Skip to main content

Advertisement

SpringerLink
Log in

TargetCPP: accurate prediction of cell-penetrating peptides from optimized multi-scale features using gradient boost decision tree

  • Published:
Journal of Computer-Aided Molecular Design Aims and scope Submit manuscript

Abstract

Cell-penetrating peptides (CPPs) are short length permeable proteins have emerged as drugs delivery tool of therapeutic agents including genetic materials and macromolecules into cells. Recently, CPP has become a hotspot avenue for life science research and paved a new way of disease treatment without harmful impact on cell viability due to nontoxic characteristic. Therefore, the correct identification of CPPs will provide hints for medical applications. Considering the shortcomings of traditional experimental CPPs identification, it is urgently needed to design intelligent predictor for accurate identification of CPPs for the large scale uncharacterized sequences. We develop a novel computational method, called TargetCPP, to discriminate CPPs from Non-CPPs with improved accuracy. In TargetCPP, first the peptide sequences are formulated with four distinct encoding methods i.e., composite protein sequence representation, composition transition and distribution, split amino acid composition, and information theory features. These dominant feature vectors were fused and applied intelligent minimum redundancy and maximum relevancy feature selection method to choose an optimal subset of features. Finally, the predictive model is learned through different classification algorithms on the optimized features. Among these classifiers, gradient boost decision tree algorithm achieved excellent performance throughout the experiments. Notably, the TargetCPP tool attained high prediction Accuracy of 93.54% and 88.28% using jackknife and independent test, respectively. Empirical outcomes prove the superiority and potency of proposed bioinformatics method over state-of-the-art methods. It is highly anticipated that the outcomes of this study will provide a strong background for large scale prediction of CPPs and instructive guidance in clinical therapy and medical applications.

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

Similar content being viewed by others

References

  1. Chou K-C, Shen H-B (2007) Recent progress in protein subcellular location prediction. Anal Biochem 370(1):1–16

    CAS  PubMed  Google Scholar 

  2. Krogh A et al (2001) Predicting transmembrane protein topology with a hidden Markov model: application to complete genomes. J Mol Biol 305(3):567–580

    CAS  Google Scholar 

  3. Lennernäs H et al (1996) Comparison between active and passive drug transport in human intestinal epithelial (Caco-2) cells in vitro and human jejunum in vivo. Int J Pharm 127(1):103–107

    Google Scholar 

  4. Ramsey JD, Flynn NH (2015) Cell-penetrating peptides transport therapeutics into cells. Pharmacol Ther 154:78–86

    CAS  PubMed  Google Scholar 

  5. Khalili P et al (2006) A non–RGD-based integrin binding peptide (ATN-161) blocks breast cancer growth and metastasis in vivo. Mol Cancer Ther 5(9):2271–2280

    CAS  PubMed  Google Scholar 

  6. Trabulo S et al (2013) Cell-penetrating peptides as nucleic acid delivery systems: from biophysics to biological applications. Curr Pharm Des 19(16):2895–2923

    CAS  PubMed  Google Scholar 

  7. Gebbing M et al (2015) Gene therapeutic approaches to inhibit hepatitis B virus replication. World J Hepatol 7(2):150

    PubMed  PubMed Central  Google Scholar 

  8. Michiue H et al (2014) The acceleration of boron neutron capture therapy using multi-linked mercaptoundecahydrododecaborate (BSH) fused cell-penetrating peptide. Biomaterials 35(10):3396–3405

    CAS  PubMed  Google Scholar 

  9. Frankel AD, Pabo CO (1988) Cellular uptake of the tat protein from human immunodeficiency virus. Cell 55(6):1189–1193

    CAS  PubMed  Google Scholar 

  10. Green M, Loewenstein PM (1988) Autonomous functional domains of chemically synthesized human immunodeficiency virus tat trans-activator protein. Cell 55(6):1179–1188

    CAS  PubMed  Google Scholar 

  11. Fonseca SB, Pereira MP, Kelley SO (2009) Recent advances in the use of cell-penetrating peptides for medical and biological applications. Adv Drug Deliv Rev 61(11):953–964

    CAS  PubMed  Google Scholar 

  12. Nakase I et al (2011) Efficient intracellular delivery of nucleic acid pharmaceuticals using cell-penetrating peptides. Acc Chem Res 45(7):1132–1139

    PubMed  Google Scholar 

  13. Lakshmanan M et al (2012) Rapid and efficient gene delivery into plant cells using designed peptide carriers. Biomacromol 14(1):10–16

    Google Scholar 

  14. Rüter C et al (2010) A newly identified bacterial cell-penetrating peptide that reduces the transcription of pro-inflammatory cytokines. J Cell Sci 123(13):2190–2198

    PubMed  Google Scholar 

  15. Zhang D, Wang J, Xu D (2016) Cell-penetrating peptides as noninvasive transmembrane vectors for the development of novel multifunctional drug-delivery systems. J Control Release 229:130–139

    CAS  PubMed  Google Scholar 

  16. Patel A, Cholkar K, Mitra AK (2014) Recent developments in protein and peptide parenteral delivery approaches. Therapeutic delivery 5(3):337–365

    CAS  PubMed  PubMed Central  Google Scholar 

  17. Soler M et al (2014) Identification of BP16 as a non-toxic cell-penetrating peptide with highly efficient drug delivery properties. Org Biomol Chem 12(10):1652–1663

    CAS  PubMed  Google Scholar 

  18. Kato T et al (2016) Plasmid DNA delivery by arginine-rich cell-penetrating peptides containing unnatural amino acids. Bioorg Med Chem 24(12):2681–2687

    CAS  PubMed  Google Scholar 

  19. Farkhani SM et al (2016) Enhanced cellular internalization of CdTe quantum dots mediated by arginine-and tryptophan-rich cell-penetrating peptides as efficient carriers. Artificial cells, nanomedicine, and biotechnology 44(6):1424–1428

    CAS  PubMed  Google Scholar 

  20. Mäger I et al (2012) The role of endocytosis on the uptake kinetics of luciferin-conjugated cell-penetrating peptides. Biochim Biophys Acta (BBA) 1818(3):502–511

    Google Scholar 

  21. Zaro JL, Shen W-C (2015) Cationic and amphipathic cell-penetrating peptides (CPPs): Their structures and in vivo studies in drug delivery. Front Chem Sci Eng 9(4):407–427

    CAS  Google Scholar 

  22. Zhang R et al (2006) Molecular modeling studies of peptide drug candidates against SARS. Med Chem 2(3):309–314

    CAS  PubMed  Google Scholar 

  23. Chou K-C et al (2006) Progress in computational approach to drug development against SARS. Curr Med Chem 13(27):3263–3270

    CAS  PubMed  Google Scholar 

  24. Zhang Q, Gao H, He Q (2015) Taming cell penetrating peptides: never too old to teach old dogs new tricks. Mol Pharm 12(9):3105–3118

    CAS  PubMed  Google Scholar 

  25. Yang Y et al (2015) Synergistic targeted delivery of payload into cancer cells using liposomes co-modified with photolabile-caged cell-penetrating peptides and targeting ligands. J Control Release 213:e128

    PubMed  Google Scholar 

  26. Otvos L (2008) In Peptide-based drug design. Peptide-based drug design: here and now, Springer. pp 1–8.

  27. Raucher D, Ryu JS (2015) Cell-penetrating peptides: strategies for anticancer treatment. Trends Mol Med 21(9):560–570

    CAS  PubMed  Google Scholar 

  28. Simon MJ et al. (2010) Evaluation of the cell-penetrating peptide TAT as a trans-blood-brain barrier delivery vehicle. In: Bioengineering Conference, Proceedings of the 2010 IEEE 36th Annual Northeast. IEEE

  29. Gao S et al (2011) An unusual cell penetrating peptide identified using a plasmid display-based functional selection platform. ACS Chem Biol 6(5):484–491

    CAS  PubMed  PubMed Central  Google Scholar 

  30. Lee JH et al (2012) Screening of cell-penetrating peptides using mRNA display. Biotechnol J 7(3):387–396

    CAS  PubMed  Google Scholar 

  31. Hansen M, Kilk K, Langel Ü (2008) Predicting cell-penetrating peptides. Adv Drug Deliv Rev 60(4–5):572–579

    CAS  PubMed  Google Scholar 

  32. Dobchev A et al (2010) Prediction of cell-penetrating peptides using artificial neural networks. Curr Comput-Aided Drug Des 6(2):79–89

    CAS  PubMed  Google Scholar 

  33. Sanders WS et al (2011) Prediction of cell penetrating peptides by support vector machines. PLoS Comput Biol 7(7):e1002101

    CAS  PubMed  PubMed Central  Google Scholar 

  34. Gautam, A., et al., CPPsite: a curated database of cell penetrating peptides. Database, 2012. 2012.

  35. Holton TA et al (2013) CPPpred: prediction of cell penetrating peptides. Bioinformatics 29(23):3094–3096

    CAS  Google Scholar 

  36. Chen L et al (2015) Prediction and analysis of cell-penetrating peptides using pseudo-amino acid composition and random forest models. Amino Acids 47(7):1485–1493

    CAS  PubMed  Google Scholar 

  37. Tang H et al (2016) Prediction of cell-penetrating peptides with feature selection techniques. Biochem Biophys Res Commun 477(1):150–154

    CAS  PubMed  Google Scholar 

  38. Diener C et al (2016) Effective design of multifunctional peptides by combining compatible functions. PLoS Comput Biol 12(4):e1004786

    PubMed  PubMed Central  Google Scholar 

  39. Wei L, Tang J, Zou Q (2017) SkipCPP-Pred: an improved and promising sequence-based predictor for predicting cell-penetrating peptides. BMC Genomics 18(7):1

    Google Scholar 

  40. Wei L et al (2017) CPPred-RF: a sequence-based predictor for identifying cell-penetrating peptides and their uptake efficiency. J Proteome Res 16(5):2044–2053

    CAS  PubMed  Google Scholar 

  41. Zhang L et al (2015) An ensemble method to distinguish bacteriophage virion from non-virion proteins based on protein sequence characteristics. Int J Mol Sci 16(9):21734–21758

    CAS  PubMed  PubMed Central  Google Scholar 

  42. Zhang Y-N et al (2012) Predicting protein-ATP binding sites from primary sequence through fusing bi-profile sampling of multi-view features. BMC Bioinform 13(1):118

    CAS  Google Scholar 

  43. Han GS et al (2013) An ensemble method for predicting subnuclear localizations from primary protein structures. PLoS ONE 8(2):e57225

    CAS  PubMed  PubMed Central  Google Scholar 

  44. Kabir M et al (2018) Intelligent computational method for discrimination of anticancer peptides by incorporating sequential and evolutionary profiles information. Chemom Intell Lab Syst 182:158–165

    CAS  Google Scholar 

  45. Ali F et al (2018) DBPPred-PDSD: Machine learning approach for prediction of DNA-binding proteins using Discrete Wavelet Transform and optimized integrated features space. Chemom Intell Lab Syst 182:21–30

    CAS  Google Scholar 

  46. Li W, Godzik A (2006) Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences. Bioinformatics 22(13):1658–1659

    CAS  Google Scholar 

  47. Wei Z-S et al (2015) A cascade random forests algorithm for predicting protein-protein interaction sites. IEEE Trans Nanobiosci 14(7):746–760

    Google Scholar 

  48. Hu J et al. (2019) TargetDBP: accurate DNA-binding protein prediction via sequence-based multi-view feature learning. IEEE/ACM transactions on computational biology and bioinformatics

  49. Ahmad K, Waris M, Hayat M (2016) Prediction of protein submitochondrial locations by incorporating dipeptide composition into Chou’s general pseudo amino acid composition. J Membr Biol 249:1–12

    Google Scholar 

  50. Kurgan L et al (2009) CRYSTALP2: sequence-based protein crystallization propensity prediction. BMC Struct Biol 9(1):50

    PubMed  PubMed Central  Google Scholar 

  51. Golmohammadi SK et al. (2007) Classification of cell membrane proteins. in Frontiers in the Convergence of Bioscience and Information Technologies, 2007. FBIT 2007. IEEE

  52. Xia X, Li W-H (1998) What amino acid properties affect protein evolution? J Mol Evol 47(5):557–564

    CAS  PubMed  Google Scholar 

  53. Qiu W-R et al (2017) iKcr-PseEns: identify lysine crotonylation sites in histone proteins with pseudo components and ensemble classifier. Genomics 110:239–246

    PubMed  Google Scholar 

  54. Hayat M, Khan A (2011) Predicting membrane protein types by fusing composite protein sequence features into pseudo amino acid composition. J Theor Biol 271(1):10–17

    CAS  PubMed  Google Scholar 

  55. Chen W et al (2016) iACP: a sequence-based tool for identifying anticancer peptides. Oncotarget 7(13):16895–16909

    PubMed  PubMed Central  Google Scholar 

  56. Hayat M, Khan A, Yeasin M (2012) Prediction of membrane proteins using split amino acid and ensemble classification. Amino Acids 42(6):2447–2460

    CAS  PubMed  Google Scholar 

  57. Singh O, Su EC-Y (2016) Prediction of HIV-1 protease cleavage site using a combination of sequence, structural, and physicochemical features. BMC Bioinform 17(17):478

    Google Scholar 

  58. Tang H, Chen W, Lin H (2016) Identification of immunoglobulins using Chou's pseudo amino acid composition with feature selection technique. Mol BioSyst 12(4):1269–1275

    CAS  PubMed  Google Scholar 

  59. Eisenberg D et al (1984) Analysis of membrane and surface protein sequences with the hydrophobic moment plot. J Mol Biol 179(1):125–142

    CAS  PubMed  Google Scholar 

  60. Karshikoff A, Nilsson L, Ladenstein R (2015) Rigidity versus flexibility: the dilemma of understanding protein thermal stability. FEBS J 282(20):3899–3917

    CAS  PubMed  Google Scholar 

  61. Huber R (1987) Flexibility and rigidity, requirements for the function of proteins and protein pigment complexes. Portland Press Limited, London

    Google Scholar 

  62. Kedarisetti KD, Kurgan L, Dick S (2006) Classifier ensembles for protein structural class prediction with varying homology. Biochem Biophys Res Commun 348(3):981–988

    CAS  PubMed  Google Scholar 

  63. Dubchak I et al (1995) Prediction of protein folding class using global description of amino acid sequence. Proc Natl Acad Sci 92(19):8700–8704

    CAS  PubMed  Google Scholar 

  64. Bhadra P et al (2018) AmPEP: Sequence-based prediction of antimicrobial peptides using distribution patterns of amino acid properties and random forest. Sci Rep 8(1):1697

    PubMed  PubMed Central  Google Scholar 

  65. Nair R, Rost B (2005) Mimicking cellular sorting improves prediction of subcellular localization. J Mol Biol 348(1):85–100

    CAS  PubMed  Google Scholar 

  66. Cai C et al (2003) SVM-Prot: web-based support vector machine software for functional classification of a protein from its primary sequence. Nucleic Acids Res 31(13):3692–3697

    CAS  PubMed  PubMed Central  Google Scholar 

  67. Jones A. et al. (2015) RF-Phos: random forest-based prediction of phosphorylation sites. in 2015 IEEE international conference on bioinformatics and biomedicine (BIBM). IEEE

  68. Zhang X, Liu S (2016) RBPPred: predicting RNA-binding proteins from sequence using SVM. Bioinformatics 33(6):854–862

    Google Scholar 

  69. Govindan G, AS Nair (2011) Composition, transition and distribution (CTD)—a dynamic feature for predictions based on hierarchical structure of cellular sorting. in India Conference (INDICON), 2011 Annual IEEE. IEEE

  70. Capra JA, Singh M (2007) Predicting functionally important residues from sequence conservation. Bioinformatics 23(15):1875–1882

    CAS  PubMed  Google Scholar 

  71. Wei L. et al. (2017) Fast prediction of protein methylation sites using a sequence-based feature selection technique. IEEE/ACM Transactions On Computational Biology and Bioinformatics

  72. Ismail HD, Newman RH (2016) RF-Hydroxysite: a random forest based predictor for hydroxylation sites. Mol BioSyst 12(8):2427–2435

    CAS  PubMed  PubMed Central  Google Scholar 

  73. Arif M, Hayat M, Jan Z (2018) iMem-2LSAAC: a two-level model for discrimination of membrane proteins and their types by extending the notion of SAAC into Chou's pseudo amino acid composition. J Theor Biol 442:11–21

    CAS  PubMed  Google Scholar 

  74. Khan ZU, Hayat M, Khan MA (2015) Discrimination of acidic and alkaline enzyme using Chou’s pseudo amino acid composition in conjunction with probabilistic neural network model. J Theor Biol 365:197–203

    CAS  PubMed  Google Scholar 

  75. Ahmad S, Kabir M, Hayat M (2015) Identification of Heat Shock Protein families and J-protein types by incorporating Dipeptide Composition into Chou's general PseAAC. Comput Methods Programs Biomed 122(2):165–174

    PubMed  Google Scholar 

  76. Mirza MT et al (2013) MitProt-Pred: Predicting mitochondrial proteins of Plasmodium falciparum parasite using diverse physiochemical properties and ensemble classification. Comput Biol Med 43(10):1502–1511

    CAS  PubMed  Google Scholar 

  77. Wang S et al (2016) Analysis and identification of aptamer-compound interactions with a maximum relevance minimum redundancy and nearest neighbor algorithm. BioMed Res Int 102:1567–1577

    Google Scholar 

  78. Cheng F et al (2012) Prediction of chemical-protein interactions network with weighted network-based inference method. PLoS ONE 7(7):e41064

    CAS  PubMed  PubMed Central  Google Scholar 

  79. Iqbal M, Hayat M (2016) “iSS-Hyb-mRMR”: identification of splicing sites using hybrid space of pseudo trinucleotide and pseudo tetranucleotide composition. Comput Methods Programs Biomed 128:1–11

    PubMed  Google Scholar 

  80. Win TS et al (2018) PAAP: A web server for predicting antihypertensive activity of peptides. Future Med Chem 10(15):1749–1767

    CAS  Google Scholar 

  81. Peng H, Long F, Ding C (2005) Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell 27(8):1226–1238

    PubMed  Google Scholar 

  82. Zhang Y, Ding C, Li T (2008) Gene selection algorithm by combining reliefF and mRMR. BMC genomics 9(2):S27

    PubMed  PubMed Central  Google Scholar 

  83. Xu Y et al (2014) Identification of thyroid carcinoma related genes with mRMR and shortest path approaches. PLoS ONE 9(4):e94022

    PubMed  PubMed Central  Google Scholar 

  84. Li Z et al (2014) The prediction of methylation states in human DNA sequences based on hexanucleotide composition and feature selection. Anal Methods 6(6):1897–1904

    CAS  Google Scholar 

  85. Cai Y et al (2012) Prediction of lysine ubiquitination with mRMR feature selection and analysis. Amino Acids 42(4):1387–1395

    CAS  PubMed  Google Scholar 

  86. Ding H et al (2013) Prediction of Golgi-resident protein types by using feature selection technique. Chemom Intell Lab Syst 124:9–13

    CAS  Google Scholar 

  87. Peng H, Long F, Ding C (2005) Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell 8:1226–1238

    Google Scholar 

  88. Chen T, C. Guestrin (2016) Xgboost: A scalable tree boosting system. In: Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining. ACM

  89. Pal M, Mather PM (2003) An assessment of the effectiveness of decision tree methods for land cover classification. Remote Sens Environ 86(4):554–565

    Google Scholar 

  90. Feng PM et al (2013) Naive Bayes classifier with feature selection to identify phage virion proteins. Computat Math Methods Med. https://doi.org/10.1155/2013/530696

    Article  Google Scholar 

  91. Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29:1189–1232

    Google Scholar 

  92. Chen F et al (2017) Prediction of luciferase inhibitors by the high-performance MIEC-GBDT approach based on interaction energetic patterns. Phys Chem Chem Phys 19(15):10163–10176

    CAS  PubMed  Google Scholar 

  93. Liao Z et al (2016) In silico prediction of gamma-aminobutyric acid type-A receptors using novel machine-learning-based SVM and GBDT approaches. BioMed Res Int. https://doi.org/10.1155/2016/2375268

    Article  PubMed  PubMed Central  Google Scholar 

  94. Zhou C et al (2017) Multi-scale encoding of amino acid sequences for predicting protein interactions using gradient boosting decision tree. PLoS ONE 12(8):e0181426

    PubMed  PubMed Central  Google Scholar 

  95. Rawi R et al (2017) PaRSnIP: sequence-based protein solubility prediction using gradient boosting machine. Bioinformatics 34(7):1092–1098

    PubMed Central  Google Scholar 

  96. Arif M et al (2020) Pred-BVP-Unb: fast prediction of bacteriophage Virion proteins using un-biased multi-perspective properties with recursive feature elimination. Genomics 112(2):1565–1574

    CAS  PubMed  Google Scholar 

  97. Wang Y et al (2017) Improved detection of DNA-binding proteins via compression technology on PSSM information. PLoS ONE 12(9):e185587

    Google Scholar 

Download references

Acknowledgements

This work was supported by the National Natural Science Foundation of China (Nos. 61772273 and 61373062) and Fundamental Research Funds for the Central Universities (No. 30918011104).

Author information

Authors and Affiliations

  1. School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, 210094, China

    Muhammad Arif, Saeed Ahmad, Farman Ali, Ge Fang, Min Li & Dong-Jun Yu

Authors
  1. Muhammad Arif
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Saeed Ahmad
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Farman Ali
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ge Fang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Min Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Dong-Jun Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Dong-Jun Yu.

Ethics declarations

Conflict of interests

The authors declare that they have no conflict of interests.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 18 kb)

Supplementary file2 (ZIP 3911 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Arif, M., Ahmad, S., Ali, F. et al. TargetCPP: accurate prediction of cell-penetrating peptides from optimized multi-scale features using gradient boost decision tree. J Comput Aided Mol Des 34, 841–856 (2020). https://doi.org/10.1007/s10822-020-00307-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10822-020-00307-z

Keywords

Search

Navigation