Abstract
Background: Anthrapyrazoles are a new class of antitumor agents and successors to anthracyclines possessing a broad range of antitumor activity in various model tumors.
Objectives: The present study introduces novel QSAR models for the prediction of antitumor activity of anthrapyrazole analogues.
Methods: The predictive performance of four machine learning algorithms, namely artificial neural networks, boosted trees, multivariate adaptive regression splines, and random forest, was studied in terms of variation of the observed and predicted data, internal validation, predictability, precision, and accuracy.
Results: ANN and boosted trees algorithms met the validation criteria. It means that these procedures may be able to forecast the anticancer effects of the anthrapyrazoles studied. Evaluation of validation metrics, calculated for each approach, indicated the artificial neural network (ANN) procedure as the algorithm of choice, especially with regard to the obtained predictability as well as the lowest value of mean absolute error. The designed multilayer perceptron (MLP)-15-7-1 network displayed a high correlation between the predicted and the experimental pIC50 value for the training, test, and validation set. A conducted sensitivity analysis enabled an indication of the most important structural features of the studied activity.
Conclusion: The ANN strategy combines topographical and topological information and can be used for the design and development of novel anthrapyrazole analogues as anticancer molecules.
Graphical Abstract
[1]
Mross, K.; Scheulen, M.E.; Licht, T.; Unger, C.; Richly, H.; Stern, A.C.; Kutz, K.; Camboni, M.G.; Barbieri, P.; Verdi, E.; Vincenzi, B.; Bernareggi, A. Phase I clinical and pharmacokinetic study of BBR 3576, a novel aza-anthrapyrazole, administered i.v. every 4 weeks in patients with advanced solid tumors: A phase I study group trial of the Central European Society of Anticancer-Drug Research (CESAR). Anticancer Drugs, 2004, 15(1), 15-22.
[http://dx.doi.org/10.1097/00001813-200401000-00003] [PMID: 15090738]
[http://dx.doi.org/10.1097/00001813-200401000-00003] [PMID: 15090738]
[2]
Duchnowska, R.; Chmielowska, E.; Streb, J.; Chudzik, M.; Czartoryska-Arlukowicz, B.; Litwiniuk, M. The role of anthracyclines and dose dense therapy in an adjuvant setting, in HER2-positive early breast cancer, in clinical practice. Oncol Clin Pract., 2016, 12(1), 8-11.
[3]
Schirone, L.; Toldo, S.; Cianflone, E.; Sala, V.; Greco, E. The role of Anthracyclines in Cardio-Oncology: Oxidative stress, inflammation, and autophagy. Oxid. Med. Cell. Longev., 2022, 2022, 9862524.
[4]
Showalter, H.D.H.; Johnson, J.L.; Hoftiezer, J.M.; Turner, W.R.; Werbel, L.M.; Leopold, W.R.; Shillis, J.L.; Jackson, R.C.; Elslager, E.F. Anthrapyrazole anticancer agents. Synthesis and structure-activity relationships against murine leukemias. J. Med. Chem., 1987, 30(1), 121-131.
[http://dx.doi.org/10.1021/jm00384a021] [PMID: 3806589]
[http://dx.doi.org/10.1021/jm00384a021] [PMID: 3806589]
[5]
Leopold, W.R.; Nelson, J.M.; Plowman, J.; Jackson, R.C. Anthrapyrazoles, a new class of intercalating agents with high-level, broad spectrum activity against murine tumors. Cancer Res., 1985, 45(11 Pt 1), 5532-5539.
[PMID: 4053027]
[PMID: 4053027]
[6]
Begleiter, A.; Lin, D.; Larson, K.K.; Lang, J.; Wu, X.; Cabral, T.; Taylor, H.; Guziec, L.J.; Kerr, P.D.; Hasinoff, B.B.; Guziec, F.S., Jr Structure-activity studies with cytotoxic anthrapyrazoles. Oncol. Rep., 2006, 15(6), 1575-1580.
[PMID: 16685398]
[PMID: 16685398]
[7]
Leteurtre, F.; Kohlhagen, G.; Paull, K.D.; Pommier, Y. Topoisomerase II inhibition and cytotoxicity of the anthrapyrazoles DuP 937 and DuP 941 (Losoxantrone) in the National Cancer Institute preclinical antitumor drug discovery screen. J. Natl. Cancer Inst., 1994, 86(16), 1239-1244.
[http://dx.doi.org/10.1093/jnci/86.16.1239] [PMID: 8040892]
[http://dx.doi.org/10.1093/jnci/86.16.1239] [PMID: 8040892]
[8]
Wang, J.; Zhao, H.; Luo, Z.; Wang, Z.; Zhang, Y.; Zhao, J. Synthesis and biological activity of anthrapyrazoles derivatives as potential antitumor agents. Med. Chem., 2014, 10(8), 772-777.
[http://dx.doi.org/10.2174/1573406410666140428152227] [PMID: 24773347]
[http://dx.doi.org/10.2174/1573406410666140428152227] [PMID: 24773347]
[9]
Dibia, K.T.; Igbokwe, P.K.; Ezemagu, G.I.; Asadu, C.O. Exploration of the quantitative Structure-Activity relationships for predicting Cyclooxygenase-2 inhibition bioactivity by Machine learning approaches. Results Chem, 2022, 4, 100272.
[http://dx.doi.org/10.1016/j.rechem.2021.100272]
[http://dx.doi.org/10.1016/j.rechem.2021.100272]
[10]
Prasanna, S.; Doerksen, R. Topological polar surface area: A useful descriptor in 2D-QSAR. Curr. Med. Chem., 2009, 16(1), 21-41.
[http://dx.doi.org/10.2174/092986709787002817] [PMID: 19149561]
[http://dx.doi.org/10.2174/092986709787002817] [PMID: 19149561]
[11]
TIBCO Software Inc. IBCO Statistica® User’s Guide. 2017. Available From: https://docs.tibco.com/products/tibco-statistica-13-3-0
[12]
Baskin, I.I.; Palyulin, V.A.; Zefirov, N.S. Neural networks in building QSAR models. Methods Mol. Biol., 2008, 458(458), 137-158.
[PMID: 19065809]
[PMID: 19065809]
[13]
Dobchev, D.; Karelson, M. Have artificial neural networks met expectations in drug discovery as implemented in QSAR framework? Expert Opin. Drug Discov., 2016, 11(7), 627-639.
[http://dx.doi.org/10.1080/17460441.2016.1186876] [PMID: 27149299]
[http://dx.doi.org/10.1080/17460441.2016.1186876] [PMID: 27149299]
[14]
Breiman, L. Random forests. Mach. Learn., 2001, 45(1), 5-32.
[http://dx.doi.org/10.1023/A:1010933404324]
[http://dx.doi.org/10.1023/A:1010933404324]
[15]
Svetnik, V.; Liaw, A.; Tong, C.; Culberson, J.C.; Sheridan, R.P.; Feuston, B.P. Random forest: A classification and regression tool for compound classification and QSAR modeling. J. Chem. Inf. Comput. Sci., 2003, 43(6), 1947-1958.
[http://dx.doi.org/10.1021/ci034160g] [PMID: 14632445]
[http://dx.doi.org/10.1021/ci034160g] [PMID: 14632445]
[16]
De’ath, G. Boosted trees for ecological modeling and prediction. Ecology, 2007, 88(1), 243-251.
[http://dx.doi.org/10.1890/0012-9658(2007)88[243:BTFEMA]2.0.CO;2] [PMID: 17489472]
[http://dx.doi.org/10.1890/0012-9658(2007)88[243:BTFEMA]2.0.CO;2] [PMID: 17489472]
[18]
De Veaux, R.D.; Psichogios, D.C.; Ungar, L.H. A comparison of two nonparametric estimation schemes: MARS and neural networks. Comput. Chem. Eng., 1993, 17(8), 819-837.
[http://dx.doi.org/10.1016/0098-1354(93)80066-V]
[http://dx.doi.org/10.1016/0098-1354(93)80066-V]
[19]
Roy, K.; Ambure, P.; Kar, S.; Ojha, P.K. Is it possible to improve the quality of predictions from an “intelligent” use of multiple QSAR/QSPR/QSTR models? J. Chemometr., 2018, 32(4), e2992.
[http://dx.doi.org/10.1002/cem.2992]
[http://dx.doi.org/10.1002/cem.2992]
[20]
Sung, H.; Ferlay, J.; Siegel, R.L.; Laversanne, M.; Soerjomataram, I.; Jemal, A Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. Cancer J Clin., 2021, 71(3), 209-249.
[21]
Gackowski, M.; Szewczyk-Golec, K.; Pluskota, R.; Koba, M.; Mądra-Gackowska, K.; Woźniak, A. Application of Multivariate Adaptive Regression Splines (MARSplines) for predicting antitumor activity of anthrapyrazole derivatives. Int. J. Mol. Sci., 2022, 23(9), 5132.
[http://dx.doi.org/10.3390/ijms23095132] [PMID: 35563523]
[http://dx.doi.org/10.3390/ijms23095132] [PMID: 35563523]
[22]
Velázquez-Libera, J.L.; Caballero, J.; Toropova, A.P.; Toropov, A.A. Estimation of 2D autocorrelation descriptors and 2D Monte Carlo descriptors as a tool to build up predictive models for acetylcholinesterase (AChE) inhibitory activity. Chemom. Intell. Lab. Syst., 2019, 184, 14-21.
[http://dx.doi.org/10.1016/j.chemolab.2018.11.008]
[http://dx.doi.org/10.1016/j.chemolab.2018.11.008]
[23]
Tropsha, A.; Weifan, Z. Identification of the descriptor pharmacophores using variable selection QSAR: Applications to database mining. Curr. Pharm. Des., 2001, 7(7), 599-612.
[http://dx.doi.org/10.2174/1381612013397834] [PMID: 11375770]
[http://dx.doi.org/10.2174/1381612013397834] [PMID: 11375770]
[24]
Carhart, R.E.; Smith, D.H.; Venkataraghavan, R. Atom pairs as molecular features in structure-activity studies: Definition and applications. J. Chem. Inf. Comput. Sci., 1985, 25(2), 64-73.
[http://dx.doi.org/10.1021/ci00046a002]
[http://dx.doi.org/10.1021/ci00046a002]
[25]
Dehmer, M.; Emmert-Streib, F.; Tripathi, S. Large-scale evaluation of molecular descriptors by means of clustering. PLoS One, 2013, 8(12), e83956.
[http://dx.doi.org/10.1371/journal.pone.0083956] [PMID: 24391854]
[http://dx.doi.org/10.1371/journal.pone.0083956] [PMID: 24391854]
[26]
Grisoni, F.; Reker, D.; Schneider, P.; Friedrich, L.; Consonni, V.; Todeschini, R.; Koeberle, A.; Werz, O.; Schneider, G. Matrix-based molecular descriptors for prospective virtual compound screening. Mol. Inform., 2017, 36(1-2), 1600091.
[http://dx.doi.org/10.1002/minf.201600091] [PMID: 27650559]
[http://dx.doi.org/10.1002/minf.201600091] [PMID: 27650559]
[27]
Roy, K.; Ghosh, G. Exploring QSARs with Extended Topochemical Atom (ETA) indices for modeling chemical and drug toxicity. Curr. Pharm. Des., 2010, 16(24), 2625-2639.
[http://dx.doi.org/10.2174/138161210792389270] [PMID: 20642426]
[http://dx.doi.org/10.2174/138161210792389270] [PMID: 20642426]
[28]
Roy, K.; Das, R.N. The “ETA” Indices in QSAR/QSPR/QSTR Research.Pharmaceutical Sciences: Breakthroughs in research and practice; IGI Global: Pennsylvania, 2017, p. 34.
[29]
Consonni, V.; Todeschini, R.; Pavan, M.; Gramatica, P. Structure/response correlations and similarity/diversity analysis by GETAWAY descriptors. 2. Application of the novel 3D molecular descriptors to QSAR/QSPR studies. J. Chem. Inf. Comput. Sci., 2002, 42(3), 693-705.
[http://dx.doi.org/10.1021/ci0155053] [PMID: 12086531]
[http://dx.doi.org/10.1021/ci0155053] [PMID: 12086531]
[30]
Roy, K.; Mitra, I. Electrotopological state atom (E-state) index in drug design, QSAR, property prediction and toxicity assessment. Curr. Computeraided Drug Des., 2012, 8(2), 135-158.
[http://dx.doi.org/10.2174/157340912800492366] [PMID: 22497469]
[http://dx.doi.org/10.2174/157340912800492366] [PMID: 22497469]
[31]
Hall, L.H.; Kier, L.B. The E-state as the basis for molecular structure space definition and structure similarity. J. Chem. Inf. Comput. Sci., 2000, 40(3), 784-791.
[http://dx.doi.org/10.1021/ci990140w] [PMID: 10850783]
[http://dx.doi.org/10.1021/ci990140w] [PMID: 10850783]
[32]
Roy, K.; Dc, A.U.; Sengupta, C. QSAR with electro topological state atom index: Antialirenergic activi ty of N,N-dimethyl-2-bromo-2-phenylethylami nesl'. Semantic Scholar, 1999, 39, 942-949.
[33]
Yilmaz, H.; Rasulev, B.; Leszczynski, J. Modeling the dispersibility of single walled carbon nanotubes in organic solvents by quantitative structure-activity relationship approach. Nanomaterials, 2015, 5(2), 778-791.
[http://dx.doi.org/10.3390/nano5020778 ] [PMID: 28347035]
[http://dx.doi.org/10.3390/nano5020778 ] [PMID: 28347035]
[34]
Paukku, Y.; Rasulev, B.; Syrov, V.; Khushbaktova, Z.; Leszczynski, J. Structure-hepatoprotective activity relationship study of sesquiterpene lactones: A QSAR analysis. Int. J. Quantum Chem., 2009, 109(1), 17-27.
[http://dx.doi.org/10.1002/qua.21647]
[http://dx.doi.org/10.1002/qua.21647]
[35]
Gupta, V.P. Approximate Molecular Orbital Theories. Principles and Applications of Quantum Chemistry; Elsevier: Amsterdam, 2016, pp. 127-153.
[http://dx.doi.org/10.1016/B978-0-12-803478-1.00004-2]
[http://dx.doi.org/10.1016/B978-0-12-803478-1.00004-2]
