Abstract
Background: Ion channels are a large and growing protein family. Many of them are associated with diseases, and consequently, they are targets for over 700 drugs. Discovery of new ion channels is facilitated with computational methods that predict ion channels and their types from protein sequences. However, these methods were never comprehensively compared and evaluated.
Objective: We offer first-of-its-kind comprehensive survey of the sequence-based predictors of ion channels. We describe eight predictors that include five methods that predict ion channels, their types, and four classes of the voltage-gated channels. We also develop and use a new benchmark dataset to perform comparative empirical analysis of the three currently available predictors.
Results: While several methods that rely on different designs were published, only a few of them are currently available and offer a broad scope of predictions. Support and availability after publication should be required when new methods are considered for publication. Empirical analysis shows strong performance for the prediction of ion channels and modest performance for the prediction of ion channel types and voltage-gated channel classes. We identify a substantial weakness of current methods that cannot accurately predict ion channels that are categorized into multiple classes/types.
Conclusion: Several predictors of ion channels are available to the end users. They offer practical levels of predictive quality. Methods that rely on a larger and more diverse set of predictive inputs (such as PSIONplus) are more accurate. New tools that address multi-label prediction of ion channels should be developed.
Keywords: Ion channel, voltage-gated ion channel, ligand-gated ion channel, prediction.
Graphical Abstract
[1]
Domene CS, Haider MSP. Sansom, Ion channel structures: a review of recent progress. Curr Opin Drug Discov Devel 2003; 6(5): 611-9.
[2]
Bagal SK, Brown AD, Cox PJ, et al. Ion channels as therapeutic targets: a drug discovery perspective. J Med Chem 2013; 56(3): 593-624.
[3]
Ger MF, Rendon G, Tilson JL, Jakobsson E, et al. Domain-based identification and analysis of glutamate receptor ion channels and their relatives in prokaryotes. PLoS One 2010; 5(10): e12827.
[5]
Bech-Hansen NT, Naylor MJ, Maybaum TA, et al. Loss-of-function mutations in a calcium-channel alpha1-subunit gene in Xp11.23 cause incomplete X-linked congenital stationary night blindness. Nat Genet 1998; 19(3): 264-7.
[6]
Jentsch TJ. Neuronal KCNQ potassium channels: physiology and role in disease. Nat Rev Neurosci 2000; 1(1): 21-30.
[7]
Peters DJ, Spruit L, Saris JJ, et al. Chromosome 4 localization of a second gene for autosomal dominant polycystic kidney disease. Nat Genet 1993; 5(4): 359-62.
[8]
Curran ME, Splawski I, Timothy KW, et al. A molecular basis for cardiac arrhythmia: HERG mutations cause long QT syndrome. Cell 1995; 80(5): 795-803.
[9]
Wang Q, Shen J, Splawski I, et al. SCN5A mutations associated with an inherited cardiac arrhythmia, long QT syndrome. Cell 1995; 80(5): 805-11.
[10]
Lafreniere RG, Cader MZ, Poulin JF, et al. A dominant-negative mutation in the TRESK potassium channel is linked to familial migraine with aura. Nat Med 2010; 16(10): 1157-U1501.
[11]
Kaczorowski GJ, McManus OB, Priest BT, et al. Ion channels as drug targets: The next GPCRs. JGP 2008; 131(5): 399-405.
[12]
Sheu S-S, Lederer W. Lidocaine’s negative inotropic and antiarrhythmic actions. Dependence on shortening of action potential duration and reduction of intracellular sodium activity. Circ Res 1985; 57(4): 578-90.
[13]
Skov MJ, Beck JC, de Kater AW, et al. Nonclinical safety of ziconotide: an intrathecal analgesic of a new pharmaceutical class. Int J Toxicol 2007; 26(5): 411-21.
[14]
Schmidtko A, Lötsch J, Freynhagen R, Geisslinger G, et al. Ziconotide for treatment of severe chronic pain. Lancet 2010; 375(9725): 1569-77.
[15]
Santos R, Ursu O, Gaulton A, et al. A comprehensive map of molecular drug targets. Nat Rev Drug Discov 2017; 16(1): 19.
[16]
Gabashvili IS, Sokolowski BH, Morton CC, Giersch AB, et al. Ion Channel Gene Expression in the Inner Ear. J Assoc Res Otolaryngol 2007; 8(3): 305-28.
[17]
Consortium U. UniProt: the universal protein knowledgebase. Nucleic Acids Res 2018; 46(5): 2699.
[18]
Saha S, Zack J, Singh B, Raghava GP, et al. VGIchan: prediction and classification of voltage-gated ion channels. Genomics Proteomics Bioinformatics 2006; 4(4): 253-8.
[19]
Chen W, Lin H. Identification of voltage-gated potassium channel subfamilies from sequence information using support vector machine. Comput Biol Med 2012; 42(4): 504-7.
[20]
Liu LX, Li ML, Tan FY, et al. Local sequence information‐based support vector machine to classify voltage‐gated potassium channels. Acta Biochim Biophys Sin (Shanghai) 2006; 38(6): 363-71.
[21]
Liu W, Deng EZ, Chen W, Lin H. Identifying the subfamilies of voltage-gated potassium channels using feature selection technique. Int J Mol Sci 2014; 15(7): 12940-51.
[22]
Gao J, Cui W, Sheng Y, et al. PSIONplus: Accurate sequence-based predictor of ion channels and their types. PLoS One 2016; 11(4): e0152964.
[23]
Lin H, Ding H. Predicting ion channels and their types by the dipeptide mode of pseudo amino acid composition. J Theor Biol 2011; 269(1): 64-9.
[24]
Tiwari AK, Srivastava R. An efficient approach for the prediction of ion channels and their subfamilies. Comput Biol Chem 2015; 58: 205-21.
[25]
Zhao YW, Su ZD, Yang W, et al. IonchanPred 2.0: a tool to predict ion channels and their types. Int J Mol Sci 2017; 18(9)
[26]
Altschul SF, Madden TL, Schäffer AA, et al. Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. Nucleic Acids Res 1997; 25(17): 3389-402.
[27]
Cao R, Cheng J. Integrated protein function prediction by mining function associations, sequences, and protein-protein and gene-gene interaction networks. Methods 2016; 93: 84-91.
[28]
Cao R, Cheng J. Protein single-model quality assessment by feature-based probability density functions. Sci Rep 2016; 6: 23990.
[29]
Cao R, Freitas C, Chan L, et al. ProLanGO: Protein function prediction
using neural machine translation based on a recurrent neural
network. Mol 2017; 22(10).
[30]
Cao R, Wang Z, Wang Y, Cheng J. SMOQ: a tool for predicting the absolute residue-specific quality of a single protein model with support vector machines. BMC Bioinformatics 2014; 15: 120.
[31]
Meng F, Uversky VN, Kurgan L. Comprehensive review of methods for prediction of intrinsic disorder and its molecular functions. Cell Mol Life Sci 2017; 74(17): 3069-90.
[32]
Hayat M, Khan A. Mem-PHybrid: Hybrid features-based prediction system for classifying membrane protein types. Anal Biochem 2012; 424(1): 35-44.
[33]
Meng F, Wang C, Kurgan L. fDETECT webserver: fast predictor of propensity for protein production, purification, and crystallization. BMC Bioinformatics 2018; 18(1): 580.
[34]
Mishra NK, Chang J, Zhao PX. Prediction of membrane transport proteins and their substrate specificities using primary sequence information. PLoS One 2014; 9(6): e100278.
[35]
Peng Z, Kurgan L. High-throughput prediction of RNA, DNA and protein binding regions mediated by intrinsic disorder. Nucleic Acids Res 2015; 43(18): e121-1.
[36]
Gao J, Eshel F, Yaoqi Z, Jishou R, Lukasz K. BEST: improved prediction of B-cell epitopes from antigen sequences. PLoS One 2012; 7(6): e40104.
[37]
Xianfang W, Wang J, Wang X, Zhang Y. Predicting the Types of Ion Channel-Targeted Conotoxins Based on AVC-SVM Model. J BioMed Res Int 2017; 2017: 8.
[38]
Nugent T, Jones DT. Detecting pore-lining regions in transmembrane protein sequences. BMC Bioinformatics 2012; 13: 169.
[39]
Zheng C, Kurgan L. Prediction of beta-turns at over 80% accuracy based on an ensemble of predicted secondary structures and multiple alignments. BMC Bioinformatics 2008; 9: 430-0.
[40]
Yan J, Marcus M, Kurgan L. Comprehensively designed consensus of standalone secondary structure predictors improves Q3 by over 3%. J Biomol Struct Dyn 2014; 32(1): 36-51.
[41]
Yan J, Mizianty MJ, Filipow PL, Uversky VN, Kurgan L. RAPID: Fast and accurate sequence-based prediction of intrinsic disorder content on proteomic scale. Biochim Biophys Acta 2013; 1834(8): 1671-80.
[42]
Kumar R, Kumari B, Kumar M. Proteome-wide prediction and annotation of mitochondrial and sub-mitochondrial proteins by incorporating domain information. Mitochondrion 2018; 42: 11-22.
[43]
Hayat S, Elofsson A. BOCTOPUS: improved topology prediction of transmembrane β barrel proteins. Bioinformatics 2012; 28(4): 516-22.
[44]
Disfani FM, Hsu WL, Mizianty MJ, et al. MoRFpred, a computational tool for sequence-based prediction and characterization of short disorder-to-order transitioning binding regions in proteins. Bioinformatics 2012; 28(12): i75-83.
[45]
Zhang T, Zhang H, Chen K, et al. Accurate sequence-based prediction of catalytic residues. Bioinformatics 2008; 24(20): 2329-38.
[46]
Kurgan L, Cios K, Chen K. SCPRED: Accurate prediction of protein structural class for sequences of twilight-zone similarity with predicting sequences. BMC Bioinformatics 2008; 9: 226-6.
[47]
Chen K, Mizianty MJ, Kurgan L. ATPsite: sequence-based prediction of ATP-binding residues. Proteome Sci 2011; 9(Suppl. 1): S4-4.
[48]
Cao R, Debswapna B, Jie H, Jianlin C. DeepQA: improving the estimation of single protein model quality with deep belief networks. BMC Bioinformatics 2016; 17(1): 495.
[49]
Gao J, Yang Y, Zhou Y. Grid-based prediction of torsion angle probabilities of protein backbone and its application to discrimination of protein intrinsic disorder regions and selection of model structures. BMC Bioinformatics 2018; 19(1): 29.
[50]
Gao J, Yang Y, Zhou Y. Predicting the errors of predicted local backbone angles and non-local solvent- accessibilities of proteins by deep neural networks. Bioinformatics 2016; 32(24): 3768-73.
[51]
Fu L, Niu B, Zhu Z, Wu S, Li W, et al. CD-HIT: accelerated for clustering the next-generation sequencing data. Bioinformatics 2012; 28(23): 3150-2.
[52]
Huang Y, Niu B, Gao Y, Fu L, Li W, et al. CD-HIT Suite: a web server for clustering and comparing biological sequences. Bioinformatics 2010; 26(5): 680-2.
[53]
Wang H, Feng L, Webb GI, et al. Critical evaluation of bioinformatics tools for the prediction of protein crystallization propensity. Brief Bioinform 2017; 18(6): 1092.
[54]
Yan J, Friedrich S, Kurgan L. A comprehensive comparative review of sequence-based predictors of DNA- and RNA-binding residues. Brief Bioinform 2016; 17(1): 88-105.
[55]
Zhao H, Yang Y, Zhou Y. Prediction of RNA binding proteins comes of age from low resolution to high resolution. Mol Biosyst 2013; 9(10): 2417-25.
[56]
Peng Z, Mizianty MJ, Kurgan L. Genome-scale prediction of proteins with long intrinsically disordered regions. Proteins 2014; 82(1): 145-58.
[57]
Zheng C, Kurgan L. Prediction of beta-turns at over 80% accuracy based on an ensemble of predicted secondary structures and multiple alignments. BMC Bioinformatics 2008; 9: 430.
[58]
Jiang Q, Jin X, Lee SJ, Yao S, et al. Protein secondary structure prediction: A survey of the state of the art. J Mol Graph Model 2017; 76: 379-402.
[59]
Zhang H, Zhang T, Chen K, et al. Critical assessment of high-throughput standalone methods for secondary structure prediction. Brief Bioinform 2011; 12(6): 672-88.
[60]
Gao J, Zhang N, Ruan J. Prediction of protein modification sites of gamma-carboxylation using position specific scoring matrices based evolutionary information. Comput Biol Chem 2013; 47: 215-20.
[61]
Wang T, Zheng W, Wuyun Q, et al. PrAS: Prediction of amidation sites using multiple feature extraction. Comput Biol Chem 2017; 66: 57-62.
[62]
Mizianty MJ, Kurgan L. Improved identification of outer membrane beta barrel proteins using primary sequence, predicted secondary structure, and evolutionary information. Proteins 2011; 79(1): 294-303.
[63]
Tsaousis GN, Hamodrakas SJ, Bagos PG. Predicting Beta Barrel Transmembrane Proteins Using HMMs. Hidden Markov Models: Methods Mol Biol 2017; 1552: 43-61.
[64]
Miao Z, Westhof E. A Large-Scale Assessment of Nucleic Acids Binding Site Prediction Programs. PLOS Comput Biol 2015; 11(12): e1004639.
[65]
Zhang J, Ma Z, Kurgan L. Comprehensive review and empirical analysis of hallmarks of DNA-, RNA- and protein-binding residues in protein chains. Brief Bioinform 2017.
[66]
Ding XM, Pan XY, Xu C, Shen HB. Computational prediction of DNA-protein interactions: a review. Curr Comput Aided Drug Des 2010; 6(3): 197-206.
[67]
Walia RR, El-Manzalawy Y, Honavar VG, Dobbs D, et al. Sequence-based prediction of rna-binding residues in proteins. Prediction of Protein Secondary Structure. Methods Mol Biol 2017; 1484: 205-35.
[68]
Yan J, Kurgan L. DRNApred, fast sequence-based method that accurately predicts and discriminates DNA- and RNA-binding residues. Nucleic Acids Res 2017; 45(10): e84.
[69]
Zhang J, Kurgan L. Review and comparative assessment of sequence-based predictors of protein-binding residues. Brief Bioinform 2018; 19(5): 821-37.
[70]
Zhang ML, Zhou ZH. A review on multi-label learning algorithms. IEEE Trans Knowl Data Eng 2014; 26(8): 1819-37.
[71]
Cerri R, Barros RC, André CPLF, et al. Reduction strategies for hierarchical multi-label classification in protein function prediction. BMC Bioinformatics 2016; 17: 373.
[72]
Wan S, Mak M-W, Kung S-Y. Mem-ADSVM: A two-layer multi-label predictor for identifying multi-functional types of membrane proteins. J Theor Biol 2016; 398: 32-42.
[73]
Stojanova D, Ceci M, Malerba D, Dzeroski S. Using PPI network autocorrelation in hierarchical multi-label classification trees for gene function prediction. BMC Bioinformatics 2013; 14: 285.
[74]
Guo X, Fulin L, Ying J, Zhen W, Chunyu W, et al. Human protein subcellular localization with integrated source and multi-label ensemble classifier. Sci Rep 2016; 6: 28087.
Article Metrics
41
2