Peter Boor

This study compares hypothermic and normothermic machine perfusion in a murine kidney model, finding that NMP causes more severe tubular injury and immune cell mobilization compared to HMP.

This study establishes a mouse model of cyclic uremia without kidney injury, showing it drives cardiovascular disease and immunosenescence independently of traditional risk factors.

This study shows that chronic low-concentration PM2.5 exposure after ischemic injury accelerates CKD through mitochondrial dysfunction and lysosomal stress, with nicotinamide reversing some effects.

This study identifies polyploid cardiomyocytes as disease-specific transcriptional states in the mammalian heart and suggests targeting them for heart failure treatment.

This study identifies age-related rewiring of type I IFN signaling in immune cells linked to increased inflammation and altered antibody responses in COVID-19.

This study develops a murine model of trauma-related acute kidney injury and identifies early renal stress responses and inflammatory changes.

This study investigates the role of PDGFR-{beta} in uremic vascular calcification using ex vivo and in vivo models, showing that PDGFR-{beta} activation promotes calcification and VSMC phenotypic switching.

This study uses spatial proteomics and machine learning to analyze AATD in human liver tissue, revealing peroxisomal upregulation and a terminal hepatocyte state with distinct proteomic signatures.

This study identifies JAK2V617F zygosity-specific vascular changes in MPN and shows IFNα inhibits EndMT, offering a novel antifibrotic mechanism.

PILOT uses optimal transport to analyze single-cell and pathomics data, detecting disease-associated samples and non-linear changes in cell populations and tissue structures.

This study generates a high-resolution spatial multi-omic map of human myocardial infarction by integrating single-cell gene expression, chromatin accessibility, and spatial transcriptomic data to reveal cellular zones of injury, repair, and remodeling.

This paper evaluates adversarial robustness of CNNs and ViTs in computational pathology, finding ViTs are more robust to attacks.

This study benchmarks AI methods for end-to-end computational pathology, showing ResNet and ViT outperform MIL and CLAM in mutation prediction but not in tumor subtyping.

This paper introduces Swarm Learning, a decentralized machine learning approach for disease classification using transcriptomic data, demonstrating its effectiveness in developing classifiers for COVID-19, tuberculosis, and leukemias while preserving privacy.

This paper develops a deep learning method to predict genetic alterations from histological images across multiple cancer types.

The paper identifies response eQTLs that modify genetic regulation during immune activation and shows their enrichment in autoimmune disease GWAS signals.