Funct. Mater. 2026; 33 (3): 544-552.
Machine learning–driven design of π-conjugated systems in isomer space with target absorption spectra: a case study of Effenberger dye
School of Chemistry, V. N. Karazin Kharkiv National University, Svobody sq., 4, Kharkiv, 61022, Ukraine
This work presents a proof-of-concept study exploring the isomer space of the Effenberger dye to evaluate approaches for predicting optical properties aimed at the design of new compounds. A diverse library of isomers was generated, differing from the reference dye, and quantum chemical parameters were calculated using the Tight Binding Density Functional Theory (DFTB) method, a computationally efficient approximation to TD-DFT. This allowed the evaluation of a large number of molecules with reasonable accuracy. For each isomer, a broad set of molecular descriptors was calculated, including geometric, electronic, and topological parameters. The Boruta algorithm was applied to select the most relevant descriptors, reducing dimensionality and avoiding overfitting. Regression analysis was used as a simple baseline to correlate descriptors with long-wavelength transition energies. An artificial neural network (ANN) was then constructed using TensorFlow/Keras, with three hidden layers, ReLU activations, a linear output, and regularization methods. The model was trained on a representative subset, while the remaining molecules (30%) formed the test set. The ANN achieved high predictive performance, showing good agreement between predicted and reference TD-DFT values. This approach demonstrates that even a relatively small but diverse set of isomers can be used to build effective predictive models. The combination of DFTB, molecular descriptors, Boruta-based feature selection, and ANN modeling provides a versatile framework for designing new π-conjugated materials with tailored optical properties.
1. K. Roy, A. Banerjee, Materials Informatics I: Methods, first ed., Springer Cham, 2025. https://doi.org/10.1007/978-3-031-78736-2
2. J. Neugebauer, T. Hickel, Density functional theory in materials science, Wiley Interdiscip. Rev. Comput. Mol. Sci. 3(5) (2013) 438-448. https://doi.org/10.1002/wcms.1125
3. F. Giustino, Materials modelling using density functional theory: properties and predictions, first ed., Oxford University Press, 2014.
4. M. Cheng, C. L. Fu, R. Okabe, A. Chotrattanapituk, A. Boonkird, N. T. Hung, M. Li, Artificial intelligence-driven approaches for materials design and discovery, Nat. Mater. 25 (2026) 1-17. https://doi.org/10.1038/s41563-025-02403-7
5. M. B. Kursa, W. R. Rudnicki, Feature selection with the Boruta package, J. Stat. Softw. 36 (2010) 1-13. https://doi.org/10.18637/jss.v036.i11
6. F. Effenberger, F. Würthner, 5-Dimethylamino-5′-nitro-2, 2′-bithiophene - a New Dye with Pronounced Positive Solvatochromism, Angew. Chem. Int. Ed. Engl. 32 (1993) 719. https://doi.org/10.1002/anie.199307191
7. C. E. de Melo, M. Dominguez, M. C. Rezende, V. G. Machado, Solvatochromism of dyes inspired in Effenberger’s probe, Dyes Pigm. 184 (2021) 108757. https://doi.org/10.1016/j.dyepig.2020.108757
8. M. C. dos Santos, F. T. Souto, C. R. Nicoleti, M. C. Colaco, G. F. Caramori, V. G. Machado, Synthesis and solvatochromism of dipodal and tripodal dyes derived from Brooker’s merocyanine, J. Mol. Liq. 386 (2023) 122476. https://doi.org/10.1016/j.molliq.2023.122476
9. R. Mera-Adasme, M. C. Rezende, M. Domínguez, On the physical-chemical nature of solvent polarizability and dipolarity, Spectrochim. Acta A Mol. Biomol. Spectrosc. 229 (2020) 118008. https://doi.org/10.1016/j.saa.2019.118008
10. B. Pigulski, J. Cichos, S. Szafert, Polyynes as Precursors of Photoluminescent Solvent Polarity Probes, ACS Sustain. Chem. Eng. 5(8) (2017) 7077-7085. https://doi.org/10.1021/acssuschemeng.7b01274
11. I. V. Khristenko, A. V. Panteleimonov, R. Yu. Iliashenko, A.O. Doroshenko, V.V. Ivanov, O.S. Tkachenko, E.V. Benvenutti, Yu. V. Kholin, Heterogeneous polarity and surface acidity of silica-organic materials with fixed 1-n-propyl-3-methylimidazolium chloride as probed by solvatochromic and fluorescent dyes, Colloids Surf. A: Physicochem. Eng. Asp. 538 (2018) 280-286. https://doi.org/10.1016/j.colsurfa.2017.11.018
12. J. Liu, R. Li, X. Si, D. Zhou, Y. Shi, Y. Wang, X. Jing, P. Wang, Oligothiophene dye-sensitized solar cells, Energy Environ. Sci. 3(12) (2010) 1924-1928. https://doi.org/10.1039/c0ee00304b
13. M. R. Elmorsy, F. H. Abdelhamed, A. sultan Alqahtani, E. Abdel-Latif, A. A. Abdel-Shafi, M. A. Ismail, Computational design and experimental investigation of novel thiophene-based organic dyes with N, N-dimethylaminophenyl and morpholinophenyl donors for dye-sensitized solar cells, Opt. Mater. 151 (2024) 115386. https://doi.org/10.1016/j.optmat.2024.115386
14. S. K. Panja, S. S. Sharma, K. Sharma, K. Patel, A.L. Prajapat, S. Saha, S. Bera, N. Srivastava, J. Ray, Thiophene oligomer based NIR dyes: Photophysical properties and application in dye sensitized solar cells, Chem. Phys. 595 (2025) 112721. https://doi.org/10.1016/j.chemphys.2025.112721
15. D. Demeter, J. Roncali, S. Jungsuttiwong, F. Melchiorre, P. Biagini, R. Po, Linearly π‑conjugated oligothiophenes as simple metal-free sensitizers for dye-sensitized solar cells, J. Mater. Chem. C 3(29) (2015) 7756-7761. https://doi.org/10.1039/C5TC01183C
16. A. Sreekumar, A. R. Nair, R. Chandramani, P. S. Iyer, G. Sadasivan, P. T. Sylajadevi, R. Pillai, A. Nizam, A. Sivan, Thiophene-centered small molecule emitters, in: AIP Conference Proceedings 3171(1), AIP Publishing LLC, 2024, p. 020001. https://doi.org/10.1063/5.0222858
17. R. Isci, T. Ozturk, Thienothiophene-based organic light-emitting diode: synthesis, photophysical properties and application, Beilstein J. Org. Chem. 19(1) (2023) 1849-1857. https://doi.org/10.3762/bjoc.19.137
18. M. Zavelani-Rossi, G. Lanzani, S. De Silvestri, M. Anni, G. Gigli, R. Cingolani, Tunable efficient laser emission from electroluminescent functionalized oligothiophene, in: Summaries of Papers Presented at the Lasers and Electro-Optics CLEO’02, IEEE, 2002, pp. 459-460. https://doi.org/10.1109/CLEO.2002.1034201
19. W. Zhang, F. Ren, Y. Wen, Z. Xu, J. Sun, Z. Yan, L. Ding, X. Hai, Q. Zhang, Enhancing Hole Transport of Quantum-Dot Light-Emitting Diodes by a Cruciform Oligothiophene for Effective p-Type Doping, Macromol. Rapid Commun. 43(15), (2022) 2200187. https://doi.org/10.1002/marc.202200187
20. J. N. Pedroza-Montero, F. A. Delesma, R. I. Delgado-Venegas, P. Calaminici, A. M. Köster, Static and dynamic polarizabilities of oligothiophenes, Theor. Chem. Acc. 135(9) (2016) 230. https://doi.org/10.1007/s00214-016-1984-8
21. T. Kosa, P. Palffy-Muhoray, H. Zhang, T. Ikeda, Large optical torque enhancement by oligothiophene dye in a nematic liquid crystal host, Mol. Cryst. Liq. Cryst. 421(1) (2010) 107-115. https://doi.org/10.1080/15421400490501581
22. S. Muhammad, A. Bibi, S. Bibi, A. G. Al-Sehemi, H. Algarni, F. Sarwar, Exploring the quinoidal oligothiophenes to their robust limit for efficient linear and nonlinear optical response properties, Chem. Pap. 76(7) (2022) 4273-4288. https://doi.org/10.1007/s11696-022-02167-3
23. A. Bibi, S. Muhammad, S. UrRehman, S. Bibi, S. Bashir, K. Ayub, M. Adnan, M. Khalid, Chemically modified quinoidal oligothiophenes for enhanced linear and third-order nonlinear optical properties, ACS omega, 6(38) (2021) 24602-24613. https://doi.org/10.1021/acsomega.1c03218
24. J. Yokota, A. Shishido, Nonlinear optical molecular orientation of oligothiophene-doped liquid crystals, Mol. Cryst. Liq. Cryst. 768(17) (2024) 975-992. https://doi.org/10.1080/15421406.2024.2360220
25. M. I. Berdnyk, A. B. Zakharov, V. V. Ivanov, Application of L1-regularization approach in QSAR problem. Linear regression and artificial neural networks, Methods Objects Chem. Anal. 14 (2019) 79–90. https://doi.org/10.17721/moca.2019.79-90
26. A. B. Zakharov, D. K. Tsarenko, V. V. Ivanov, Topological characteristics of iterated line graphs in the QSAR problem: a multigraph in the description of properties of unsaturated hydrocarbons, Struct Chem. 32 (2021) 1629–1639. https://doi.org/10.1007/s11224-021-01737-7
27. A. B. Zakharov, M. Kyrpa, A. V. Kyrychenko, S. M. Kovalenko, O. N. Kalugin, V. V. Ivanov, L. Adamowicz, Towards the computational design of organic molecules with specified properties, Struct Chem. 36 (2025) 723–738. https://doi.org/10.1007/s11224-024-02441-y
28. M. Kyrpa, A. Zakharov, V. Ivanov, Fast vs Accurate: Evaluating TD-DFTB for Large-Scale Screening of Organic Dyes, Kharkiv Univ Bull Chem Ser 44 (2025) 72-80. https://doi.org/10.26565/2220-637X-2025-44-07
29. A. B. Zakharov, A. V. Dyachenko, V. V. Ivanov, Topological characteristics of iterated line graphs in QSAR problem: octane numbers of saturated hydrocarbons, J. Chemom. 33(9), (2019) e3169. https://doi.org/10.1002/cem.3169
30. B. Hourahine, M. Berdakin, J. A. Bich, F. P. Bonafé, C. Camacho, Q. Cui, M. Y. Deshaye, G. Díaz Mirón, S. Ehlert, M. Elstner, T. Frauenheim, N. Goldman, R. A. González León, T. van der Heide, S. Irle, T. Kowalczyk, T. Kubař, I. S. Lee, C. R. Lien-Medrano, A. Maryewski, T. Melson, S. K. Min, T. Niehaus, A. M. N. Niklasson, A. Pecchia, K. Reuter, C. G. Sánchez, C. Scheurer, M. A. Sentef, P. V. Stishenko, V. Q. Vuong, B. Aradi, Recent developments in DFTB+, a software package for efficient atomistic quantum mechanical simulations, J. Phys. Chem. A. 129(24) (2025) 5373-5390. https://doi.org/10.1021/acs.jpca.5c01146
31. DFTB+ simulation package — DFTB+ https://dftbplus.org/
32. DFTB+ recipes - Read the Docs https://dftbplus-recipes.readthedocs.io/en/latest/
33. F. Neese, The ORCA program system, Wiley Interdiscip. Rev. Comput. Mol. Sci. 2(1) (2012) 73-78. https://doi.org/10.1002/wcms.81
34. F. Neese, Software update: the ORCA program system ‑ version 6.0, Rev. Comput. Mol. Sci. 15 (2025) e70019. https://doi.org/10.1002/wcms.70019
35. C. W. Yap, PaDEL-descriptor: An open source software to calculate molecular descriptors and fingerprints, J. Comput. Chem. 32(7) (2011) 1466-1474. https://doi.org/10.1002/jcc.21707
36. D. A. Papaconstantopoulos, M. J. Mehl, The Slater–Koster tight-binding method: a computationally efficient and accurate approach, J. Phys. Condens. Matter. 15(10) (2023) R413. https://doi.org/10.1088/0953-8984/15/10/201
37. M. Petitjean, Applications of the radius-diameter diagram to the classification of topological and geometrical shapes of chemical compounds, J. Chem. Inf. Comput. Sci. 32(4) (1992) 331-337. https://doi.org/10.1021/ci00008a012
38. M. Abadi M, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Devin, S. Ghemawat, G. Irving, M. Isard, M. Kudlur, J. Levenberg, R. Monga, S. Moore, D. G. Murray, B. Steiner, P. Tucker, V. Vasudevan, P. Warden, M. Wicke, Y. Yu, X. Zheng, Tensorflow: A system for large-scale machine learning, in: 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), pp. 265–283. https://doi.org/10.48550/arXiv.1605.08695
39. C. Mattmann, Machine Learning with TensorFlow, second ed., Manning Publications Co., New York, 2020.
40. M. Barysz, G. Jashari, L. S. Lall, V. K. Srivastava, N. Trinajsti, On the Distance Matrix of Molecules Containing Heteroatoms, in: Chemical applications of Graph Theory and Topology, R. B. King (Ed.), Elsevier Science Publishers, Amsterdam, 1983. http;s://doi.org/10.1016/S0003-2670%2800%2982967-0
41. M. Stone, Cross-validatory choice and assessment of statistical predictions, J. R. Stat. Soc. Series B Stat. 36(2) (1974) 111-133. https://doi.org/10.1111/j.2517-6161.1974.tb00994.x