The biodegradation of therapeutic magnetic-oxide nanoparticles (MONPs) in the human body raises concerns about their lifespan, functionality, and health risks. Interactions between apoferritin proteins and MONPs in the spleen, liver, and inflammatory macrophages significantly accelerate nanoparticle degradation, releasing metal ions taken up by apoferritin. This can alter the protein’s biological structure and properties, potentially causing health hazards. This study examines changes in apoferritin’s shape, electrical surface potential (ESP), and protein-core composition after incubation with cobalt-ferrite (CoFe₂O₄) oxide nanoparticles. Using atomic force microscopy (AFM) and scanning Kelvin probe force microscopy (SKPFM), we observed changes in the topography and ESP distribution in apoferritin nanofilms over time. After 48 h, the characteristic apoferritin hole (∼1.35 nm) vanished, and the protein’s height increased from ∼3.5 to ∼7.5 nm due to hole filling. This resulted in a significant ESP increase on the filled-apoferritin surface, attributed to the formation of a heterogeneous chemical composition and crystal structure (γ-Fe₂O₃, Fe₃O₄, CoO, CoOOH, FeOOH, and Co₃O₄). These changes enhance electrostatic interactions and surface charge between the protein and the AFM tip. This approach aids in predicting and improving the MONP lifespan while reducing their toxicity and preventing apoferritin deformation and dysfunction.

Porous carbons as solid adsorbent materials possess effective porosity characteristics that are the most important factors for gas storage. The chemical activating routes facilitate hydrogen storage by adsorbing on the high surface area and microporous features of porous carbon-based adsorbents. The present research proposed to predict H₂ storage using four nature-inspired algorithms applied in the random forest (RF) model. Various carbon-based adsorbents, chemical activating agents, ratios, micro-structural features, and operational parameters as input variables are applied in the ML model to predict H₂ uptake (wt%). Particle swarm and gray wolf optimizations (PSO and GWO) in the RF model display accuracy in the train and test phases, with an R² of ~0.98 and 0.91, respectively. Sensitivity analysis demonstrated the ranks for temperature, total pore volume, specific surface area, and micropore volume in first to fourth, with relevancy scores of 1 and 0.48. The feasibility of algorithms in training sizes 80 to 60% evaluated that RMSE and MAE achieved 0.6 to 1, and 0.38 to 0.52. This study contributes to the development of sustainable energy sources by providing a predictive model and insights into the design of porous carbon adsorbents for hydrogen storage. The use of nature-inspired algorithms in the model development process is also a novel approach that could be applied to other areas of materials science and engineering.