Optimizing Neural Networks for Chemical Reaction Prediction: Insights from Methylene Blue Reduction Reactions

Overview

Journal Int J Mol Sci

Publisher MDPI

Specialties Biochemistry
Chemistry
Molecular Biology

Date 2024 Apr 13

PMID 38612671

Authors

Ivan Malashin

Vadim Tynchenko

Andrei Gantimurov

Vladimir Nelyub

Aleksei Borodulin

Affiliations

Soon will be listed here.

Abstract

This paper offers a thorough investigation of hyperparameter tuning for neural network architectures using datasets encompassing various combinations of Methylene Blue (MB) Reduction by Ascorbic Acid (AA) reactions with different solvents and concentrations. The aim is to predict coefficients of decay plots for MB absorbance, shedding light on the complex dynamics of chemical reactions. Our findings reveal that the optimal model, determined through our investigation, consists of five hidden layers, each with sixteen neurons and employing the Swish activation function. This model yields an NMSE of 0.05, 0.03, and 0.04 for predicting the coefficients A, B, and C, respectively, in the exponential decay equation + · . These findings contribute to the realm of drug design based on machine learning, providing valuable insights into optimizing chemical reaction predictions.

References

Kalantari K, Ahmad M, Fard Masoumi H, Shameli K, Basri M, Khandanlou R . Rapid adsorption of heavy metals by Fe3O4/talc nanocomposite and optimization study using response surface methodology. Int J Mol Sci. 2014; 15(7):12913-27. PMC: 4139881. DOI: 10.3390/ijms150712913. View

Nayak A, Pal A . Green and efficient biosorptive removal of methylene blue by Abelmoschus esculentus seed: Process optimization and multi-variate modeling. J Environ Manage. 2017; 200:145-159. DOI: 10.1016/j.jenvman.2017.05.045. View

Bao Y, Kong W, Liu F, Qiu Z, He Y . Detection of glutamic acid in oilseed rape leaves using near infrared spectroscopy and the least squares-support vector machine. Int J Mol Sci. 2012; 13(11):14106-14. PMC: 3509568. DOI: 10.3390/ijms131114106. View

Fisher K, Vreugdenhil A . Adsorption of Chromium (VI) Using an Activated Carbon Derived from Petroleum Coke Feedstock. Int J Mol Sci. 2022; 23(24). PMC: 9783347. DOI: 10.3390/ijms232416172. View

Marzban N, Moheb A, Filonenko S, Hosseini S, Nouri M, Libra J . Intelligent modeling and experimental study on methylene blue adsorption by sodium alginate-kaolin beads. Int J Biol Macromol. 2021; 186:79-91. DOI: 10.1016/j.ijbiomac.2021.07.006. View

Ronnberg J, Lunner T, Zekveld A, Sorqvist P, Danielsson H, Lyxell B . The Ease of Language Understanding (ELU) model: theoretical, empirical, and clinical advances. Front Syst Neurosci. 2013; 7:31. PMC: 3710434. DOI: 10.3389/fnsys.2013.00031. View

Hallock A, Berman E, Zare R . Ultratrace kinetic measurements of the reduction of methylene blue. J Am Chem Soc. 2003; 125(5):1158-9. DOI: 10.1021/ja028129r. View

Bellido-Pedraza C, Calatrava V, Llamas A, Fernandez E, Sanz-Luque E, Galvan A . Nitrous Oxide Emissions from Nitrite Are Highly Dependent on Nitrate Reductase in the Microalga . Int J Mol Sci. 2022; 23(16). PMC: 9409008. DOI: 10.3390/ijms23169412. View

Yin X, Goudriaan J, Lantinga E, Vos J, Spiertz H . A flexible sigmoid function of determinate growth. Ann Bot. 2003; 91(3):361-71. PMC: 4244967. DOI: 10.1093/aob/mcg029. View

10.

Ramimoghadam D, Hussein M, Hin Taufiq-Yap Y . The effect of sodium dodecyl sulfate (SDS) and cetyltrimethylammonium bromide (CTAB) on the Properties of ZnO synthesized by hydrothermal method. Int J Mol Sci. 2012; 13(10):13275-93. PMC: 3497326. DOI: 10.3390/ijms131013275. View

11.

Luna J, Rufino R, Albuquerque C, Sarubbo L, Campos-Takaki G . Economic optimized medium for tensio-active agent production by Candida sphaerica UCP0995 and application in the removal of hydrophobic contaminant from sand. Int J Mol Sci. 2011; 12(4):2463-76. PMC: 3127128. DOI: 10.3390/ijms12042463. View

12.

Mahmoodi-Babolan N, Heydari A, Nematollahzadeh A . Removal of methylene blue via bioinspired catecholamine/starch superadsorbent and the efficiency prediction by response surface methodology and artificial neural network-particle swarm optimization. Bioresour Technol. 2019; 294:122084. DOI: 10.1016/j.biortech.2019.122084. View

13.

Cannavo S, Bertoldi A, Valeri M, Damiani F, Reale L, Brilli F . Impact of High Light Intensity and Low Temperature on the Growth and Phenylpropanoid Profile of . Int J Mol Sci. 2023; 24(10). PMC: 10218715. DOI: 10.3390/ijms24108554. View

14.

Koutsoukas A, Monaghan K, Li X, Huan J . Deep-learning: investigating deep neural networks hyper-parameters and comparison of performance to shallow methods for modeling bioactivity data. J Cheminform. 2017; 9(1):42. PMC: 5489441. DOI: 10.1186/s13321-017-0226-y. View