Interpretable Active Learning Identifies Iron-Doped Carbon Dots With High Photothermal Conversion Efficiency for Antitumor Synergistic Therapy

Abstract

Active learning (AL) is a powerful method for accelerating novel materials discovery but faces huge challenges for extracting physical meaning. Herein, we novelly apply an interpretable AL strategy to efficiently optimize the photothermal conversion efficiency (PCE) of carbon dots (CDs) in photothermal therapy (PTT). An equivalent value (SHapley Additive exPlanations equivalent value [SHAP-EV]) is proposed which explicitly quantifies the linear contributions of experimental variables to the PCE, derived from the joint SHAP values. The SHAP-EV, with an R² of 0.960 correlated to feature's joint SHAP, is integrated into the AL utility functions to enhance evaluation efficiency during optimization. Using this approach, we successfully synthesized iron-doped CDs (Fe-CDs) with PCE exceeding 78.7% after only 16 experimental trials over four iterations. This achievement significantly advances the previously low PCE values typically reported for CDs. Furthermore, Fe-CDs demonstrated multienzyme-like activities, which could respond to the tumor microenvironment (TME). In vitro and in vivo experiments demonstrate that Fe-CDs could enhance ferroptosis through synergistic PTT and chemodynamic therapy (CDT), thereby achieving remarkable antitumor efficacy. Our interpretable AL strategy offers new insights for accelerating bio-functional materials development in antitumor treatments.

Keywords

active learning / ferroptosis / nanozyme / photothermal therapy / SHapley Additive exPlanations equivalent value (SHAP-EV)

References

[1] L. Rao, Y. Yuan, X. Shen, G. Yu, and X. Chen, “Designing Nanotheranostics With Machine Learning,” Nature Nanotechnology 19 (2024): 1769-1781.

[2] J. Zhao, S. Sun, H. Wang, and Z. Cao, “Promoting Active Learning With Mixtures of Gaussian Processes,” Knowledge-Based System 188 (2020): 105044.

[3] B. Cao, T. Su, S. Yu, et al., “Active Learning Accelerates the Discovery of High Strength and High Ductility Lead-Free Solder Alloys,” Materials & Design 241 (2024): 112921.

[4] J. Ma, B. Cao, S. Dong, et al., “MLMD: A Programming-Free AI Platform to Predict and Design Materials,” npj Computational Materials 10 (2024): 59.

[5] M. Jiang, X. Hu, C. Xing, et al., “Fast Parameter Optimization for High-Fidelity Crystal Plasticity Simulation Using Active Learning,” Journal of Materials Informatics 4 (2024): 22.

[6] J. Xiong, S.-Q. Shi, and T.-Y. Zhang, “Machine Learning of Phases and Mechanical Properties in Complex Concentrated Alloys,” Journal of Materials Science & Technology 87 (2021): 133-142.

[7] B. Cao, S. Yang, A. Sun, Z. Dong, and T.-Y. Zhang, “Domain Knowledge-Guided Interpretive Machine Learning: Formula Discovery for the Oxidation Behavior of Ferritic-Martensitic Steels in Supercritical Water,” Journal of Materials Informatics 2 (2022): 4.

[8] Z. Feng, Q. Hou, Y. Zheng, et al., “Method of Artificial Intelligence Algorithm to Improve the Automation Level of Rietveld Refinement,” Computational Materials Science 156 (2019): 310-314.

[9] T. Su, B. Cao, S. Hu, M. Li, and T.-Y. Zhang, “CGWGAN: Crystal Generative Framework Based on Wyckoff Generative Adversarial Network,” Journal of Materials Informatics 4 (2024): 20.

[10] Q. Wei, B. Cao, H. Yuan, et al., “Divide and Conquer: Machine Learning Accelerated Design of Lead-Free Solder Alloys with High Strength and High Ductility,” npj Computational Materials 9 (2023): 1.

[11] F. Creutzig and F. Kapmeier, “Engage, Don't Preach: Active Learning Triggers Climate Action,” Energy Research & Social Science 70 (2020): 101779.

[12] M. Kulichenko, B. Nebgen, N. Lubbers, et al., “Data Generation for Machine Learning Interatomic Potentials and Beyond,” Chemical Reviews 124 (2024): 13681-13714.

[13] L. Rokach, Y. Aperstein, and A. Akselrod-Ballin, “Deep Active Learning Framework for Chest-Abdominal CT Scans Segmentation,” Expert Systems With Applications 263 (2025): 125522.

[14] A. M. Martella, R. C. Martella, J. K. Yatcilla, A. Newson, E. N. Shannon, and C. Voorhis, “How Rigorous Is Active Learning Research in STEM Education? An Examination of Key Internal Validity Controls in Intervention Studies,” Educational Psychology Review 35 (2023): 107.

[15] F. Cichos, K. Gustavsson, B. Mehlig, and G. Volpe, “Machine Learning for Active Matter,” Nature Machine Intelligence 2 (2020): 94-103.

[16] M. Reymond, C. F. Hayes, D. Steckelmacher, D. M. Roijers, and A. Nowé, “Actor-Critic Multi-Objective Reinforcement Learning for Non-Linear Utility Functions,” Autonomous Agents and Multi-Agent Systems 37 (2023): 23.

[17] P. Jenkins, A. Farag, J. S. Jenkins, H. X. Yao, S. H. Wang, and Z. H. Li, “Assoc Advancement Artificial,” in 35th AAAI Conference on Artificial Intelligence/33rd Conference on Innovative Applications of Artificial Intelligence/11th Symposium on Educational Advances in Artificial Intelligence, (Electr Network, 2021), 7917-7925.

[18] B. Sayin, E. Krivosheev, J. Yang, A. Passerini, and F. Casati, “A Review and Experimental Analysis of Active Learning Over Crowdsourced Data,” Artificial Intelligence Review 54 (2021): 5283-5305.

[19] D. M. Pardoll, “The Blockade of Immune Checkpoints in Cancer Immunotherapy,” Nature Reviews Cancer 12 (2012): 252-264.

[20] Y. Liu, P. Bhattarai, Z. Dai, and X. Chen, “Photothermal Therapy and Photoacoustic Imaging via Nanotheranostics in Fighting Cancer,” Chemical Society Reviews 48 (2019): 2053-2108.

[21] F. Xue, Y. Wen, P. Wei, et al., “A Smart Drug: A pH-Responsive Photothermal Ablation Agent for Golgi Apparatus Activated Cancer Therapy,” Chemical Communications 53 (2017): 6424-6427.

[22] Z. Fang, S. Zhang, W. Wang, et al., “Aggregation-Induced Emission-Based Phototheranostics to Combat Bacterial Infection at Wound Sites: A Review,” Biomaterials 315 (2024): 122950.

[23] R. Han, Y. Xiao, Q. Yang, et al., “Ag2S Nanoparticle-Mediated Multiple Ablations Reinvigorates the Immune Response for Enhanced Cancer Photo-Immunotherapy,” Biomaterials 264 (2021): 120451.

[24] X. Xu, J. Sun, J. Zhao, et al., “Cell Membrane-Camouflaged Nanoarchitectonics of Photosensitizer Nanoparticles for Enhanced Phototherapy in Surgery,” Journal of Colloid & Interface Science 679 (2025): 726-736.

[25] F. Oudjedi and A. G. Kirk, “Near-Infrared Nanoparticle-Mediated Photothermal Cancer Therapy: A Comprehensive Review of Advances in Monitoring and Controlling Thermal Effects for Effective Cancer Treatment,” Nano Select 6 (2024): e202400107.

[26] B. Geng, H. Qin, F. Zheng, et al., “Carbon Dot-Sensitized MoS 2 Nanosheet Heterojunctions as Highly Efficient NIR Photothermal Agents for Complete Tumor Ablation at an Ultralow Laser Exposure,” Nanoscale 11 (2019): 7209-7220.

[27] B. Geng, D. Yang, D. Pan, et al., “NIR-Responsive Carbon Dots for Efficient Photothermal Cancer Therapy at Low Power Densities,” Carbon 134 (2018): 153-162.

[28] Y. Li, C. Huang, Z. Wang, et al., “Near-Infrared Modulated Photothermal/Nanozymatic Dual-Modal Strategy for Combating Cancer via Molybdenum Selenide Nanourchins,” Cancer Nanotechnology 15 (2024): 56.

[29] Z. C. Wu, W. P. Li, C. H. Luo, C. H. Su, and C. S. Yeh, “Rattle-Type Fe₃O₄ @CuS Developed to Conduct Magnetically Guided Photoinduced Hyperthermia at First and Second NIR Biological Windows,” Advanced Functional Materials 25 (2015): 6527-6537.

[30] J. Zhou, Y. Jiang, S. Hou, et al., “Compact Plasmonic Blackbody for Cancer Theranosis in the Near-Infrared II Window,” ACS Nano 12 (2018): 2643-2651.

[31] H. Wang, P. Li, D. Yu, et al., “Unraveling the Enzymatic Activity of Oxygenated Carbon Nanotubes and Their Application in the Treatment of Bacterial Infections,” Nano Letters 18 (2018): 3344-3351.

[32] Y. Sang, W. Li, H. Liu, et al., “Construction of Nanozyme-Hydrogel for Enhanced Capture and Elimination of Bacteria,” Advanced Functional Materials 29 (2019): 1900518.

[33] A. S. Rasal, T. M. Subrahmanya, S. Kizhepat, et al., “Carbon Quantum Dots: Classification-Structure-Property-Application Relationship for Biomedical and Environment Remediation,” Coordination Chemistry Reviews 533 (2025): 216510.

[34] Y. Liu, B. Xu, M. Lu, et al., “Ultrasmall Fe-doped Carbon Dots Nanozymes for Photoenhanced Antibacterial Therapy and Wound Healing,” Bioactive Materials 12 (2022): 246-256.

[35] M. Lan, S. Zhao, Z. Zhang, et al., “Two-Photon-Excited Near-Infrared Emissive Carbon Dots as Multifunctional Agents for Fluorescence Imaging and Photothermal Therapy,” Nano Research 10 (2017): 3113-3123.

[36] J. Ge, Q. Jia, W. Liu, et al., “Red-Emissive Carbon Dots for Fluorescent, Photoacoustic, and Thermal Theranostics in Living Mice,” Advanced Materials 27 (2015): 4169-4177.

[37] X. F. Ning, Y. Q. Zhu, H. Sun, Y. Yang, and M. X. Liu, “The Latest Applications of Carbon-Nitride-Based Materials for Combination Treatment of Cancer,” ACS Applied Materials & Interfaces 16 (2024): 64410-64423.

[38] R. Sekar, N. Basavegowda, S. Jena, et al., “Recent Developments in Heteroatom/Metal-Doped Carbon Dot-Based Image-Guided Photodynamic Therapy for Cancer,” Pharmaceutics 14 (2022): 1869.

[39] S. Balou, P. Shandilya, and A. Priye, “Carbon Dots for Photothermal Applications,” Frontiers in Chemistry 10 (2022): 1023602.

[40] B. Geng, W. Shen, F. Fang, et al., “Enriched Graphitic N Dopants of Carbon Dots as F Cores Mediate Photothermal Conversion in the NIR-II Window With High Efficiency,” Carbon 162 (2020): 220-233.

[41] J. Zhou, X. Li, W. Chen, R. Cui, and X. Wu, “Investigation on the Photothermal Performance of Carbon Quantum Dots Nanofluid with High-Stability,” Diamond and Related Materials 128 (2022): 109233.

[42] V. Picheny, T. Wagner, and D. Ginsbourger, “A Benchmark of Kriging-Based Infill Criteria for Noisy Optimization,” Structural and Multidisciplinary Optimization 48 (2013): 607-626.

[43] J. M. Hernández-Lobato, M. W. Hoffman, and Z. Ghahramani, “Predictive Entropy Search for Efficient Global Optimization of Black-Box Functions,” Advances in Neural Information Processing Systems 1 (2014): 918-926.

[44] P. Auer, “Using Confidence Bounds for Exploitation-Exploration Trade-Offs,” Journal of Machine Learning Research 3 (2002): 397-422.

[45] S. Y. Lim, W. Shen, and Z. Gao, “Carbon Quantum Dots and Their Applications,” Chemical Society Reviews 44 (2015): 362-381.

[46] K. Hola, Y. Zhang, Y. Wang, E. P. Giannelis, R. Zboril, and A. L. Rogach, “Carbon Dots—Emerging Light Emitters for Bioimaging, Cancer Therapy and Optoelectronics,” Nano Today 9 (2014): 590-603.

[47] X. T. Zheng, A. Ananthanarayanan, K. Q. Luo, and P. Chen, “Glowing Graphene Quantum Dots and Carbon Dots: Properties, Syntheses, and Biological Applications,” Small 11 (2014): 1620-1636.

[48] T. Li, L. Lin, D. Wang, et al., “Injectable Hydrogel Incorporated With Iron-Doped Carbon Dots Exhibiting Peroxidase-like Activity for Antibacterial Therapy and Wound Healing,” Advanced Therapeutics 7 (2024): 2300368.

[49] T. Pan, H. Chen, X. Gao, Z. Wu, Y. Ye, and Y. Shen, “Engineering Efficient Artificial Nanozyme Based on Chitosan Grafted Fe-Doped-Carbon Dots for Bacteria Biofilm Eradication,” Journal of Hazardous Materials 435 (2022): 128996.

[50] M. Xu, Y. Hu, Y. Xiao, et al., “Near-Infrared-Controlled Nanoplatform Exploiting Photothermal Promotion of Peroxidase-Like and OXD-Like Activities for Potent Antibacterial and Anti-Biofilm Therapies,” ACS Applied Materials & Interfaces 12 (2020): 50260-50274.

[51] G. Getachew, C. Korupalli, A. S. Rasal, and J.-Y. Chang, “ROS Generation/Scavenging Modulation of Carbon Dots as Phototherapeutic Candidates and Peroxidase Mimetics to Integrate with Polydopamine Nanoparticles/GOx Towards Cooperative Cancer Therapy,” Composites Part B: Engineering 226 (2021): 109364.

[52] A. Wibrianto, G. Getachew, W. B. Dirersa, et al., “A Multifunctional Nanocatalyst Based on Ultra-Fluorescent Carbon Quantum Dots for Cascade Enzymatic Activity and Stimuli-Responsive Chemotherapy of Cancer,” Carbon 208 (2023): 191-207.

[53] P. Muhammad, S. Hanif, J. Li, et al., “Carbon Dots Supported Single Fe Atom Nanozyme for Drug-Resistant Glioblastoma Therapy by Activating Autophagy-Lysosome Pathway,” Nano Today 45 (2022): 101530.

[54] K. Fan, J. Xi, L. Fan, et al., “In Vivo Guiding Nitrogen-Doped Carbon Nanozyme for Tumor Catalytic Therapy,” Nature Communications 9 (2018): 1440.

[55] W. Zhang, S. Hu, J.-J. Yin, et al., “Prussian Blue Nanoparticles as Multienzyme Mimetics and Reactive Oxygen Species Scavengers,” Journal of the American Chemical Society 138 (2016): 5860-5865.

[56] L. Yao, M.-M. Zhao, Q.-W. Luo, et al., “Carbon Quantum Dots-Based Nanozyme From Coffee Induces Cancer Cell Ferroptosis to Activate Antitumor Immunity,” ACS Nano 16 (2022): 9228-9239.

[57] X. Wang, M. He, Y. Zhao, et al., “Bimetallic PtPd Atomic Clusters as Apoptosis/Ferroptosis Inducers for Antineoplastic Therapy Through Heterogeneous Catalytic Processes,” ACS Nano 18 (2024): 8083-8098.

[58] G. Getachew, C. H. Hsiao, A. Wibrianto, et al., “High Performance Carbon Dots Based Prodrug Platform: Image-Guided Photodynamic and Chemotherapy With on-Demand Drug Release Upon Laser Irradiation,” Journal of Colloid & Interface Science 633 (2023): 396-410.

[59] Z. Wang, X. Wang, X. Dai, et al., “2D Catalytic Nanozyme Enables Cascade Enzyodynamic Effect-Boosted and Ca²⁺ Overload-Induced Synergistic Ferroptosis/Apoptosis in Tumor,” Advanced Materials 36 (2024): 2312316.

[60] B. Geng, J. Hu, Y. Li, et al., “Near-Infrared Phosphorescent Carbon Dots for Sonodynamic Precision Tumor Therapy,” Nature Communications 13 (2022): 5735.

[61] Z. Zhou, Z. Gao, W. Chen, et al., “Nitric Oxide-Mediated Regulation of Mitochondrial Protective Autophagy for Enhanced Chemodynamic Therapy Based on Mesoporous Mo-Doped Cu9S5 Nanozymes,” Acta Biomaterialia 151 (2022): 600-612.

RIGHTS & PERMISSIONS

2025 The Author(s). Aggregate published by SCUT, AIEI, and John Wiley & Sons Australia, Ltd.