Multidimensional in silico evaluation of fluorine-18 radiopharmaceuticals: integrating pharmacokinetics, ADMET, and clustering for diagnostic stratification.

Fluorine-18-labeled radiopharmaceuticals are central to PET-based oncology imaging, yet comparative evaluations of their mechanistic behavior and diagnostic potential remain fragmented. In this study, we present a multidimensional in silico framework integrating pharmacokinetic modeling, structural ADMET prediction, and unsupervised clustering to systematically evaluate five widely used F-labeled PET radiopharmaceuticals: [F]FDG, [F]FET, [F]DOPA, [F]FMISO, and [F]FLT. Each radiopharmaceutical was simulated using a harmonized three-compartment model in COPASI to capture uptake dynamics under both normal and pathological conditions. Key pharmacokinetic parameters, including area under the curve, tumor-to-normal tissue ratios, and early-phase uptake slope, were computed and subjected to local sensitivity analysis to assess model robustness. In parallel, in silico ADMET descriptors were extracted via ADMETlab 3.0, providing quantitative insight into lipophilicity, permeability, distribution volume, and metabolic clearance. All features were normalized and integrated into a joint dataset for principal component analysis and hierarchical clustering. The resulting stratification revealed two distinct mechanistic clusters: [F]FDG and [F]FLT were characterized by irreversible trapping and high intracellular retention, whereas [F]FET, [F]DOPA, and [F]FMISO exhibited transporter-mediated uptake with greater sensitivity to permeability and efflux parameters. Diagnostic strengths varied by context, with [F]FET optimal for early-phase imaging and [F]FMISO demonstrating superior tumor selectivity at later timepoints. ADMET features reinforced kinetic signatures, supporting the structure-function rationale underlying radiopharmaceutical performance. This multidimensional in silico evaluation establishes a mechanistically interpretable platform for PET radiopharmaceutical profiling and stratification, advancing preclinical radiopharmaceutical selection and informing precision multiradiopharmaceutical imaging protocols in oncology. However, while our computational approach offers a mechanism-driven platform for radiopharmaceutical stratification, future validation against experimental PET imaging data in both healthy individuals and patients with relevant pathologies is essential to confirm its predictive value and clinical applicability.