Background: In this study, our aim was to identify molecular aberrations predictive for response to everolimus, an mTOR inhibitor, regardless of tumor type. Methods: To generate hypotheses about potential markers for sensitivity to mTOR inhibition, drug sensitivity and genomic profiles of 835 cell lines were analyzed. Subsequently, a multicenter study was conducted. Patients with advanced solid tumors lacking standard of care treatment options were included and underwent a pre-treatment tumor biopsy to enable DNA sequencing of 1,977 genes, derive copy number profiles and determine activation status of pS6 and pERK. Treatment benefit was determined according to TTP ratio and RECIST. We tested for associations between treatment benefit and single molecular aberrations, clusters of aberrations and pathway perturbation. Results: Cell line screens indicated several genes, such as PTEN (P = 0.016; Wald test), to be associated with sensitivity to mTOR inhibition. Subsequently 73 patients were included, of which 59 started treatment with everolimus. Response and molecular data were available from 43 patients. PTEN aberrations, i.e. copy number loss or mutation, were associated with treatment benefit (P = 0.046; Fisher's exact test). Conclusion: Loss-of-function aberrations in PTEN potentially represent a tumor type agnostic biomarker for benefit from everolimus and warrants further confirmation in subsequent studies.@en

Patients with BRAF mutated (BRAF-mt) metastatic melanoma benefit significantly from treatment with BRAF inhibitors. Currently, the BRAF status is determined on archival tumor tissue or on fresh tumor tissue from an invasive biopsy. The aim of this study was to evaluate whether radiomics can predict the BRAF status in a non-invasive manner. Patients with melanoma lung metastases, known BRAF status, and a pretreatment computed tomography scan were included. After semi-automatic annotation of the lung lesions (maximum two per patient), 540 radiomics features were extracted. A chest radiologist scored all segmented lung lesions according to the Lung Image Database Consortium (LIDC) criteria. Univariate analysis was performed to assess the predictive value of each feature for BRAF mutation status. A combination of various machine learning methods was used to develop BRAF decision models based on the radiomics features and LIDC criteria. A total of 169 lung lesions from 103 patients (51 BRAF-mt; 52 BRAF wild type) were included. There were no features with a significant discriminative value in the univariate analysis. Models based on radiomics features and LIDC criteria both performed as poorly as guessing. Hence, the BRAF mutation status in melanoma lung metastases cannot be predicted using radiomics features or visually scored LIDC criteria.@en