Spatial proteomics of human diabetic kidney disease, from health to class III.

AIMS/HYPOTHESIS: Diabetic kidney disease (DKD) is the leading cause of chronic and end-stage kidney disease in the USA and worldwide. Animal models have taught us much about DKD mechanisms, but translation of this knowledge into treatments for human disease has been slowed by the lag in our molecular understanding of human DKD. METHODS: Using our Spatial TissuE Proteomics (STEP) pipeline (comprising curated human kidney tissues, multiplexed immunofluorescence and powerful analysis tools), we imaged and analysed the expression of 21 proteins in 23 tissue sections from individuals with diabetes and healthy kidneys (n=5), compared to those with DKDIIA, IIA-B and IIB (n=2 each) and DKDIII (n=1). RESULTS: These analyses revealed the existence of 11 cellular clusters (kidney compartments/cell types): podocytes, glomerular endothelial cells, proximal tubules, distal nephron, peritubular capillaries, blood vessels (endothelial cells and vascular smooth muscle cells), macrophages, myeloid cells, other CD45+ inflammatory cells, basement membrane and the interstitium. DKD progression was associated with co-localised increases in inflammatory cells and collagen IV deposition, with concomitant loss of native proteins of each nephron segment. Cell-type frequency and neighbourhood analyses highlighted a significant increase in inflammatory cells and their adjacency to tubular and αSMA+ (α-smooth muscle actin-positive) cells in DKD. Finally, DKD progression showed marked regional variability within single tissue sections, as well as inter-individual variability within each DKD class. CONCLUSIONS/INTERPRETATION: Using the STEP pipeline, we found alterations in protein expression, cellular phenotypic composition and microenvironment structure with DKD progression, demonstrating the power of this pipeline to reveal the pathophysiology of human DKD.

Deriving spatial features from in situ proteomics imaging to enhance cancer survival analysis.

MOTIVATION: Spatial proteomics data have been used to map cell states and improve our understanding of tissue organization. More recently, these methods have been extended to study the impact of such organization on disease progression and patient survival. However, to date, the majority of supervised learning methods utilizing these data types did not take full advantage of the spatial information, impacting their performance and utilization. RESULTS: Taking inspiration from ecology and epidemiology, we developed novel spatial feature extraction methods for use with spatial proteomics data. We used these features to learn prediction models for cancer patient survival. As we show, using the spatial features led to consistent improvement over prior methods that used the spatial proteomics data for the same task. In addition, feature importance analysis revealed new insights about the cell interactions that contribute to patient survival. AVAILABILITY AND IMPLEMENTATION: The code for this work can be found at gitlab.com/enable-medicine-public/spatsurv.

7-UP: Generating in silico CODEX from a small set of immunofluorescence markers.

Multiplex immunofluorescence (mIF) assays multiple protein biomarkers on a single tissue section. Recently, high-plex CODEX (co-detection by indexing) systems enable simultaneous imaging of 40+ protein biomarkers, unlocking more detailed molecular phenotyping, leading to richer insights into cellular interactions and disease. However, high-plex data can be slower and more costly to collect, limiting its applications, especially in clinical settings. We propose a machine learning framework, 7-UP, that can computationally generate in silico 40-plex CODEX at single-cell resolution from a standard 7-plex mIF panel by leveraging cellular morphology. We demonstrate the usefulness of the imputed biomarkers in accurately classifying cell types and predicting patient survival outcomes. Furthermore, 7-UP's imputations generalize well across samples from different clinical sites and cancer types. 7-UP opens the possibility of in silico CODEX, making insights from high-plex mIF more widely available.

Graph deep learning for the characterization of tumour microenvironments from spatial protein profiles in tissue specimens.

Multiplexed immunofluorescence imaging allows the multidimensional molecular profiling of cellular environments at subcellular resolution. However, identifying and characterizing disease-relevant microenvironments from these rich datasets is challenging. Here we show that a graph neural network that leverages spatial protein profiles in tissue specimens to model tumour microenvironments as local subgraphs captures distinctive cellular interactions associated with differential clinical outcomes. We applied this spatial cellular-graph strategy to specimens of human head-and-neck and colorectal cancers assayed with 40-plex immunofluorescence imaging to identify spatial motifs associated with cancer recurrence and with patient survival after treatment. The graph deep learning model was substantially more accurate in predicting patient outcomes than deep learning approaches that model spatial data on the basis of the local composition of cell types, and it generated insights into the effect of the spatial compartmentalization of tumour cells and granulocytes on patient prognosis. Local graphs may also aid in the analysis of disease-relevant motifs in histology samples characterized via spatial transcriptomics and other -omics techniques.