Machine Learning Accelerates Discovery of High-Performance Corrole Photosensitizers for Optical Imaging Diagnosis and Photodynamic Therapeutics of Nasopharyngeal Carcinoma
Top Cited Papers
- 30 November 2025
- journal article
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry Letters
- Vol. 16 (49) , 12579-12588
Abstract
This study centers on corrole, an emerging photosensitizer with great application potential, and innovatively develops an intelligent machine learning-based screening strategy. Through integrating molecular descriptor generation, feature engineering, multiple predictive models, and SHapley Additive exPlanations (SHAP)-based feature analysis, we have predicted two key performances of corrole photosensitizers, involving absorption peak wavelength and singlet-triplet intersystem crossing rate (kISC). Among 10 tested models, XGBoost outperforms other models. After introducing descriptors such as electronic structure and excited-state characteristics and conducting dimensionality reduction, its coefficient of determination is up to 0.87 for kISC prediction. SHAP analysis clarifies core design principles such as flat molecular structure, HOMO localization/LUMO delocalization and low surface electrostatic potential. The screened corrole with peripheral pyridyls, central nonmetallic P, and hydroxyls has excellent red light/NIR optical performance. Upon light irradiations, it exhibits a robust capacity for generating reactive oxygen species and enables the complete inactivation of cancer cells in vitro and in vivo. By leveraging fluorescence lifetime imaging, this corrole enables effective discrimination between normal cells and cancer cells. The intelligent screening strategy offers a novel paradigm for the efficient development of high-performance photosensitizers with distinct clinical translation potential.Keywords
Funding Information
- Basic and Applied Basic Research Foundation of Guangdong Province (2020A1515010426, 2022A1515010006, 2024A1515030116)
- National Natural Science Foundation of China (62005322)
This publication has 26 references indexed in Scilit:
- Heterodimeric Photosensitizer as Radical Generators to Promoting Type I Photodynamic Conversion for Hypoxic Tumor TherapyAdvanced Materials, 2025
- Antimicrobial Peptides as Broad-Spectrum Therapeutics: Computational Analysis to Identify Universal Physical-Chemical Features Responsible for Multitarget ActivityThe Journal of Physical Chemistry Letters, 2024
- Efficient Electron Transfer Driven by Excited-State Structural Relaxation in Corrole–Perylenedimiide DyadThe Journal of Physical Chemistry Letters, 2024
- Photophysics of corroles and closely related systems for emergent solar energy, medicinal, and materials science applicationsCoordination Chemistry Reviews, 2023
- Metal-Based Photosensitizers as Inducers of Regulated Cell Death MechanismsChemical Reviews, 2023
- Photodynamic and Photothermal Therapies: Synergy Opportunities for NanomedicineACS Nano, 2023
- Machine‐Learning Classification for the Prediction of Catalytic Activity of Organic Photosensitizers in the Nickel(II)‐Salt‐Induced Synthesis of PhenolsAngewandte Chemie International Edition, 2023
- Hallmarks of anticancer and antimicrobial activities of corrolesDrug Resistance Updates, 2023
- Quantum Chemical Calculations and Machine Learning Predictions Innovate Synthesis for High-Performance Optical Gold NanorodsChemistry of Materials, 2022
- Multiwfn: A multifunctional wavefunction analyzerJournal of Computational Chemistry, 2011