Histopathology-based protein multiplex generation using deep learning
Sonali Andani, Boqi Chen, Joanna Ficek-Pascual, Simon Heinke, Ruben Casanova, Bernard Friedrich Hild, Bettina Sobottka, Bernd Bodenmiller, Rudolf Aebersold, Melike Ak, Faisal Alquaddoomi, Silvana I. Albert, Jonas Albinus, Ilaria Alborelli, Sonali Andani, Per-Olof Attinger, Marina Bacac, Daniel Baumhoer, Beatrice Beck‐Schimmer, Niko Beerenwinkel, Christian Beisel, Lara Bernasconi, Anne Bertolini, Bernd Bodenmiller, Ximena Bonilla, Lars Bosshard, Byron Calgua, Ruben Casanova, Stéphane Chevrier, Natalia Chicherova, Ricardo Coelho, Maya D’Costa, Esther Danenberg, Natalie R. Davidson, Monica-Andreea Baciu-Drăgan, Reinhard Dummer, Stefanie Engler, Martin Erkens, Katja Eschbach, Cinzia Esposito, André Fedier, Pedro Ferreira, Joanna Ficek-Pascual, Anja Frei, Bruno S. Frey, Sandra Goetze, Linda Grob, Gabriele Gut, Detlef Günther, Pirmin Haeuptle, Viola Heinzelmann‐Schwarz, Sylvia Herter, René Holtackers, Tamara Huesser, Alexander Immer, Anja Irmisch, Francis Jacob, Andrea Jacobs, Tim M. Jaeger, Katharina Jahn, Alva Rani James, Philip Jermann, André Kahles, Abdullah Kahraman, Viktor H. Koelzer, Werner Kuebler, Jack Kuipers, Christian P. Kunze, Christian Kurzeder, Kjong-Van Lehmann, Mitchell P. Levesque, Ulrike Lischetti, Flavio C. Lombardo, Sebastian Lugert, Gerd Maass, Markus G. Manz, Philipp Markolin, Martin Mehnert, Julien Mena, Julian M. Metzler, Nicola Miglino, Emanuela S. Milani, H. Moch, Simone Muenst, Riccardo Murri, Charlotte K.Y. Ng, Stefan Nicolet, Marta Nowak, Mónica Núñez López, Patrick G. A. Pedrioli, Lucas Pelkmans, Salvatore Piscuoglio, Michael Prummer, Laurie Prélot, Natalie Rimmer, Mathilde Ritter, Christian Rommel, Mara L. Rosano-González, Gunnar Rätsch, Natascha Santacroce
Abstract
Multiplexed protein imaging offers valuable insights into interactions between tumours and their surrounding tumour microenvironment, but its widespread use is limited by cost, time and tissue availability. Here we present HistoPlexer, a deep learning framework that generates spatially resolved protein multiplexes directly from standard haematoxylin and eosin (H&E) histopathology images. HistoPlexer jointly predicts multiple tumour and immune markers using a conditional generative adversarial architecture with custom loss functions designed to ensure pixel- and embedding-level similarity while mitigating slice-to-slice variations. A comprehensive evaluation of metastatic melanoma samples demonstrates that HistoPlexer-generated protein maps closely resemble real maps, as validated by expert assessment. They preserve crucial biological relationships by capturing spatial co-localization patterns among proteins. The spatial distribution of immune infiltration from HistoPlexer-generated protein multiplex enables stratification of tumours into immune subtypes. In an independent cohort, integration of HistoPlexer-derived features into predictive models enhances performance in survival prediction and immune subtype classification compared to models using H&E features alone. To assess broader applicability, we benchmarked HistoPlexer on publicly available pixel-aligned datasets from different cancer types. In all settings, HistoPlexer consistently outperformed baseline methods, demonstrating robustness across diverse tissue types and imaging conditions. By enabling whole-slide protein multiplex generation from routine H&E images, HistoPlexer offers a cost- and time-efficient approach to tumour microenvironment characterization with strong potential to advance precision oncology.