Journal Article

Deep Visual Proteomics defines single-cell identity and heterogeneity

Hollandi, Réka, Schweizer, Lisa, Dyring-Andersen, Beatrice, Lundberg, Emma, Horvath, Peter, Bzorek, Michael, Lengyel, Ernst, Brunner, Andreas-David, Bulkescher, Jutta, Coscia, Fabian, Santos, Alberto, Gnann, Christian, Mann, Matthias, Migh, Ede, Lukas, Claudia, Eckert, Mark Adam, Kriston, András, Rahbek-Gjerdrum, Lise Mette, Naimy, Soraya, Mund, Andreas, Kovács, Ferenc

2022

Overview

Despite the availabilty of imaging-based and mass-spectrometry-based methods for spatial proteomics, a key challenge remains connecting images with single-cell-resolution protein abundance measurements. Here, we introduce Deep Visual Proteomics (DVP), which combines artificial-intelligence-driven image analysis of cellular phenotypes with automated single-cell or single-nucleus laser microdissection and ultra-high-sensitivity mass spectrometry. DVP links protein abundance to complex cellular or subcellular phenotypes while preserving spatial context. By individually excising nuclei from cell culture, we classified distinct cell states with proteomic profiles defined by known and uncharacterized proteins. In an archived primary melanoma tissue, DVP identified spatially resolved proteome changes as normal melanocytes transition to fully invasive melanoma, revealing pathways that change in a spatial manner as cancer progresses, such as mRNA splicing dysregulation in metastatic vertical growth that coincides with reduced interferon signaling and antigen presentation. The ability of DVP to retain precise spatial proteomic information in the tissue context has implications for the molecular profiling of clinical samples. Deep Visual Proteomics combines machine learning, automated image analysis and single-cell proteomics.

• Publisher: Nature Publishing Group US,Nature Publishing Group
• Subject: 631/45/475 / 631/553/2706 / 631/67/2329 / 631/80/304 / acinar cell carcinoma / adult / Agriculture / Antigen presentation / Antigens / Automation / Bioinformatics / Biomedical and Life Sciences / Biomedical Engineering/Biotechnology / Biomedicine / Biotechnology / Cell culture / cell heterogeneity / Cell identity / cell nucleus / Cells / Cellular phenotypes / Cellulars / chemistry / Context / controlled study / Dermatology / female / genetics / Heterogeneity / human / human cell / human tissue / Humans / Image analysis / Image processing / Intelligence / Interferon / interferon signaling / Invasiveness / laser capture microdissection / laser microdissection / Laser microdissections / Life Sciences / Link protein / Machine learning / Mass spectrometry / Mass spectroscopy / melanocyte / Melanocytes / Melanoma / messenger RNA / Metastases / middle aged / Molecular biology / molecular fingerprinting / mRNA / Nuclei / Oncology / phenotype / Phenotypes / procedures / protein fingerprinting / Proteins / proteome / Proteomes / Proteomics / RNA splicing / salivary gland carcinoma / Scientific imaging / single cell analysis / Single cell resolution / Single cells / Spectroscopy / Splicing / Tissue / U2OS cell line / Ultra-high-sensitivity / Visual discrimination learning