: AI generation of multiplex immunofluorescence staining from histopathology images.

Hematoxylin and eosin (H&E) is a common and inexpensive histopathology assay. Though widely used and information-rich, it cannot directly inform about specific molecular markers, which require additional experiments to assess. To address this gap, we present a deep-learning framework that computationally imputes the expression and localization of dozens of proteins from H&E images.

A replicating LCMV-based vaccine for the treatment of solid tumors.

Harnessing the immune system to eradicate tumors requires identification and targeting of tumor antigens, including tumor-specific neoantigens and tumor-associated self-antigens. Tumor-associated antigens are subject to existing immune tolerance, which must be overcome by immunotherapies. Despite many novel immunotherapies reaching clinical trials, inducing self-antigen-specific immune responses remains challenging.

X-ray reflectivity study of the heat shock protein Hsp70 interaction with an artificial cell membrane model.

Membrane-bound heat shock protein 70 (Hsp70) apart from its intracellular localization was shown to be specifically expressed on the plasma membrane surface of tumor but not normal cells. Although the association of Hsp70 with lipid membranes is well documented the exact mechanisms for chaperone membrane anchoring have not been fully elucidated. Herein, we addressed the question of how Hsp70 interacts with negatively charged phospholipids in artificial lipid compositions employing the X-ray reflectivity (XRR) studies.

S-CIMA: Supervised spatial single-cell image analysis for identifying disease-associated cell-type compositions in tissue.

The spatial organization of various cell types within the tissue microenvironment is a key element for the formation of physiological and pathological processes, including cancer and autoimmune diseases. Here, we present S-CIMA, a weakly supervised convolutional neural network model that enables the detection of disease-specific microenvironment compositions from high-dimensional proteomic imaging data. We demonstrate the utility of this approach by determining cancer outcome- and cellular-signaling-specific spatial cell-state compositions in highly multiplexed fluorescence microscopy data of the tumor microenvironment in colorectal cancer.