Leveraging Machine Learning and IUPAC names to identify TDP1 inhibitors

Ivanova, Mariya; Russo, Nicola; Mihaylov, Gueorgui; Konstantin, Nikolic

Leveraging Machine Learning and IUPAC names to identify TDP1 inhibitors

Lists

Ivanova, Mariya, Russo, Nicola, Mihaylov, Gueorgui and Konstantin, Nikolic ORCID: https://orcid.org/0000-0002-6551-2977 (2025) Leveraging Machine Learning and IUPAC names to identify TDP1 inhibitors. Computational and Structural Biotechnology. (Submitted)

Preview

PDF (PDF/A)
Leveraging Machine Learning and IUPAC names to identify TDP1 inhibitors_IvanovaM_accessible.pdf - Submitted Version
Available under License Creative Commons Attribution.
Download (1MB) | Preview

Abstract

This paper introduces a series of computational approaches to assist drug developers in the discovery of new inhibitors for human tyrosyl-DNA phosphodiesterase 1 (TDP1), using a PubChem bioassay as a case study. The methodologies are underpinned by a custom dataset, generated by tokenizing the IUPAC names of compounds into over 5,000 distinct functional group fragments, with labels derived from the initial TDP1 inhibition data. First, a RandomForestClassifier (RFC) model was developed to predict whether a compound was a TDP1 inhibitor. Trained on more than 94,000 samples, the model demonstrated a strong performance with an accuracy of 70.9% and an ROC score of 70.8%. Building on this, two subsequent approaches provided deeper insights into the structural characteristics influencing inhibition. By reordering the feature importance list based on the proportion of active cases, the research identified the expected effects of specific functional groups. This was further refined by pinpointing the most and least desirable fragments for TDP1 inhibition. A separate, highly efficient CID_SID ML model was also developed, using only compound and substance identifiers from PubChem. This model outperformed the RFC model, achieving a superior accuracy of 85.2% and a precision of 94.2%, demonstrating the potential for rapid and effective screening using simplified input data. Collectively, these methods offer valuable computational tools for accelerating the drug discovery process.

Item Type:	Article
Keywords:	scikit-learn, PubChem, HTS, bioassay, CID_SID ML model
Subjects:	Computing
Depositing User:	Mariya Ivanova
Date Deposited:	16 Sep 2025 13:49
Last Modified:	16 Sep 2025 14:00
URI:	https://repository.uwl.ac.uk/id/eprint/14068

Downloads

Downloads per month over past year

Actions (login required)

View Item

References

[1] H. Guo, X. Xing, Y. Zhou, W. Jiang, X. Chen, T. Wang, et al. A Survey of Large Language Model for Drug Research and Development. IEEE Access 13 (2025) 51110-51129. https://doi.org/10.1080/14656566.2022.2161366
[2] J. M. Metselaar, T. Lammers Challenges in nanomedicine clinical translation. Drug Deliv. and Transl. Res. 10 (2020) 721–725 https://doi.org/10.1007/s13346-020-00740-5
[3] International Union of Pure and Applied Chemistry. Home page https://iupac.org/
[4] J. Mao, J. Wang, K-H. Cho, K. T. No (2023) iupacGPT: IUPAC-based large-scale molecular pre-trained model for property prediction and molecule generation. ChemRxiv. (2023). https://doi.org/10.26434/chemrxiv-2023-5kjvh
[5] Q. Pei, L. Wu, K. Gao, X. Liang, Y. Fang, J. Zhu, et al. BioT5+: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuning. ArXiv (2024)
https://doi.org/10.48550/arXiv.2402.17810
[6] S. M. Reed. Augmented and Programmatically Optimized LLM Prompts Reduce Chemical. Journal of Chemical Information and Modeling 65 (2025) 4274-4280 https://doi.org/10.1021/acs.jcim.4c02322
[7] J. Handsel, B. Matthews, N.J. Knight, J.C Simon Translating the InChI: adapting neural machine translation to predict IUPAC names from a chemical identifier. J Cheminform 13 (2021) 79. https://doi.org/10.1186/s13321-021-00535-x
[8] J. Carracedo-Cosme, C. Romero-Muñiz, P. Pou, R. Pérez. Molecular Identification from AFM Images Using the IUPAC Nomenclature and Attribute Multimodal Recurrent Neural Networks, ACS Appl. Mater. Interfaces 15 (2023) 22692–22704. https://doi.org/10.1021/acsami.3c01550
[9] National Institutes of Health, PubChem, qHTS for Inhibitors of Human Tyrosyl-DNA Phosphodiesterase 1 (TDP1): qHTS in Cells in Absence of CPT https://pubchem.ncbi.nlm.nih.gov/bioassay/686978 (Accessed 10 February 2025)
[10] H. Zhang, Y. Xiong, D. Su, et al. TDP1-independent pathways in the process and repair of TOP1-induced DNA damage. Nature Communications 13, 4240 (2022). https://doi.org/10.1038/s41467-022-31801-7
[11] A-K. Jakobsen, S. Yuusufi, L. B. Madsen, P. Meldgaard, B. R. Knudsen and M. Stougaard. TDP1 and TOP1 as targets in anticancer treatment of NSCLC: Activity and protein level in normal and tumor tissue from 150 NSCLC patients correlated to clinical data. Lung Cancer 164 (2022) 23-32. https://doi.org/10.1016/j.lungcan.2021.12.010
[12] I. Anticevic, C. Otten, L. Vinkovic, L. Jukic and M. Popovic. Tyrosyl-DNA phosphodiesterase 1 (TDP1) and SPRTN protease repair histone 3 and topoisomerase 1 DNA–protein crosslinks in vivo. Open Biology 13 (2023)13230113. http://doi.org/10.1098/rsob.230113
[13] C. G. Goh, A. S. Bader, T-A. Tran, R. Belotserkovskaya, G. D’Alessandro and S. P. Jackson. TDP1 splice-site mutation causes HAP1 cell hypersensitivity to topoisomerase I inhibition. Nucleic Acids Research (2024) https://doi.org/10.17863/CAM.113417
[14] H. Takashima, C. Boerkoel, J. John et al. Mutation of TDP1, encoding a topoisomerase I–dependent DNA damage repair enzyme, in spinocerebellar ataxia with axonal neuropathy. Nature Genetics 32, (2022) 267–272. https://doi.org/10.1038/ng987
[15] M. Geraud, A. Cristini, S. Salimbeni, N. Bery, G. Capranico, O. Sordet, et al. TDP1 Mutation Causing SCAN1 Neurodegenerative Syndrome Hampers the Repair of Transcriptional DNA Double-Strand Breaks. Cell Reports 43 (2024) 114214. https://doi.org/10.1016/j.celrep.2024.114214
[16] M.A.M. Salih, H. Takashima and C. F. Boerkoel. Spinocerebellar Ataxia with Axonal Neuropathy Type 1. 2007 Oct 22 [Updated 2022 Jun 30]. In: Adam MP, Feldman J, Mirzaa GM, et al., editors. University of Washington, Seattle. Available from: https://www.ncbi.nlm.nih.gov/books/NBK1105/ (Accessed 10 Feruary 2025)
[17] P. Scott, A. A. Kindi, A. A. Fahdi, N. A. Yarubi, Z. Bruwer, S. A. Adawi, R. Nandhagopal, Spinocerebellar ataxia with axonal neuropathy type 1 revisited, Journal of Clinical Neuroscience 67 (2019) 139-144. https://doi.org/10.1016/j.jocn.2019.05.060
[18] National Institutes of Health, PubChem, Aqueous Solubility from MLSMR Stock Solutions. https://pubchem.ncbi.nlm.nih.gov/bioassay/1996 (Accessed 10 February 2025)
[19] I. Mohammed, and S. R. Sagurthi. Current Approaches and Strategies Applied in First-in-class Drug Discovery. ChemMedChem (2024) e202400639. https://doi.org/10.1002/cmdc.202400639
[20] M. L. Ivanova, N. Russo, N. Djaid, and K. Nikolic. Application of Machine Learning for Predicting G9a Inhibitors. Digital Discovery 3 (2024) 2010-2018. https://doi.org/10.1039/D4DD00101J
[21] D. Ru, J. Li, O. Xie, L. Peng, H. Jiang, and R. Qiu, (2022) Explainable artificial intelligence based on feature optimization for age at onset prediction of spinocerebellar ataxia type 3. Frontiers in Neuroinformatics 16 (2022) 978630. https://doi.org/10.3389/fninf.2022.978630
[22] M. L. Ivanova, N. Russo, and K. Nikolic. Leveraging 13C NMR Spectroscopic Data Derived from SMILES to Predict the Functionality of Small Biomolecules by Machine Learning: a Case Study on Human Dopamine D1 Receptor Antagonists. ArXiv, 2025,
https://doi.org/10.48550/arXiv.2501.14044
[23] C. H. Lai, A. P. K. Kwok, and K. C. Wong. Cheminformatic Identification of Tyrosyl-DNA Phosphodiesterase 1 (Tdp1) Inhibitors: A Comparative Study of SMILES-Based Supervised Machine Learning Models. Journal of Personalized Medicine 14 (2024) 981. https://doi.org/10.3390/jpm14090981
[24] M. L. Ivanova, N. Russo, and K. Nikolic. Predicting Novel Pharmacological Activities of Compounds Using PubChem IDs and Machine Learning (CID-SID ML Model). ArXiv, 2025.
https://doi.org/10.48550/arXiv.2501.02154
[25] L. Breiman. Random Forests. Machine Learning 45 (2001) 5–32. https://doi.org/10.1023/A:1010933404324
[26] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel et al. Scikit-learn: Machine Learning in Python. Jornal of Machine Learning Research 12 (2011) 2825-2830. https://scikit-learn.org/stable/about.html (Accessed 10 February 2025)
[27] A. Y-T. Wang, R. J. Murdock, S. K. Kauwe, A. O. Oliynyk, A. Gurlo, T. D. Sparks, et al. Machine Learning for Materials Scientists: An Introductory Guide toward Best Practices. Chemistry of Materials 32 (2020) 4954-4965. https://doi.org/10.1021/acs.chemmater.0c01907
[28] T. Akiba, S. Sano, T. Yanase, T. Ohta and M. Koyama Optuna: A Next-generation Hyperparameter Optimization Framework. ArXiv (2019).
https://doi.org/10.48550/arXiv.1907.1090

Tools

CORE (COnnecting REpositories)

The University of West London

Leveraging Machine Learning and IUPAC names to identify TDP1 inhibitors

Abstract

Downloads

Actions (login required)

Menu