sarah Haller for technical support. This research was financially supported by the Swiss National Science Foundation (grants no. CRSII2_160699, no. 200021_157190 and no. IZSEZ0_177477). M.H. was financially supported by “Tobitate! (Leap for tomorrow)” study abroad initiative (Japan’s Ministry of Education, Culture, Sports, Science, and Technology [MEXT]).

Author contributions

G.S., F.G., J.A.H. and M.K. designed the study. M.H., G.G., F.G. and C.S.N. produced and curated the dataset. M.H. performed the calculations and developed the models under the supervision of F.G. and G.S.; F.G. analyzed and validated the models; C.S.N. designed and supervised peptide synthesis and in vitro experiments, and analyzed the experimental results. All authors discussed the work and provided feedbacks and ideas. F.G. wrote the manuscript. All authors contributed to manuscript revision and approved the final version.

Supplementary material

894_2019_4007_MOESM1_ESM.pdf (1.9 mb)
ESM 1 (PDF 1904 kb)
894_2019_4007_MOESM2_ESM.csv (35 kb)
ESM 2 (CSV 34 kb)
894_2019_4007_MOESM3_ESM.csv (37 kb)
ESM 3 (CSV 36 kb)


  1. 1.
    Gabernet G, Müller AT, Hiss JA, Schneider G (2016) Membranolytic anticancer peptides. Med Chem Commun 7:2232–2245. CrossRefGoogle Scholar
  2. 2.
    Papo N, Shai Y (2005) Host defense peptides as new weapons in cancer treatment. Cell Mol Life Sci 62:784–790. CrossRefPubMedGoogle Scholar
  3. 3.
    Mader JS, Hoskin DW (2006) Cationic antimicrobial peptides as novel cytotoxic agents for cancer treatment. Expert Opin Investig Drugs 15:933–946. CrossRefPubMedGoogle Scholar
  4. 4.
    Hoskin DW, Ramamoorthy A (2008) Studies on anticancer activities of antimicrobial peptides. Biochim Biophys Acta 1778:357–375. CrossRefPubMedGoogle Scholar
  5. 5.
    Riedl S, Zweytick D, Lohner K (2011) Membrane-active host defense peptides – challenges and perspectives for the development of novel anticancer drugs. Chem Phys Lipids 164:766–781. CrossRefPubMedPubMedCentralGoogle Scholar
  6. 6.
    Dennison SR, Whittaker M, Harris F, Phoenix DA (2006) Anticancer α-helical peptides and structure/function relationships underpinning their interactions with tumour cell membranes. Curr Protein Pept Sci 7:487–499CrossRefGoogle Scholar
  7. 7.
    Gaspar D, Veiga AS, Castanho MARB (2013) From antimicrobial to anticancer peptides. A review. Front Microbiol 4:294. CrossRefPubMedPubMedCentralGoogle Scholar
  8. 8.
    Fosgerau K, Hoffmann T (2015) Peptide therapeutics: current status and future directions. Drug Discov Today 20:122–128. CrossRefPubMedGoogle Scholar
  9. 9.
    Wang G, Li X, Wang Z (2016) APD3: the antimicrobial peptide database as a tool for research and education. Nucleic Acids Res 44:D1087–D1093. CrossRefPubMedGoogle Scholar
  10. 10.
    Shoombuatong W, Schaduangrat N, Nantasenamat C (2018) Unraveling the bioactivity of anticancer peptides as deduced from machine learning. EXCLI J 17:734. CrossRefPubMedPubMedCentralGoogle Scholar
  11. 11.
    Tyagi A, Tuknait A, Anand P et al (2015) CancerPPD: a database of anticancer peptides and proteins. Nucleic Acids Res 43:D837–D843. CrossRefPubMedGoogle Scholar
  12. 12.
    (2018) Cancer Facts & Figures 2018 | American Cancer Society. Accessed 11 Nov 2018
  13. 13.
    Siegel RL, Miller KD, Jemal A (2018) Cancer statistics, 2018. CA Cancer J Clin 68:7–30. CrossRefGoogle Scholar
  14. 14.
    Grisoni F, Neuhaus CS, Gabernet G et al (2018) Designing anticancer peptides by constructive machine learning. ChemMedChem 13:1300–1302. CrossRefPubMedGoogle Scholar
  15. 15.
    Merk D, Friedrich L, Grisoni F, Schneider G (2018) De novo design of bioactive small molecules by artificial intelligence. Mol Inf 37:1700153. CrossRefGoogle Scholar
  16. 16.
    Tyagi A, Kapoor P, Kumar R et al (2013) In silico models for designing and discovering novel anticancer peptides. Sci Rep 3:2984. CrossRefPubMedGoogle Scholar
  17. 17.
    Hajisharifi Z, Piryaiee M, Mohammad Beigi M et al (2014) Predicting anticancer peptides with Chou′s Pseudo amino acid composition and investigating their mutagenicity via Ames test. J Theor Biol 341:34–40. CrossRefPubMedGoogle Scholar
  18. 18.
    Vijayakumar S, PTV L (2015) ACPP: a web server for prediction and design of anti-cancer peptides. Int J Pept Res Ther 21:99–106. CrossRefGoogle Scholar
  19. 19.
    Chen W, Ding H, Feng P et al (2016) iACP: a sequence-based tool for identifying anticancer peptides. Oncotarget 7:16895–16909. CrossRefPubMedPubMedCentralGoogle Scholar
  20. 20.
    Manavalan B, Basith S, Shin TH et al (2017) MLACP: machine-learning-based prediction of anticancer peptides. Oncotarget 8:77121–77136. CrossRefPubMedPubMedCentralGoogle Scholar
  21. 21.
    Xu L, Liang G, Wang L et al (2018) A novel hybrid sequence-based model for identifying anticancer peptides. Genes 9:158. CrossRefPubMedCentralGoogle Scholar
  22. 22.
    Akbar S, Hayat M, Iqbal M, Jan MA (2017) iACP-GAEnsC: evolutionary genetic algorithm based ensemble classification of anticancer peptides by utilizing hybrid feature space. Artif Intell Med 79:62–70. CrossRefPubMedGoogle Scholar
  23. 23.
    Hecht-Nielsen R (1987) Counterpropagation networks. Appl Opt 26:4979–4984. CrossRefPubMedGoogle Scholar
  24. 24.
    (2018) Cancer. In: World Health Organ. Accessed 12 Nov 2018
  25. 25.
    Koch CP, Perna AM, Pillong M et al (2013) Scrutinizing MHC-I binding peptides and their limits of variation. PLoS Comput Biol 9:e1003088CrossRefGoogle Scholar
  26. 26.
    Müller AT, Gabernet G, Hiss JA, Schneider G (2017) modlAMP: python for antimicrobial peptides. Bioinformatics 33:2753–2755. CrossRefPubMedGoogle Scholar
  27. 27.
    Kruskal JB (1964) Nonmetric multidimensional scaling: a numerical method. Psychometrika 29:115–129. CrossRefGoogle Scholar
  28. 28.
    Ballabio D, Grisoni F, Todeschini R (2018) Multivariate comparison of classification performance measures. Chemom Intell Lab Syst 174:33–44. CrossRefGoogle Scholar
  29. 29.
    Brown JB (2018) Classifiers and their metrics quantified. Mol Inf 37:1700127. CrossRefGoogle Scholar
  30. 30.
    Zupan J, Novič M, Ruisánchez I (1997) Kohonen and counterpropagation artificial neural networks in analytical chemistry. Chemom Intell Lab Syst 38:1–23. CrossRefGoogle Scholar
  31. 31.
    Kohonen T (2012) Self-organization and associative memory. Springer, Berlin.
  32. 32.
    Goldberg DE, Holland JH (1988) Genetic algorithms and machine learning. Mach Learn 3:95–99. CrossRefGoogle Scholar
  33. 33.
    Ballabio D, Vasighi M, Consonni V, Kompany-Zareh M (2011) Genetic algorithms for architecture optimisation of counter-propagation artificial neural networks. Chemom Intell Lab Syst 105:56–64. CrossRefGoogle Scholar
  34. 34.
    Ballabio D, Consonni V, Todeschini R (2009) The Kohonen and CP-ANN toolbox: a collection of MATLAB modules for self organizing maps and counterpropagation artificial neural networks. Chemom Intell Lab Syst 98:115–122. CrossRefGoogle Scholar
  35. 35.
    Merrifield RB (1963) Solid phase peptide synthesis. I. The synthesis of a tetrapeptide. J Am Chem Soc 85:2149–2154. CrossRefGoogle Scholar
  36. 36.
    Breiman L (1996) Bagging predictors. Mach Learn 24:123–140. CrossRefGoogle Scholar
  37. 37.
    Guo X, Ma C, Du Q et al (2013) Two peptides, TsAP-1 and TsAP-2, from the venom of the Brazilian yellow scorpion, Tityus Serrulatus: evaluation of their antimicrobial and anticancer activities. Biochimie 95:1784–1794. CrossRefPubMedGoogle Scholar
  38. 38.
    Baker MA, Maloy WL, Zasloff M, Jacob LS (1993) Anticancer efficacy of Magainin2 and analogue peptides. Cancer Res 53:3052–3057PubMedGoogle Scholar
  39. 39.
    Usmani SS, Bedi G, Samuel JS et al (2017) THPdb: database of FDA-approved peptide and protein therapeutics. PLoS One 12:e0181748. CrossRefPubMedPubMedCentralGoogle Scholar
  40. 40.
    Schneider G, Neidhart W, Giller T, Schmid G (1999) “Scaffold-hopping” by topological pharmacophore search: a contribution to virtual screening. Angew Chem Int Ed 38:2894–2896.<2894::AID-ANIE2894>3.0.CO;2-F CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of Chemistry and Applied Biosciences, RETHINKETH ZurichZurichSwitzerland
  2. 2.Department of Earth and Environmental SciencesUniversity of Milano-BicoccaMilanItaly
  3. 3.Department of Chemical System Engineering, School of EngineeringUniversity of TokyoTokyoJapan
  4. 4.School of Life Science and TechnologyTokyo Institute of TechnologyTokyoJapan

Personalised recommendations