Accumulating evidence suggests that inherited melanoma is not rare and approx. one in seven individuals with melanoma has clinically relevant hereditable cancer-predisposing and/or -susceptibility variant(s). Concerning its germline genetic background, genetic screening aims to identify either variants of predisposing genes with high penetrance or variants of susceptibility genes with medium or low penetrance. However, less attention is paid to genetic testing of germline variants of genes influencing patients’ survival outcomes or enhancing the design of new therapies. We aimed to investigate whether the germline genetic background of a Hungarian melanoma cohort (n = 17) contains any pathogenic or likely pathogenic variants of the BRCA2, POLE, WRN, FANCI, PALB2, and RAD54B genes and if the presence of these variants correlate with the clinical findings of the patients, including the advanced stage of melanoma, poor prognosis, and poor survival. We identified three novel variants in the FANCI gene and one novel variant in the RAD54B gene. We detected rapid disease progression, unfavorable outcome, and therapeutic resistance in the patient carrying the likely pathogenic FANCI variant. Our study highlights the importance of screening germline variants of genes influencing melanoma progression, therapy resistance, and survival of patients.

Summary: Precise spatiotemporal protein organization is critical for fundamental biological processes including cell division ^1,2 . Indeed, aberrant mitosis and mitotic factors are involved in diverse diseases, including various cancers ^3,4 , Alzheimer’s disease ⁵ , and rare diseases ⁶ . During mitosis, complex spatial rearrangements and regulation ensure the accurate separation of replicated sister chromatids to produce genetically identical daughter cells ^7–9 . Previous studies employed high-throughput methodologies to follow specific proteins during mitosis ^10–15 . Still a temporally refined systems-level approach capable of monitoring morphological and proteomic changes throughout mitosis has been lacking. Here, we achieved unprecedented resolution by phenotypically decomposing mitosis into 40 subsections of a regression plane for proteomic analysis using deep learning and regression techniques. Our deep visual proteomics (DVP) workflow ¹⁶ , revealed rapid, dynamic proteomic changes throughout mitosis. We quantified 4,350 proteins with high confidence, demonstrating that 147 show significant dynamic abundance changes during mitotic progression. Clustering revealed coordinated patterns of protein regulation, while network analysis uncovered tight regulation of core cell cycle proteins and a link between cell cycle and cancer-linked mutations. Immunofluorescence validated abundance changes and linked previously uncharacterised proteins, like C19orf53, to mitosis. To facilitate data navigation, we developed Mito-Omix, a user-friendly online platform that integrates intricate morphological and molecular data. Our morphological and proteomic dataset spans mitosis at high resolution, providing a rich resource for understanding healthy and aberrant cell division.

Recently we have concluded that image-based features derived from the microenvironment have an enormous impact on successfully determining the class of an object ¹ . Here we demonstrate that deep learning-based phenotypic analysis of cells with a properly chosen microenvironment-size provides results comparable to our earlier neighbourhood-based methods that utilise hand-crafted image features. We hypothesised that treating cells with equal weight, regardless of their position within the cellular microenvironment, is suboptimal, and direct neighbours have a larger impact on the phenotype of the cell-of-interest than cells in its larger proximity. Hence we present a novel approach that (1) considers the fully featured view of the cell-of-interest, (2) includes the neighbourhood and (3) gives lesser weight to cells that are far from the cell. To achieve this, we present a transformation similar to those characteristic for fisheye cameras. Such a transformation satisfies all the above defined criteria, with a fast rate of transform for any images. Using the proposed transformation with proper settings we could significantly increase the accuracy of single-cell phenotyping, both in case of cell culture and tissue-based microscopy images. The range of potential applications of the proposed method goes beyond microscopy, as we present improved results on the iWildCam 2020 dataset containing images of wild animals.