Biology subjects

Oldenburg, L.

Publications and source records attributed to Oldenburg, L..

3 recordsLinked to original sources

bioRxiv2025

AI-powered Deep Visual Proteomics reveals critical molecular transitions in pancreatic cancer precursors

Pancreatic ductal adenocarcinoma (PDAC) evolves through non-invasive precursor lesions, yet its earliest molecular events remain unclear. We established the first spatially resolved proteomic atlas of these lesions using Deep Visual Proteomics (DVP). AI-driven computational pathology classified normal ducts, acinar-ductal metaplasia (ADM), and pancreatic intraepithelial neoplasia (PanIN) from cancer-free organ donors (incidental, "iPanINs") and PDAC patients (cancer-associated, "cPanINs"). Laser microdissection of 96 discrete regions containing as few as 100 phenotypically matched cells and ultrasensitive mass spectrometry quantified a total of 8,512 proteins from formalin-fixed tissues. Distinct molecular signatures stratifying cPanINs from iPanINs, and remarkably, many cancer-associated proteins already marked histologically normal epithelium. Four core programs - stress adaptation, immune engagement, metabolic reprogramming, mitochondrial dysfunction - emerged early and intensified during progression. By integrating DVP with AI-guided tissue annotation, we demonstrate that molecular reprogramming precedes histological transformation, creating opportunities for earlier detection and interception of a near-uniformly lethal cancer. SignificanceOur spatially-resolved proteomics atlas uncovers distinct molecular signatures in pancreatic cancer adjacent precursor lesions, clearly diverging from those in incidental, cancer-free pancreatic lesions. Our deep proteomics dataset offers a valuable resource for identifying novel biomarkers and therapeutic targets, informed by the earliest cancer-associated molecular events in archival pancreatic tissues.

cancer biology↗

bioRxiv2024

AI-driven Discovery of Morphomolecular Signatures in Toxicology

Early identification of drug toxicity is essential yet challenging in drug development. At the preclinical stage, toxicity is assessed with histopathological examination of tissue sections from animal models to detect morphological lesions. To complement this analysis, toxicogenomics is increasingly employed to understand the mechanism of action of the compound and ultimately identify lesion-specific safety biomarkers for which in vitro assays can be designed. However, existing works that aim to identify morphological correlates of expression changes rely on qualitative or semi-quantitative morphological characterization and remain limited in scale or morphological diversity. Artificial intelligence (AI) offers a promising approach for quantitatively modeling this relationship at an unprecedented scale. Here, we introduce GEESE, an AI model designed to impute morphomolecular signatures in toxicology data. Our model was trained to predict 1,536 gene targets on a cohort of 8,231 hematoxylin and eosin-stained liver sections from Rattus norvegicus across 127 preclinical toxicity studies. The model, evaluated on 2,002 tissue sections from 29 held-out studies, can yield pseudo-spatially resolved gene expression maps, which we correlate with six key drug-induced liver injuries (DILI). From the resulting 25 million lesion-expression pairs, we established quantitative relations between up and downregulated genes and lesions. Validation of these signatures against toxicogenomic databases, pathway enrichment analyses, and human hepatocyte cell lines asserted their relevance. Overall, our study introduces new methods for characterizing toxicity at an unprecedented scale and granularity, paving the way for AI-driven discovery of toxicity biomarkers. Live demo: https://mahmoodlab.github.io/tox-discovery-ui/

bioinformatics↗

bioRxiv2024

Deep Learning-based Modeling for Preclinical Drug Safety Assessment

In drug development, assessing the toxicity of candidate compounds is crucial for successfully transitioning from preclinical research to early-stage clinical trials. Drug safety is typically assessed using animal models with a manual histopathological examination of tissue sections to characterize the dose-response relationship of the compound - a timeintensive process prone to inter-observer variability and predominantly involving tedious review of cases without abnormalities. Artificial intelligence (AI) methods in pathology hold promise to accelerate this assessment and enhance reproducibility and objectivity. Here, we introduce TRACE, a model designed for toxicologic liver histopathology assessment capable of tackling a range of diagnostic tasks across multiple scales, including situations where labeled data is limited. TRACE was trained on 15 million histopathology images extracted from 46,734 digitized tissue sections from 157 preclinical studies conducted on Rattus norvegicus. We show that TRACE can perform various downstream toxicology tasks spanning histopathological response assessment, lesion severity scoring, morphological retrieval, and automatic dose-response characterization. In an independent reader study, TRACE was evaluated alongside ten board-certified veterinary pathologists and achieved higher concordance with the consensus opinion than the average of the pathologists. Our study represents a substantial leap over existing computational models in toxicology by offering the first framework for accelerating and automating toxicological pathology assessment, promoting significant progress with faster, more consistent, and reliable diagnostic processes. Live Demo: https://mahmoodlab.github.io/tox-foundation-ui/

bioinformatics↗