journal article·2024-06Open access

Revolutionizing inverse design of ionic liquids through the multi-property prediction of over 300,000 novel variants using ensemble deep learning

Tarek Lemaoui, Tarek Eid, Ahmad S. Darwish, Hassan A. Arafat, Fawzi Banat, Inas AlNashef

Abstract

In the flourishing field of materials science and engineering, ionic liquids (ILs) stand out for their advantageous features, unique tunable properties, and environmentally friendly attributes, making them ideal candidates for various applications. However, the enormous diversity of ILs presents a challenge that has traditionally been addressed through extensive experimental work. In this study, a computational approach that combines robust molecular modeling and advanced ensemble deep learning is employed. This proof-of-concept approach allows for the simultaneous prediction of multiple properties of ILs, thereby enabling a simplified pathway to eco-efficient inverse solvent design. Based on an extensive dataset from ILThermo with 73,847 data points of 2917 ILs from 1213 references and using insightful molecular features derived from COSMO-RS, 8 machine learning algorithms were used to predict various physical properties of ILs. Artificial Neural Networks (ANNs) have been proven to be the optimal choice based on the results obtained. The ANN model was carefully tuned, resulting in an ensemble model with a total of 11,241 parameters that exhibited remarkable predictive ability with R2 values of 0.993, 0.907, 0.931, and 0.875 for density, viscosity, surface tension, and melting temperature, respectively. A remarkable feature of this study is the extensive screening of 303,880 ILs obtained by combining all possible pairs from a set of 1070 cations and 284 anions (1070×284). This demonstrates a pragmatic approach to identifying different property profiles that significantly narrow the spectrum for experimental validation. Based on the screening, an open-source “Inverse Designer Tool” was developed as an advanced database filter to explore ILs based on user-defined criteria, facilitating the identification of promising IL candidates for specific applications. The results presented here open a door for a new approach to the exploration and application of ILs and catalyze their integration in various industrial fields as potential environmentally friendly solvents.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Ionic liquids properties and applications · Machine Learning in Materials Science · Innovative Microfluidic and Catalytic Techniques Innovation

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (81)

Show source-provided references
1. Anastas · Chem. Soc. Rev. · 2010 · 39 · 30110.1039/B918763B ↗
2. Constable · Green. Chem. · 2002 · 4 · 52110.1039/B206169B ↗
3. Petkovic · Chem. Soc. Rev. · 2011 · 40 · 138310.1039/C004968A ↗
4. Plechkova · Chem. Soc. Rev. · 2008 · 37 · 12310.1039/B006677J ↗
5. Huang · Chem. Eng. J. · 2023 · 464
6. Lee · Chem. Eng. J. · 2022 · 446
7. Barbosa · Chem. Eng. J. · 2023 · 47810.1016/j.cej.2023.147388 ↗
8. Han · Chem. Eng. J. · 2022 · 437
9. Li · Chem. Eng. J. · 2024 · 481
10. Xu · Chem. Eng. J. · 2023 · 477
11. Deng · J. Hazard. Mater. · 2011 · 192 · 135010.1016/j.jhazmat.2011.06.053 ↗
12. Mao · Chem. Eng. J. · 2024 · 481
13. Yin · Chem. Eng. J. · 2023 · 470
14. Zhu · Chem. Eng. J. · 2024
15. Wang · Chem. Eng. J. · 2023 · 473
16. Koutsoukos · Chem. Sci. · 2021 · 12 · 682010.1039/D1SC01000J ↗
17. Zuo · Mater. Today · 2021 · 51 · 12610.1016/j.mattod.2021.08.012 ↗
18. Tang · Mater. Today · 2020 · 41 · 7210.1016/j.mattod.2020.06.010 ↗
19. Rostami · Chem. Eng. Res. Des. · 2019 · 147 · 64810.1016/j.cherd.2019.05.031 ↗
20. Paduszyński · Ind. Eng. Chem. Res. · 2012 · 51 · 59110.1021/ie202134z ↗
21. Paduszyński · Ind. Eng. Chem. Res. · 2019 · 58 · 532210.1021/acs.iecr.9b00130 ↗
22. Baghban · J. Mol. Liq. · 2017 · 236 · 45210.1016/j.molliq.2017.04.019 ↗
23. Yu · AIChE J. · 2011 · 58 · 288510.1002/aic.12786 ↗
24. Paduszyński · J. Chem. Inf. Model. · 2014 · 54 · 131110.1021/ci500206u ↗
25. Boualem · J. Mol. Liq. · 2022 · 36810.1016/j.molliq.2022.120610 ↗
26. Koller · Int. J. Thermophys. · 2017 · 38 · 110.1007/s10765-017-2301-z ↗
27. Mohan · J. Chem. Phys. · 2023 · 15810.1063/5.0147052 ↗
28. Varnek · 2007 · 47 · 1111
29. Gharagheizi · Fluid Phase Equilib. · 2012 · 329 · 110.1016/j.fluid.2012.05.017 ↗
30. Farahani · Thermochim. Acta · 2012 · 549 · 1710.1016/j.tca.2012.09.011 ↗
31. Venkatraman · J. Mol. Liq. · 2018 · 264 · 31810.1016/j.molliq.2018.03.090 ↗
32. Low · J. Chem. Phys. · 2020 · 15310.1063/5.0016289 ↗
33. Caruana · Mach. Learn. · 1997 · 28 · 4110.1023/A:1007379606734 ↗
34. Liu · 2012
35. Bengio · IEEE Trans. Pattern Anal. Mach. Intell. · 2013 · 35 · 179810.1109/TPAMI.2013.50 ↗
36. Alyammahi · J. CO2 Util. · 2023 · 7210.1016/j.jcou.2023.102511 ↗
37. T. Lemaoui, A. Boublia, S. Lemaoui, A.S. Darwish, B. Ernst, M. Alam, Y. Benguerba, F. Banat, I.M. Alnashef, (2023).
38. Kazakov · 2023
39. Lemaoui · Ind. Eng. Chem. Res. · 2020 · 59 · 1334310.1021/acs.iecr.0c02542 ↗
40. Awaja · Chem. Eng. J. · 2023 · 47610.1016/j.cej.2023.146429 ↗
41. Kim · Nucleic Acids Res · 2021 · 49 · D138810.1093/nar/gkaa971 ↗
42. Alkhatib · Ind. Eng. Chem. Res. · 2022
43. Darwish · J. Mol. Liq. · 2023
44. Eid · J. Mol. Liq. · 2023 · 38210.1016/j.molliq.2023.121996 ↗
45. Kim · Sci. Adv. · 2020 · 6 · 1
46. Boublia · ACS Sustain. Chem. Eng. · 2022
47. Jain · IEEE Trans. Pattern Anal. Mach. Intell. · 2000 · 22 · 410.1109/34.824819 ↗
48. Chai · Geosci. Model Dev. · 2014 · 7 · 124710.5194/gmd-7-1247-2014 ↗
49. Gonc · J. Chem. Theory Comput. · 2023 · 19 · 60510.1021/acs.jctc.2c00955 ↗
50. Jung · J. Nonparametr. Stat. · 2018 · 30 · 19710.1080/10485252.2017.1404598 ↗
51. Encycl. Bioinforma. Comput. Biol.
52. Haykin · 2009
53. Lemaoui · ACS Sustain. Chem. Eng. · 2021 · 9 · 578310.1021/acssuschemeng.0c07367 ↗
54. Rokach · Artif. Intell. Rev. · 2010 · 33 · 110.1007/s10462-009-9124-7 ↗
55. Ganaie · Eng. Appl. Artif. Intell. · 2022 · 11510.1016/j.engappai.2022.105151 ↗
56. Lakshminarayanan · Adv. Neural Inf. Process. Syst. · 2017 · 30 · 6405
57. Pilania · J. Chem. Inf. Model. · 2019 · 59 · 501310.1021/acs.jcim.9b00807 ↗
58. Bejagam · J. Phys. Chem. B · 2022 · 126 · 93410.1021/acs.jpcb.1c08354 ↗
59. Lundberg · Adv. Neural Inf. Process. Syst. · 2017 · 30 · 1
60. Lundberg · Nat. Mach. Intell. · 2020 · 2 · 5610.1038/s42256-019-0138-9 ↗
61. Tropsha · QSAR Comb. Sci. · 2003 · 22 · 6910.1002/qsar.200390007 ↗
62. Hammoudi · J. Biomol. Struct. Dyn. · 2022 · 40 · 88610.1080/07391102.2020.1819878 ↗
63. Mitra · Mol. Simul. · 2010 · 36 · 106710.1080/08927022.2010.503326 ↗
64. Nabipour · Renew. Energy · 2020 · 152 · 108610.1016/j.renene.2020.01.140 ↗
65. Hammoudi · J. Mol. Struct. · 2021 · 122910.1016/j.molstruc.2020.129845 ↗
66. Ojha · Chemom. Intell. Lab. Syst. · 2011 · 109 · 14610.1016/j.chemolab.2011.08.007 ↗
67. Lemaoui · Green. Chem. · 2020 · 22 · 851110.1039/D0GC03077E ↗
68. Almi · J. Mol. Struct. · 2020 · 121110.1016/j.molstruc.2020.128015 ↗
69. Torrecilla · Green. Chem. · 2010 · 12 · 12310.1039/B919806G ↗
70. Adeyemi · J. Mol. Liq. · 2020 · 31110.1016/j.molliq.2020.113180 ↗
71. Iqbal · J. Mol. Liq. · 2019 · 273 · 21510.1016/j.molliq.2018.10.044 ↗
72. Schäfer · Phys. Chem. Chem. Phys. · 2000 · 2 · 218710.1039/b000184h ↗
73. Aghaie · Fuel · 2020 · 27910.1016/j.fuel.2020.117984 ↗
74. Pattanaik · Chem · 2020 · 6 · 120410.1016/j.chempr.2020.05.002 ↗
75. Haghighatlari · Chem · 2020 · 6 · 152710.1016/j.chempr.2020.05.014 ↗
76. Mullins · Ind. Eng. Chem. Res. · 2006 · 45 · 438910.1021/ie060370h ↗
77. Argyriou · Adv. Neural Inf. Process. Syst. · 2007 · 1
78. Kakkar · Educ. Chem. Eng. · 2021 · 36 · 11510.1016/j.ece.2021.04.003 ↗
79. Matsukawa · Fluid Phase Equilib. · 2021 · 548
80. Oluwaseye · J. King Saud. Univ. - Sci. · 2020 · 32 · 7510.1016/j.jksus.2018.02.009 ↗
81. Wu · Mol. Inform. · 2020 · 39 · 1