Brain tumoroids: Treatment prediction and drug development for brain tumors with fast, reproducible, and easy-to-use personalized models

Abstract Background The generation of patient avatars is critically needed in neuro-oncology for treatment prediction and preclinical therapeutic development. Our objective was to develop a fast, reproducible, low-cost, and easy-to-use method of tumoroids generation and analysis, efficient for all types of brain tumors, primary and metastatic. Methods Tumoroids were generated from 89 patients: 81 primary tumors including 77 gliomas, and 8 brain metastases. Tumoroids morphology and cellular and molecular characteristics were compared with the ones of the parental tumor by using histology, methylome profiling, pTERT mutations, and multiplexed spatial immunofluorescences. Their cellular stability over time was validated by flow cytometry. Therapeutic sensitivity was evaluated and predictive factors of tumoroid generation were analyzed. Results All the tumoroids analyzed had similar histological (n = 21) and molecular features (n = 7) to the parental tumor. The median generation time was 5 days. The success rate was 65 %: it was higher for high-grade gliomas and brain metastases versus IDH mutated low-grade gliomas. For high-grade gliomas, neither other clinical, neuro-imaging, histological nor molecular factors were predictive of tumoroid generation success. The cellular organization inside tumoroids analyzed by MACSima revealed territories dedicated to specific cell subtypes. Finally, we showed the correlation between tumoroid and patient treatment responses to radio-chemotherapy and their ability to respond to immunotherapy thanks to a dedicated and reproducible 3D analysis workflow. Conclusions Patient-derived tumoroid model that we developed offers a robust, user-friendly, low-cost, and reproducible preclinical model valuable for therapeutic development of all types of primary or metastatic brain tumors, allowing their integration into forthcoming early-phase clinical trials.