PredSTP: a highly accurate SVM based model to predict sequential cystine stabilized peptides

BMC Bioinformatics

Erich J Baker³  Christopher Michel Kearney²  Tanvir Sajed⁴  S. M. Ashiqul Islam¹ 

[1]Institute of Biomedical Studies, Baylor University, Waco, TX, USA

[2]Department of Biology, Baylor University, Waco, TX, USA

[3]Department of Computer Science, Baylor University, One Bear Place #97356, Waco, TX, USA

[4]Department of Computer Science, University of Alberta, Edmonton, AB, Canada

关键词: Antimicrobial peptides;    Nonknotted STPs, Insecticidal peptides;    Cylotides;    Inhibitory cytine knot (ICKs);    Sequential tri-disulfide peptides (STPs);    Tri-disulfide peptide toxins;    SVM;    Machine learning;   

Others  :  1231815
DOI  :  10.1186/s12859-015-0633-x

 received in 2014-10-02, accepted in 2015-06-01,  发布年份 2015

【 摘 要 】

Background

Numerous organisms have evolved a wide range of toxic peptides for self-defense and predation. Their effective interstitial and macro-environmental use requires energetic and structural stability. One successful group of these peptides includes a tri-disulfide domain arrangement that offers toxicity and high stability. Sequential tri-disulfide connectivity variants create highly compact disulfide folds capable of withstanding a variety of environmental stresses. Their combination of toxicity and stability make these peptides remarkably valuable for their potential as bio-insecticides, antimicrobial peptides and peptide drug candidates. However, the wide sequence variation, sources and modalities of group members impose serious limitations on our ability to rapidly identify potential members. As a result, there is a need for automated high-throughput member classification approaches that leverage their demonstrated tertiary and functional homology.

Results

We developed an SVM-based model to predict sequential tri-disulfide peptide (STP) toxins from peptide sequences. One optimized model, called PredSTP, predicted STPs from training set with sensitivity, specificity, precision, accuracy and a Matthews correlation coefficient of 94.86 %, 94.11 %, 84.31 %, 94.30 % and 0.86, respectively, using 200 fold cross validation. The same model outperforms existing prediction approaches in three independent out of sample testsets derived from PDB.

Conclusion

PredSTP can accurately identify a wide range of cystine stabilized peptide toxins directly from sequences in a species-agnostic fashion. The ability to rapidly filter sequences for potential bioactive peptides can greatly compress the time between peptide identification and testing structural and functional properties for possible antimicrobial and insecticidal candidates. A web interface is freely available to predict STP toxins from http://crick.ecs.baylor.edu/.

【 授权许可】

   
2015 Islam et al.

【 图 表 】

Fig. 1.

Fig. 2.

Fig. 3.

Fig. 4.

Fig. 5.

Fig. 1.

Fig. 2.

Fig. 3.

Fig. 4.

Fig. 5.

【 参考文献 】

• [1]Carlini CR, Grossi-de-Sá MF. Plant toxic proteins with insecticidal properties. A review on their potentialities as bioinsecticides. Toxicon Off J Int Soc Toxinol. 2002; 40:1515-1539.
• [2]Gordon YJ, Romanowski EG, McDermott AM. A review of antimicrobial peptides and their therapeutic potential as anti-infective drugs. Curr Eye Res. 2005; 30:505-515.
• [3]Lehrer RI, Lichtenstein AK, Ganz T. Defensins: antimicrobial and cytotoxic peptides of mammalian cells. Annu Rev Immunol. 1993; 11:105-128.
• [4]Hemingway J, Ranson H. Insecticide resistance in insect vectors of human disease. Annu Rev Entomol. 2000; 45:371-391.
• [5]Brooke BD, Hunt RH, Chandre F, Carnevale P, Coetzee M. Stable chromosomal inversion polymorphisms and insecticide resistance in the malaria vector mosquito Anopheles gambiae (Diptera: Culicidae). J Med Entomol. 2002; 39:568-573.
• [6]Aloush V, Navon-Venezia S, Seigman-Igra Y, Cabili S, Carmeli Y. Multidrug-resistant Pseudomonas aeruginosa: risk factors and clinical impact. Antimicrob Agents Chemother. 2006; 50:43-48.
• [7]Hiramatsu K, Aritaka N, Hanaki H, Kawasaki S, Hosoda Y, Hori S, Fukuchi Y, Kobayashi I. Dissemination in Japanese hospitals of strains of Staphylococcus aureus heterogeneously resistant to vancomycin. Lancet. 1997; 350:1670-1673.
• [8]Marr AK, Gooderham WJ, Hancock RE. Antibacterial peptides for therapeutic use: obstacles and realistic outlook. Curr Opin Pharmacol. 2006; 6:468-472.
• [9]Monroc S, Badosa E, Feliu L, Planas M, Montesinos E, Bardají E. De novo designed cyclic cationic peptides as inhibitors of plant pathogenic bacteria. Peptides. 2006; 27:2567-2574.
• [10]Braunstein A, Papo N, Shai Y. In vitro activity and potency of an intravenously injected antimicrobial peptide and its DL amino acid analog in mice infected with bacteria. Antimicrob Agents Chemother. 2004; 48:3127-3129.
• [11]Matsumura M, Signor G, Matthews BW. Substantial increase of protein stability by multiple disulphide bonds. Nature. 1989; 342:291-293.
• [12]Tugyi R, Mezö G, Fellinger E, Andreu D, Hudecz F. The effect of cyclization on the enzymatic degradation of herpes simplex virus glycoprotein D derived epitope peptide. J Pept Sci Off Publ Eur Pept Soc. 2005; 11:642-649.
• [13]Schroeder BO, Wu Z, Nuding S, Groscurth S, Marcinowski M, Beisner J, Buchner J, Schaller M, Stange EF, Wehkamp J. Reduction of disulphide bonds unmasks potent antimicrobial activity of human β-defensin 1. Nature. 2011; 469:419-423.
• [14]Circo R, Skerlavaj B, Gennaro R, Amoroso A, Zanetti M. Structural and functional characterization of hBD-1(Ser35), a peptide deduced from a DEFB1 polymorphism. Biochem Biophys Res Commun. 2002; 293:586-592.
• [15]Jennings CV, Rosengren KJ, Daly NL, Plan M, Stevens J, Scanlon MJ, Waine C, Norman DG, Anderson MA, Craik DJ. Isolation, solution structure, and insecticidal activity of kalata B2, a circular protein with a twist: do Möbius strips exist in nature? Biochemistry (Mosc). 2005; 44:851-860.
• [16]Bende NS, Dziemborowicz S, Mobli M, Herzig V, Gilchrist J, Wagner J, Nicholson GM, King GF, Bosmans F. A distinct sodium channel voltage-sensor locus determines insect selectivity of the spider toxin Dc1a. Nat Commun. 2014; 5:4350.
• [17]Reddy KVR, Yedery RD, Aranha C. Antimicrobial peptides: premises and promises. Int J Antimicrob Agents. 2004; 24:536-547.
• [18]Henriques ST, Craik DJ. Cyclotides as templates in drug design. Drug Discov Today. 2010; 15:57-64.
• [19]Lewis RJ, Garcia ML. Therapeutic potential of venom peptides. Nat Rev Drug Discov. 2003; 2:790-802.
• [20]Góngora-Benítez M, Tulla-Puche J, Albericio F. Multifaceted roles of disulfide bonds. Peptides as therapeutics. Chem Rev. 2014; 114:901-926.
• [21]Gracy J, Le-Nguyen D, Gelly J-C, Kaas Q, Heitz A, Chiche L. KNOTTIN: the knottin or inhibitor cystine knot scaffold in 2007. Nucleic Acids Res. 2008; 36(Database issue):D314-319.
• [22]Zhu S, Peigneur S, Gao B, Luo L, Jin D, Zhao Y, Tytgat J. Molecular diversity and functional evolution of scorpion potassium channel toxins. Mol Cell Proteomics MCP. 2011; 10:M110.002832.
• [23]Gould A, Ji Y, Aboye TL, Camarero JA. Cyclotides, a novel ultrastable polypeptide scaffold for drug discovery. Curr Pharm Des. 2011; 17:4294-4307.
• [24]Bulet P, Stöcklin R, Menin L. Anti-microbial peptides: from invertebrates to vertebrates. Immunol Rev. 2004;198:169–84.
• [25]Conibear AC, Rosengren KJ, Daly NL, Henriques ST, Craik DJ. The cyclic cystine ladder in θ-defensins is important for structure and stability, but not antibacterial activity. J Biol Chem. 2013; 288:10830-10840.
• [26]Conibear AC, Bochen A, Rosengren KJ, Stupar P, Wang C, Kessler H, Craik DJ. The cyclic cystine ladder of theta-defensins as a stable, bifunctional scaffold: a proof-of-concept study using the integrin-binding RGD motif. ChemBioChem. 2014; 15:451-459.
• [27]Ovchinnikova TV, Balandin SV, Aleshina GM, Tagaev AA, Leonova YF, Krasnodembsky ED, Men’shenin AV, Kokryakov VN. Aurelin, a novel antimicrobial peptide from jellyfish Aurelia aurita with structural features of defensins and channel-blocking toxins. Biochem Biophys Res Commun. 2006; 348:514-523.
• [28]Ye M, Khoo KK, Xu S, Zhou M, Boonyalai N, Perugini MA, Shao X, Chi C, Galea CA, Wang C, Norton RS. A helical conotoxin from Conus imperialis has a novel cysteine framework and defines a new superfamily. J Biol Chem. 2012; 287:14973-14983.
• [29]Craik DJ, Daly NL, Bond T, Waine C. Plant cyclotides: a unique family of cyclic and knotted proteins that defines the cyclic cystine knot structural motif. J Mol Biol. 1999; 294:1327-1336.
• [30]Craik DJ, Daly NL, Mulvenna J, Plan MR, Trabi M. Discovery, structure and biological activities of the cyclotides. Curr Protein Pept Sci. 2004; 5:297-315.
• [31]Possani LD, Becerril B, Delepierre M, Tytgat J. Scorpion toxins specific for Na + −channels. Eur J Biochem. 1999;264:287–300.
• [32]Bulet P, Hetru C, Dimarcq JL, Hoffmann D. Antimicrobial peptides in insects; structure and function. Dev Comp Immunol. 1999; 23:329-344.
• [33]Possani LD, Becerril B, Delepierre M, Tytgat J. Scorpion toxins specific for Na + −channels. Eur J Biochem. 1999; 264:287-300.
• [34]Colgrave ML, Craik DJ. Thermal, chemical, and enzymatic stability of the cyclotide kalata B1: the importance of the cyclic cystine knot †. Biochemistry (Mosc). 2004; 43:5965-5975.
• [35]Gracy J, Chiche L. Structure and modeling of knottins, a promising molecular scaffold for drug discovery. Curr Pharm Des. 2011; 17:4337-4350.
• [36]Yi H-Y, Chowdhury M, Huang Y-D, Yu X-Q: Insect antimicrobial peptides and their applications. Appl Microbiol Biotechnol. 2014;98:5807–22.
• [37]Thomma B, Cammue B, Thevissen K. Plant defensins. Planta. 2002; 216:193-202.
• [38]Kolmar H. Biological diversity and therapeutic potential of natural and engineered cystine knot miniproteins. Curr Opin Pharmacol. 2009; 9:608-614.
• [39]Smith JJ, Herzig V, King GF, Alewood PF. The insecticidal potential of venom peptides. Cell Mol Life Sci CMLS. 2013; 70:3665-3693.
• [40]Getz JA, Rice JJ, Daugherty PS. Protease-resistant peptide ligands from a knottin scaffold library. ACS Chem Biol. 2011; 6:837-844.
• [41]Vita C, Roumestand C, Toma F, Ménez A: Scorpion toxins as natural scaffolds for protein engineering. Proc Natl Acad Sci U S A. 1995;92:6404–08.
• [42]Gelly J-C, Gracy J, Kaas Q, Le-Nguyen D, Heitz A, Chiche L. The KNOTTIN website and database: a new information system dedicated to the knottin scaffold. Nucleic Acids Res. 2004; 32(Database issue):D156-159.
• [43]Kedarisetti P, Mizianty MJ, Kaas Q, Craik DJ, Kurgan L. Prediction and characterization of cyclic proteins from sequences in three domains of life. Biochim Biophys Acta. 2014; 1844(1 Pt B):181-190.
• [44]Mulvenna JP, Wang C, Craik DJ. CyBase: a database of cyclic protein sequence and structure. Nucleic Acids Res. 2006; 34(Database issue):D192-194.
• [45]Wang CKL, Kaas Q, Chiche L, Craik DJ. CyBase: a database of cyclic protein sequences and structures, with applications in protein discovery and engineering. Nucleic Acids Res. 2008; 36(Database issue):D206-210.
• [46]Kaas Q, Yu R, Jin A-H, Dutertre S, Craik DJ. ConoServer: updated content, knowledge, and discovery tools in the conopeptide database. Nucleic Acids Res. 2012; 40(Database issue):D325-330.
• [47]Herzig V, Wood DLA, Newell F, Chaumeil P-A, Kaas Q, Binford GJ, Nicholson GM, Gorse D, King GF. ArachnoServer 2.0, an updated online resource for spider toxin sequences and structures. Nucleic Acids Res. 2011; 39(Database issue):D653-657.
• [48]Muggleton S, King RD, Sternberg MJ. Protein secondary structure prediction using logic-based machine learning. Protein Eng. 1992; 5:647-657.
• [49]Bock JR, Gough DA. Predicting protein–protein interactions from primary structure. Bioinform Oxf Engl. 2001; 17:455-460.
• [50]Cai CZ, Han LY, Ji ZL, Chen X, Chen YZ. SVM-Prot: Web-based support vector machine software for functional classification of a protein from its primary sequence. Nucleic Acids Res. 2003; 31:3692-3697.
• [51]Hua S, Sun Z. A novel method of protein secondary structure prediction with high segment overlap measure: support vector machine approach. J Mol Biol. 2001; 308:397-407.
• [52]Cai YD, Liu XJ, Xu X, Zhou GP. Support vector machines for predicting protein structural class. BMC Bioinformatics. 2001; 2:3. BioMed Central Full Text
• [53]Hua S, Sun Z. Support vector machine approach for protein subcellular localization prediction. Bioinformatics. 2001; 17:721-728.
• [54]Huang Y, Niu B, Gao Y, Fu L, Li W. CD-HIT Suite: a web server for clustering and comparing biological sequences. Bioinformatics. 2010; 26:680-682.
• [55]Li W, Godzik A. Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences. Bioinformatics. 2006; 22:1658-1659.
• [56]Emeleus HJ. Advances in Inorganic Chemistry. Academic, New York; 1959.
• [57]Van Beilen JB, Neuenschwander M, Smits THM, Roth C, Balada SB, Witholt B. Rubredoxins Involved in Alkane Oxidation. J Bacteriol. 2002; 184:1722-1732.
• [58]Altschul SF, Madden TL, Schäffer AA, Zhang J, Zhang Z, Miller W, Lipman DJ. Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. Nucleic Acids Res. 1997; 25:3389-3402.
• [59]Niemann HH, Schmoldt H-U, Wentzel A, Kolmar H, Heinz DW. Barnase fusion as a tool to determine the crystal structure of the small disulfide-rich protein McoEeTI. J Mol Biol. 2006; 356:1-8.
• [60]Bosnjak I, Bojovic V, Segvic-Bubic T, Bielen A. Occurrence of protein disulfide bonds in different domains of life: a comparison of proteins from the Protein Data Bank. Protein Eng Des Sel. 2014; 27:65-72.