Open Access Open Access  Restricted Access Subscription or Fee Access

Artificial Neural Network: An Accessible Itinerary in the Rational Development of Drug Design and Development

Tushar R. Poriya


The passage for the development of any drug molecule is extremely wide and long as it takes tremendous amount of time and capital. Artificial Neural Network has become a convenient and promising tool for the development of drug thereby decreasing the manual labour, time as well as money. Learning the different types of neural networks and their wide applicability in the field of drug discovery, ANN has become a trusted approach, but only under expert knowledge. In order to increase the pace of drug discovery process high-throughput screening (HTS) and combinatorial chemistry has been introduced. To make the best use of these novel methods large amount of data sets are feed for analysis and efficient results are obtained from massive input data. To solve the complex relations between pharmaceutically relevant properties and the chemical structures of the compound ANN has proved its potential by improving the quality and diversity of virtual screening. This review imparts the focus on the latest techniques used in Artificial Neural Networks for the development of drug process. Back propagation Neural Networks was the main concept used for the drug development. Different aspects of drug discovery were considered using neural networks such as virtual screening, route of drug delivery, ADMET, physicochemical properties, toxicity profiles, drug selectivity, prediction of binding of molecule with the targeted receptors, building structural activity models with respect to targets.


high-throughput screening, drug delivery, ADMET, artificial neural network

Full Text:



McCulloch WS, Pitts W. A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys. 1943;5:115–133. doi:10.1007/ BF02478259. (L. Gentiluomo, D. Roessner, D. Augustijn, H. Svilenov, A. Kulakova, S. Mahapatra, G. Winter, W. Streicher, a. Rinnan, G.H.J. Peters, P. Harris, W. Frieß, Application of interpretable artificial neural networks to early monoclonal antibodies development, European Journal of Pharmaceutics and Biopharmaceutics (2019)).

D.E. Heckerman, E.H. Shortliffe, Artificial Intelligence Med. 4 (1992) 35–52. H.B. Jimison, L.M. Fagan, R.D. Shachter, E.H. Shortliffe, Artificial Intelligence Med. 4 (1992) 191–205.

Rosenblatt F. The perceptron: a probabilistic model for information storage and organization in the brain. Psychol Rev. 1958;65(6):386–408.

Igor I. Baskin, David Winkler & Igor V. Tetko (2016) A renaissance of neural networks in drug discovery, Expert Opinion on Drug Discovery, 11:8, 785–795.

Aoyama T, Suzuki Y, Ichikawa H. Neural networks applied to structure-activity relationships. J Med Chem. 1990;33(3):905–908.

McCulloch WS, Pitts W. A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys. 1943;5:115–133. doi:10.1007/ BF02478259.

Baskin II, Skvortsova MI, Stankevich IV, et al. On the basis of invariants of labeled molecular graphs. J Chem Inf Comput Sci.1995;35(3):527–531.

Artemenko NV, Baskin II, Palyulin VA, et al. Artificial neural network and fragmental approach in prediction of physicochemical properties of organic compounds. Russian Chem Bull. 2003;52(1):20–29.

Halberstam NM, Baskin II, Palyulin VA, et al. Neural networks as amethod for elucidating structure-property relationships for organic compounds. Russian Chem Rev. 2003;72(7):629–649.

Rumelhart DE, Hinton GE, Williams RJ. Learning internal representations by backpropagating errors. Nature. 1986;33:533–536.

Tetko IV, Livingstone DJ, Luik AI. Neural network studies. 1. Comparison of overfitting and overtraining. J Chem Inf Comput Sci. 1995;35(5):826–833.

Baskin II, Palyulin VA, Zefirov NS. Neural networks in building QSAR models. Methods Mol Biol (Clifton, NJ). 2008;458:137–158.

Varnek A, Gaudin C, Marcou G, et al. Inductive transfer of knowledge: application of multi-task learning and feature net approaches to model tissue-air partition coefficients. J Chem Inf Model. 2009;49 (1):133–144.

Caruana R. Multitask learning. Mach Learn. 1997;28(1):41–75.

Markou M, Singh S. Novelty detection: a review – part 2: neural network based approaches. Signal Process. 2003;83(12):2499–2521. doi:10.1016/j.sigpro.2003.07.019.

Karpov PV, Osolodkin DI, Baskin II, et al. One-class classification as a novel method of ligand-based virtual screening: the case of glycogen synthase kinase 3ОІ inhibitors. Bioorg Med Chem Lett. 2011;21 (22):6728–6731.

Tikhonov AN, Arsenin VY. Solutions of ill-posed problems. New York: Winston; 1977.

Burden F, Winkler D. Bayesian regularization of neural networks. Methods Mol Biol. 2008;458:25–44.

Burden FR, Ford MG, Whitley DC, et al. Use of automatic relevance determination in QSAR studies using Bayesian neural networks. J Chem Inf Comput Sci. 2000;40(6):1423–1430.

Burden FR, Winkler DA. Optimal sparse descriptor selection for QSAR using Bayesian methods. QSAR Comb Sci. 2009;28(6– 7):645–653.

Winkler DA, Burden FR. Bayesian neural nets for modeling in drug discovery. Drug Discovery Today BIOSILICO. 2004;2(3):104–111.

Bruneau P. Search for predictive generic model of aqueous solubility using Bayesian neural nets. J Chem Inf Comput Sci. 2001;41 (6):1605–1616.

Burden FR, Winkler DA. A quantitative structure-activity relationships model for the acute toxicity of substituted benzenes to Tetrahymena pyriformis using Bayesian-regularized neural networks. Chem Res Toxicol. 2000;13(6):436–440.

Epa VC, Burden FR, Tassa C, et al. Modeling biological activities of nanoparticles. Nano Lett. 2012;12(11):5808–5812.

Winkler DA, Mombelli E, Pietroiusti A, et al. Applying quantitative structure-activity relationship approaches to nanotoxicology: current status and future potential. Toxicol. 2013;313(1):15–23.

Kohonen T. Self-organizing maps. Berlin: Springer; 2001.

Anzali S, Gasteiger J, Holzgrabe U, et al. The use of self-organizing neural networks in drug design. Perspect Drug Discov Des. 1998;9:273–299.

Schneider P, Mueller AT, Gabernet G, et al. Hybrid network model for “deep learning” of chemical data: application to antimicrobial peptides. Mol Inform. 2016.


  • There are currently no refbacks.