Abstract
In this study, we show the quantitative structure-property relationship (QSPR) for amphetamine derivatives based on neighborhood degree-based topological indices and NM-polynomials. By coupling such descriptors to both polynomial regression models and Random Forest algorithms, the ability of these two methodologies to predict different physicochemical properties (boiling point, evaporation energy, flash point, molar refractivity, surface tension, polarizability and SA) is analyzed. The modeling scheme reveals that the neighborhood-based indices carry information specific to structural complexity, connectivity and electronic characteristics important for stimulant-type molecules behaviour. cubic regression models are also found to be more capable of representing nonlinear structural relationship than quadratic ones while the efficacy and generalizability are greatly improved by extra Random Forest in particular for properties with strong dependence on molecular branching and electronic distribution. In conclusion, the results here presented confirm that NM-polynomial based descriptors effectively relate molecular topology with experimentally measurable physicochemical behavior, thus suggesting their computational use in predictive property modeling, early drug screening and cheminformatics-driven design.
Similar content being viewed by others
Data availability
The datasets used and/or analysed during the current study available from the corresponding author on reasonable request.
References
Wilson, R. J. Introduction to graph theory. Pearson Education India. (1979)
Balaban, A. T. Applications of graph theory in chemistry. J. Chem. Inf. Comput. Sci.25(3), 334–343 (1985).
Huang, L., Alhulwah, K. H., Hanif, M. F., Siddiqui, M. K. & Ikram, A. S. On QSPR analysis of glaucoma drugs using machine learning with XGBoost and regression models. Comput. Biol. Med.187, 109731 (2025).
Wei, J., Hanif, M. F., Mahmood, H., Siddiqui, M. K. & Hussain, M. QSPR analysis of diverse drugs using linear regression for predicting physical properties. Polycyclic Aromat. Comp.44(7), 4850–4870 (2024).
Qin, H. et al. On QSPR analysis of pulmonary cancer drugs using python-driven topological modeling. Sci. Rep.15(1), 3965 (2025).
Qin, H. et al. A python approach for prediction of physicochemical properties of anti-arrhythmia drugs using topological descriptors. Sci. Rep.15(1), 1742 (2025).
Iqbal, S. et al. Evaluation of antiarrhythmia drug through QSPR modeling and multi criteria decision analysis. Sci. Rep.15, 29216 (2025).
Qin, H. et al. Graph theoretic and machine learning approaches in molecular property prediction of bladder cancer therapeutics. Sci. Rep.15, 28025 (2025).
Faheem, H., Ahmad, S., & Farooq, R. Maximal and minimal Zagreb indices of trees with fixed number of vertices of maximum degree. MATCH Communications in Mathematical and in Computer Chemistry.
Çolakoglu, Ö., Kamran, M. & Bonyah, E. M-polynomial and NM-polynomial of used drugs against Monkeypox. J. Math.2022(1), 9971255 (2022).
Altassan, A., Saleh, A., Alashwali, H., Hamed, M. & Muthana, N. Entire neighborhood topological indices: Theory and applications in predicting physico-chemical properties. Int. J. Anal. Appl.23, 79–79 (2025).
Hasani, M., Ghods, M., Mondal, S., Siddiqui, M. K. & Cheema, I. Z. Modeling QSPR for pyelonephritis drugs: A topological indices approach using MATLAB. J. Supercomput.81(3), 479 (2025).
Pradeepa, A. & Arathi, P. On topological characterizations and computational analysis of benzenoid networks for drug discovery and development. J. Mol. Graph. Modell.136, 108957 (2025).
Das, S. & Kumari, A. Degree-based coindices of molnupiravir and its QSPR analysis with other COVID-19 drugs. Int. J. Appl. Comput. Math.11(3), 1–23 (2025).
Nagesh, H. M. & Kumar, M. M. On the M-polynomial and degree-based topological indices of Dandelion graph. Int. J. Math. Combin.1, 39–49 (2024).
Giannakogeorgou, A. & Roden, M. Role of lifestyle and glucagon like peptide1 receptor agonists for weight loss in obesity, type 2 diabetes and steatotic liver diseases. Aliment. Pharmacol. Therapeut.59, S52–S75 (2024).
Abbas, K., Barnhardt, E. W., Nash, P. L., Streng, M. & Coury, D. L. A review of amphetamine extended release once-daily options for the management of attention-deficit hyperactivity disorder. Expert Rev. Neurother.24(4), 421–432 (2024).
Khan, R., Sadak, S., Kanbes-Dindar, C., Haider, A., & Uslu, B. Electrochemical Investigation of Benzylpiperazine. In Forensic Electrochemistry: The Voltammetry for Sensing and Analysis, 227–242. (American Chemical Society 2024).
Macedo, A. A. et al. Detection of the stimulant clobenzorex using voltammetry and screen-printed electrodes: A simple and fast screening method for application in seized samples and oral fluid of drivers. Microchem. J.207, 111679 (2024).
Gomes, N. C., Cabrices, O. G. & De Martinis, B. S. Innovative disposable pipette extraction for concurrent analysis of fourteen psychoactive substances in drug users sweat. J. Chromatogr. A1730, 465136 (2024).
Borges, G. R. et al. Determination of drugs of abuse in oral fluid using dried oral fluid spot assisted by 24-well plate and LC-MS/MS. Bioanalysis17(9), 595–605 (2025).
Inoue, T. & Suzuki, S. The metabolism of 1-phenyl-2-(N-methyl-N-benzylamino) propane (benzphetamine) and 1-phenyl-2-(N-methyl-N-furfurylamino) propane (furfenorex) in man. Xenobiotica16(7), 691–698 (1986).
Ho, K. M. & Power, B. M. Benefits and risks of furosemide in acute kidney injury. Anaesthesia65(3), 283–293 (2010).
Rendic, S., Slavica, M. & Medic-aric, M. Urinary excretion and metabolism of orally administered mefenorex. Eur. J. Drug Metab. Pharmacokinet.19, 107–117 (1994).
DeRuiter, J., Hayes, L., Valaer, A., Clark, C. R. & Noggle, F. T. Methcathinone and designer analogues: Synthesis, stereochemical analysis, and analytical properties. J. Chromatogr. Sci.32(12), 552–564 (1994).
Challman, T. D. & Lipsky, J. J. Methylphenidate: Its pharmacology and uses. In Mayo clinic proceedings 711–721 (Elsevier, Amsterdam, 2000).
Smith, S. M., Meyer, M. & Trinkley, K. E. Phentermine/topiramate for the treatment of obesity. Ann. Pharmacother.47(3), 340–349 (2013).
Gerlach, M., Youdim, M. B. H. & Riederer, P. Pharmacology of selegiline. Neurology47(6suppl3), 137S-145S (1996).
Dou, K. et al. Switch on amine substrate reactivity towards hexaazaisowurtzitane cage: Insights from a tailored machine learning model. Chem. Eng. J.501, 157677 (2024).
Feng, X. et al. AutoFE-Pointer: Auto-weighted feature extractor based on pointer network for DNA methylation prediction. Int. J. Biol. Macromol.311, 143668 (2025).
Xu, G. et al. Anonymity-enhanced sequential multi-signer ring signature for secure medical data sharing in IoMT. IEEE Trans. Inf. Forens. Sec.20, 5647–5662 (2025).
Wang, Z. et al. Precision strike strategy for liver diseases trilogy with Xiao-Chai-Hu decoction: A meta-analysis with machine learning. Phytomedicine142, 156796 (2025).
Zhou, S., Wang, S., Wu, Q., Azim, R. & Li, W. Predicting potential miRNA-disease associations by combining gradient boosting decision tree with logistic regression. Comput. Biol. Chem.85, 107200 (2020).
Xianfang, T. et al. Indicator regularized non-negative matrix factorization method-based drug repurposing for COVID-19. Front. Immunol.11, 603615 (2021).
Liu, C. et al. An improved anticancer drug-response prediction based on an ensemble method integrating matrix completion and ridge regression. Mol. Therapy Nucl. Acids21, 676–686 (2020).
Yan, Z. et al. Synthesis, bioactivity evaluation and theoretical study of nicotinamide derivatives containing diphenyl ether fragments as potential succinate dehydrogenase inhibitors. J. Mol. Struct.1308, 138331 (2024).
Shi, S. & Liu, W. B2-ViT Net: Broad vision transformer network with broad attention for seizure prediction. IEEE Trans. Neural Syst. Rehabil. Eng.32, 178–188 (2024).
Guo, B., Jiang, X., Zhu, L. & He, X. Exploring the diagnostic potential of core targets of 6PPD and its metabolite 6PPD-Q in cardiovascular diseases: An integrated analysis based on network toxicology, molecular docking, and in vitro validation. J. Appl, Toxicol (2025).
Wang, S., Yang, C. & Chen, L. LSA-DDI: Learning stereochemistry-aware drug interactions via 3D feature fusion and contrastive cross-attention. Int. J. Mol. Sci.26(14), 6799. https://doi.org/10.3390/ijms26146799 (2025).
Wang, S., Zhang, K. & Liu, A. Flat-Lattice-CNN: A model for Chinese medical-named-entity recognition. PLoS ONE20(9), e0331464 (2025).
Acknowledgements
This work was supported and funded by the Deanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University (IMSIU)(grant number IMSIU-DDRSP2601).
Author information
Authors and Affiliations
Contributions
Muhammad Farhan Hanif involved in the Computation, and analysis of the paper and also assent to the final adumbrate of the paper. Atef F. Hashem deals with data analysis, Computation, funding resources, and verification of calculations. Mazhar Hussain supervised the project, Envisioned it, Organized the methodology, coordinated it, found resources, and wrote the starting adumbrate of the paper. Osman Abubakar Fiidow contributed to Elevating the graphs of maple and Matlab calculations. Each author reviews and approves the final report of the work.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Hanif, M.F., Hashem, A.F., Hussain, M. et al. On machine learning based QSPR analysis of amphetamine derivatives using regression models. Sci Rep (2026). https://doi.org/10.1038/s41598-025-34694-w
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-025-34694-w
