Abstract
ROCK II is an important pharmacological target linked to central nervous system disorders such as Alzheimer’s disease. The purpose of this research is to generate ROCK II inhibitor prediction models by machine learning approaches. Firstly, four sets of descriptors were calculated with MOE 2010 and PaDEL-Descriptor, and optimized by F-score and linear forward selection methods. In addition, four classification algorithms were used to initially build 16 classifiers with k-nearest neighbors \((k\hbox {NN})\), naïve Bayes, Random forest, and support vector machine. Furthermore, three sets of structural fingerprint descriptors were introduced to enhance the predictive capacity of classifiers, which were assessed with fivefold cross-validation, test set validation and external test set validation. The best two models, MFK + MACCS and MLR + SubFP, have both MCC values of 0.925 for external test set. After that, a privileged substructure analysis was performed to reveal common chemical features of ROCK II inhibitors. Finally, binding modes were analyzed to identify relationships between molecular descriptors and activity, while main interactions were revealed by comparing the docking interaction of the most potent and the weakest ROCK II inhibitors. To the best of our knowledge, this is the first report on ROCK II inhibitors utilizing machine learning approaches that provides a new method for discovering novel ROCK II inhibitors.
Graphical Abstract
Similar content being viewed by others
References
Julian L, Olson MF (2014) Rho-associated coiled-coil containing kinases (ROCK): structure, regulation, and functions. Small GTPases 5:e29846. doi:10.4161/sgtp.29846
Matsui T, Amano M, Yamamoto T, Chihara K, Nakafuku M, Ito M, Nakano T, Okawa K, Iwamatsu A, Kaibuchi K (1996) Rho-associated kinase, a novel serine/threonine kinase, as a putative target for small GTP binding protein Rho. EMBO J 15:2208–2216
Schofield AV, Bernard O (2013) Rho-associated coiled-coil kinase (ROCK) signaling and disease. Crit Rev Biochem Mol 48:301–316. doi:10.3109/10409238.2013.786671
Iizuka M, Kimura K, Wang S, Kato K, Amano M, Kaibuchi K, Mizoguchi A (2012) Distinct distribution and localization of Rho-kinase in mouse epithelial, muscle and neural tissues. Cell Struct Funct 37:155–175. doi:10.1247/csf.12018
Nakagawa O, Fujisawa K, Ishizaki T, Saito Y, Nakao K, Narumiya S (1996) ROCK-I and ROCK-II, two isoforms of Rho-associated coiled-coil forming protein serine/threonine kinase in mice. FEBS Lett 392:189–193. doi:10.1016/0014-5793(96)00811-3
Satoh K, Fukumoto Y, Shimokawa H (2011) Rho-kinase: important new therapeutic target in cardiovascular diseases. Am J Physiol Heart Circ Physiol 301:H287–96. doi:10.1152/ajpheart.00327.2011
Mueller BK, Mack H, Teusch N (2005) Rho kinase, a promising drug target for neurological disorders. Nat Rev Drug Discov 4:387–398. doi:10.1038/nrd1719
Chong CM, Ai N, Lee S (2016) ROCK in CNS: different roles of isoforms, and therapeutic target for neurodegenerative disorders. Curr Drug Targets 18:455–462. doi:10.2174/1389450117666160401123825
Kubo T, Yamaguchi A, Iwata N, Yamashita T (2008) The therapeutic effects of Rho-ROCK inhibitors on CNS disorders. Ther Clin Risk Manag 4:605–615. doi:10.2147/TCRM.S2907
Wen X, Wang L, Liu Z, Liu Y, Hu J (2014) Intracranial injection of PEG-PEI/ROCK II-siRNA improves cognitive impairment in a mouse model of Alzheimer’s disease. Int J Neurosci 124:697–703. doi:10.3109/00207454.2013.877014
Saal K-A, Koch JC, Tatenhorst L, Szegö ÉM, Ribas VT, Michel U, Bähr M, Tönges L, Lingor P (2015) AAV. shRNA-mediated downregulation of ROCK2 attenuates degeneration of dopaminergic neurons in toxin-induced models of Parkinson’s disease in vitro and in vivo. Neurobiol Dis 73:150–162. doi:10.1016/j.nbd.2014.09.013
Feng Y, LoGrasso PV, Defert O, Li R (2015) Rho kinase (ROCK) inhibitors and their therapeutic potential. J Med Chem 59:2269–2300. doi:10.1021/acs.jmedchem.5b00683
Pan P, Shen M, Yu H, Li Y, Li D, Hou T (2013) Advances in the development of Rho-associated protein kinase (ROCK) inhibitors. Drug Discov Today 18:1323–1333. doi:10.1016/j.drudis.2013.09.010
Shah S, Savjani J (2016) A review on ROCK-II inhibitors: from molecular modelling to synthesis. Bioorg Med Chem Lett 26:2383–2391. doi:10.1016/j.bmcl.2016.03.113
Sasaki Y, Suzuki M, Hidaka H (2002) The novel and specific Rho-kinase inhibitor (S)-(+)-2-methyl-1-[(4-methyl-5-isoquinoline)sulfonyl]-homopiperazine as a probing molecule for Rho-kinase-involved pathway. Pharmacol Ther 93:225–232. doi:10.1016/S0163-7258(02)00191-2
Ikenoya M, Hidaka H, Hosoya T, Suzuki M, Yamamoto N, Sasaki Y (2002) Inhibition of Rho-kinase-induced myristoylated alanine-rich C kinase substrate (MARCKS) phosphorylation in human neuronal cells by H-1152, a novel and specific Rho-kinase inhibitor. J Neurochem 81:9–16. doi:10.1046/j.1471-4159.2002.00801.x
Logé C, Wallez V, Scalbert E, Cariotourmaniantz C, Loirand G, Pacaud P, Lesieur D (2002) Rho-kinase Inhibitors: pharmacomodulations on the lead compound Y-32885. J Enzyme Inhib Med Chem 17:381–390. doi:10.1080/1475636021000005659
Yamaguchi H, Miwa Y, Kasa M, Kitano K, Amano M, Kaibuchi K, Hakoshima T (2006) Structural basis for induced-fit binding of Rho-kinase to the inhibitor Y-27632. J Biochem 140:305–311. doi:10.1093/jb/mvj172
Yin Y, Lin L, Ruiz C, Cameron MD, Pocas J, Grant W, Schröter T, Chen W, Duckett D, Schürer S (2009) Benzothiazoles as Rho-associated kinase (ROCK-II) inhibitors. Bioorg Med Chem Lett 19:6686–6690. doi:10.1016/j.bmcl.2009.09.115
Chen YT, Bannister TD, Weiser A, Griffin E, Lin L, Ruiz C, Cameron MD, Schürer S, Duckett D, Schröter T, LoGrasso P, Feng Y (2008) Chroman-3-amides as potent Rho kinase inhibitors. Bioorg Med Chem Lett 18:6406–6409. doi:10.1016/j.bmcl.2008.10.080
Chowdhury S, Sessions EH, Pocas JR, Grant W, Schröter T, Lin L, Ruiz C, Cameron MD, Schürer S, Lograsso P (2011) Discovery and optimization of indoles and 7-azaindoles as Rho kinase (ROCK) inhibitors (part-I). Bioorg Med Chem Lett 21:7107–7112. doi:10.1016/j.bmcl.2011.09.083
Feng Y, Yin Y, Weiser A, Griffin E, Cameron MD, Lin L, Ruiz C, Schürer SC, Inoue T, Rao PV (2008) Discovery of substituted 4-(pyrazol-4-yl)-phenylbenzodioxane-2-carboxamides as potent and highly selective Rho kinase (ROCK-II) inhibitors. J Med Chem 51:6642–6645. doi:10.1021/jm800986w
Gong LL, Fang LH, Peng JH, Liu AL, Du GH (2010) Integration of virtual screening with high-throughput screening for the identification of novel Rho-kinase I inhibitors. J Biotechnol 145:295–303. doi:10.1016/j.jbiotec.2009.12.003
Shen M, Yu H, Li Y, Li P, Pan P, Zhou S, Zhang L, Li S, Lee SM-Y, Hou T (2013) Discovery of Rho-kinase inhibitors by docking-based virtual screening. Mol Biosyst 9:1511–1521. doi:10.1039/c3mb00016h
Shen M, Tian S, Pan P, Sun H, Li D, Li Y, Zhou H, Li C, Lee SM-Y, Hou T (2015) Discovery of novel ROCK1 inhibitors via integrated virtual screening strategy and bioassays. Sci Rep 5:16749. doi:10.1038/srep16749
Gong H, Yuan Z, Zhan L (2016) High-throughput screening against \(\sim \)6.1 million structurally diverse, lead-like compounds to discover novel ROCK inhibitors for cerebral injury recovery. Mol Divers 20:537–549. doi:10.1007/s11030-015-9650-y
Shen M, Zhou S, Li Y, Pan P, Zhang L, Hou T (2013) Discovery and optimization of triazine derivatives as ROCK1 inhibitors: molecular docking, molecular dynamics simulations and free energy calculations. Mol Biosyst 9:361–374. doi:10.1039/c2mb25408e
Zhu L, Yang Y, Lu X (2016) The selectivity and promiscuity of brain-neuroregenerative inhibitors between ROCK1 and ROCK2 isoforms: an integration of SB-QSSR modelling, QM/MM analysis and in vitro kinase assay. SAR QSAR Environ Res 27:47–65. doi:10.1080/1062936X.2015.1132765
Fang J, Liu C, Wang Q, Lin P, Cheng F (2017) In silico polypharmacology of natural products. Brief Bioinform 2017:1–19. doi:10.1093/bib/bbx045
Fang J, Yang R, Gao L, Zhou D, Yang S, Liu A-l, Du G-h (2013) Predictions of BuChE inhibitors using support vector machine and naive Bayesian classification techniques in drug discovery. J Chem Inf Model 53:3009–3020. doi:10.1021/ci400331p
Fang J, Yang R, Gao L, Yang S, Pang X, Li C, He Y, Liu A-L, Du G-H (2015) Consensus models for CDK5 inhibitors in silico and their application to inhibitor discovery. Mol Divers 19:149–162. doi:10.1007/s11030-014-9561-3
Fang J, Li Y, Liu R, Pang X, Li C, Yang R, He Y, Lian W, Liu A-L, Du G-H (2015) Discovery of multitarget-directed ligands against Alzheimer’s disease through systematic prediction of chemical-protein interactions. J Chem Inf Model 55:149–164. doi:10.1021/ci500574n
Fang J, Pang XC, Yan R, Lian W, Li C, Wang Q, Liu AL, Du G (2016) Discovery of neuroprotective compounds by machine learning approaches. RSC Adv 6:9857–9871. doi:10.1039/C5RA23035G
Chemical Computing Group Inc (2010) Molecular Operating Environment (MOE), version 2010.10. Montreal, Quebec, Canada. https://www.chemcomp.com/MOE-Molecular_Operating_Environment.htm
Yap CW (2011) PaDEL-descriptor: an open source software to calculate molecular descriptors and fingerprints. J Comput Chem 32:1466–1474. doi:10.1002/jcc.21707
Liu T, Lin Y, Wen X, Jorissen RN, Gilson MK (2007) BindingDB: a web-accessible database of experimentally determined protein-ligand binding affinities. Nucl Acids Res 35(suppl 1):D198–D201. doi:10.1093/nar/gkl999
MDL Information Systems Inc (2002) MDL ISIS/BASE, version 2.5. http://www.iop.vast.ac.vn/theor/conferences/smp/1st/kaminuma/ChemDraw/isisbaseinfo.html
Mysinger MM, Carchia M, Irwin JJ, Shoichet BK (2012) Directory of useful decoys, enhanced (DUD-E): better ligands and decoys for better benchmarking. J Med Chem 55:6582–6594. doi:10.1021/jm300687e
Boland S, Bourin A, Alen J, Geraets J, Schroeders P, Castermans K, Kindt N, Boumans N, Panitti L, Fransen S (2015) Design, synthesis, and biological evaluation of novel, highly active soft ROCK inhibitors. J Med Chem 58:4309–4324. doi:10.1021/acs.jmedchem.5b00308
Patel RA, Liu Y, Wang B, Li R, Sebti SM (2014) Identification of novel ROCK inhibitors with anti-migratory and anti-invasive activities. Oncogene 33:550–555. doi:10.1038/onc.2012.634
Oh K-S, Oh BK, Park CH, Seo HW, Kang NS, Lee JH, Lee JS, Lee BH (2013) Cardiovascular effects of a novel selective Rho kinase inhibitor, 2-(1H-indazole-5-yl) amino-4-methoxy-6-piperazino triazine (DW1865). Eur J Pharmacol 702:218–226. doi:10.1016/j.ejphar.2013.01.027
Shaw D, Hollingworth G, Soldermann N, Sprague E, Schuler W, Vangrevelinghe E, Duggan N, Thomas M, Kosaka T, Waters N (2014) Novel ROCK inhibitors for the treatment of pulmonary arterial hypertension. Bioorg Med Chem Lett 24:4812–4817. doi:10.1016/j.bmcl.2014.09.002
Schirok H, Kast R, Figueroa-Pérez S, Bennabi S, Gnoth MJ, Feurer A, Heckroth H, Thutewohl M, Paulsen H, Knorr A (2008) Design and synthesis of potent and selective azaindole-based Rho kinase (ROCK) inhibitors. ChemMedChem 3:1893–1904. doi:10.1002/cmdc.200800211
Yin Y, Cameron MD, Lin L, Khan S, Schröter T, Grant W, Pocas J, Chen YT, Schürer S, Pachori A (2010) Discovery of potent and selective urea-based ROCK inhibitors and their effects on intraocular pressure in rats. ACS Med Chem Lett 1:175–179. doi:10.1021/ml1000382
Pireddu R, Forinash KD, Sun NN, Martin MP, Sung S-S, Alexander B, Zhu J-Y, Guida WC, Schönbrunn E, Sebti SM (2012) Pyridylthiazole-based ureas as inhibitors of Rho associated protein kinases (ROCK1 and 2). MedChemComm 3:699–709. doi:10.1039/C2MD00320A
Klekota J, Roth FP (2008) Chemical substructures that enrich for biological activity. Bioinformatics 24:2518–2525. doi:10.1093/bioinformatics/btn479
Wang L, Wang M, Yan A, Dai B (2013) Using self-organizing map (SOM) and support vector machine (SVM) for classification of selectivity of ACAT inhibitors. Mol Divers 17:85–96. doi:10.1007/s11030-012-9404-z
Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten IH (2009) The WEKA data mining software: an update. SIGKDD Explor 11:10–18. doi:10.1145/1656274.1656278
Chen YW, Lin CJ (2006) Combining SVMs with various feature selection strategies. Springer 207:315–324. doi:10.1007/978-3-540-35488-8_13
Chang C, Lin C (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2:1–27. doi:10.1145/1961189.1961199
Demsar J, Curk T, Erjavec A, Gorup C, Hocevar T, Milutinovic M, Mozina M, Polajnar M, Toplak M, Staric A, Stajdohar M, Umek L, Zagar L, Zbontar J, Zitnik M, Zupan B (2013) Orange: data mining toolbox in Python. J Mach Learn Res 14:2349–2353
Larose DT (2005) Discovering knowledge in data: an introduction to data mining. Wiley, Hoboken. doi:10.1002/0471687545
Xia X, Maliski EG, Gallant P, Rogers D (2004) Classification of kinase inhibitors using a Bayesian model. J Med Chem 47:4463–4470. doi:10.1021/jm0303195
Breiman L (2001) Random forests. Mach Learn 45:5–32. doi:10.1023/A:1010933404324
Byvatov E, Schneider G (2002) Support vector machine applications in bioinformatics. Appl Bioinform 2:67–77
Yang ZR (2004) Biological applications of support vector machines. Brief Bioinform 5:328–338. doi:10.1093/bib/5.4.328
Vapnik VN (1999) An overview of statistical learning theory. IEEE Trans Neural Netw 10:988–999. doi:10.1109/72.788640
Fawcett T (2006) An introduction to ROC analysis. Pattern Recognit Lett 27:861–874. doi:10.1016/j.patrec.2005.10.010
Schnur DM, Hermsmeier MA, Tebben AJ (2006) Are target-family-privileged substructures truly privileged? J Med Chem 49:2000–2009. doi:10.1021/jm0502900
Jensen BF, Vind C, Padkjær SB, Brockhoff PB, Refsgaard HH (2007) In silico prediction of cytochrome P450 2D6 and 3A4 inhibition using Gaussian kernel weighted k-nearest neighbor and extended connectivity fingerprints, including structural fragment analysis of inhibitors versus noninhibitors. J Med Chem 50:501–511. doi:10.1021/jm060333s
Ma S, Dai Y (2011) Principal component analysis based methods in bioinformatics studies. Brief Bioinform 12:714–722. doi:10.1093/bib/bbq090
Amin SA, Adhikari N, Jha T, Gayen S (2016) First molecular modeling report on novel arylpyrimidine kynurenine monooxygenase inhibitors through multi-QSAR analysis against Huntington’s disease: a proposal to chemists!. Bioorg Med Chem Lett 26:5712–5718. doi:10.1016/j.bmcl.2016.10.058
Amin SA, Adhikari N, Jha T, Gayen S (2016) Exploring structural requirements of unconventional Knoevenagel-type indole derivatives as anticancer agents through comparative QSAR modelling approaches. Can J Chem 94:637–644. doi:10.1139/cjc-2016-0050
Acknowledgements
This work was supported by the National Natural Science Foundation of China (Nos. 81273817, 81473740, 81673627), Doctoral Fund of Education Ministry of China (No. 20134425110003), Guangdong Provincial Major Science and Technology for Special Program of China (No. 2012A080202017), the South China Chinese Medicine Collaborative Innovation Center (No. A1-AFD01514A05).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflicts of interest
All the authors do not have any conflicts of interest.
Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Cai, C., Wu, Q., Luo, Y. et al. In silico prediction of ROCK II inhibitors by different classification approaches. Mol Divers 21, 791–807 (2017). https://doi.org/10.1007/s11030-017-9772-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11030-017-9772-5