Library Generation and Screening in Search of Efficient Dyes for Dye-Sensitized Solar Cells: A Machine Learning Assisted Approach

Sufyan Ahmad; Waqas Muqbool

Library Generation and Screening in Search of Efficient Dyes for Dye-Sensitized Solar Cells: A Machine Learning Assisted Approach

Abstract

Dye-sensitized solar cells (DSSCs) have garnered considerable research and industrial attention due to their low material costs, high power conversion efficiencies, and straightforward fabrication processes. However, there is a need for high-throughput screening of efficient dyes that avoids traditional trial-and-error experimental methods in order to enhance the performance of DSSCs. Recently, the scientific community focused on DSSCs has displayed a growing interest in the application of machine learning (ML). This study employs ML techniques for the design and evaluation of dyes intended for DSSCs. The power conversion efficiency (PCE) of DSSCs is predicted through the use of various machine learning models, with over 40 different models being assessed to determine the most effective Light Gradient Boosting (LGBM) regressor model. New dyes are developed based on pre-selected building blocks, and their PCEs are estimated using a pre-trained machine learning model. The resulting chemical space of the dyes is visualized using a t-distributed stochastic neighbor embedding (t-SNE) plot. Additionally, the synthetic accessibility of the designed dyes is evaluated, and a chemical similarity analysis is conducted to understand the properties of the compounds. Furthermore, clustering and heatmap techniques are utilized. Experimental chemists are expected to benefit from the information on synthetic accessibility for the design of dyes suitable for use in DSSCs.

Keywords

Machine learning, Data science, Descriptors, Dye-sensitized solar cells, Synthetic accessibility

References

B. O'Regan and M. Grätzel, “A low-cost, high-efficiency solar cell based on dye-sensitized colloidal TiO2 films,” Nature, vol. 353, pp. 737-740. 1991.
A. Mahmood, “Recent research progress on quasi-solid-state electrolytes for dye-sensitized solar cells,” J. Energy Chem., vol. 24, pp. 686-692, 2015.
M. Freitag and G. Boschloo, “The revival of dye-sensitized solar cells,” Current Opinion in Electrochemistry, vol. 2, pp. 111-119, 2017.
M. Stojanović et al., “The rise of dye-sensitized solar cells: from molecular photovoltaics to emerging solid-state photovoltaic technologies”, Helv. Chim. Acta, vol. 104, p. e2000230, 2021.
D. Zhang et al., “A molecular photosensitizer achieves a Voc of 1.24 V enabling highly efficient and stable dye-sensitized solar cells with copper(II/I)-based electrolyte,” Nat. Commun., vol. 12, p. 1777, 2021.
A. Hagfeldt, G. Boschloo, L. Sun, L. Kloo and H. Pettersson, “Dye-sensitized solar cells,” Chem. Rev., vol. 110, pp. 6595-6663, 2010.
A. Mahmood, “Triphenylamine based dyes for dye sensitized solar cells: A review”, Solar Energy, vol. 123, pp. 127-144, 2016.
B. Zhang et al., “The first application of isoindigo-based polymers in non-fullerene organic solar cells,” Science China Chemistry, vol. 63, pp. 1262-1271, 2020.
B. Zhang, J. Li, A. Tang, Y. Geng, Q. Guo and E. Zhou, “Utilizing benzotriazole-fused DAD-type heptacyclic ring to construct n-type polymer for all-polymer solar cell application,” ACS Applied Energy Materials, vol. 4, pp. 4217-4223, 2021.
A. Mahmood, J. Hu, A. Tang, F. Chen, X. Wang, and E. Zhou, “A novel thiazole based acceptor for fullerene-free organic solar cells,” Dyes Pigm., vol. 149, pp. 470-474, 2018.

W. Sun et al., “Machine learning–assisted molecular design and efficiency prediction for high-performance organic photovoltaic materials,” Sci. Adv., vol. 5, p. eaay4275, 2019.
B. Xiao et al., “Effects of oxygen atoms introduced at different positions of non-fullerene acceptors in the performance of organic solar cells with poly(3-hexylthiophene),” ACS Appl. Mater. Interfaces, vol. 12, pp. 1094-1102, 2020.
B. Xiao et al., “Side chain engineering of quinoxaline-based small molecular nonfullerene acceptors for high-performance poly(3-hexylthiophene)-based organic solar cells,” Science China Chemistry, vol. 63, pp. 254-264, 2020.
A. Mahmood et al., “Effect of thiophene rings on UV/visible spectra and non-linear optical (NLO) properties of triphenylamine based dyes: a quantum chemical perspective,” J. Phys. Org. Chem., vol. 28, pp. 418-422, 2015.
A. Mahmood, “Photovoltaic and charge transport behavior of diketopyrrolopyrrole based compounds with A–D–A–D–A skeleton,” J. Cluster Sci., vol. 30, pp. 1123-1130, 2019.
M. Ishfaq, M. Aamir, F. Ahmad, A. M. Mebed and S. Elshahat, “Machine learning-assisted prediction of the biological activity of aromatase inhibitors and data mining to explore similar compounds,” ACS Omega, vol. 7, pp. 48139-48149, 2022.
J.A. Bhutto et al., “Virtual screening and library enumeration of new hydroxycinnamates based antioxidant compounds: A complete framework,” J. Saudi Chem. Soc., vol. 27, p. 101670, 2023.
M. Ishfaq, Z. Rahman, M. Aamir, I. Ali, Y. Guan and Z. Hu, “Insight into potent TLR2 inhibitors for the treatment of disease caused by Mycoplasma pneumoniae based on machine learning approaches,” Mol. Divers., vol. 27, pp. 371-387, 2023.
Z. Zhu et al., “Insight into TLR4 receptor inhibitory activity via QSAR for the treatment of Mycoplasma pneumonia disease,” RSC Adv., vol. 13, pp. 2057-2069, 2023.
F. Ahmad, A. Mahmood and T. Muhmood, “Machine learning-integrated omics for the risk and safety assessment of nanomaterials,” Biomater. Sci., vol. 9, pp. 1598-1608, 2021.
F. Häse, L. M. Roch, P. Friederich and A. Aspuru-Guzik, “Designing and understanding light-harvesting devices with machine learning,” Nat. Commun., vol. 11, p. 4587, 2020.
A. Mahmood and J.-L. Wang, “A time and resource efficient machine learning assisted design of non-fullerene small molecule acceptors for P3HT-based organic solar cells and green solvent selection,” J. Mater. Chem. A, vol. 9, pp. 15684-15695, 2021.
A. Mahmood, A. Irfan and J.-L. Wang, “Developing efficient small molecule acceptors with sp2-Hybridized nitrogen at different positions by density functional theory calculations, molecular dynamics simulations and machine learning,” Chem. Eur. J., vol. 28, p. e202103712, 2022.
M. R. S. A. Janjua, A. Irfan, M. Hussien, M. Ali, M. Saqib and M. Sulaman, “Machine-learning analysis of small-molecule donors for fullerene based organic solar cells,” Energy Technol., vol. 10, p. 2200019, 2022.
A. Mahmood and J.-L. Wang, “Machine learning for high performance organic solar cells: current scenario and future prospects,” Energy Environ. Sci., vol. 14, pp. 90-105, 2021.
L. Zhang, M. He and S. Shao, “Machine learning for halide perovskite materials,” Nano Energy, vol. 78, p. 105380, 2020.
BlueDesc, in, University of Tübingen.
G. Landrum, RDKit: Open-source cheminformatics. http://www.rdkit.org
M. Ishfaq, S. Z. A. Shah, I. Ahmad and Z. Rahman, “Multinomial classification of NLRP3 inhibitory compounds based on large scale machine learning approaches,” Mol. Divers., 2023.
Z. Hu, Y. Guan, W. Hu, Z. Xu and M. Ishfaq, “An overview of pharmacological activities of baicalin and its aglycone baicalein: New insights into molecular mechanisms and signaling pathways,” Iran. J. Basic Med. Sci., vol. 25, pp. 14-26, 2022.
J. Kern, S. Venkatram, M. Banerjee, B. Brettmann and R. Ramprasad, “Solvent selection for polymers enabled by generalized chemical fingerprinting and machine learning,” Phys. Chem. Chem. Phys., vol. 24, pp. 26547-26555, 2022.
S.R. Pandala, Lazy Predict, in, 2021.
T. Mubashir et al., “Statistical analysis and visualization of data of non-fullerene small molecule acceptors from Harvard organic photovoltaic database. Structural similarity analysis with famous non-fullerene small molecule acceptors to search new building blocks,” J. Photochem. Photobiol. A, vol. 437, p. 114501, 2023.
M. Ishfaq, Z. Wu, J. Wang, R. Li, C. Chen and J. Li, “Baicalin alleviates Mycoplasma gallisepticum-induced oxidative stress and inflammation via modulating NLRP3 inflammasome-autophagy pathway,” Int. Immunopharmacol., vol. 101, p. 108250, 2021.
T. Mubashir et al., “Designing of symmetric and asymmetric small molecule acceptors for organic solar cells: A farmwork based on Machine learning, virtual screening and structural analysis,” J. Photochem. Photobiol. A, vol. 444, p. 114977, 2023.
J. Degen, C. Wegscheid-Gerlach, A. Zaliani and M. Rarey, “On the art of compiling and using 'drug-like' chemical fragment spaces,” ChemMedChem, vol. 3, pp. 1503-1507, 2008.
S. Hussain, S. Ali, S. Shahzadi and M. Shahid, “Heterobimetallic complexes containing Sn(IV) and Pd(II) with 4-(2-Hydroxyethyl)piperazine-1-carbodithioic acid: Synthesis, characterization and biological activities,” Cogent Chemistry, vol. 1, p. 1029038, 2015.
S. Hussain, S. Ali, S. Shahzadi, M.N. Tahir and M. Shahid, “Synthesis, characterization, biological activities, crystal structure and DNA binding of organotin(IV) 5-chlorosalicylates,” J. Coord. Chem., vol. 68, pp. 2369-2387, 2015.
M. I. Abdullah, M. R. S. A. Janjua, M. F. Nazar and A. Mahmood, “Quantum chemical designing of efficient TC4-based sensitizers by modification of auxiliary donor and π-spacer,” Bull. Chem. Soc. Jpn., vol. 86, pp. 1272-1281, 2013.
P. Ertl and A. Schuffenhauer, “Estimation of synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions,” J. Cheminformatics, vol. 1, no. 8, 2009.
A. Mahmood, M. Saqib, M. Ali, M.I. Abdullah and B. Khalid, “Theoretical investigation for the designing of novel antioxidants,” Can. J. Chem., vol. 91, pp. 126-130, 2013.
M.U. Khan et al., “First theoretical framework of Z-shaped acceptor materials with fused-chrysene core for high performance organic solar cells,” Spectrochim. Acta - A: Mol. Biomol. Spectrosc., vol. 245, p. 118938, 2021.
A. Mahmood, Y. Sandali and J.-L. Wang, “Easy and fast prediction of green solvents for small molecule donor-based organic solar cells through machine learning,” Phys. Chem. Chem. Phys., vol. 25, pp. 10417-10426, 2023.
M. R. S. A. Janjua, “Impact of symmetry breaking on the performance of non-fullerene acceptors (NFAs) for photo and thermally stable organic solar cells (OSCs): A DFT-based interrogation and investigation,” J. Photochem. Photobiol. A, vol. 444, p. 115003, 2023.
A. Mahmood, A. Irfan and J.-L. Wang, “Machine Learning for Organic Photovoltaic Polymers: A Minireview,” Chin. J. Polym. Sci., vol. 40, pp. 870-876, 2022.
A. Mahmood, A. Irfan and J.-L. Wang, “Molecular level understanding of the chalcogen atom effect on chalcogen-based polymers through electrostatic potential, non-covalent interactions, excited state behaviour, and radial distribution function,” Polym. Chem., vol. 13, pp. 5993-6001, 2022.

Details

Primary Language

English

Subjects

Computational Material Sciences, Organic Semiconductors

Journal Section

Research Article

Authors

Sufyan Ahmad
0009-0003-6271-8288
Pakistan

Waqas Muqbool ^*
0009-0005-9522-641X
Pakistan

Early Pub Date

December 31, 2025

Publication Date

December 31, 2025

Submission Date

May 24, 2025

Acceptance Date

October 2, 2025

Published in Issue

Year 2025 Volume: 1 Number: 1

IZ

https://izlik.org/JA39ZT86SW

APA

Ahmad, S., & Muqbool, W. (2025). Library Generation and Screening in Search of Efficient Dyes for Dye-Sensitized Solar Cells: A Machine Learning Assisted Approach. Universal Materials and Physics, 1(1), 23-38. https://izlik.org/JA39ZT86SW

AMA

1.Ahmad S, Muqbool W. Library Generation and Screening in Search of Efficient Dyes for Dye-Sensitized Solar Cells: A Machine Learning Assisted Approach. Univ. Mater. Phys. 2025;1(1):23-38. https://izlik.org/JA39ZT86SW

Chicago

Ahmad, Sufyan, and Waqas Muqbool. 2025. “Library Generation and Screening in Search of Efficient Dyes for Dye-Sensitized Solar Cells: A Machine Learning Assisted Approach”. Universal Materials and Physics 1 (1): 23-38. https://izlik.org/JA39ZT86SW.

EndNote

Ahmad S, Muqbool W (December 1, 2025) Library Generation and Screening in Search of Efficient Dyes for Dye-Sensitized Solar Cells: A Machine Learning Assisted Approach. Universal Materials and Physics 1 1 23–38.

IEEE

[1]S. Ahmad and W. Muqbool, “Library Generation and Screening in Search of Efficient Dyes for Dye-Sensitized Solar Cells: A Machine Learning Assisted Approach”, Univ. Mater. Phys., vol. 1, no. 1, pp. 23–38, Dec. 2025, [Online]. Available: https://izlik.org/JA39ZT86SW

ISNAD

Ahmad, Sufyan - Muqbool, Waqas. “Library Generation and Screening in Search of Efficient Dyes for Dye-Sensitized Solar Cells: A Machine Learning Assisted Approach”. Universal Materials and Physics 1/1 (December 1, 2025): 23-38. https://izlik.org/JA39ZT86SW.

JAMA

1.Ahmad S, Muqbool W. Library Generation and Screening in Search of Efficient Dyes for Dye-Sensitized Solar Cells: A Machine Learning Assisted Approach. Univ. Mater. Phys. 2025;1:23–38.

MLA

Ahmad, Sufyan, and Waqas Muqbool. “Library Generation and Screening in Search of Efficient Dyes for Dye-Sensitized Solar Cells: A Machine Learning Assisted Approach”. Universal Materials and Physics, vol. 1, no. 1, Dec. 2025, pp. 23-38, https://izlik.org/JA39ZT86SW.

Vancouver

1.Sufyan Ahmad, Waqas Muqbool. Library Generation and Screening in Search of Efficient Dyes for Dye-Sensitized Solar Cells: A Machine Learning Assisted Approach. Univ. Mater. Phys. [Internet]. 2025 Dec. 1;1(1):23-38. Available from: https://izlik.org/JA39ZT86SW