Abstract
Cyclin-dependent kinase 5 (CDK5) has emerged as a principal therapeutic target for Alzheimer’s disease. It is highly desirable to develop computational models that can predict the inhibitory effects of a compound towards CDK5 activity. In this study, two machine learning tools (naive Bayesian and recursive partitioning) were used to generate four single classifiers from a large dataset containing 462 CDK5 inhibitors and 1,500 non-inhibitors. Then, two types of consensus models [combined classifier-artificial neural networks (CC-ANNs) and consensus prediction] were applied to combine four single classifiers to obtain superior performance. The results showed that both consensus models outperformed four single classifiers, and (MCC \(=\) 0.806) was superior to consensus prediction (MCC \(=\) 0.711) for an external test set. To illustrate the practical applications of the CC-ANN model in virtual screening, an in-house dataset containing 29,170 compounds was screened, and 40 compounds were selected for further bioactivity assays. The assay results showed that 13 out of 40 compounds exerted CDK5/p35 inhibitory activities with IC\(_{50}\) values ranging from 9.23 to \(229.76 \;\upmu \hbox {M}\). Interestingly, three new scaffolds that had not been previously reported as CDK5 inhibitors were found in this study. These studies prove that our protocol is an effective approach to predict small-molecule CDK5 affinity and identify novel lead compounds.
Graphical Abstract
Similar content being viewed by others
References
Melnikova I (2007) Therapies for Alzheimer’s disease. Nat Rev Drug Discov 6:341–342. doi:10.1038/nrd2314
Querfurth HW, LaFerla FM (2010) Alzheimer’s disease. N Engl J Med 362:329–344. doi:10.1056/NEJMra0909142
Dudash K (2011) Alzheimer’s disease: new therapies and the role of biomarkers. Biotechnol Healthc 8:22–23
Dhavan R, Tsai LH (2001) A decade of cdk5. Nat Rev Mol Cell Biol 2:749–759. doi:10.1038/35096019
Cruz JC, Tsai LH (2004) Cdk5 deregulation in the pathogenesis of Alzheimer’s disease. Trends Mol Med 10:452–458. doi:10.1016/j.molmed.2004.07.001
Goedert M (1993) Tau protein and the neurofibrillary pathology of Alzheimer’s disease. Trends Neurosci 16:460–465. doi:10.1111/j.1749-6632.1996.tb34410.x
Tolnay M, Probst A (1999) REVIEW: tau protein pathology in Alzheimer’s disease and related disorders. Neuropathol Appl Neurobiol 25:171–187. doi:10.1046/j.1365-2990.00182.x
Patrick GN, Zukerberg L, Nikolic M, Monte S, Dikkes P, Tsai LH (1999) Conversion of p35 to p25 deregulates Cdk5 activity and promotes neurodegeneration. Nature 402:615–622. doi:10.1038/45159
Lau LF, Patricia AS, Mark AS, Schachter JB (2002) Cdk5 as a drug target for the treatment of Alzheimer’s disease. J Mol Neurosci 19:267–270. doi:10.1385/JMN:19:3:267
Hosoi T, Uchiyama M, Okumura E, Saito T, Ishiguro K, Uchida T, Okuyama A, Kishimoto T, Hisanaga S (1995) Evidence for cdk5 as a major activity phosphorylating tau protein in porcine brain extract. J Biochem 117:741–749
Cardone A, Hassan SA, Albers RW, Sriram RD, Pant HC (2010) Structural and dynamic determinants of ligand binding and regulation of cyclin-dependent kinase 5 by pathological activator p25 and inhibitory peptide CIP. J Mol Biol 401:478–492. doi:10.1016/j.jmb.2010.06.040
Ahlijanian MK, Barrezueta NX, Williams RD, Jakowski A, Kowsz KP, McCarthy S, Coskran T, Carlo A, Seymour PA, Burkhardt JE, Nelson RB, McNeish JD (2000) Hyperphosphorylated tau and neurofilament and cytoskeletal disruptions in mice overexpressing human p25, an activator of cdk5. Proc Natl Acad Sci USA 97:2910–2915. doi:10.1073/pnas.040577797
Fischer A, Sananbenesi F, Pang PT, Lu B, Tsai LH (2005) Opposing roles of transient and prolonged expression of p25 in synaptic plasticity and hippocampus-dependent memory. Neuron 48:825–838. doi:10.1016/j.neuron.2005.10.033
Cruz JC, Tseng HC, Goldman JA, Shih H, Tsai LH (2003) Aberrant Cdk5 activation by p25 triggers pathological events leading to neurodegeneration and neurofibrillary tangles. Neuron 40:471–483. doi:10.1016/S0896-6273(03)00627-5
Chou KC, Watenpaugh KD, Heinrikson RL (1999) A model of the complex between cyclin-dependent kinase 5 (Cdk5) and the activation domain of neuronal Cdk5 activator. Biochem Biophys Res Commun 259:420–428. doi:10.1006/bbrc.1999.0792
Chou KC (2004) Insights from modelling the 3D structure of the extracellular domain of alpha7 nicotinic acetylcholine receptor. Biochem Biophys Res Commun 319:433–438. doi:10.1016/j.bbrc.2004.05.016
Chou KC (2004) Insights from modeling the tertiary structure of human BACE2. J Proteome Res 3:1069–1072. doi:10.1021/pr049905s
Chou KC (2005) Modeling the tertiary structure of human cathepsin-E. Biochem Biophys Res Commun 331:56–60. doi:10.1016/j.bbrc.2005.03.123
Chou KC, Howe WJ (2002) Prediction of the tertiary structure of the beta-secretase zymogen. Biochem Biophys Res Commun 292:702–708. doi:10.1006/bbrc.2002.6686
Chou KC (2004) Structural bioinformatics and its impact to biomedical science. Curr Med Chem 11:2105–2134. doi:10.2174/0929867043364667
Chou KC, Luan CH, Chou KC, Johnson GV (2002) Identification of the N-terminal functional domains of Cdk5 by molecular truncation and computer modeling. Proteins 48:447–453. doi:10.1002/prot.10173
Pielak RM, Schnell JR, Chou JJ (2009) Mechanism of drug inhibition and drug resistance of influenza A M2 channel. Proc Natl Acad Sci USA 106:7379–7384. doi:10.1073/pnas.0902548106
Chou KC, Wei DQ, Zhong WZ (2003) Binding mechanism of coronavirus main proteinase with ligands and its implication to drug design against SARS. Biochem Biophys Res Commun 308:148–151. doi:10.1016/S0006-291X(03)01342-1
Du QS, Huang RB, Chou KC (2008) Recent advances in QSAR and their applications in predicting the activities of chemical molecules, peptides and proteins for drug design. Curr Protein Pept Sci 9:248–260. doi:10.2174/138920308784534005
Du QS, Huang RB, Wei YT, Du LQ, Chou KC (2008) Multiple field three dimensional quantitative structure–activity relationship (MF-3D-QSAR). J Comput Chem 29:211–219. doi:10.1002/jcc.20776
Du QS, Huang RB, Wei YT, Pang ZW, Du LQ, Chou KC (2009) Fragment-based quantitative structure–activity relationship (FB-QSAR) for fragment-based drug design. J Comput Chem 30:295–304. doi:10.1002/jcc.21056
Prado-Prado FJ, Martinez de la Vega O (2009) Unified QSAR approach to antimicrobials. 4. Multi-target QSAR modeling and comparative multi-distance study of the giant components of antiviral drug–drug complex networks. Bioorg Med Chem 17:569–575. doi:10.1016/j.bmc.2008.11.075
Fang J, Huang D, Zhao W, Ge H, Luo HB, Xu J (2011) A new protocol for predicting novel GSK-3\(\beta \) ATP competitive inhibitors. J Chem Inf Model 51:1431–1438. doi: 10.1021/ci2001154
Fang J, Yang R, Gao L, Zhou D, Yang S, Liu AL, Du GH (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
Singh N, Chaudhury S, Liu R, AbdulHameed MD, Tawa G, Wallqvist A (2012) QSAR classification model for antibacterial compounds and its use in virtual screening. J Chem Inf Model 52:2559–2569. doi:10.1021/ci300336v
Myint KZ, Wang L, Tong Q, Xie XQ (2012) Molecular fingerprint-based artificial neural networks QSAR for ligand biological activity predictions. Mol Pharm 9:2912–2923. doi:10.1021/mp300237z
Fernandez M, Tundidor-Camba A, Caballero J (2005) Modeling of cyclin-dependent kinase inhibition by 1H-pyrazolo[3,4-d]pyrimidine derivatives using artificial neural network ensembles. J Chem Inf Model 45:1884–1895. doi:10.1021/ci050263i
Li J, Liu H, Yao X, Liu M, Hu Z, Fan B (2007) Structure–activity relationship study of oxindole-based inhibitors of cyclin-dependent kinases based on least-squares support vector machines. Anal Chim Acta 581:333–342. doi:10.1016/j.aca.2006.08.031
Ducrot P, Legraverend M, Grierson DS (2000) 3D-QSAR CoMFA on cyclin-dependent kinase inhibitors. J Med Chem 43:4098–4108. doi:10.1021/jm000965t
Kunick C, Lauenroth K, Wieking K, Xie X, Schultz C, Gussio R, Zaharevitz D, Leost M, Meijer L, Weber A, Jorgensen FS, Lemcke T (2004) Evaluation and comparison of 3D-QSAR CoMSIA models for CDK1, CDK5, and GSK-3 inhibition by paullones. J Med Chem 47:22–36. doi:10.1021/jm0308904
Singh SK, Dessalew N, Bharatam PV (2006) 3D-QSAR CoMFA study on indenopyrazole derivatives as cyclin dependent kinase 4 (CDK4) and cyclin dependent kinase 2 (CDK2) inhibitors. Eur J Med Chem 41:1310–1319. doi:10.1016/j.ejmech.2006.06.010
Singh SK, Dessalew N, Bharatam PV (2007) 3D-QSAR CoMFA study on oxindole derivatives as cyclin dependent kinase 1 (CDK1) and cyclin dependent kinase 2 (CDK2) inhibitors. Med Chem 3:75–84. doi:10.2174/157340607779317517
Caballero J, Fernandez M, Gonzalez-Nilo FD (2008) Structural requirements of pyrido[2,3-d]pyrimidin-7-one as CDK4/D inhibitors: 2D autocorrelation, CoMFA and CoMSIA analyses. Bioorg Med Chem 16:6103–6115. doi:10.1016/j.bmc.2008.04.048
Babu PA, Smiles DJ, Narasu ML, Srinivas K (2008) Identification of novel CDK2 inhibitors by QSAR and virtual screening procedures. QSAR Comb Sci 27:1362–1373. doi:10.1002/qsar.200860041
Dessalew N, Singh SK (2008) 3D-QSAR CoMFA and CoMSIA study on benzodipyrazoles as cyclin dependent kinase 2 inhibitors. Med Chem 4:313–321. doi:10.2174/157340608784872244
Liu T, Lin Y, Wen X, Jorissen RN, Gilson MK (2007) BindingDB: a web-accessible database of experimentally determined protein–ligand binding affinities. Nucleic Acids Res 35:D198–201. doi:10.1093/nar/gkl999
Chioua M, Samadi A, Soriano E, Lozach O, Meijer L, Marco-Contelles J (2009) Synthesis and biological evaluation of 3,6-diamino-1H-pyrazolo[3,4-b]pyridine derivatives as protein kinase inhibitors. Bioorg Med Chem Lett 19:4566–4569. doi:10.1016/j.bmcl.2009.06.099
Helal CJ, Kang Z, Lucas JC, Gant T, Ahlijanian MK, Schachter JB, Richter KE, Cook JM, Menniti FS, Kelly K, Mente S, Pandit J, Hosea N (2009) Potent and cellularly active 4-aminoimidazole inhibitors of cyclin-dependent kinase 5/p25 for the treatment of Alzheimer’s disease. Bioorg Med Chem Lett 19:5703–5707. doi:10.1016/j.bmcl.2009.08.019
Jain P, Flaherty PT, Yi S, Chopra I, Bleasdell G, Lipay J, Ferandin Y, Meijer L, Madura JD (2011) Design, synthesis, and testing of an 6-O-linked series of benzimidazole based inhibitors of CDK5/p25. Bioorg Med Chem 19:359–373. doi:10.1016/j.bmc.2010.11.022
Kassis P, Brzeszcz J, Beneteau V, Lozach O, Meijer L, Le Guevel R, Guillouzo C, Lewinski K, Bourg S, Colliandre L, Routier S, Merour JY (2011) Synthesis and biological evaluation of new 3-(6-hydroxyindol-2-yl)-5-(Phenyl) pyridine or pyrazine V-Shaped molecules as kinase inhibitors and cytotoxic agents. Eur J Med Chem 46:5416–5434. doi:10.1016/j.ejmech.2011.08.048
Laha JK, Zhang X, Qiao L, Liu M, Chatterjee S, Robinson S, Kosik KS, Cuny GD (2011) Structure–activity relationship study of 2,4-diaminothiazoles as Cdk5/p25 kinase inhibitors. Bioorg Med Chem Lett 21:2098–2101. doi:10.1016/j.bmcl.2011.01.140
Shiradkar M, Thomas J, Kanase V, Dighe R (2011) Studying synergism of methyl linked cyclohexyl thiophenes with triazole: synthesis and their cdk5/p25 inhibition activity. Eur J Med Chem 46:2066–2074. doi:10.1016/j.ejmech.2011.02.059
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
Chemical Computing Group Inc. (2010) Molecular Operating Environment (MOE), version 2010.10. Chemical Computing Group Inc., Montreal, Canada
Accelrys Inc. (2012) Discovery Studio 3.1. Accelrys Inc., San Diego. http://www.accelrys.com
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
MathWorks Inc. Matlab Version 7.5.0.342 (R2007b). MathWorks Inc., Natick
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
Lamanna C, Bellini M, Padova A, Westerberg G, Maccari L (2008) Straightforward recursive partitioning model for discarding insoluble compounds in the drug discovery process. J Med Chem 51:2891–2897. doi:10.1021/jm701407x
Cheng F, Yu Y, Shen J, Yang L, Li W, Liu G, Lee PW, Tang Y (2011) Classification of cytochrome P450 inhibitors and noninhibitors using combined classifiers. J Chem Inf Model 51:996–1011. doi:10.1021/ci200028n
Mansouri K, Ringsted T, Ballabio D, Todeschini R, Consonni V (2013) Quantitative structure–activity relationship models for ready biodegradability of chemicals. J Chem Inf Model 53:867–878. doi:10.1021/ci4000213
Andrea TA, Kalayeh H (1991) Applications of neural networks in quantitative structure–activity relationships of dihydrofolate reductase inhibitors. J Med Chem 34:2824–2836. doi:10.1021/jm00113a022
Huang YS, Liu K, Suen CY (1994) A neural network approach for multiclassifier recognition systems. In: Proceedings of the fourth international workshop on frontiers in handwriting recognition, Taiwan, Dec, pp 235–244
Fan YN, Xiao X, Min JL, Chou KC (2014) iNR-Drug: predicting the interaction of drugs with nuclear receptors in cellular networking. Int J Mol Sci 15:4915–4937. doi:10.3390/ijms15034915
Xu Y, Wen X, Wen LS, Wu LY, Deng NY, Chou KC (2014) iNitro-Tyr: prediction of nitrotyrosine sites in proteins with general pseudo amino acid composition. PLoS One 9:e105018. doi:10.1371/journal.pone.0105018
Xiao X, Wu ZC, Chou KC (2014) iLoc-Virus: a multi-label learning classifier for identifying the subcellular localization of virus proteins with both single and multiple sites. J Theor Biol 284:42–51. doi:10.1016/j.jtbi.2011.06.005
Chen L, Zeng WM, Cai YD, Feng KY, Chou KC (2012) Predicting Anatomical Therapeutic Chemical (ATC) classification of drugs by integrating chemical–chemical interactions and similarities. PLoS One 7:e35254. doi:10.1371/journal.pone.0035254
Chou KC (2013) Some remarks on predicting multi-label attributes in molecular biosystems. Mol Biosyst 9:1092–1100. doi:10.1039/c3mb25555g
Zatloukal M, Jorda R, Gucky T, Reznickova E, Voller J, Pospisil T, Malinkova V, Adamcova H, Krystof V, Strnad M (2013) Synthesis and in vitro biological evaluation of 2,6,9-trisubstituted purines targeting multiple cyclin-dependent kinases. Eur J Med Chem 61:61–72. doi:10.1016/j.ejmech.2012.06.036
Demange L, Abdellah FN, Lozach O, Ferandin Y, Gresh N, Meijer L, Galons H (2013) Potent inhibitors of CDK5 derived from roscovitine: synthesis, biological evaluation and molecular modelling. Bioorg Med Chem Lett 23:125–131. doi:10.1016/j.bmcl.2012.10.141
Malmstrom J, Viklund J, Slivo C, Costa A, Maudet M, Sandelin C, Hiller G, Olsson LL, Aagaard A, Geschwindner S, Xue Y, Vasange M (2012) Synthesis and structure–activity relationship of 4-(1,3-benzothiazol-2-yl)-thiophene-2-sulfonamides as cyclin-dependent kinase 5 (cdk5)/p25 inhibitors. Bioorg Med Chem Lett 22:5919–5923. doi:10.1016/j.bmcl.2012.07.068
Demange L, Lozach O, Ferandin Y, Hoang NT, Meijer L, Galons H (2012) Synthesis and evaluation of new potent inhibitors of CK1 and CDK5, two kinases involved in Alzheimer’s disease. Med Chem Res 22:3247–3258. doi:10.1007/s00044-012-0334-1
Baki A, Bielik A, Molnar L (2007) A high throughput luminescent assay for glycogen synthase kinase-3 inhibitors. Assay Drug Dev Technol 5:75–83. doi:10.1089/adt.2006.029
Ma S, Dai Y (2011) Principal component analysis based methods in bioinformatics studies. Brief Bioinform 12:714–722. doi:10.1093/bib/bbq090
Acknowledgments
This work was funded in part by the Research Special Fund for Public Welfare Industry of Health (No. 200802041), the National Great Science and Technology Projects (2012ZX09301002, 2014ZX09507003-002), the International Collaboration Project (2011DFR31240), and Peking Union Medical College graduate student innovation fund (2013-1007-18)
Conflict of interest
The authors declare no competing financial interest.
Author information
Authors and Affiliations
Corresponding authors
Additional information
Jiansong Fang and Ranyao Yang have contributed equally to this work.
Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Fang, J., Yang, R., Gao, L. et al. Consensus models for CDK5 inhibitors in silico and their application to inhibitor discovery. Mol Divers 19, 149–162 (2015). https://doi.org/10.1007/s11030-014-9561-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11030-014-9561-3