An artificial intelligence-assisted PARP-1-targeted PET imaging agent [⁶⁸Ga]Ga-DOTA-FZPF: From bench to clinic

Considering that clinical data for ⁶⁸Ga-labeled poly(ADP-ribose) polymerase (PARP)-targeted probes have not yet been reported and integrated artificial intelligence (AI) workflows for radiotracer development are still lacking, to support radiotracer development and clinical translation, we constructed an AI-assisted multi-stage prioritization workflow and then synthesized two ⁶⁸Ga-labeled PARP-1-targeted probes, validating their performance through in vitro, in vivo, and clinical evaluations. An AI-guided multi-objective workflow (encoder-decoder recurrent neural network (RNN) generation, convolutional neural network (CNN) docking scoring, Synthetic Complexity Learned from a Reaction Corpus (SCScore)-based tractability triage, and deep neural network (DNN)) was used to prioritize a derivatization-ready Fuzuloparib analog (NH₂-FZPF) and to guide chelator installation, yielding DOTA-FZPF and NOTA-FZPF precursors for subsequent ⁶⁸Ga radiolabeling. Both [⁶⁸Ga]Ga-DOTA-FZPF and [⁶⁸Ga]Ga-NOTA-FZPF exhibited high radiochemical purity, stability, and PARP-1-targeted specificity. In tumor models, [⁶⁸Ga]Ga-DOTA-FZPF displayed favorable tumor uptake and rapid background clearance, supporting further evaluation. Exploratory positron emission tomography (PET) assessments of Fuzuloparib target engagement show the specificity and functionality of [⁶⁸Ga]Ga-DOTA-FZPF, supporting in vivo evaluation of PARP inhibitor target engagement and pharmacodynamics. This study recruited 4 cancer patients and performed positron emission tomography/computed tomography (PET/CT) scans using [⁶⁸Ga]Ga-DOTA-FZPF. Biopsy specimens showed that PET/CT-positive lesions corresponded to regions of high PARP-1 expression. This study demonstrates how an AI rational design workflow can support decision-making in radiotracer design while maintaining synthetic feasibility and translational potential. These preliminary findings support the clinical feasibility of [⁶⁸Ga]Ga-DOTA-FZPF and suggest that it is promising for non-invasive assessment of PARP-1 expression and dynamic monitoring of in vivo target occupancy and pharmacodynamics.