Inhibitor_Mol_VAE: a variational autoencoder approach for generating corrosion inhibitor molecules
Source abstract
Abstract
Deep learning-based generative modeling demonstrates proven advantages as an effective approach in molecular discovery. This study introduces a generative-network based method called Inhibitor_Mol_VAE, which uses a variational autoencoder model to generate corrosion inhibitor molecules with targeted inhibition efficiency. We first evaluate the model’s ability to reconstruct molecules. Then, we assess the model’s ability to generate new inhibitor molecules using physiochemical properties (including MolWt, LogP, Vdw_volume, and Electronegativity). New molecules with high inhibition efficiencies at low concentrations, such as [ethoxy(methoxy)phosphoryl]-phenylmethanol and (alpha-methylamino-benzyl)-phosphonsaeure-monoaethylester are successfully discovered.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Corrosion Behavior and Inhibition · Hydrogen embrittlement and corrosion behaviors in metals · Concrete Corrosion and Durability
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (40)
Show source-provided references
1. Hou, B. et al. The cost of corrosion in China. npj Mater. Degrad. 1, 4 (2017).10.1038/s41529-017-0005-2 ↗
2. Gece, G. Drugs: A review of promising novel corrosion inhibitors. Corros. Sci. 53, 3873–3898 (2011).10.1016/j.corsci.2011.08.006 ↗
3. Abou-Elseoud, W. S., Abdel-karim, A. M., Hassan, E. A. & Hassan, M. L. Enzyme-and acid-extracted sugar beet pectin as green corrosion inhibitors for mild steel in hydrochloric acid solution. Carbohydr. Polym. Technol. Appl. 2, 100072 (2021).
4. Harvey, T. G. et al. The effect of inhibitor structure on the corrosion of AA2024 and AA7075. CORROSION SCIENCE 53, 2184–2190 (2011).10.1016/j.corsci.2011.02.040 ↗
5. Assad, H. & Kumar, A. Understanding functional group effect on corrosion inhibition efficiency of selected organic compounds. JOURNAL OF MOLECULAR LIQUIDS 344, https://doi.org/10.1016/j.molliq.2021.117755 (2021).10.1016/j.molliq.2021.117755 ↗
6. Satpati, S. et al. Amino acid and cinnamaldehyde conjugated Schiff bases as proficient corrosion inhibitors for mild steel in 1 M HCl at higher temperature and prolonged exposure: Detailed electrochemical, adsorption and theoretical study. JOURNAL OF MOLECULAR LIQUIDS 324, https://doi.org/10.1016/j.molliq.2020.115077 (2021).10.1016/j.molliq.2020.115077 ↗
7. Rezaeivala, M., Karimi, S., Sayin, K. & Tüzün, B. Experimental and theoretical investigation of corrosion inhibition effect of two piperazine-based ligands on carbon steel in acidic media. COLLOIDS AND SURFACES A-PHYSICOCHEMICAL AND ENGINEERING ASPECTS 641, https://doi.org/10.1016/j.colsurfa.2022.128538 (2022).10.1016/j.colsurfa.2022.128538 ↗
8. Elqars, E. et al. New 3-(2-methoxyphenyl)-isoxazole-carvone: synthesis, spectroscopic characterization, and prevention of carbon steel corrosion in hydrochloric acid. JOURNAL OF MOLECULAR LIQUIDS 347, https://doi.org/10.1016/j.molliq.2021.118311 (2022).10.1016/j.molliq.2021.118311 ↗
9. Lazrak, J. et al. Detailed DFT/MD simulation, surface analysis and electrochemical computer explorations of aldehyde derivatives for mild steel in 1.0 M HCl. COLLOIDS AND SURFACES A-PHYSICOCHEMICAL AND ENGINEERING ASPECTS 632, https://doi.org/10.1016/j.colsurfa.2021.127822 (2022).10.1016/j.colsurfa.2021.127822 ↗
10. Obot, I. B., Macdonald, D. D. & Gasem, Z. M. Density functional theory (DFT) as a powerful tool for designing new organic corrosion inhibitors. Part 1: An overview. CORROSION SCIENCE 99, 1–30 (2015).10.1016/j.corsci.2015.01.037 ↗
11. Verma, C. et al. Molecular dynamics and Monte Carlo simulations as powerful tools for study of interfacial adsorption behavior of corrosion inhibitors in aqueous phase: A review. JOURNAL MOLECULAR LIQUIDS 260, 99–120 (2018).10.1016/j.molliq.2018.03.045 ↗
12. Galvao, T. L. P., Novell-Leruth, G., Kuznetsova, A., Tedim, J. & Gomes, J. R. B. Elucidating Structure-Property Relationships in Aluminum Alloy Corrosion Inhibitors by Machine Learning. JOURNAL PHYSICAL CHEMISTRY C. 124, 5624–5635 (2020).10.1021/acs.jpcc.9b09538 ↗
13. Zhao, H. X., Zhang, X. H., Ji, L., Hu, H. X. & Li, Q. S. Quantitative structure-activity relationship model for amino acids as corrosion inhibitors based on the support vector machine and molecular design. CORROSION SCIENCE 83, 261–271 (2014).10.1016/j.corsci.2014.02.023 ↗
14. Li, L. et al. The discussion of descriptors for the QSAR model and molecular dynamics simulation of benzimidazole derivatives as corrosion inhibitors. CORROSION SCIENCE 99, 76–88 (2015).10.1016/j.corsci.2015.06.003 ↗
15. Chen, F. F. et al. Correlation between molecular features and electrochemical properties using an artificial neural network. MATERIALS DESIGN 112, 410–418 (2016).10.1016/j.matdes.2016.09.084 ↗
16. Quadri, T. W. et al. Development of QSAR-based (MLR/ANN) predictive models for effective design of pyridazine corrosion inhibitors. MATERIALS TODAY COMMUNICATIONS 30, https://doi.org/10.1016/j.mtcomm.2022.103163 (2022).10.1016/j.mtcomm.2022.103163 ↗
17. Ser, C. T., Zuvela, P. & Wong, M. W. Prediction of corrosion inhibition efficiency of pyridines and quinolines on an iron surface using machine learning-powered quantitative structure-property relationships. APPLIED SURFACE SCIENCE 512, https://doi.org/10.1016/j.apsusc.2020.145612 (2020).10.1016/j.apsusc.2020.145612 ↗
18. Schiessler, E. J. et al. Predicting the inhibition efficiencies of magnesium dissolution modulators using sparse machine learning models. NPJ COMPUTATIONAL MATERIALS 7, https://doi.org/10.1038/s41524-021-00658-7 (2021).10.1038/s41524-021-00658-7 ↗
19. Dai, J. et al. Cross-category prediction of corrosion inhibitor performance based on molecular graph structures via a three-level message passing neural network model. Corros. Sci. 209, 110780 (2022).10.1016/j.corsci.2022.110780 ↗
20. Ma, J. et al. Data-driven corrosion inhibition efficiency prediction model incorporating 2D–3D molecular graphs and inhibitor concentration. Corros. Sci. 222, 111420 (2023).10.1016/j.corsci.2023.111420 ↗
21. Weininger, D. SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules. J. Chem. Inf. computer Sci. 28, 31–36 (1988).10.1021/ci00057a005 ↗
22. Segler, M. H. S., Kogej, T., Tyrchan, C. & Waller, M. P. Generating Focused Molecule Libraries for Drug Discovery with Recurrent Neural Networks. ACS CENTRAL SCIENCE 4, 120–131 (2018).10.1021/acscentsci.7b00512 ↗
23. Grisoni, F., Moret, M., Lingwood, R. & Schneider, G. Bidirectional Molecule Generation with Recurrent Neural Networks. JOURNAL CHEMICAL INFORMATION MODELING 60, 1175–1183 (2020).10.1021/acs.jcim.9b00943 ↗
24. Liu, H., Huang, Y. B. A., Liu, X. J. & Deng, L. Attention-wise masked graph contrastive learning for predicting molecular property. BRIEFINGS IN BIOINFORMATICS 23, https://doi.org/10.1093/bib/bbac303 (2022).10.1093/bib/bbac303 ↗
25. Lim, J., Hwang, S. Y., Moon, S., Kim, S. & Kim, W. Y. Scaffold-based molecular design with a graph generative model. CHEMICAL SCIENCE 11, 1153–1164 (2020).10.1039/C9SC04503A ↗
26. Gao, Z. X. et al. Fragment-based deep molecular generation using hierarchical chemical graph representation and multi-resolution graph variational autoencoder. MOLECULAR INFORMATICS 42, https://doi.org/10.1002/minf.202200215 (2023).10.1002/minf.202200215 ↗
27. Wu, B. H., Li, L. J., Cui, Y. & Zheng, K. Cross-Adversarial Learning for Molecular Generation in Drug Design. FRONTIERS IN PHARMACOLOGY 12, https://doi.org/10.3389/fphar.2021.827606 (2022).10.3389/fphar.2021.827606 ↗
28. Thomas, M., O’Boyle, N. M., Bender, A. & de Graaf, C. Augmented Hill-Climb increases reinforcement learning efficiency for language-based de novo molecule generation. JOURNAL OF CHEMINFORMATICS 14, https://doi.org/10.1186/s13321-022-00646-z (2022).10.1186/s13321-022-00646-z ↗
29. Blaschke, T., Olivecrona, M., Engkvist, O., Bajorath, J. & Chen, H. Application of generative autoencoder in de novo molecular design. Mol. Inform. 37, 1700123 (2018).10.1002/minf.201700123 ↗
30. Gómez-Bombarelli, R. et al. Automatic chemical design using a data-driven continuous representation of molecules. ACS Cent. Sci. 4, 268–276 (2018).10.1021/acscentsci.7b00572 ↗
31. Kingma, D. P. & Welling, M. An introduction to variational autoencoders. Found. Found. Trends® Mach. Learn. 12, 307–392 (2019).10.1561/2200000056 ↗
32. Li, C. et al. Geometry-based molecular generation with deep constrained variational autoencoder. IEEE Trans. Neural Netw. Learn. Syst. 35, 4852–4861 (2022).10.1109/TNNLS.2022.3147790 ↗
33. Landrum, G. Rdkit documentation. Release 1, 4 (2013).
34. Camacho-Mendoza, R. L., Feria, L., Angel Zarate-Hernandez, L., Alvarado-Rodriguez, J. G. & Cruz-Borbolla, J. New QSPR model for prediction of corrosion inhibition using conceptual density functional theory. JOURNAL OF MOLECULAR MODELING 28, https://doi.org/10.1007/s00894-022-05240-6 (2022).10.1007/s00894-022-05240-6 ↗
35. Quadri, T. W. et al. Multilayer perceptron neural network-based QSAR models for the assessment and prediction of corrosion inhibition performances of ionic liquids. COMPUTATIONAL MATERIALS SCIENCE 214, https://doi.org/10.1016/j.commatsci.2022.111753 (2022).10.1016/j.commatsci.2022.111753 ↗
36. Hadisaputra, S., Irham, A. D., Purwoko, A. A., Junaidi, E. & Hakim, A. Development of QSPR models for furan derivatives as corrosion inhibitors for mild steel. INTERNATIONAL JOURNAL OF ELECTROCHEMICAL SCIENCE 18, https://doi.org/10.1016/j.ijoes.2023.100207 (2023).10.1016/j.ijoes.2023.100207 ↗
37. Pham, T. H., Le, P. K. & Son, D. N. A data-driven QSPR model for screening organic corrosion inhibitors for carbon steel using machine learning techniques. RSC ADVANCES 14, 11157–11168 (2024).10.1039/D4RA02159B ↗
38. Lu, T. & Chen, F. Multiwfn: A multifunctional wavefunction analyzer. J. computational Chem. 33, 580–592 (2012).10.1002/jcc.22885 ↗
39. Dollar, O., Joshi, N., Beck, D. A. & Pfaendtner, J. Attention-based generative models for de novo molecular design. Chem. Sci. 12, 8362–8372 (2021).10.1039/D1SC01050F ↗
40. Bajusz, D., Rácz, A. & Héberger, K. Why is Tanimoto index an appropriate choice for fingerprint-based similarity calculations? JOURNAL OF CHEMINFORMATICS 7, https://doi.org/10.1186/s13321-015-0069-3 (2015).10.1186/s13321-015-0069-3 ↗