Thompson, Kevin J.

Abstract Background Plasma biomarkers offer improved accessibility compared to established diagnostic modalities for Alzheimer's disease (AD). However, current plasma biomarker candidates have not been tested comprehensively in diverse populations, and represent only a fraction of pathways dysregulated in AD. This study seeks to address these knowledge gaps through untargeted plasma biomarker discovery in African Americans (AA), an underrepresented group in AD research despite having a higher risk of developing dementia compared to non‐Hispanic Whites (NHW). Method Untargeted proteomics were generated using the SomaScan 7k platform on plasma samples from AA study participants clinically diagnosed as AD dementia ( n = 181) or cognitively unimpaired (CU; n = 142). Machine learning was implemented to identify a set of plasma proteins to distinguish between AD dementia and CU. Predictive models were constructed by elastic net regression optimized with nested cross‐validation on 6,853 proteins and evaluated by receiver operating characteristic analysis. The generalizability of plasma protein predictors was evaluated in an external Alzheimer's Disease Research Center cohort of 369 NHW and AA study participants diagnosed as AD dementia or CU. Result Thirty‐six proteins were selected as predictors. Proteins selected by machine learning were enriched for processes previously associated with AD including synaptic dysfunction, inflammation, vascular dysfunction, and amyloid processing. The 36 plasma proteins alone achieved an area under the curve (AUC) of 0.94 to classify AD dementia in the discovery cohort, representing a 22% improvement over a model including age and sex. The 36 proteins were validated in an external cohort also achieving AUC=0.94, a 35% improvement over age and sex. Conclusion Biomarker discovery combining untargeted proteomics and machine learning identified a set of plasma proteins that could serve as a novel and highly accurate diagnostic plasma biomarker panel for AD. Work is underway to assess the association of the predictive panel with p ‐tau217, medical comorbidities, and social/structural determinants of health.

Abstract INTRODUCTION African American (AA) individuals are underrepresented in biomarker studies for Alzheimer's disease (AD). Biomarkers that reflect the heterogeneity of AD and achieve the greatest accuracy across populations are sorely needed. METHODS Untargeted proteome measurements were obtained using the SomaScan 7k platform to identify novel plasma biomarkers for AD in AA participants with clinical diagnoses of AD dementia ( n = 181) and cognitively unimpaired (CU, n = 142). Machine learning was used to identify a set of plasma proteins that yielded the best classification accuracy. RESULTS A set of 36 proteins achieved an area under the curve (AUC) of 0.94 to classify AD dementia versus CU, a 16% improvement over age, sex, and apolipoprotein E ( APOE) . This finding was replicated in multiple plasma and brain datasets (AUCs 0.73–0.97). Our findings underscore the importance of matrisome and cerebrovascular dysfunction in AD pathophysiology. DISCUSSION This study demonstrates the potential of biomarker discovery through untargeted plasma proteomics and machine learning. Highlights Conducted large‐scale plasma proteomics in Alzheimer's disease (AD) versus cognitively unimpaired controls. Machine learning biomarker discovery was replicated in an independent cohort. Novel set of proteins distinguishes AD versus controls with high accuracy (area under the curve [AUC] = 0.94). Achieved reproducibility across multiple replication cohorts (AUC = 0.73–0.97). Network analyses implicates matrisome biology and cerebrovascular dysfunction.

Abstract Deep learning has advanced digital pathology and multi-omics data analysis. However, there is still a critical need to integrate these modalities to better understand complex diseases. Deep learning models, such as Prov-Gigapath, a state-of-the-art pathology foundation model, have been developed for analyzing whole-slide images (WSI). Our previously published deep-learning framework, OmicsFootPrint (OFP), transforms high-dimensional multi-omics data into intuitive genomically-arranged circular images and utilizes transfer learning to overcome the challenges of high-dimensional, low-sample-size data. In this study, we aimed to combine WSI and multi-omics data to develop a framework capable of distinguishing between invasive ductal carcinoma (IDC) and invasive lobular carcinoma (ILC), which is clinically significant as it may help explain differential responses to therapies, such as tamoxifen versus letrozole. We enhanced the performance of our OFP model by dividing each multi-omics circular image (1024x1024x3 pixels) into 16 equal-sized patches (256x256x3 pixels). Each patch was trained using a separate EfficientNetV2 architecture with pre-trained ImageNet weights. The probability outcomes from these 16 models were subsequently combined through a meta-learner model using the AutoGluon framework. Concurrently, WSI images corresponding to the same patients were independently trained, maintaining consistent train/validation/test splits. The Prov-Gigapath model, which was trained using a dataset from the Providence Health System, was employed to extract patch-level embeddings from the WSI data. These embeddings were fine-tuned using a LongNet-based masked autoencoder to predict outcomes. Finally, predictions from the OFP model and the WSI-based Prov-Gigapath model were integrated through a meta-learner, preserving the original train/validation/test split. Model performances (AUC) were evaluated using the held-out test set. The gold standard used for the analysis was histological identification of IDC versus ILC, against which the performance of omics data alone, WSI data alone, and the multi-modal integration approach were compared. We evaluated our integrated model as a proof-of-concept using The Cancer Genome Atlas (TCGA) breast cancer cohort, comprising 92 ILC and 391 IDC samples. Multi-omics data, including gene expression, microRNA, copy number variation, and RPPA, were analyzed using the OFP framework, while WSI data were processed using the Prov-Gigapath method. The results demonstrated that the multi-modal integration approach significantly outperformed individual modalities, achieving an AUC of 0.98 compared to 0.87 for OFP (original), 0.95 for OFP (16-patches), and 0.92 for WSI. Integrating WSI and multi-omics data improves predictive accuracy, significantly improving the classification of breast cancer subtypes over histology alone. Citation Format: Naresh Prodduturi, Xiaojia Tang, Hamid R. Tizhoosh, Kevin J. Thompson, Richard Weinshilboum, Karthik V. Giridhar, Judy C. Boughey, Eric W. Klee, Liewei Wang, Matthew P. Goetz, Vera Suman, Krishna R. Kalari. A multi-modal learning framework to integrate digital pathology image and multi-omics data in breast cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 2429.

Abstract Alzheimer’s disease (AD) affects 40 million individuals globally and is characterized by the accumulation of amyloid-beta (Aβ) proteins, which aggregate and form plaques. BBB dysfunction drives AD cerebrovascular pathology and BBB integrity is maintained by neurovascular unit (NVU). Specifically, within the NVU, the cerebral endothelial cells maintain vascular homeostasis. In this study, we isolated endothelial-enriched regions of interest (ROIs) using the Nanostring GeoMx digital spatial profiler and employed a deconvolution model to evaluate transcriptomic changes. We observed dysregulation of cellular signaling potentially disrupting the APP+ BBB integrity. Analysis of ligand-receptor pairings that are the foundation of the NVU intercellular signaling indicated that the endothelial vasculature completes a feedback loop with the NVU to the regulating astroctyes. Further, we identified potentially antagonistic signaling roles for opioid receptor species that should be further investigated for potential therapeutic targets. Graphical Abstract

ABSTRACTType 2 diabetes mellitus (T2DM), characterized by insulin resistance, is closely associated with Alzheimer's disease (AD). Cerebrovascular dysfunction is manifested in both T2DM and AD, and is often considered as a pathological link between the two diseases. Insulin signaling regulates critical functions of the blood–brain barrier (BBB), and endothelial insulin resistance could lead to BBB dysfunction, aggravating AD pathology. However, insulin signaling is intrinsically dynamic and involves interactions among numerous molecular mediators. Hence, a mechanistic systems biology model is needed to understand how insulin regulates BBB physiology and the consequences of its impairment in T2DM and AD. In this study, we investigated the pharmacodynamic effect of insulin on the expression of vascular cell adhesion molecule 1 (VCAM1), a marker of cerebrovascular inflammation. Intriguingly, normal insulin concentrations selectively activated the PI3K‐AKT pathway, leading to decreased VCAM1 expression. However, exposure to supraphysiological insulin levels, which is present in insulin resistance, activated both PI3K‐AKT and MEK–ERK pathways, and increased VCAM1 expression. We developed a mathematical model that adequately described the dynamics of various insulin signaling nodes and VCAM1 expression. Further, the model was integrated with in vitro proteomics and transcriptomics data from AD patients to simulate VCAM1 expression under pathological conditions. This approach allowed us to establish a quantitative systems pharmacology framework to investigate BBB dysfunction in AD and metabolic syndrome, thereby offering opportunities to identify specific disruptions in molecular networks that will enable us to identify novel therapeutic targets.

Abstract The OmicsFootPrint framework addresses the need for advanced multi-omics data analysis methodologies by transforming data into intuitive two-dimensional circular images and facilitating the interpretation of complex diseases. Utilizing deep neural networks and incorporating the SHapley Additive exPlanations algorithm, the framework enhances model interpretability. Tested with The Cancer Genome Atlas data, OmicsFootPrint effectively classified lung and breast cancer subtypes, achieving high area under the curve (AUC) scores—0.98 ± 0.02 for lung cancer subtype differentiation and 0.83 ± 0.07 for breast cancer PAM50 subtypes, and successfully distinguished between invasive lobular and ductal carcinomas in breast cancer, showcasing its robustness. It also demonstrated notable performance in predicting drug responses in cancer cell lines, with a median AUC of 0.74, surpassing nine existing methods. Furthermore, its effectiveness persists even with reduced training sample sizes. OmicsFootPrint marks an enhancement in multi-omics research, offering a novel, efficient and interpretable approach that contributes to a deeper understanding of disease mechanisms.

e13036 Background: In January 2023, the FDA approved elacestrant for ESR1-mutated, ER+/HER2- MBC based on a companion diagnostic cell free (cf)DNA test (Guardant Health). In this study, we analyze the trends of liquid biopsy utilization at Mayo Clinic (MC) over a 3 year period to understand the impact of this drug approval on testing patterns and identify emergent alterations in patients (pts) with MBC. Methods: We extracted clinically performed Guardant 360 and Guardant 360 CDx ordered at MC sites in Rochester (MN), Florida (FL), Arizona (AZ), and across 9 additional Mayo Clinic Health System (MCHS) sites. Pts with MBC were identified using the EMR and analyzing visit diagnosis codes and staging information. Shifts in testing patterns were analyzed over a 3 year period from January 1, 2021 - December 31, 2023. Data was collected on the number of tests, serial testing, frequency of pathogenic mutations, and emergent mutations in ESR1 and PIK3CA. Chi-square test was used to compare the categorical values. Results: Between 2021-2023, 2,741 pts with MBC were seen across all sites. A total of 408 cfDNA tests were performed in 370 unique patients with MBC. Most pts (90%) had 1 test performed. The proportion of pts with MBC tested was 85/1350 (6.3%) in 2021, 77/1495 (5.2%) in 2022, and 208/1558 (13.4%) in 2023. The increased proportion of pts tested in 2023 was statistically significant compared to prior years (p<0.0001), while no difference was observed between 2021 and 2022 (p 0.19). Testing patterns varied by site, with FL ordering the highest number of tests, followed by MN and AZ. Of the 34 providers practicing during the entire period seeing more than 10 MBC pts, the number of providers ordering Guardant testing increased from 15/34 (2021) and 14/34 (2022) to 20/34 (2023), though not statistically significant (p 0.15). Of the 41% with EMR-documented staging available, testing was highest in the ER+/HER2- (81.3%) subtype, followed by TNBC (13.6%) and then HER2+ (5.2%). The most commonly identified mutations identified in the first testing were PIK3CA (41.1%), TP53 (40.5%), ESR1 (30.5%), and ATM (13.2%). D538G (8.0%), Y537N (4.4%), and Y537S (3.5%) were frequent emergent mutations seen in ESR1. Conclusions: We observed an increase in cfDNA testing at the start of 2023 which aligns with the FDA approval of elacestrant. We observed variation by site and individual providers that warrants further exploration to improve cfDNA testing in MBC pts at Mayo Clinic.

Background: A strong body of evidence suggests that cerebrovascular pathologies augment the onset and progression of Alzheimer’s disease (AD). One distinctive aspect of this cerebrovascular dysfunction is the degeneration of brain pericytes—often overlooked supporting cells of blood-brain barrier endothelium. Objective: The current study investigates the influence of pericytes on gene and protein expressions in the blood-brain barrier endothelium, which is expected to facilitate the identification of pathophysiological pathways that are triggered by pericyte loss and lead to blood-brain barrier dysfunction in AD. Methods: Bioinformatics analysis was conducted on the RNA-Seq expression counts matrix (GSE144474), which compared solo-cultured human blood-brain barrier endothelial cells against endothelial cells co-cultured with human brain pericytes in a non-contact model. We constructed a similar cell culture model to verify protein expression using western blots. Results: The insulin resistance and ferroptosis pathways were found to be enriched. Western blots of the insulin receptor and heme oxygenase expressions were consistent with those observed in RNA-Seq data. Additionally, we observed more than 5-fold upregulation of several genes associated with neuroprotection, including insulin-like growth factor 2 and brain-derived neurotrophic factor. Conclusions: Results suggest that pericyte influence on blood-brain barrier endothelial gene expression confers protection from insulin resistance, iron accumulation, oxidative stress, and amyloid deposition. Since these are conditions associated with AD pathophysiology, they imply mechanisms by which pericyte degeneration could contribute to disease progression.

AbstractBackground:Triple-negative breast cancer (TNBC) is the most aggressive breast cancer subtype. Patients with TNBC are primarily treated with neoadjuvant chemotherapy (NAC). Response to NAC is prognostic, with reductions in low overall survival and disease-free survival rates in those patients who do not achieve pathological complete response (pCR). Based on this premise, we focused on patients with residual disease and hypothesized that paired analysis of primary and residual TNBC tumors following NAC could identify unique biomarkers associated with post-NAC recurrence.Methods and Results: We investigated 24 TNBC tumors from 12 patients with pre- and post-NAC data, including four patients who recurred shortly after surgery(<24 months) and eight who remained recurrence-free (> 48 months). These tumors were collected from a prospective NAC breast cancer study (BEAUTY) conducted at the Mayo Clinic. Differential expression analysis of pre-NAC biopsies showed minimal gene expression differences between early recurrent and non-recurrent TNBC tumors; however, post-NAC samples demonstrated a significant alteration in expression patterns in response to intervention. Topological-level differences associated with early recurrence were implicated in 251 gene sets, and an independent assessment of microarray gene expression data from the paired NAC I-SPY1 trial confirmed 56 genesets. Underlying these 56 gene sets, 113 genes were observed to be differentially expressed in the I-SPY1 and BEAUTY post-NAC studies. An independent (n=392) breast cancer data set with relapse-free survival (RFS) data was used to refine our gene list to a 17 gene signature. A three-fold cross-validation analysis of the gene signature with the combined BEAUTY and I-SPY1 data yielded an average AUC of 0.88 for six machine learning models. Due to the limited studies with pre-and post-NAC TNBC tumor data, further validation of the signature is needed.Conclusion:Analysis of multi-omics data from post-NAC TNBC chemoresistant tumors showed downregulation of mismatch repair, purin, and tubulin pathways. Additionally, weidentified a 17 gene signature in TNBC associated with post-NAC recurrence enriched with down-regulation of immune genes.

Abstract Triple-negative breast cancer (TNBC) is the most aggressive breast cancer subtype with low overall survival rates and high molecular heterogeneity; therefore, few targeted therapies are available. The luminal androgen receptor (LAR) is the most consistently identified TNBC subtype, but the clinical utility has yet to be established. Here, we constructed a novel genomic classifier, LAR-Sig, that distinguishes the LAR subtype from other TNBC subtypes and provide evidence that it is a clinically distinct disease. A meta-analysis of seven TNBC datasets (n = 1086 samples) from neoadjuvant clinical trials demonstrated that LAR patients have significantly reduced response (pCR) rates than non-LAR TNBC patients (odds ratio = 2.11, 95% CI: 1.33, 2.89). Moreover, deconvolution of the tumor microenvironment confirmed an enrichment of luminal epithelium corresponding with a decrease in basal and myoepithelium in LAR TNBC tumors. Increased immunosuppression in LAR patients may lead to a decreased presence of cycling T-cells and plasma cells. While, an increased presence of myofibroblast-like cancer-associated cells may impede drug delivery and treatment. In summary, the lower levels of tumor infiltrating lymphocytes (TILs), reduced immune activity in the micro-environment, and lower pCR rates after NAC, suggest that new therapeutic strategies for the LAR TNBC subtype need to be developed.