Have artificial neural networks met expectations in drug discovery as implemented in QSAR framework?

Expert Opinion on Drug Discovery

Volumn 11, Issue 7, 2016, Pages 627-639

  Dobchev, Dimitar ^a   Karelson, Mati ^b  

^a TALLINN UNIVERSITY OF TECHNOLOGY   (Estonia)

^b UNIVERSITY OF TARTU   (Estonia)

Author keywords

Artificial neural networks; drug discovery; QSAR

Indexed keywords

ARTIFICIAL NEURAL NETWORK; DRUG DEVELOPMENT; HUMAN; IMMUNITY; NONLINEAR SYSTEM; PRIORITY JOURNAL; QUANTITATIVE STRUCTURE ACTIVITY RELATION; RESPONSE VARIABLE; REVIEW; SCREENING; SENSITIVITY ANALYSIS; ALGORITHM; ANIMAL; CHEMISTRY; DRUG DESIGN; PROCEDURES; THEORETICAL MODEL;

DRUG;

ALGORITHMS; ANIMALS; DRUG DESIGN; DRUG DISCOVERY; HUMANS; MODELS, THEORETICAL; NEURAL NETWORKS (COMPUTER); NONLINEAR DYNAMICS; PHARMACEUTICAL PREPARATIONS; QUANTITATIVE STRUCTURE-ACTIVITY RELATIONSHIP;

EID: 84975298002     PISSN: 17460441     EISSN: 1746045X     Source Type: Journal    
DOI: 10.1080/17460441.2016.1186876     Document Type: Review

References (99)

1. F.Sams-Dodd Drug discovery: selecting the optimal approach. Drug Disc Today. 2006;11:465–472.
2. S.Mandal, M.Moudgil, S.K.Mandal. Rational drug design. E J Pharmacology. 2009 25;625(1–3):90–100.
3. A.Katritzky, M.Kuanar, S.Slavov, et al. Quantitative correlations of physical and chemical properties with chemical structure; utility for prediction. Chem Rev. 2010;110(10):5714–5789.•• Important review for extensive QSAR approach and applications.
4. A.R.Katritzky, D.A.Dobchev, M.Karelson. Physical, chemical, and technological property correlation with chemical structure: the potential of QSPR. Zeitschrift Naturforsch B. 2006;61(4):373–384.
5. O.P.Sharma, N.K.Saini, V.Gupta, et al. Evolutionary history of QSAR: a review. J Natur Cons. 2011;1(4):266–272.
6. A.Tropsha. Best practices for QSAR model development, validation, and exploitation. Mol Inf. 2010;29:476–488.
7. C.Hansch, A.Leo. In exploring QSAR: fundamentals and applications in chemistry and biology. Washington (DC): American Chemical Society; 1995.
8. J.Dearden. The history and development of quantitative structure-activity relationships. Ijqspr. 2016;1(1):1–44.
9. K.Roy, S.Kar, R.Das. Understanding the basics of QSAR for applications in pharmaceutical sciences and risk assessment. Amsterdam: Academic Press; 2015.
10. J.McKinney, A.Richard, C.Waller, et al. The practice of SAR in toxicology. Toxicol Sci. 2000;56:8–17.
11. M.Sternberg, S.Muggleton. Structure activity relationships and pharmacophore discovery using inductive logic programming. QSAR Comb Sci. 2003;22:510–518.
12. N.Nikolova, J.Jaworska. Approaches to measure chemical similarity: a review. QSAR Combi Sci. 2003;22:1006–1012.
13. C.Grepin, C.Pernelle. High-throughput screening. Drug Disc Today. 2000;5(5):212–214.
14. L.M.Mayr, D.Bojanic. Novel trends in high-throughput screening. Cur Opin Pharmacol. 2009;9(5):580–588.
15. A.P.Engelbrecht. Computational intelligence: an introduction. New York, NY: Wiley; 2003.
16. A.Konar. Computational intelligence; principles, techniques and applications. Berlin: Springer; 2005.
17. D.A.Dobchev, G.G.Pillai, M.Karelson. In silico machine learning methods in drug development. Curr Top Med Chem. 2014;14(16):1913–1922.
18. J.Devillers. Neural networks in QSAR and drug design. London: Academic Press; 1996.
19. V.Lobanov. Using artificial neural networks to drive virtual screening of combinatorial libraries. Drug Disc Today. 2004;2(4):149–156.
20. W.S.McCutloch, W.Pttts. A logical calculus of the ideas imminent in nervous activity. Bull Math Biophys. 1943;5:115–133.
21. S.Haykin. Neural networks: a comprehensive foundation. London: Pearson; 1999.•• An extensive book describing ANN theory including various types of ANNs.
22. M.H.Hassoun. Fundamentals of artificial neural networks. Cambridge (MA): A Bradford Book, MIT Press; 2003.
23. L.Fausett. Fundamentals of neural networks: architectures, algorithms, and applications. Prentice-Hall (NJ); 1994.
24. B.Lucic, N.Trinajstic. Multivariate regression outperforms several robust architectures of neural networks in QSAR modeling. J Chem Inf Comput Sci. 1999;39:121–132.
25. I.I.Baskin, V.A.Palyulin, N.S.Zefirov. Neural networks in building QSAR models. Methods Mol Biol. 2008;458:137–158.
26. I.V.Tetko, D.J.Livingstone, A.I.Luik. Neural network studies. 1. Comparison of overfitting and overtraining. J Chem Inf Comput Sci. 1995;35:826–833.
27. F.Burden, D.Winkler. Bayesian regularization of neural networks. Methods Mol Biol. 2008;458:25–44.
28. D.J.Livingstone, D.T.Manallack. Statistics using neural networks: chance effects. J Med Chem. 1993;36:1295–1297.
29. F.Burden, D.Winkler. An optimal self-pruning neural network and nonlinear descriptor selection in QSAR. QSAR Combi Sci. 2009;28(10):1092–1097.
30. D.Manallack, D.J.Livingstone. Artificial neural networks: application and chance effects for QSAR data analysis. Med Chem Res. 1992;2:181–190.
31. C.Munteanu, V.Aguiar-Pulido, A.Freire, et al. Graph-based processing of macromolecular information. Curr Bioinformatics. 2015;10(5):606–631.
32. R.Guha, P.C.Jurs. Interpreting computational neural network QSAR models: a measure of descriptor importance. J Chem Inf Model. 2005;45(3):800–806.
33. J.Borišek, V.Drgan, N.Minovski. Mechanistic interpretation of artificial neural network-based QSAR model for prediction of cathepsin K inhibition potency. J Chemometrics. 2014;28:272–281.
34. P.Ojha, K.Roy. Comparative QSARs for antimalarial endochins: importance of descriptor-thinning and noise reduction prior to feature selection. Chemom Intell Lab Sys. 2011;109:146–161.
35. M.Karelson, V.S.Lobanov, A.R.Katritzky. Quantum-chemical descriptors in QSAR/QSPR studies. Chem Rev. 1996;96:1027–1043.
36. M.Karelson. Molecular descriptors in QSAR/QSPR. New York, NY: Wiley-Interscience; 2000.
37. R.Todeschini, V.Consonni. Handbook of molecular descriptors. Weinheim: Wiley-VCH, Verlag GmbH; 2008.
38. N.Nikolova, J.Jaworska. Approaches to measure chemical similarity – a review. QSAR Comb Sci. 2003;22:1006–1026.
39. D.Dobchev, I.Tulp, G.Karelson, et al. Subchronic oral and inhalation toxicities: a challenging attempt for modeling and prediction. Mol Informatics. 2013;32:793–01.
40. S.Agatonovic-Kustrin, R.Beresford. Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research. J Pharm Biomed. 2000;22(5):717–727.
41. PubChem [Internet]. [Cited 2016 May 16]. Available from: https://pubchem.ncbi.nlm.nih.gov/.
42. X.-Q.Xie. Exploiting PubChem for virtual screening. Expert Opin Drug Discov. 2010;5(12):1205–1220.
43. CheMbl database [Internet]. [cited 2016 May 16]. Available from: https://www.ebi.ac.uk/chembldb/.
44. Matlab package [Internet]. [cited 2016 May 16]. Available from: http://www.mathworks.com.
45. Mathematica package. [cited 2016 May 16]. Available from: https://www.wolfram.com/mathematica/.
46. Statistica software [Internet]. [cited 2016 May 16]. Available from: www.statsoft.com.
47. Neuralware software [Internet]. [cited 2016 May 16]. Available from: http://neuralware.com/.
48. RRegrs package [Internet]. [cited 2016 May 16]. Available from: https://github.com/enanomapper/RRegrs/.
49. G.Tsiliki, C.Munteanu, J.Seoane, et al. RRegrs: an R package for computer-aided model selection with multiple regression models. J Chemoinformatics. 2015;7(1):1–16.
50. Virtual computational chemistry lab [Internet]. [cited 2016 May 16]. Available from: http://www.vcclab.org.
51. I.V.Tetko, J.Gasteiger, R.Todeschini, et al. Virtual computational chemistry laboratory - design and description. J Comput Aid Mol Des. 2005;19:453–463.
52. NL-MIND-BEST service [Internet]. [cited 2016 May 16]. Available from: http://bio-aims.udc.es/NL-MIND-BEST.php.
53. J.Zupan, J.Gasteiger. Neural networks in chemistry and drug design. Weinheim: Wiley-VCH; 1999.• Classical book on ANN applications and theory.
54. W.J.Lu, Y.L.Chen, W.P.Ma, et al. QSAR study of neuraminidase inhibitors based on heuristic method and radial basis function network. Eur J Med Chem. 2008;43:569–576.
55. F.Gharagheizi. QSPR analysis for intrinsic viscosity of polymer solutions by means of GA-MLR and RBFNN. Comput Mater Sci. 2007;40:159–167.
56. T.Kohonen. Self-organizing maps. 3rd ed. Berlin: Springer; 2000.
57. K.-L.Du. Clustering: a neural network approach. Neural Net. 2010;23:89–107.
58. R.M.Neal. Bayesian learning for neural networks. New York, NY: Lecture notes in statistics, Springer; 1996.
59. D.A.Winkler, F.R.Burden. Application of neural networks to large dataset QSAR, virtual screening, and library design. In: L.B.English, editor. Combinatorial library. Methods in molecular biology. Clifton (NY): Springer Protocols; 2002.
60. C.M.Bishop. Neural networks for pattern recognition. Oxford: Clarendon Press; 2005.
61. S.P.Niculescu. Artificial neural networks and genetic algorithms in QSAR. J Mol Struc. 2003;622(1–2):71–83.
62. B.Ramsundar, S.Kearnes, P.Riley, et al. Massively multitask networks for drug discovery. arXiv:1502.02072 [stat.ML].• Interesting article indicating the capacity of ANNs.
63. A.Speck-Planche, V.Kleandrova, M.Cordeiro. Chemoinformatics for rational discovery of safe antibacterial drugs: simultaneous predictions of biological activity against streptococci and toxicological profiles in laboratory animals. Bioorg Med Chem. 2013;21(10):2727–2732.
64. K.Myint, L.R.Wang, Q.Tong, et al. Molecular fingerprint-based artificial neural networks QSAR (FANN-QSAR) for ligand biological activity predictions. Mol Pharmaceutics. 2012;9:2912–2923.
65. NCI database [Internet]. [cited 2016 May 16]. Available from: http://dctd.cancer.gov/ResearchResources/default.htm.
66. S.Sardari, H.Kohanzad, G.Ghavami. Artificial neural network modeling of antimycobacterial chemical space to introduce efficient descriptors employed for drug design. Chemom Intel Lab Sys. 2014;130:151–158.
67. S.Eric, M.Kalinic, A.Popovic, et al. Prediction of aqueous solubility of drug-like molecules using a novel algorithm for automatic adjustment of relative importance of descriptors implemented in counter-propagation artificial neural networks. Int J Pharm. 2012;437(1–2):232–241.
68. R.Mueller, E.S.Dawson, J.Meiler, et al. Discovery of 2-(2-benzoxazoyl amino)-4-aryl-5-cyanopyrimidine as negative allosteric modulators (NAMs) of metabotropic glutamate receptor 5 (mGlu5): from an artificial neural network virtual screen to an in vivo tool compound. Chemom Med Chem. 2012;7:406–414.
69. J.C.Patra, B.H.Chua. Artificial neural network-based drug design for diabetes mellitus using flavonoids. J Comput Chem. 2011;32(4):555–567.
70. J.C.Patra, O.Singh. Artificial neural networks-based approach to design ARIs using QSAR for diabetes mellitus. J Comput Chem. 2009;30:2494–2508.
71. D.A.Dobchev, I.Mager, I.Tulp, et al. Prediction of cell-penetrating peptides using artificial neural networks. Cur Comp-Aided Drug Des. 2010;6:79–89.
72. S.Polak, B.Wisniowska, M.Ahamadi, et al. Prediction of the hERG potassium channel inhibition potential with use of the artificial neural networks. Adv Intel Soft Comput. 2010;75:91–99.
73. A.Guerra, J.A.Paez, N.E.Campillo. Artificial neural networks in ADMET modeling: prediction of blood-brain barrier permeation. QSAR Combi Sci. 2007;27(5):586–594.
74. N.Khatri, V.Lather, A.Madan. Diverse classification models for anti-hepatitis C virus activity of thiourea derivatives. Chemom Intel Lab Sys. 2015;140:13–21.
75. L.Lancashire, R.C.Rees, G.Ball. Identification of gene transcript signatures predictive for estrogen receptor and lymph node status using a stepwise forward selection artificial neural network modeling approach. Art Intel Med. 2008;43:99–111.
76. A.R.Katritzky, D.A.Dobchev, D.Fara, et al. Skin permeation rate as a function of chemical structure. J Med Chem. 2006;49(11):3305–3314.
77. A.R.Katritzky, Z.Q.Wang, S.Slavov, et al. Synthesis and bioassay of novel mosquito repellents predicted from chemical structure. Proc Natl Acad Sci. 2008;105:7359–7364.
78. H.González-Díaz, D.M.Herrera-Ibatá, A.Duardo-Sánchez, et al. ANN multiscale model of anti-HIV drugs activity vs AIDS prevalence in the US at county level based on information indices of molecular graphs and social networks. J Chem Inf Model. 2014;54(3):744–755.
79. O.Guner. History and evolution of the pharmacophore concept in computer-aided drug design. Curr Top Med Chem. 2002;2(12):1321–1332.
80. O.Dror, A.Shulman-Peleg, R.Nussinov, et al. Predicting molecular interactions in silico: I. A guide to pharmacophore identification and its applications to drug design. Curr Med Chem. 2004;11(1):71–90.
81. R.D.Cramer, S.A.DePriest, D.E.Patterson, et al. In: H.Kubinyi, editor. The developing practice of comparative molecular field analysis, in 3D QSAR in drug design: theory, methods and applications. Netherlands: ESCOM; 1993. p. 443–485.
82. G.Klebe, U.Abraham, T.Mietzner. Molecular similarity indices in a comparative analysis (CoMSIA) of drug molecules to correlate and predict their biological activity. J Med Chem. 1994;37:4130–4146.
83. M.Akamatsu. Current state and perspectives of 3D-QSAR. Curr Top Med Chem. 2002;2(12):1381–1394.
84. A.K.Debnath. Application of 3D-QSAR techniques in anti-HIV-1 drug design-an overview. Curr Pharm Des. 2005;11(24):3091–3110.
85. C.A.Kontogiorgis, P.Papaioannou, D.J.Hadjipavlou-Litina. Matrix metalloproteinase inhibitors: a review on pharmacophore mapping and (Q)SARs results. Curr Med Chem. 2005;12(3):339–355.
86. O.Nicolotti, C.Altomare, M.Pellegrini-Calace, et al. Neuronal nicotinic acetylcholine receptor agonists: pharmacophores, evolutionary QSAR and 3D-QSAR models. Curr Top Med Chem. 2004;4(3):335–360.
87. A.Nayyar, A.Malde, R.Jain, et al. 3D-QSAR study of ring substituted quinoline class of anti-tuberculosis agents. Bioorg Med Chem. 2006;14(3):847–856.
88. H.Matter, P.Kotsonis. Biology and chemistry of the inhibition of nitric oxide synthases by pteridine-derivatives as therapeutic agents. Med Res Rev. 2004;24(5):662–684.
89. W.Li, Y.Tang, Y.L.Zheng, et al. Molecular modeling and 3D-QSAR studies of indolomorphinan derivatives as kappa opioid antagonists. Bioorg Med Chem. 2006;14(3):601–610.
90. D.R.Flower, H.McSparron, M.J.Blythe, et al. Computational vaccinology: quantitative approaches. Novartis Found Symp. 2003;254:102–120.
91. B.Bordas, T.Komives, A.Lopata. Ligand-based computer-aided pesticide design. A review of applications of the CoMFA and CoMSIA methodologies. Pest Manag Sci. 2003;59(4):393–400.
92. G.Schneider. Neural networks are useful tools for drug design. Neural Net. 2000;13:15–16.
93. R.Hecht-Nielsen. Counterpropagation networks. Appl Opt. 1987;26(23):4979–4983.
94. M.Shin, D.Jang, H.Nam, et al. Predicting the absorption potential of chemical compounds through a deep learning approach. IEEE/ACM Trans Comput Bio Bioinf. 2016;PP(99):1–1.
95. ScienceDirect indexing [Internet]. [cited 2016 May 16]. Available from: http://www.sciencedirect.com/.
96. D.Manallack, D.Livingstone. Neural networks in drug discovery: have they lived up to their promise? Eur J Med Chem. 1999;34:195−208.
97. Dragon software [Internet]. [cited 2016 May 16]. Available from: http://www.talete.mi.it/products/dragon_description.htm.
98. CODESA-PRO software [Internet]. [cited 2016 May 16]. Available from: http://codessa-pro.com/.
99. R.Guha. Chemical informatics functionality in R. J Stat Soft. 2007;6:4–18.