Identifying Potential Machine Learning Algorithms for the Simulation of Binding Affinities to Molecularly Imprinted Polymers

Molecularly imprinted polymers (MIPs) are synthetic receptors engineered towards the selective binding of a target molecule; however, the manner in which MIPs interact with other molecules is of great importance. Being able to rapidly analyze the binding of potential molecular interferences and determine the selectivity of a MIP can be a long tedious task, being time- and resource-intensive. Identifying computational models capable of reliably predicting and reporting the binding of molecular species is therefore of immense value in both a research and commercial setting. This research therefore sets focus on comparing the use of machine learning algorithms (multitask regressor, graph convolution, weave model, DAG model, and inception) to predict the binding of various molecular species to a MIP designed towards 2-methoxphenidine. To this end, each algorithm was “trained” with an experimental dataset, teaching the algorithms the structures and binding affinities of various molecular species at varying concentrations. A validation experiment was then conducted for each algorithm, comparing experimental values to predicted values and facilitating the assessment of each approach by a direct comparison of the metrics. The research culminates in the construction of binding isotherms for each species, directly comparing experimental vs. predicted values and identifying the approach that best emulates the real-world data.

[1]  Horst M. Sulzbach,et al.  NMR chemical shielding surface of N‐Acetyl‐N′‐Methylalaninamide: A density functional study , 1997, J. Comput. Chem..

[2]  Marta Janczura,et al.  Imprinting Technology for Effective Sorbent Fabrication: Current State-of-Art and Future Prospects , 2021, Materials.

[3]  Hongfei Xu,et al.  Machine Learning and Deep Learning in Chemical Health and Safety: A Systematic Review of Techniques and Applications , 2020, ACS Chemical Health & Safety.

[4]  Sergey A. Piletsky,et al.  Solid‐Phase Synthesis of Molecularly Imprinted Polymer Nanoparticles with a Reusable Template–“Plastic Antibodies” , 2013, Advanced functional materials.

[5]  H. Thatoi,et al.  Physicochemical characterization, modelling and optimization of ultrasono-assisted acid pretreatment of two Pennisetum sp. using Taguchi and artificial neural networking for enhanced delignification. , 2017, Journal of environmental management.

[6]  Yan Li,et al.  A Multitask Approach to Learn Molecular Properties , 2021, J. Chem. Inf. Model..

[7]  A. Buleté,et al.  High-field and benchtop NMR spectroscopy for the characterization of new psychoactive substances. , 2021, Forensic science international.

[8]  Joseph J BelBruno,et al.  Molecularly Imprinted Polymers. , 2018, Chemical reviews.

[9]  Youngjun Yoo,et al.  Hyperparameter optimization of deep neural network using univariate dynamic encoding algorithm for searches , 2019, Knowl. Based Syst..

[10]  C. García-Ruiz,et al.  Chemical classification of new psychoactive substances (NPS) , 2020 .

[11]  N. Pałka,et al.  Monitoring the role of enantiomers in the surface modification and adsorption process of polymers imprinted by chiral molecules: theory and practice , 2020, Journal of Materials Science.

[12]  Igor V Tetko,et al.  A renaissance of neural networks in drug discovery , 2016, Expert opinion on drug discovery.

[13]  M. Liechti,et al.  Effects of the new psychoactive substances diclofensine, diphenidine, and methoxphenidine on monoaminergic systems , 2018, European journal of pharmacology.

[14]  Dongsup Kim,et al.  Development of a graph convolutional neural network model for efficient prediction of protein-ligand binding affinities , 2021, PloS one.

[15]  Luhua Lai,et al.  Computational Chemical Synthesis Analysis and Pathway Design , 2018, Front. Chem..

[16]  Jerzy Leszczynski,et al.  SMILES‐based optimal descriptors: QSAR analysis of fullerene‐based HIV‐1 PR inhibitors by means of balance of correlations , 2009, J. Comput. Chem..

[17]  S. Ambrosini,et al.  Solid-phase synthesis of molecularly imprinted nanoparticles for protein recognition. , 2013, Chemical communications.

[18]  T. Żołek,et al.  A computational exploration of imprinted polymer affinity based on voriconazole metabolites. , 2014, The Analyst.

[19]  T. Cleij,et al.  Substrate displacement colorimetry for the detection of diarylethylamines , 2019, Sensors and Actuators B: Chemical.

[20]  Noof A. Alenazi,et al.  Selectivity Enhancement in Molecularly Imprinted Polymers for Binding of Bisphenol A , 2016, Sensors.

[21]  Vijay S. Pande,et al.  Molecular graph convolutions: moving beyond fingerprints , 2016, Journal of Computer-Aided Molecular Design.

[22]  M. Baron,et al.  Computationally Designed Perrhenate Ion Imprinted Polymers for Selective Trapping of Rhenium Ions , 2020 .

[23]  Eriola Betiku,et al.  Modeling and optimization of bioethanol production from breadfruit starch hydrolyzate vis-à-vis response surface methodology and artificial neural network , 2015 .

[24]  Klavs F Jensen,et al.  RDChiral: An RDKit Wrapper for Handling Stereochemistry in Retrosynthetic Template Extraction and Application , 2019, J. Chem. Inf. Model..

[25]  Samuel T Hutchinson,et al.  Solvent-Specific Featurization for Predicting Free Energies of Solvation through Machine Learning , 2019, J. Chem. Inf. Model..

[26]  Alexandre Tkatchenko,et al.  Machine learning for chemical discovery , 2020, Nature Communications.

[27]  Jiayu Zhou,et al.  Graph convolutional networks for computational drug development and discovery , 2019, Briefings Bioinform..

[28]  Joseph W. Lowdon,et al.  MIPs for commercial application in low-cost sensors and assays – An overview of the current status quo , 2020, Sensors and Actuators B: Chemical.

[29]  C. Banks,et al.  Engineering molecularly imprinted polymers (MIPs) for the selective extraction and quantification of the novel psychoactive substance (NPS) methoxphenidine and its regioisomers. , 2018, The Analyst.

[30]  Evan N. Feinberg,et al.  Improvement in ADMET Prediction with Multitask Deep Featurization. , 2020, Journal of medicinal chemistry.

[31]  Claudio N. Cavasotto,et al.  Computational chemistry in drug lead discovery and design , 2018, International Journal of Quantum Chemistry.

[32]  A. N. Hasanah,et al.  An Update on Molecularly Imprinted Polymer Design through a Computational Approach to Produce Molecular Recognition Material with Enhanced Analytical Performance , 2021, Molecules.

[33]  Pierre Baldi,et al.  Deep Architectures and Deep Learning in Chemoinformatics: The Prediction of Aqueous Solubility for Drug-Like Molecules , 2013, J. Chem. Inf. Model..

[34]  Dongsup Kim,et al.  FP2VEC: a new molecular featurizer for learning molecular properties , 2019, Bioinform..

[35]  Adam C Mater,et al.  Deep Learning in Chemistry , 2019, J. Chem. Inf. Model..

[36]  Po-Yao Huang,et al.  Structural Analysis and Optimization of Convolutional Neural Networks with a Small Sample Size , 2020, Scientific Reports.

[37]  Hojjat Adeli,et al.  Nature-Inspired Chemical Reaction Optimisation Algorithms , 2017, Cognitive Computation.

[38]  Philipp Marquetand,et al.  Machine Learning for Organic Synthesis: Are Robots Replacing Chemists? , 2018, Angewandte Chemie.

[39]  D. Lonati,et al.  Analytically diagnosed intoxication by 2-methoxphenidine and flubromazepam mimicking an ischemic cerebral disease , 2017, Clinical toxicology.

[40]  Zofia Iskierko,et al.  Bioinspired intelligent molecularly imprinted polymers for chemosensing: A mini review , 2015 .

[41]  B. Manohar,et al.  An artificial neural network analysis of porcine pancreas lipase catalysed esterification of anthranilic acid with methanol , 2005 .

[42]  Ji‐Xin Cheng,et al.  High-Speed Chemical Imaging by Dense-Net Learning of Femtosecond Stimulated Raman Scattering. , 2020, The journal of physical chemistry letters.

[43]  Tassaneewan Laksanasopin,et al.  Point-of-Care Diagnostics: Recent Developments in a Connected Age. , 2017, Analytical chemistry.

[44]  G. Horvai,et al.  The Selectivity of Polymers Imprinted with Amines , 2018, Molecules.

[45]  Humberto González Díaz,et al.  Computational chemistry comparison of stable/nonstable protein mutants classification models based on 3D and topological indices , 2007, J. Comput. Chem..

[46]  Munish Shorie,et al.  Nanomaterial based aptasensors for clinical and environmental diagnostic applications , 2019, Nanoscale advances.