摘要
背景：阿尔茨海默病席卷全球各个角落，全球患者人数不断增加。目前，全世界有多达3000万阿尔茨海默病患者，到2050年预计将超过8000万人。因此，阿尔茨海默氏症药物的研究已成为最受欢迎的医学专题之一。 方法：在本研究中，为了构建阿尔茨海默氏症药物和靶标的预测模型，将属性鉴别因子CfsSubsetEval，ConsistencySubsetEval和FilteredSubsetEval与BestFirst，GeneticSearch和Greedystepwise等搜索方法相结合，以过滤分子描述符。然后使用诸如BayesNet，SVM，KNN和C4.5的机器学习算法来构建2D结构活动关系（2D-SAR）模型。其建模结果用于接收器操作特性曲线（ROC）分析。 结果：使用Randomforest对AChE，BChE，MAO-B，BACE1，Tau蛋白和非抑制剂的正确性预测率分别为77.0％，79.1％，100.0％，94.2％，93.2％和94.9％，这些都是势不可挡的与BayesNet，BP，SVM，KNN，AdaBoost和C4.5相比。 结论：在本文中，我们得出结论，随机森林是预测阿尔茨海默氏症药物和靶标的最佳学习者模型。此外，我们在http://47.106.158.30:8080/AD/建立了一个在线服务器来预测小分子是否是阿尔茨海默氏症靶标的抑制剂。此外，它可以区分小分子的靶蛋白。
关键词: 机器学习（ML），阿尔茨海默病，BayesNet，BP神经网络（BP），支持向量机（SVM），K最近邻（KNN），AdaBoost，随机森林（RF），C4.5，Web服务器。
[2]
Cuello AC, Garofalo L, Maysinger D, Pioro EP, Silva ARD. Chapter 32 Injury and repair of central cholinergic neurons.Elsevier Science & Technology,. (1990)
[3]
Lewczuk P. Tau protein phosphorylated at threonine 181 in CSF as a neurochemical biomarker in Alzheimer’s disease: original data and review of the literature MN MN. J Mol Neurosci (No 1-2): 115-22. (2004)
[4]
Hardy JA, Higgins GA. Alzheimer’s disease: the amyloid cascade hypothesis. Science 256(5054): 184-5. (1992)
[5]
Dodart JC, Marr RA, Koistinaho M, Gregersen BM, Malkani S, Verma IM, et al. Gene delivery of human apolipoprotein E alters brain Abeta burden in a mouse model of Alzheimer”s disease. Proc Natl Acad Sci USA 102(4): 1211-6. (2005)
[6]
Zhao G. Excitatory amino acid toxicity and ischemic brain injuryCerebrovas Dis Foreign Med Sci. (2004)
[7]
Lane R, Feldman HH, Meyer J, He Y, Ferris SH, Nordberg A, et al. Synergistic effect of apolipoprotein E epsilon 4 and butyrylcholinesterase K-variant on progression from mild cognitive impairment to Alzheimer’s disease. Pharmacogenet Genomics 18(4): 289-98. (2008)
[8]
Zhang X, Hu H, Liu T, Yang Y, Peng Y, Cai Q, et al. Multi-armed poly(L-glutamic acid)-graft-polypropyleneinime as effective and serum resistant gene delivery vectors. Intern J Pharm 465(1-2): 444-54. (2014)
[9]
Wang L, You Z-H, Chen X, Xia S-X, Liu F, Yan X, et al. A Computational-based method for predicting drug-target interactions by using stacked autoencoder deep neural network. J Comput Biol 25(3): 361-73. (2018)
[10]
Jain S, Kotsampasakou E, Ecker GF. Comparing the performance of meta-classifiers-a case study on selected imbalanced data sets relevant for prediction of liver toxicity. J Comput Aided Mol Design 32(5): 583-90. (2018)
[11]
Negin F, Rodriguez P, Koperski M, Kerboua A, Gonzalez J, Bourgeois J, et al. PRAXIS: towards automatic cognitive assessment using gesture recognition. Exp Sys Applic 106: 21-35. (2018)
[12]
Kim KW, Choi JD, Lee H, Lee NK, Park S, Chin J, et al. Social event memory test (semt): A video-based memory test for predicting amyloid positivity for Alzheimer’s disease. Sci Rep 8(1): 10421-21. (2018)
[13]
Cao P, Liu X, Yang J, Zhao D, Huang M, Zaiane O. l(2,1) - l(1) regularized nonlinear multi-task representation learning based cognitive performance prediction of Alzheimer’s disease. Patt Recog 79: 195-5. (2018)
[14]
Niu B, Zhao M, Su Q, Zhang M, Lv W, Chen Q, et al. 2D-SAR and 3D-QSAR analyses for acetylcholinesterase inhibitors. Mol Diver 21(2): 413-26. (2017).
[15]
Deb PK, Sharma A, Piplani P, Akkinepally RR. Molecular docking and receptor-specific 3D-QSAR studies of acetylcholinesterase inhibitors. Mol Diver (No.4): 803-23. (2012)
[16]
Rizzo S, Bartolini M, Ceccarini L, Piazzi L, Gobbi S, Cavalli A. 2 Targeting Alzheimer’s disease: novel indanone hybrids bearing a pharmacophoric fragment of AP2238. Bioorganic Med Chem 18(5): 1749-60. (2010)
[17]
Wang L, Esteban G, Ojima M, Bautista-Aguilera O, Inokuchi T, Moraleda I, et al. Donepezil plus propargylamine+8-hydroxyquinoline hybrids as new multifunctional metal-chelators, ChE and MAO inhibitors for the potential treatment of Alzheimer’s disease. Eur J Med Chem 543-61.
[18]
Zhan Z-J, Bian H-L, Wang J-W, Shan W-G. Synthesis of physostigmine analogues and evaluation of their anticholinesterase activities. Bioorgan Med Chem Lett 20(5): 1532-4. (2010)
[19]
Liua J, Chenb W, Xub Y, Rena S, Zhanga W, Lia Y. Design, synthesis and biological evaluation of tasiamide B derivatives as BACE1 inhibitors. Bioorg Med Chem 23(9): 1963-74. (2015)
[20]
Liu J-K, Gu W, Cheng X-R, Cheng J-P, Nie A-H, Zhou W-X. Design and synthesis of 5-cyclopropyl substituted cyclic acylguanidine compounds as BACE1 inhibitors. Chinese Chem Lett (No 10): 1626-9. (2016)
[21]
Ciordia M, Pérez-Benito L, Delgado F, Trabanco AA, Tresadern G. The application of free energy perturbation for the design of bace1 inhibitors. J Chem Inf Model 59(9): 1856-71. (2016)
[22]
Iserloh U, Pan J, Stamford AW, Kennedy ME, Zhang Q, Zhang L, et al. Discovery of an orally efficaceous 4-phenoxypyrrolidine-based BACE-1 inhibitor. Bioorg Med Chem Lett 18(1): 418-22. (2008)
[23]
Coburn CA, Stachel SJ, Jones KG, Steele TG, Rush DM, DiMuzio J, et al. BACE-1 inhibition by a series of psi[CH2NH] reduced amide isosteres. Bioorg Med Chem Lett 16(14): 3635-8. (2006)
[24]
Pietrak BL, Crouthamel M-C, Tugusheva K, Lineberger JE, Xu M, DiMuzio JM, et al. Biochemical and cell-based assays for characterization of BACE-1 inhibitors. Anal Biochem 342(1): 144-51. (2005)
[25]
Garino C, Pietrancosta N, Laras Y, Moret V, Rolland A, Quéléver G, et al. BACE-1 inhibitory activities of new substituted phenyl-piperazine coupled to various heterocycles: Chromene, coumarin and quinoline. Bioorgan Med Chem Lett 16(7): 1995-9. (2006)
[26]
Jeon SY, Kwon SH, Seong YH, Bae K, Hur JM, Lee YY, et al. Beta-secretase (BACE1)-inhibiting stilbenoids from Smilax Rhizoma. Phytomedicine 14(6): 403-8. (2007)
[27]
Piazzi L, Cavalli A, Colizzi F, Belluti F, Bartolini M, Mancini F, et al. Multi-target-directed coumarin derivatives: hAChE and BACE1 inhibitors as potential anti-Alzheimer compounds. Bioorganic Med Chem Lett (No.1): 423-26. (2008)
[28]
Pisani L, Farina R, Nicolotti O, Gadaleta D, Soto-Otero R, Catto M, et al. In silico design of novel 2H-chromen-2-one derivatives as potent and selective MAO-B inhibitors. Eur J Med Chem 89: 98-105. (2015)
[29]
Jayaprakash V, Sinha BN, Ucar G, Ercan A. Pyrazoline-based mycobactin analogues as MAO-inhibitors. Bioorgan Med Chem Lett 18(24): 6362-8. (2008)
[30]
Skrzypek A, Matysiak J, Niewiadomy A, Bajda M, Szymański P. Synthesis and biological evaluation of 1,3,4-thiadiazole analogues as novel AChE and BuChE inhibitors. Eur J Med Chem 62: 311-9. (2013)
[31]
Yerdelen KO, Tosun E. Synthesis, docking and biological evaluation of oxamide and fumaramide analogs as potential AChE and BuChE inhibitors. Med Chem Res 24(2): 588-602. (2015)
[32]
Rosini M, Melchiorre C, Simoni E, Bartolini M, Cavalli A, Ceccarini L, et al. Inhibition of acetylcholinesterase, beta-amyloid aggregation, and NMDA receptors in Alzheimer’s disease: a promising direction for the multi-target-directed ligands gold rush. J Med Chem 51(15): 4381-4. (2008)
[33]
Bulic B, Pickhardt M, Khlistunova I, Biernat J, Mandelkow EM, Mandelkow E, et al. Rhodanine-based tau aggregation inhibitors in cell models of tauopathy. Angew Chem Int Ed Engl 46(48): 9215-9. (2007)
[34]
Crowe A, Ballatore C, Hyde E, Trojanowski JQ, Lee VM-Y. High throughput screening for small molecule inhibitors of heparin-induced tau fibril formation. Biochem Biophys Res Commun (No 1): 1-6. (2007)
[35]
Crowe A, Huang W. BaIlatore C, Johnson RL, Hogan A-ML, Huang R, et al. Identification of aminothienopyridazine inhibitors of tau assembly by quantitative high-throughput screening. Biochemistry 48(32): 7732-45. (2009)
[36]
Pickhardt M, Larbig G, Khlistunova I, Coksezen A, Meyer B, Mandelkow E-M, et al. Phenylthiazolyl-hydrazide and its derivatives are potent inhibitors of aggregation and toxicity in vitro and in cells. Biochemistry 46(35): 10016. (2007)
[37]
Taniguchi S, Suzuki N, Masuda M, Hisanaga S-I, Iwatsubo T, Goedert M, et al. Inhibition of heparin-induced tau filament formation by phenothiazines, polyphenols, and porphyrins. J Biol Chem 280(9): 7614-23. (2005)
[38]
Wischik CM, Edwards PC. Selective inhibition of Alzheimer disease-like tau aggregation by phenothiazines. Proc Natl Acad Sci USA 93(20): 11213-3. (1996)
[39]
Consonni V, Todeschini R. In: Recent advances in QSAR studies: methods and applications. Puzyn T; Leszczynski J; Cronin MT, Eds.; Springer Netherlands: Dordrecht, 2010; pp. 29-102.
[40]
Hall MA. Proc Fourth International Conference on Neural Information Processing and Intelligent Information Systems. Dunedin, New Zealand. (1997)
[43]
Robnik-Sikonja M. Kononenko I. In: Fourteenth International Conference on Machine Learning. 1997; pp. 296-304.
[44]
Guyon I, Weston J, Barnhill S, Vapnik V. Gene selection for cancer classification using support vector machines. Mach Learn 46(1-3): 389-422. (2002)
[47]
Prasoon A, Petersen K, Igel C, Lauze F, Dam E, Nielsen M. Deep feature learning for knee cartilage segmentation using a triplanar convolutional neural network. Lect Notes Comput Sci 8150: 246-53. (2013)
[48]
Zhang PB, Yang ZX. A novel adaboost framework with robust threshold and structural optimization. IEEE Trans Cybern 48(1): 64-76. (2018)
[49]
Schapire RE. The boosting approach to machine learning: An overview Springer: New York,. (2003)
[51]
Vapnik VN. An overview of statistical learning theory. IEEE Trans Neural Networks 10(5): 988-99. (1999)
[53]
Altman NS. An introduction to Kernel and nearest-neighbor nonparametric regression. Am Statis 46(3): 175. (1992)
[55]
Zhang M, Su Q, Lu Y, Zhao M, Niu B. Application of machine learning approaches for protein-protein interactions prediction. Med Chem 13(6): 506-14. (2017)
[56]
Chen W, Peng J, Hong H, Shahabi H, Pradhan B, Liu J, et al. Landslide susceptibility modelling using GIS-based machine learning techniques for Chongren County, Jiangxi Province, China. Sci Total Environ 626: 1121-35. (2018)
Related Books
Frontiers in Clinical Drug Research - CNS and Neurological Disorders
Frontiers in Clinical Drug Research - CNS and Neurological Disorders
Frontiers in Clinical Drug Research - CNS and Neurological Disorders
Frontiers in Clinical Drug Research-Dementia
Frontiers in Clinical Drug Research - CNS and Neurological Disorders
Article Metrics
49
4
1