Quantitative prediction of imprinting factor of molecularly imprinted polymers by artificial neural network

Abstract

Artificial neural network (ANN) implementing the back-propagation algorithm was applied for the calculation of the imprinting factors (IF) of molecularly imprinted polymers (MIP) as a function of the computed molecular descriptors of template and functional monomer molecules and mobile phase descriptors. The dataset used in our study were obtained from the literature and classified into two distinctive datasets on the basis of the polymer's morphology, irregularly sized MIP and uniformly sized MIP datasets. Results revealed that artificial neural network was able to perform well on datasets derived from uniformly sized MIP (n = 23, r = 0.946, RMS = 2.944) while performing poorly on datasets derived from irregularly sized MIP (n = 75, r = 0.382, RMS = 6.123). The superior performance of the uniformly sized MIP dataset over the irregularly sized MIP dataset could be attributed to its more predictable nature owing to the consistency of MIP particles, uniform number and association constant of binding sites, and minimal deviation of the imprinted polymers. The ability to predict the imprinting factor of imprinted polymer prior to performing actual experimental work provide great insights on the feasibility of the interaction between template-functional monomer pairs.

Computational Design of Molecularly Imprinted Polymers

“…in calculations aimed at prediction of optimal template-monomer pairs. 76 The imprinting factor was predicted by artificial neural networks as a function of the calculated molecular descriptors and the mobile phase descriptors (the protocol is shown in Fig. 6.16).…”

“…161,162 Traditional factors that depend on monitoring the effects of changing one factor at a time on a response are extremely time consuming besides producing erroneous optimums in experiments. 161 However, chemometrics, often combined with artificial network simulations, 76 can help significantly in optimization and design of experiments for changing selected factors simultaneously to predict optimum conditions thus reducing the number of experiments necessary, 161 and providing error free analysis. There are a number of tools that are available to recognize patterns in the data and suggest predicted optimums while providing error analysis.…”

“…-Rational approaches that involve combinatorial methods, where an array of MIPs were prepared that could be analyzed in situ by binding assays 57-61 -Use of a virtual library of functional monomers to assign and screen against the target template molecule 62-65 -Rational approaches that involve computation of total energies (E), energy differences (DE), and distances (d) of closest approach between the monomers and template using molecular dynamics 66 -The use of density functional theory (DFT) method to calculate the binding energy ΔE, between a template and monomers as a measure of their interaction that facilitates the selection of the monomers 67,68 -Rational design that involve conformation of template-functional monomer complexes employing semi empirical methods 69-74 -Chemometric approaches to optimize monomer, template, and cross linker ratios 75 -Predicting template monomer complexes using neural network methods 76,77 The following sections discuss each of the above-mentioned computational methods for the rational design of MIPs. Table 6.1 summarizes the different computational procedures adopted for the rational design of MIPs for a variety of templates or analysis of polymer properties.…”

Theoretical and Computational Strategies for the Study of the Molecular Imprinting Process and Polymer Performance

“…Nantasenamat et al used literature data as the basis for a similar approach [146,151]. They applied ANN to correlate imprinting factors from diverse published HPLC studies with molecular descriptors and mobile phase compositions [152].…”

Prediction of GFP spectral properties using artificial neural network

“…41 In fact, descriptors derived from RECON have been successfully applied in various QSPR studies. 39,42,43 E-DRAGON produced over 1600 molcular descriptors 44 comprising of 20 types with the quantity of descriptors for each type shown in parenthesis: Constitutional descriptors (48), topological descriptors (119), walk and path counts (47), connectivity indices (33), information indices (47), 2D autocorrelations (96), (14), and molecular properties (31).…”