Machine Learning and Structural Analysis for Generation‐Wise Selection of Perylene Diimide Dendrimers Based on Topological Compatibility With Drug Molecules
- 1Department of Basic Sciences & Humanities College of Electrical & Mechanical Engineering National University of Sciences & Technology Islamabad Pakistan
- 2Department of Mathematics, Department of Computer Science, Department of Software Engineering National University of Modern Languages Rawalpindi, Islamabad Pakistan
- 3School of Computer Science Northumbria University Newcastle upon Tyne UK
Abstract
Machine learning is increasingly used to explore structure–property relationships in dendrimer‐drug systems; however, its integration with topology‐based structural compatibility analysis remains limited. This study presents a learning‐driven framework to evaluate the topology‐based structural compatibility of perylene diimide core dendrimers with antiviral, antioxidant, and imaging agents. Within a quantitative structure–property relationship framework, linear regression, Gaussian process regression (GPR), and artificial neural networks are employed to identify dominant graph‐theoretic topological indices and to capture linear and nonlinear structure–property relationships. These insights are combined with a structure‐based compatibility analysis that ranks dendrimer generations without altering drug identity or ordering. Generation‐wise compatibility is computed using standardized Euclidean distance after global normalization, and ranking stability is assessed through monotonic and magnitude analysis. Results show class‐dependent descriptor relevance, with GPR achieving test‐set R ² values above 0.94 for molecular weight, exact mass, monoisotopic mass, and heavy atom count. The generation‐wise compatibility analysis further reveals distinct topology‐based structural compatibility patterns across the investigated drug classes, highlighting the value of integrating machine learning with graph‐theoretic analysis for rational nanocarrier design and the computational assessment of potential encapsulation suitability.
Related
- Stoichiometry-Dependent Structural Defects in Low-Generation PAMAM Dendrimers
- Precision chemical engineering of dendrimers for nucleic acid delivery
- Structural Analysis of HRF-4467, a Potent Second-Generation HIV-1 Maturation Inhibitor
- DEL-Flow: AI-Driven Structural Generation and Activity Validation of MDM2-Targeting Macrocyclic Peptides
- Modulating the polarization-resolved second harmonic generation response of a Sulfamic acid multicomponent crystal via amino acid coformer selection
BibTeX
@article{bibi2026machine,
title = {{Machine Learning and Structural Analysis for Generation‐Wise Selection of Perylene Diimide Dendrimers Based on Topological Compatibility With Drug Molecules}},
author = {Zainab Bibi and Jabbar Ali and Sana Irshad and Muhammad Saad Ghafar and Yasir Ali and Yilun Shang},
journal = {ChemistryOpen},
year = {2026},
month = oct,
doi = {10.1002/open.70324},
url = {https://chemistry-europe.onlinelibrary.wiley.com/doi/10.1002/open.70324},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Machine Learning and Structural Analysis for Generation‐Wise Selection of Perylene Diimide Dendrimers Based on Topological Compatibility With Drug Molecules
AU - Zainab Bibi
AU - Jabbar Ali
AU - Sana Irshad
AU - Muhammad Saad Ghafar
AU - Yasir Ali
AU - Yilun Shang
PY - 2026
DA - 2026/10/29
JO - ChemistryOpen
DO - 10.1002/open.70324
UR - https://chemistry-europe.onlinelibrary.wiley.com/doi/10.1002/open.70324
AB - Machine learning is increasingly used to explore structure–property relationships in dendrimer‐drug systems; however, its integration with topology‐based structural compatibility analysis remains limited. This study presents a learning‐driven framework to evaluate the topology‐based structural compatibility of perylene diimide core dendrimers with antiviral, antioxidant, and imaging agents. Within a quantitative structure–property relationship framework, linear regression, Gaussian process regression (GPR), and artificial neural networks are employed to identify dominant graph‐theoretic topological indices and to capture linear and nonlinear structure–property relationships. These insights are combined with a structure‐based compatibility analysis that ranks dendrimer generations without altering drug identity or ordering. Generation‐wise compatibility is computed using standardized Euclidean distance after global normalization, and ranking stability is assessed through monotonic and magnitude analysis. Results show class‐dependent descriptor relevance, with GPR achieving test‐set R ² values above 0.94 for molecular weight, exact mass, monoisotopic mass, and heavy atom count. The generation‐wise compatibility analysis further reveals distinct topology‐based structural compatibility patterns across the investigated drug classes, highlighting the value of integrating machine learning with graph‐theoretic analysis for rational nanocarrier design and the computational assessment of potential encapsulation suitability.
SN - 2191-1363
SN - 2191-1363
ER -