Prediction of K562 Cells Functional Inhibitors Based on Machine Learning Approaches

Yuan       Zhang; Zhenyan       Han; Qian       Gao; Xiaoyi       Bai; Chi       Zhang; Hongying       Hou
Abstract

Background: β thalassemia is a common monogenic genetic disease that is very harmful to human health. The disease arises is due to the deletion of or defects in β-globin, which reduces synthesis of the β-globin chain, resulting in a relatively excess number of α-chains. The formation of inclusion bodies deposited on the cell membrane causes a decrease in the ability of red blood cells to deform and a group of hereditary haemolytic diseases caused by massive destruction in the spleen.
Methods: In this work, machine learning algorithms were employed to build a prediction model for inhibitors against K562 based on 117 inhibitors and 190 non-inhibitors.
Results: The overall accuracy (ACC) of a 10-fold cross-validation test and an independent set test using Adaboost were 83.1% and 78.0%, respectively, surpassing Bayes Net, Random Forest, Random Tree, C4.5, SVM, KNN and Bagging.
Conclusion: This study indicated that Adaboost could be applied to build a learning model in the prediction of inhibitors against K526 cells.
Keywords: Machine learning, cross-validation test, independent set test, Adaboost; feature selection, K526 cells.
[1] 
Giardine B, Borg J, Viennas E, et al. Updates of the HbVar database of human hemoglobin variants and thalassemia mutations. Nucleic Acids Res  2014; 42(Database issue): D1063-9.
[http://dx.doi.org/10.1093/nar/gkt911] [PMID:  24137000] 
[2] 
Old JM. Screening and genetic diagnosis of haemoglobin disorders. Blood Rev  2003; 17(1): 43-53.
[http://dx.doi.org/10.1016/S0268-960X(02)00061-9] [PMID:  12490210] 
[3] 
Watanapokasin R, Sanmund D, Winichagoon P, Muta K, Fucharoen S. Hydroxyurea responses and fetal hemoglobin induction in beta-thalassemia/HbE patients’ peripheral blood erythroid cell culture. Ann Hematol  2006; 85(3): 164-9.
[http://dx.doi.org/10.1007/s00277-005-0049-1] [PMID:  16389564] 
[4] 
Kohli-Kumar M, Marandi H, Keller MA, Guertin K, Hvizdala E. Use of hydroxyurea and recombinant erythropoietin in management of homozygous beta0 thalassemia. J Pediatr Hematol Oncol  2002; 24(9): 777-8.
[http://dx.doi.org/10.1097/00043426-200212000-00021] [PMID:  12468925] 
[5] 
De Franceschi L, Beuzard Y, Jouault H, Brugnara C. Modulation of erythrocyte potassium chloride cotransport, potassium content, and density by dietary magnesium intake in transgenic SAD mouse. Blood  1996; 88(7): 2738-44.
[http://dx.doi.org/10.1182/blood.V88.7.2738.bloodjournal8872738] [PMID:  8839870] 
[6] 
Olivieri NF, Rees DC, Ginder GD, et al. Treatment of thalassaemia major with phenylbutyrate and hydroxyurea. Lancet  1997; 350(9076): 491-2.
[http://dx.doi.org/10.1016/S0140-6736(05)63080-2] [PMID:  9274590] 
[7] 
McDonagh KT, Dover GJ, Donahue RE, et al. Hydroxyurea-induced HbF production in anemic primates: augmentation by erythropoietin, hematopoietic growth factors, and sodium butyrate. Exp Hematol  1992; 20(10): 1156-64.
[PMID:  1385194] 
[8] 
Macari ER, Lowrey CH. Induction of human fetal hemoglobin via the NRF2 antioxidant response signaling pathway. Blood  2011; 117(22): 5987-97.
[http://dx.doi.org/10.1182/blood-2010-10-314096] [PMID:  21464371] 
[9] 
Witt O, Monkemeyer S, Rönndahl G, et al. Induction of fetal hemoglobin expression by the histone deacetylase inhibitor apicidin. Blood  2003; 101(5): 2001-7.
[http://dx.doi.org/10.1182/blood-2002-08-2617] [PMID:  12393499] 
[10] 
Hu Y, Lu Y, Wang S, et al. Application of Machine Learning Approaches for the design and study of anticancer drugs. Curr Drug Targets  2019; 20(5): 488-500.
[PMID:  30091413] 
[11] 
Zhao M, Wang L, Zheng L, et al. 2D-QSAR and 3D-QSAR Analyses for EGFR inhibitors. BioMed Res Int  2017; 2017 4649191
[http://dx.doi.org/10.1155/2017/4649191] [PMID:  28630865] 
[12] 
Niu B, Zhao M, Su Q, et al. 2D-SAR and 3D-QSAR analyses for acetylcholinesterase inhibitors. Mol Divers  2017; 21(2): 413-26.
[http://dx.doi.org/10.1007/s11030-017-9732-0] [PMID:  28275924] 
[13] 
Niu B, Zhang M, Du P, et al. Small molecular floribundiquinone B derived from medicinal plants inhibits acetylcholinesterase activity. Oncotarget  2017; 8(34): 57149-62.
[http://dx.doi.org/10.18632/oncotarget.19169] [PMID:  28915661] 
[14] 
Niu B, Li J, Li G, Poon S, Harrington PB. Analysis and modeling for big data in cancer research. BioMed Res Int  2017; 20171972097
[http://dx.doi.org/10.1155/2017/1972097] [PMID:  28691016] 
[15] 
Zhang C, Wang X, Gu L, et al. Prediction of an interaction between bakuchiol and acetylcholinesterase using adaboost. Curr Bioinform  2016; 11(1): 79-86.
[http://dx.doi.org/10.2174/1574893611666151119220248] 
[16] 
Niu B, Xing Z, Zhao M, et al. Study of drug-drug combinations based on molecular descriptors and physicochemical properties. Comb Chem High Throughput Screen  2016; 19(2): 153-60.
[http://dx.doi.org/10.2174/1386207319666151110122931] [PMID:  26552439] 
[17] 
Bhola A, Singh S. Gene selection using high dimensional gene expression data: an appraisal. Curr Bioinform  2018; 13(3): 225-33.
[http://dx.doi.org/10.2174/1574893611666160610104946] 
[18] 
Du X, Li X, Li W, et al. Identification and analysis of cancer diagnosis using probabilistic classification vector machines with feature selection. Curr Bioinform  2018; 13(6): 625-32.
[http://dx.doi.org/10.2174/1574893612666170405125637] 
[19] 
Kumar N. Md. Hoque A, Md. Shahjaman, et al. A new approach of outlier-robust missing value imputation for metabolomics data analysis. Curr Bioinform  2019; 14(1): 43-52.
[http://dx.doi.org/10.2174/1574893612666171121154655] 
[20] 
Liao Z, Wan S, He Y, et al. Classification of small GTPases with hybrid protein features and advanced machine learning techniques. Curr Bioinform  2018; 13(5): 492-500.
[http://dx.doi.org/10.2174/1574893612666171121162552] 
[21] 
Naseem I, Khan S, Togneri R, Bennamoun M. ECMSRC: a sparse learning approach for the prediction of extracellular matrix proteins. Curr Bioinform  2017; 12(4): 361-8.
[http://dx.doi.org/10.2174/1574893611666151215213508] 
[22] 
Özkan A, Belgin İşgör SB, Şengül G, İşgör YG, et al. Benchmarking classification models for cell viability on novel cancer image datasets. Curr Bioinform  2019; 14(2): 108-14.
[http://dx.doi.org/10.2174/1574893614666181120093740] 
[23] 
Peng L, Peng M, Liao B, Huang G, Li W, Xie D. The advances and challenges of deep learning application in biological big data processing. Curr Bioinform  2018; 13(4): 352-9.
[http://dx.doi.org/10.2174/1574893612666170707095707] 
[24] 
Rajappan S, Rangasamy D. Adaptive genetic algorithm with exploration-exploitation tradeoff for preprocessing microarray datasets. Curr Bioinform  2017; 12(5): 441-51.
[http://dx.doi.org/10.2174/1574893611666161118142801] 
[25] 
Tanchotsrinon W, Lursinsap C, Poovorawan Y. An efficient prediction of hpv genotypes from partial coding sequences by chaos game representation and fuzzy k-nearest neighbor technique. Curr Bioinform  2017; 12(5): 431-40.
[http://dx.doi.org/10.2174/1574893611666161110112006] 
[26] 
Yao Y, Li X, Geng L, Nan X, Qi Z, Liao B. Recent progress in long noncoding RNAs prediction. Curr Bioinform  2018; 13(4): 344-51.
[http://dx.doi.org/10.2174/1574893612666170905153933] 
[27] 
Lu Y, Deng X, Chen J, Wang J, Chen Q, Niu B. Risk analysis of african swine fever in poland based on spatio-temporal pattern and latin hypercube sampling, 2014-2017. BMC Vet Res  2019; 15(1): 160.
[http://dx.doi.org/10.1186/s12917-019-1903-z] [PMID:  31118049] 
[28] 
Xiao X, Cheng X, Chen G, Mao Q, Chou KC. pLoc-mGpos: predict subcellular localization of gram-positive bacterial proteins by quasi-balancing training dataset and PseAAC. Genomics  2019; 111(4): 886-92.
[29] 
Qiu WR, Sun BQ, Xiao X, Xu ZC, Jia JH, Chou KC. iKcr-PseEns: identify lysine crotonylation sites in histone proteins with pseudo components and ensemble classifier. Genomics  2018; 110(5): 239-46.
[PMID:  29107015] 
[30] 
Feng P, et al. iDNA6mA-PseKNC: identifying DNA N 6 -methyladenosine sites by incorporating nucleotide physicochemical properties into PseKNC. Genomics 2018.
[31] 
Cheng X, Xiao X, Chou KC. pLoc-mEuk: predict subcellular localization of multi-label eukaryotic proteins by extracting the key GO information into general PseAAC. Genomics  2018; 110(1): 50-8.
[http://dx.doi.org/10.1016/j.ygeno.2017.08.005] [PMID:  28818512] 
[32] 
Cheng X, Xiao X, Chou KC. pLoc-mGneg: predict subcellular localization of gram-negative bacterial proteins by deep gene ontology learning via general PseAAC. Genomics   2017; S0888- 7543(17): 30102-7.
[PMID:  28989035] 
[33] 
Taguchi YH, Wang H. Genetic association between amyotrophic lateral sclerosis and cancer. Genes (Basel)  2017; 8(10)E243
[http://dx.doi.org/10.3390/genes8100243] [PMID:  28953220] 
[34] 
Bloomingdale P, Mager DE. Machine learning models for the prediction of chemotherapy-induced peripheral neuropathy. Pharm Res  2019; 36(2): 35.
[http://dx.doi.org/10.1007/s11095-018-2562-7] [PMID:  30617559] 
[35] 
Consonni V, Todeschini R. Molecular descriptors Recent advances in QSAR studies: methods and applications.  Dordrecht: Springer Netherlands 2010; pp. 29-102.
[http://dx.doi.org/10.1007/978-1-4020-9783-6_3] 
[36] 
Ansary I, Roy H, Das A, Mitra D. Regioselective synthesis, molecular descriptors of (1,5-Disubstituted 1,2,3-Triazolyl)Coumarin/Quinolone derivatives and their docking studies against cancer targets. ChemistrySelect  2019; 4(12): 3486-94.
[http://dx.doi.org/10.1002/slct.201900114] 
[37] 
Basak SC. Editor’s perspective: molecular descriptor landscape in the twenty first century and its proper use for computer-aided drug design. Curr Comput Aided Drug Des  2019; 15(1): 1-2.
[http://dx.doi.org/10.2174/157340991501181214103556] [PMID:  30569845] 
[38] 
Benguerba Y, Alnashef I, Erto A, Balsamo M, et al. A quantitative prediction of the viscosity of amine based DESs using S sigma-profile molecular descriptors. J Mol Struct  2019; 1184: 357-63.
[http://dx.doi.org/10.1016/j.molstruc.2019.02.052] 
[39] 
Bian L, Sorescu DC, Chen L, et al. Machine-learning identification of the sensing descriptors relevant in molecular interactions with metal nanoparticle-decorated nanotube field-effect transistors. ACS Appl Mater Interfaces  2019; 11(1): 1219-27.
[http://dx.doi.org/10.1021/acsami.8b15785] [PMID:  30547572] 
[40] 
Chang ED, Hogstrand C, Miller TH, Owen SF, Bury NR. The use of molecular descriptors to model pharmaceutical uptake by a fish primary gill cell culture epithelium. Environ Sci Technol  2019; 53(3): 1576-84.
[http://dx.doi.org/10.1021/acs.est.8b04394] [PMID:  30589539] 
[41] 
Esmaeili E, Shafiei F. QSAR models to predict physico-chemical properties of some barbiturate derivatives using molecular descriptors and genetic algorithm-multiple linear regressions. Iranian Chemical Communication  2019; 7(2): 170-9.
[42] 
Jeschke S, Cole IS. 3D-QSAR for binding constants of β-cyclodextrin host-guest complexes by utilising spectrophores as molecular descriptors. Chemosphere  2019; 225: 135-8.
[http://dx.doi.org/10.1016/j.chemosphere.2019.03.020] [PMID:  30870630] 
[43] 
Ma H, Peng Q, An Z, Huang W, Shuai Z. Efficient and long-lived room-temperature organic phosphorescence: theoretical descriptors for molecular designs. J Am Chem Soc  2019; 141(2): 1010-5.
[http://dx.doi.org/10.1021/jacs.8b11224] [PMID:  30565929] 
[44] 
Martínez-Santiago O, Marrero-Ponce Y, Vivas-Reyes R, et al. Higher-order and mixed discrete derivatives such as a novel graph- theoretical invariant for generating new molecular descriptors. Curr Top Med Chem  2019; 19(11): 944-56.
[http://dx.doi.org/10.2174/1568026619666190510093651] [PMID:  31074367] 
[45] 
Nazeer W, Farooq A, Younas M, Munir M, Kang SM. On molecular descriptors of carbon nanocones. Biomolecules  2018; 8(3)E92
[http://dx.doi.org/10.3390/biom8030092] [PMID:  30205520] 
[46] 
Nichols CM, Dodds JN, Rose BS, et al. Untargeted molecular discovery in primary metabolism: collision cross section as a molecular descriptor in ion mobility-mass spectrometry. Anal Chem  2018; 90(24): 14484-92.
[http://dx.doi.org/10.1021/acs.analchem.8b04322] [PMID:  30449086] 
[47] 
Rácz A, Bajusz D, Héberger K. Intercorrelation limits in molecular descriptor preselection for QSAR/QSPR. Mol Inform  2019; 38(8-9)1800154
[http://dx.doi.org/10.1002/minf.201800154] [PMID:  30945814] 
[48] 
Viarengo L, Whitty A. Development of macrocycle-specific molecular descriptors and their application in machine learning. Protein Sci  2018; 27: 221-1.
[49] 
Winter R, Montanari F, Noé F, Clevert DA. Learning continuous and data-driven molecular descriptors by translating equivalent chemical representations. Chem Sci (Camb)  2018; 10(6): 1692-701.
[http://dx.doi.org/10.1039/C8SC04175J] [PMID:  30842833] 
[50] 
Zhang PB, Yang ZX. A novel AdaBoost framework with robust threshold and structural optimization. IEEE Trans Cybern  2018; 48(1): 64-76.
[http://dx.doi.org/10.1109/TCYB.2016.2623900] [PMID:  27898387] 
[51] 
Niu B, Lu Y, Wang J, et al. 2D-SAR, Topomer CoMFA and molecular docking studies on avian influenza neuraminidase inhibitors. Comput Struct Biotechnol J  2018; 17: 39-48.
[http://dx.doi.org/10.1016/j.csbj.2018.11.007] [PMID:  30595814] 
[52] 
Lu Y, Wang S, Wang J, et al. An epidemic avian influenza prediction model based on google trends. Lett Org Chem  2019; 16(4): 303-10.
[http://dx.doi.org/10.2174/1570178615666180724103325] 
[53] 
Cortes C, Vapnik VN. Support vector networks. Mach Learn  1995; 3: 273-97.
[http://dx.doi.org/10.1007/BF00994018] 
[54] 
Vapnik VN. An overview of statistical learning theory. IEEE Trans Neural Netw  1999; 10(5): 988-99.
[http://dx.doi.org/10.1109/72.788640] [PMID:  18252602] 
[55] 
Cortes C, Vapnik V. Support-vector networks. Mach Learn  1995; 20(3): 273-97.
[http://dx.doi.org/10.1007/BF00994018] 
[56] 
Zhang M, Su Q, Lu Y, Zhao M, Niu B. Application of machine learning approaches for protein-protein interactions prediction. Med Chem  2017; 13(6): 506-14.
[http://dx.doi.org/10.2174/1573406413666170522150940] [PMID:  28530547] 
[57] 
Chen C-H, Tanaka K, Funatsu K. Random forest model with combined features: a practical approach to predict liquid-crystalline property. Mol Inform  2019; 38(4)e1800095
[http://dx.doi.org/10.1002/minf.201800095] [PMID:  30548221] 
[58] 
Rostami Z, Pourbasheer E. A comparative QSAR study of aryl-substituted isobenzofuran-1(3H)-ones inhibitors. Iranian Chemical Communication  2019; 7(1): 79-92.
[59] 
Ai H, Wu X, Zhang L, et al. QSAR modelling study of the bioconcentration factor and toxicity of organic compounds to aquatic organisms using machine learning and ensemble methods. Ecotoxicol Environ Saf  2019; 179: 71-8.
[http://dx.doi.org/10.1016/j.ecoenv.2019.04.035] [PMID:  31026752] 
[60] 
C45: Programs for Machine Learning. Elsevier Science & Technology Books  1992.
[61] 
Chen G, Peijnenburg W, Kovalishyn V, Vijver M. Development of nanostructure-activity relationships assisting the nanomaterial hazard categorization for risk assessment and regulatory decision-making. RSC Advances  2016; 6(57): 52227-35.
[http://dx.doi.org/10.1039/C6RA06159A] 
[62] 
Cheng F, Shen J, Yu Y, et al. In silico prediction of tetrahymena pyriformis toxicity for diverse industrial chemicals with substructure pattern recognition and machine learning methods. Chemosphere  2011; 82(11): 1636-43.
[http://dx.doi.org/10.1016/j.chemosphere.2010.11.043] [PMID:  21145574] 
[63] 
Kong Y, Yan A. QSAR models for predicting the bioactivity of polo-like kinase 1 inhibitors. Chemom Intell Lab Syst  2017; 167: 214-25.
[http://dx.doi.org/10.1016/j.chemolab.2017.06.011] 
[64] 
Sun X, Li Y, Liu X, et al. Classification of bioaccumulative and non-bioaccumulative chemicals using statistical learning approaches. Mol Divers  2008; 12(3-4): 157-69.
[http://dx.doi.org/10.1007/s11030-008-9092-x] [PMID:  18937041] 
[65] 
Yang X-G, Chen D, Wang M, Xue Y, Chen YZ. Prediction of antibacterial compounds by machine learning approaches. J Comput Chem  2009; 30(8): 1202-11.
[http://dx.doi.org/10.1002/jcc.21148] [PMID:  18988254] 
[66] 
Ambure P, Halder AK, González Díaz H, Cordeiro MNDS. QSAR-Co: an open source software for developing robust multitasking or multitarget classification-based QSAR models. J Chem Inf Model  2019; 59(6): 2538-44.
[http://dx.doi.org/10.1021/acs.jcim.9b00295] [PMID:  31083984] 
[67] 
Ancuceanu R, Dinu M, Neaga I, Laszlo FG, Boda D. Development of QSAR machine learning-based models to forecast the effect of substances on malignant melanoma cells. Oncol Lett  2019; 17(5): 4188-96.
[http://dx.doi.org/10.3892/ol.2019.10068] [PMID:  31007759] 
[68] 
Cardoso-Silva J, Papadatos G, Papageorgiou LG, Tsoka S. Optimal piecewise linear regression algorithm for QSAR modelling. Mol Inform  2019; 38(3)e1800028
[http://dx.doi.org/10.1002/minf.201800028] [PMID:  30251339] 
[69] 
García-Jacas CR, Marrero-Ponce Y, Cortés-Guzmán F, et al. Enhancing acute oral toxicity predictions by using consensus modeling and algebraic form-based 0D-to-2D molecular encodes. Chem Res Toxicol  2019; 32(6): 1178-92.
[http://dx.doi.org/10.1021/acs.chemrestox.9b00011] [PMID:  31066547] 
[70] 
Kaneko H. Data visualization, regression, applicability domains and inverse analysis based on generative topographic mapping. Mol Inform  2019; 38(3) e1800088
[http://dx.doi.org/10.1002/minf.201800088] [PMID:  30259699] 
[71] 
Veríssimo GC, Menezes Dutra EF, Teotonio Dias AL, et al. HQSAR and random forest-based QSAR models for anti-T. Vaginalis activities of nitroimidazoles derivatives. J Mol Graph Model  2019; 90: 180-91.
[http://dx.doi.org/10.1016/j.jmgm.2019.04.007] [PMID:  31100677] 
[72] 
Chen W, Peng J, Hong H, et al. Landslide susceptibility modelling using GIS-based machine learning techniques for chongren county, jiangxi province, china. Sci Total Environ  2018; 626: 1121-35.
[http://dx.doi.org/10.1016/j.scitotenv.2018.01.124] [PMID:  29898519] 
[73] 
Farahani FV, Ahmadi A, Zarandi MHF. Hybrid intelligent approach for diagnosis of the lung nodule from CT images using spatial kernelized fuzzy c-means and ensemble learning. Math Comput Simul  2018; 149: 48-68.
[http://dx.doi.org/10.1016/j.matcom.2018.02.001] 
[74] 
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 Des  2018; 32(5): 583-90.
[http://dx.doi.org/10.1007/s10822-018-0116-z] [PMID:  29626291] 
Cite As
Current Pharmaceutical Design

Prediction of K562 Cells Functional Inhibitors Based on Machine Learning Approaches

Abstract
