Milp-hyperbox classification for structure-based drug design in the discovery of small molecule inhibitors of SIRTUIN6

Tardu, Mehmet; Rahim, Fatih; Halil Kavakli, I.; Turkay, Metin

RAIRO - Operations Research - Recherche Opérationnelle, Special issue: Research on Optimization and Graph Theory dedicated to COSI 2013 / Special issue: Recent Advances in Operations Research in Computational Biology, Bioinformatics and Medicine, Tome 50 (2016) no. 2, pp. 387-400.

Virtual screening of chemical libraries following experimental assays of drug candidates is a common procedure in structure-based drug discovery. However, virtual screening of chemical libraries with millions of compounds requires a lot of time for computing and data analysis. A priori classification of compounds in the libraries as low- and high-binding free energy sets decreases the number of compounds for virtual screening experiments. This classification also reduces the required computational time and resources. Data analysis is demanding since a compound can be described by more than one thousand attributes that make any data analysis very challenging. In this paper, we use the hyperbox classification method in combination with partial least squares regression to determine the most relevant molecular descriptors of the drug molecules for an efficient classification. The effectiveness of the approach is illustrated on a target protein, SIRT6. The results indicate that the proposed approach outperforms other approaches reported in the literature with 83.55% accuracy using six common molecular descriptors (SC-5, SP-6, SHBd, minHaaCH, maxwHBa, FMF). Additionally, the top 10 hit compounds are determined and reported as the candidate inhibitors of SIRT6 for which no inhibitors have so far been reported in the literature.

P. Armutlu, M.E. Ozdemir, F. Uney-Yuksektepe, I.H. Kavakli and M. Turkay, Classification of drug molecules considering their ic50 values using mixed-integer linear programming based hyper-boxes method. BMC Bioinform. 9 (2008) 411. | DOI

P. Armutlu, M.E. Ozdemir, S. Ozdas, İ.H. Kavakli and M. Turkay, Discovery of novel cyp17 inhibitors for the treatment of prostate cancer with structure-based drug design. Lett. Drug Design Discov. 6 (2009) 337–344. | DOI

A.P. Bento, et al., The chembl bioactivity database: an update. Nucleic Acids Research 42 (2014) D1083–D1090. | DOI

E.E. Bolton, Y. Wang, P.A. Thiessen and S.H. Bryant, Pubchem: integrated platform of small molecules and biological activities. Ann. Rep. Comput. Chem. 4 (2008) 217–241. | DOI

B. Cakir, O. Dagliyan, E. Dagyildiz, I. Baris, I.H. Kavakli, S. Kizilel and M. Turkay, Structure based discovery of small molecules to regulate the activity of human insulin degrading enzyme. PloS One 7 (2012) e31787. | DOI

J.G. Cleary and L.E. Trigg, K*: An instance-based learner using an entropic distance measure. In vol. 5 of Proc. of the 12th International Conference on Machine learning (1995) 108–114.

O. Dagliyan, I.H. Kavakli and M. Turkay, Classification of cytochrome p450 inhibitors with respect to binding free energy and pic50 using common molecular descriptors. J. Chem. Inf. Model. 49 (2009) 2403–2411. | DOI

O. Dagliyan, F. Uney-Yuksektepe, I.H. Kavakli and M. Turkay, Optimization based tumor classification from microarray gene expression data. PloS One 6 (2011) e14579. | DOI

J.-P. Etchegaray, L. Zhong and R. Mostoslavsky, The histone deacetylase sirt6: at the crossroads between epigenetics, metabolism and disease. Curr. Topics Med. Chem. 13 (2013) 2991–3000. | DOI

T. Finkel, C.-X. Deng and R. Mostoslavsky, Recent progress in the biology and physiology of sirtuins. Nature 460 (2009) 587–591. | DOI

E. Frank, M. Hall, L. Trigg, G. Holmes and I.H. Witten, Data mining in bioinformatics using weka. Bioinform. 20 (2004) 2479–2481. | DOI

J. Friedman, et al., Additive logistic regression: a statistical view of boosting (with discussion and a rejoinder by the authors). Ann. Statist. 28 (2000) 337–407. | DOI | MR | Zbl

R.A. Frye, Phylogenetic classification of prokaryotic and eukaryotic sir2-like proteins. Biochem. Biophys. Res. Commun. 273 (2000) 793–798. | DOI

D. Heckerman, A tutorial on learning with Bayesian networks. Springer (1998). | Zbl

IBM ILOG, Cplex user’s manual 12.2 (2010).

J.J. Irwin and B.K. Shoichet, Zinc-a free database of commercially available compounds for virtual screening. J. Chem. Inf. Model. 45 (2005) 177–182. | DOI

W.L. Jorgensen, The many roles of computation in drug discovery. Science 303 (2004) 1813–1818. | DOI

P. Kahraman and M. Turkay, Classification of 1, 4-dihydropyridine calcium channel antagonists using the hyperbox approach. Ind. Eng. Chem. Res. 46 (2007) 4921–4929. | DOI

A. Kaidi, B.T. Weinert, C. Choudhar, and S.P. Jackson, Human sirt6 promotes dna end resection through ctip deacetylation. Science 329 (2010) 1348–1353. | DOI

Y. Kanfi, et al., Regulation of sirt6 protein levels by nutrient availability. FEBS Lett. 582 (2008) 543–548. | DOI

T.L.A. Kawahara, et al., Sirt6 links histone h3 lysine 9 deacetylation to nf-$\kappa$b-dependent gene expression and organismal life span. Cell 136 (2009) 62–74. | DOI

D.B. Kitchen, H. Decornez, J.R. Furr and J. Bajorath, Docking and scoring in virtual screening for drug discovery: methods and applications. Nat. Rev. Drug Discov. 3 (2004) 935–949. | DOI

H. Kubinyi, Similarity and dissimilarity: a medicinal chemist’s view. Perspect. Drug Discov. Design 9 (1998) 225–252. | DOI

C.A. Lipinski, F. Lombardo, B.W. Dominy and P.J. Feeney, Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings. Adv. Drug Delivery Rev. 64 (2012) 4–17. | DOI

G. Liszt, E. Ford, M. Kurtev and L. Guarente, Mouse sir2 homolog sirt6 is a nuclear adp-ribosyltransferase. J. Biol. Chem. 280 (2005) 21313–21320. | DOI

A.D. Mackerell, et al., All-atom empirical potential for molecular modeling and dynamics studies of proteins. J. Phys. Chem. B 102 (1998) 3586–3616. | DOI

Z. Mao, C. Hine, X. Tian, M. Van Meter, M. Au, A. Vaidya, A. Seluanov and V. Gorbunova, Sirt6 promotes dna repair under stress by activating parp1. Science 332 (2011) 1443–1446. | DOI

E. Michishita, J.Y. Park, J.M. Burneskis, J.C. Barrett and I. Horikawa, Evolutionarily conserved and nonconserved cellular localizations and functions of human sirt proteins. Mol. Biol. Cell 16 (2005) 4623–4635. | DOI

T. Mitchell and G.A. Showell, Design strategies for building drug-like chemical libraries. Curr. Opin. Drug Discov. Devel. 4 (2001) 314–318.

R. Mostoslavsky, et al., Genomic instability and aging-like phenotype in the absence of mammalian sirt6. Cell 124 (2006) 315–329. | DOI

P.W. Pan, J.L. Feldman, M.K. Devries, A. Dong, A.M. Edwards and J.M. Denu, Structure and biochemical functions of sirt6. J. Biol. Chem. 286 (2011) 14575–14587. | DOI

J.C. Phillips, R. Braun, W. Wang, J. Gumbart, E. Tajkhorshid, E. Villa, C. Chipot, R.D. Skeel, L. Kale and K. Schulten, Scalable molecular dynamics with namd. J. Comput. Chem. 26 (2005) 1781–1802. | DOI

J. Platt, Fast training of support vector machines using sequential minimal optimization. In vol. 3 of Advances in Kernel Methods-Support Vector Learn. (1999).

Y. Qu, B.-L. Adam, Y. Yasui, M.D. Ward, L.H. Cazares, P.F. Schellhammer, Z. Feng, O.J. Semmes and G.L. Wright, Boosted decision tree analysis of surface-enhanced laser desorption/ionization mass spectral serum profiles discriminates prostate cancer from noncancer patients. Clin. Chem. 48 (2002) 1835–1843. | DOI

R.E. Rosenthal, Gams – a user’s guide (2015).

M. Szachniuk, M.C. De Cola, G. Felicia and J. Blazewicz, The orderly colored longest path problem – a survey of applications and new algorithms. RAIRO: OR 48 (2014) 25–51. | DOI | Numdam | MR | Zbl

O. Trott and A.J. Olson, Autodock vina: improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading. J. Comput. Chem. 31 (2010) 455–461.

F. Uney and M. Turkay, A mixed-integer programming approach to multi-class data classification problem. Eur. J. Oper. Res. 173 (2006) 910–920. | DOI | MR | Zbl

H.O. Villar and M.R. Hansen, Design of chemical libraries for screening. Expert Opinion on Drug Discovery 4 (2009) 1215–1220. | DOI

D.C. Whitley, M.G. Ford and D.J. Livingstone, Unsupervised forward selection: a method for eliminating redundant variables. J. Chem. Inf. Comput. Sci. 40 (2000) 1160–1168. | DOI

I.H. Witten and E. Frank, Data Mining: Practical machine learning tools and techniques. Morgan Kaufmann (2005). | Zbl

S. Wold, M. Sjöström and L. Eriksson, Pls-regression: a basic tool of chemometrics. Chemometrics and Intelligent Laboratory Systems 58 (2001) 109–130. | DOI

C.W. Yap, Padel-descriptor: An open source software to calculate molecular descriptors and fingerprints. J. Comput. Chem. 32 (2011) 1466–1474. | DOI

L. Zhong, et al., The histone deacetylase sirt6 regulates glucose homeostasis via hif1$\alpha$. Cell 140 (2010) 280–293. | DOI