RESUMO
Serous borderline tumors (SBT) are epithelial neoplastic lesions of the ovaries that commonly have a good prognosis. In 10-15% of cases, however, SBT will recur as low-grade serous cancer (LGSC), which is deeply invasive and responds poorly to current standard chemotherapy1,2,3. While genetic alterations suggest a common origin, the transition from SBT to LGSC remains poorly understood4. Here, we integrate spatial proteomics5 with spatial transcriptomics to elucidate the evolution from SBT to LGSC and its corresponding metastasis at the molecular level in both the stroma and the tumor. We show that the transition of SBT to LGSC occurs in the epithelial compartment through an intermediary stage with micropapillary features (SBT-MP), which involves a gradual increase in MAPK signaling. A distinct subset of proteins and transcripts was associated with the transition to invasive tumor growth, including the neuronal splicing factor NOVA2, which was limited to expression in LGSC and its corresponding metastasis. An integrative pathway analysis exposed aberrant molecular signaling of tumor cells supported by alterations in angiogenesis and inflammation in the tumor microenvironment. Integration of spatial transcriptomics and proteomics followed by knockdown of the most altered genes or pharmaceutical inhibition of the most relevant targets confirmed their functional significance in regulating key features of invasiveness. Combining cell-type resolved spatial proteomics and transcriptomics allowed us to elucidate the sequence of tumorigenesis from SBT to LGSC. The approach presented here is a blueprint to systematically elucidate mechanisms of tumorigenesis and find novel treatment strategies.
RESUMO
Machine learning and in particular deep learning (DL) are increasingly important in mass spectrometry (MS)-based proteomics. Recent DL models can predict the retention time, ion mobility and fragment intensities of a peptide just from the amino acid sequence with good accuracy. However, DL is a very rapidly developing field with new neural network architectures frequently appearing, which are challenging to incorporate for proteomics researchers. Here we introduce AlphaPeptDeep, a modular Python framework built on the PyTorch DL library that learns and predicts the properties of peptides ( https://github.com/MannLabs/alphapeptdeep ). It features a model shop that enables non-specialists to create models in just a few lines of code. AlphaPeptDeep represents post-translational modifications in a generic manner, even if only the chemical composition is known. Extensive use of transfer learning obviates the need for large data sets to refine models for particular experimental conditions. The AlphaPeptDeep models for predicting retention time, collisional cross sections and fragment intensities are at least on par with existing tools. Additional sequence-based properties can also be predicted by AlphaPeptDeep, as demonstrated with a HLA peptide prediction model to improve HLA peptide identification for data-independent acquisition ( https://github.com/MannLabs/PeptDeep-HLA ).
