A major challenge in radiomics is assembling data from multiple centers. Sharing data between hospitals is restricted by legal and ethical regulations. Distributed learning is a technique, enabling training models on multicenter data without data leaving the hospitals ("privacy-preserving" distributed learning). This study tested feasibility of distributed learning of radiomics data for prediction of two year overall survival and HPV status in head and neck cancer (HNC) patients. Pretreatment CT images were collected from 1174 HNC patients in 6 different cohorts. 981 radiomic features were extracted using Z-Rad software implementation. Hierarchical clustering was performed to preselect features. Classification was done using logistic regression. In the validation dataset, the receiver operating characteristics (ROC) were compared between the models trained in the centralized and distributed manner. No difference in ROC was observed with respect to feature selection. The logistic regression coefficients were identical between the methods (absolute difference <10-7). In comparison of the full workflow (feature selection and classification), no significant difference in ROC was found between centralized and distributed models for both studied endpoints (DeLong p > 0.05). In conclusion, both feature selection and classification are feasible in a distributed manner using radiomics data, which opens new possibility for training more reliable radiomics models.

Fanconi anemia (FA) is a cancer predisposition syndrome characterized by congenital abnormalities, bone marrow failure, and hypersensitivity to aldehydes and crosslinking agents. For FA patients, gene editing holds promise for therapeutic applications aimed at functionally restoring mutated genes in hematopoietic stem cells. However, intrinsic FA DNA repair defects may obstruct gene editing feasibility. Here, we report on the CRISPR/Cas9-mediated correction of a disruptive mutation in Fancf. Our experiments revealed that gene editing could effectively restore Fancf function via error-prone end joining resulting in a 27% increased survival in the presence of mitomycin C. In addition, templated gene correction could be achieved after double strand or single strand break formation. Although templated gene editing efficiencies were low (≤6%), FA corrected embryonic stem cells acquired a strong proliferative advantage over non-corrected cells, even without imposing genotoxic stress. Notably, Cas9 nickase activity resulted in mono-allelic gene editing and avoidance of undesired mutagenesis. In conclusion: DNA repair defects associated with FANCF deficiency do not prohibit CRISPR/Cas9 gene correction. Our data provide a solid basis for the application of pre-clinical models to further explore the potential of gene editing against FA, with the eventual aim to obtain therapeutic strategies against bone marrow failure.

HPV-negative head and neck squamous cell carcinomas (HNSCCs) develop in precancerous changes in the mucosal lining of the upper-aerodigestive tract. These precancerous cells contain cancer-associated genomic changes and cause primary tumors and local relapses. Therapeutic strategies to eradicate these precancerous cells are very limited. Using functional genomic screens, we identified the therapeutic vulnerabilities of premalignant mucosal cells, which are shared with fully malignant HNSCC cells. We screened 319 previously identified tumor-lethal siRNAs on a panel of cancer and precancerous cell lines as well as primary fibroblasts. In total we identified 147 tumor-essential genes including 34 druggable candidates. Of these 34, 13 were also essential in premalignant cells. We investigated the variable molecular basis of the vulnerabilities in tumor and premalignant cell lines and found indications of collateral lethality. Wee1-like kinase (WEE1) was amongst the most promising targets for both tumor and precancerous cells. All four precancerous cell lines were highly sensitive to Wee1 inhibition by Adavosertib (AZD1775), while primary keratinocytes tolerated this inhibitor. Wee1 inhibition caused induction of DNA damage during S-phase followed by mitotic failure in (pre)cancer cells. In conclusion, we uncovered Wee1 inhibition as a promising chemopreventive strategy for precancerous cells, with comparable responses as fully transformed HNSCC cells.