Citations

Abstract Alzheimer’s disease (AD) is characterized by diminished capacity to mount adaptive cellular stress responses required to maintain energy homeostasis and proteostasis. An emerging therapeutic strategy is to restore adaptive stress responses by inducing mild energetic stress through inhibition of mitochondrial complex I (mtCI). However, pharmacological inhibition of the respiratory chain has remained challenging, as it can induce bioenergetic failure rather than beneficial signaling. Here, we describe C273, a brain-penetrant small molecule that delivers controlled, weak attenuation of mtCI activity to therapeutically restore endogenous adaptive stress pathways. This work establishes a first-in-class mechanism in which calibrated activation of multifaceted adaptive mechanisms enhances cellular resilience, rather than impairing mitochondrial function. Structure-activity relationship optimization yielded a compound with high potency against Aβ-induced cellular toxicity, strong selectivity for mtCI, and favorable drug-like properties. C273 demonstrated excellent oral bioavailability, metabolic stability in mouse, rat, and human microsomes, minimal CYP liabilities, and a clean ancillary pharmacology profile in the Eurofins CEREP44 panel. In vivo , C273 readily crosses the blood-brain barrier and activates AMP-activated protein kinase (AMPK), initiating a coordinated hormetic response characterized by enhanced antioxidant defenses, suppression of inflammatory signaling, induction of autophagy, and increased mitochondrial biogenesis and turnover. Genetic deletion of AMPKα1/α2 abolished these responses, establishing AMPK as a critical mediator of C273 activity. Pharmacological competition experiments further confirmed the target, as pretreatment with non-toxic concentrations of rotenone blocked C273 interaction with the quinone-binding site of mtCI and eliminated its neuroprotective effects. Repeated oral administration of C273 (20-80 mg/kg/day) to wild-type mice for one month produced no detectable cardiac or hepatic toxicity, indicating a favorable in vivo safety margin. Importantly, C273 activated these mechanisms and reduced Aβ and p-Tau levels in induced pluripotent stem cell-derived cerebral organoids from patients with sporadic AD. Collectively, these results establish controlled mtCI modulation as a therapeutic strategy and position C273 as a promising disease-modifying candidate for AD.

Abstract Scientific foundation models learn high-dimensional representations from diverse data modalities, yet what they encode and how to extract that knowledge remain open questions. Here we show that probing the internal representations of Evo 2, a 7-billion-parameter genomic foundation model, enables accurate and interpretable genetic variant effect prediction. We introduce a covariance-based probe that captures second-order structure from Evo 2 sequence embeddings to predict variant pathogenicity across variant types and functional consequences, matching or exceeding specialized predictors within their domains. To ground these predictions in known biological mechanisms, we train a complementary panel of probes on existing annotations to detect which genomic properties are disrupted by a variant. This categorized evidence is then integrated with each variant’s genomic context through a language model to generate variant-specific mechanistic hypotheses. Our pathogenicity predictions correlate with experimental measures of variant function, clinical penetrance, and biobank disease associations while the mechanistic hypotheses are consistent with expert reviews, known mechanism classes, and downstream molecular readouts. We release pathogenicity scores, disruption profiles, and contextualized interpretations for 4.2 million variants from the ClinVar database as an open resource through the Evo Variant Effect Explorer (EVEE). More broadly, this structured probing approach offers a general framework for interrogating foundation models across scientific disciplines and grounding their outputs in existing domain concepts.

Abstract STUDY QUESTION What is the fertility preservation (FP) utilization rate among transgender and gender diverse (TGD) patients at the Transgender and Intersex Specialty Care Clinic (TISCC) within the Mayo Clinic? SUMMARY ANSWER The rate of utilization of FP services by TGD patients at Mayo Clinic’s TISCC was determined to be 6.62%. WHAT IS KNOWN ALREADY TGD patients encounter several barriers when pursuing FP, which may contribute to a lower utilization rate of these services. These barriers include financial constraints and lack of insurance coverage, as well as societal and healthcare provider attitudes; TGD individuals face discrimination or lack of understanding, making it uncomfortable or difficult to discuss FP options. Additionally, there continues to be a lack of inclusive policies and support within healthcare systems that can further impede access to FP services for TGD individuals. STUDY DESIGN, SIZE, DURATION The study was executed in two phases. In the first phase, a retrospective cohort study was completed with TGD patients who provided electronic health record (EHR) research authorization from Mayo Clinic’s TISCC in Rochester, MN between 1 January 2015 and 30 July 2021. Search terms related to FP were used to determine the FP utilization rate among this patient population. In the second phase of the study, two sets of patients, (i) patients who were included in the cohort study in Phase 1, and (ii) members of JASMYN, a community organization specializing in care and wellness coordination for Lesbian, Gay, Bisexual, and Transgender (LGBT) teens and young adults in North Florida. Individuals were invited to participate in a qualitative interview exploring their cumulative healthcare experiences accessing gender-affirming care. Interviews were conducted from January 2023 to June 2023. Interviews examined participants’ perceptions of FP options, motivations for pursuing FP, and barriers to accessing both gender and fertility care. When applicable, participants also discussed their experiences pursuing FP and reflected on their satisfaction with their fertility and family planning decisions. PARTICIPANTS/MATERIALS, SETTING, METHODS In phase 1, a total of N = 1189 patients sought care from Mayo Clinic’s TISCC in Rochester, MN. Out of these patients, N = 589 patients provided research authorization and were included in the retrospective cohort study. The study team assessed whether FP terms were mentioned in each patient’s EHR, and whether patients scheduled and attended appointments with either the Department of Reproductive Endocrinology or the Department of Urology. FP search terms included sperm cryopreservation, sperm extraction, sperm aspiration, testicular tissue cryopreservation, oocyte cryopreservation, embryo cryopreservation, and ovarian tissue cryopreservation. In phase 2, N = 36 participants were interviewed, with N = 25 participants recruited from Mayo Clinic’s TISCC in Rochester, MN, and N = 11 participants recruited from JASMYN in Jacksonville, FL. Participants recruited from the Mayo Clinic participated in a video-call-based interview and those enrolled from JASMYN were interviewed in person. MAIN RESULTS AND THE ROLE OF CHANCE The study team observed a 6.62% utilization rate of FP services among N = 589 patients (median age: 28 years; age range: 8–78 years) included in the retrospective cohort study. N = 39 patients completed FP, with N = 14 receiving these services at other institutions before seeking care with the TISCC at Mayo Clinic. N = 25 patients pursued FP services within the Mayo Clinic. Patients with testes were more likely to complete FP via sperm cryopreservation when compared to the utilization of egg cryopreservation among patients with ovaries. Participants who completed an interview in Phase 2 (median age 27 years; age range: 22–80 years) reflected on their decision on whether to preserve their fertility and what factors influenced these decisions, and how their satisfaction with this decision has changed over their lifespan. The major themes reported here include the desire for biological children, planning gender care around fertility desires, conversations about FP options, physical and psychosocial barriers to pursuing FP, reflections on personal FP decisions, and reflections on having to make decisions about FP at a young age. LIMITATIONS, REASONS FOR CAUTION All participants who completed an interview have done so voluntarily; as such, there is a possibility of selection and recall bias. WIDER IMPLICATIONS OF THE FINDINGS Findings suggest that there is a need for more structured conversations around FP when TGD patients seek medical and surgical gender-affirming care. Accessibility, including financial barriers and limited insurance coverage, continues to limit the utilization of FP services among TGD patients. Increased affordability through insurance coverage may additionally improve FP utilization. STUDY FUNDING/COMPETING INTEREST(S) This project was funded by the Mayo Clinic Department of Obstetrics and Gynecology and the Mayo Clinic Center for Clinical and Translational Science (CCaTS), grant number UL1TR002377. This project was also supported by Clinical and Translational Science Award (CTSA) Grant Number TL1TR002380 from the National Center for Advancing Translational Sciences (NCATS). Its contents are solely the responsibility of the authors and do not necessarily represent the official views of the NIH. Felicity Enders reports grants from the National Institutes of Health and the Agency for Healthcare Research and Quality paid to her institution; speakers’ fees for lectures or presentations from Mount Sinai, University of Washington, University of Minnesota, University of Rochester, Cincinnati University, the National Institutes of Health, Duke University, Wake Forest University, the Patient Centered Outcomes Research Institute, Johns Hopkins University; travel support from the Association for Clinical and Translational Science and Cold Spring Harbor Laboratory; and an unpaid leadership role on the Board of Directors of the Association for Clinical and Translational Science. All other authors declare no conflicts of interest. TRIAL REGISTRATION NUMBER N/A.

Abstract INTRODUCTION Anti—amyloid‐β (Aβ) therapies are reshaping Alzheimer's disease (AD) management. Understanding changes in real‐world patterns of diagnostic testing and infusion chair usage is essential for optimizing access to care. METHODS Retrospective analysis of Mayo Clinic enterprise electronic health records (Jan 2019–Mar 2025) assessed trends in AD‐relevant brain imaging, fluid biomarkers, apolipoprotein E (APOE) testing, and lecanemab infusions. Rates of amyloid‐beta (Aβ) positivity by sex and age, APOE genotype frequencies, and lecanemab treatment initiation and discontinuation were evaluated. RESULTS Following national insurance coverage changes, lecanemab infusions grew by 110 infusions per quarter to 605 in Q1 2025. Aβ positron emission tomography scans increased (+22/quarter), cerebrospinal fluid biomarker orders declined (−25/quarter), and plasma p‐tau 217 orders rapidly increased (+238/quarter). Females were more likely to be Aβ positive ( p < 0.006). APOE ‐ε4 homozygotes were less likely to initiate lecanemab (HR = 0.11, p < 0.001). DISCUSSION The adoption of anti‐Aβ therapies coincided with a rapid shift in diagnostic workflows.

Abstract Background: Hepatocellular carcinoma (HCC) is largely refractory to immune checkpoint blockade due to immune exclusion, stromal barriers, and aberrant vasculature. We evaluated whether multimodal therapy - external beam radiotherapy (EBRT) for antigen release, intratumoral dendritic cell (DC) vaccination for antigen presentation, PD-L1 blockade for immune activation, and VEGF inhibition for vascular normalization - could convert “cold” HCC tumors into sustained immune-inflamed states. Methods: Serial biopsies (baseline, post-EBRT, end-of-treatment [EOT], and progression [PD] when available) from three patients enrolled in an ongoing phase II trial (NCT03942328) underwent multiplex immunofluorescence, spatial neighborhood analysis, and transcriptomic profiling. Longitudinal changes in cellular composition, immune-stromal architecture, spatial contact networks, and pathway activity were compared. Results: Baseline tumor microenvironments (TMEs) were strongly immune-excluded, dominated by tumor (PanCK+60-70%) and stroma (SMA+/Vimentin+25-30%) with sparse immune infiltration (&lt;10-15%). Post-therapy, immune complexity and spatial connectivity increased 2-3-fold in all patients. Patient 1 showed robust cold-to-hot conversion with CD8+(3x), CD4+(2.2x), and DC (2.3x) expansion, increased CD8-DC interactions (2.5x), and reduced tumor fraction (-40%). Transcriptomics showed marked upregulation of IFN-γ (↑3.4x), HLA-DRA (↑2.7x), and reductions in VEGFR2 (↓50%) and HIF1A (↓40%), consistent with vascular normalization. Patient 2 exhibited stromal/vascular remodeling and improved T-cell infiltration but restricted immune diversity, with CD4+/CD8+ dyads (↑2.2x) and B/NK cells(↓ 60%). Neighborhood diversity rose (3→7 communities) and immune-tumor proximity improved (distance ↓ 35%). Patient 3 showed transient inflaming with CD8+(↑3x), DC(↑2x), and new CD4-CD20/CD4-CD56 interactions, followed by relapse marked by stromal/myeloid re-expansion (SMA+↑1.8x, CD14+↑2.5x), angiogenic resurgence (VEGFR2/CD34+↑2.2x), contraction of immune networks, and genomic shift from activating CTNNB1 mutation loss to ATM gain. DCs accumulated but localized mainly to DC-DC or DC-myeloid niches, indicating non-productive antigen presentation. Conclusions: Multimodal EBRT+DC+PD-L1/VEGF blockade induces four-sided synergistic TME reprogramming - antigen release, immune priming, checkpoint release, and vascular normalization - promoting cold-to-hot conversion in HCC. Durable inflaming correlates with sustained T-cell/DC expansion and vascular remodeling, whereas relapse reflects stromal/myeloid reinforcement and genomic adaptation. These findings define mechanistic trajectories of TME remodeling and highlight actionable barriers to sustained immunotherapy response in HCC. Citation Format: Lionel Aurelien Kankeu Fonkoua, Christopher L. Hallemeier, Basim Salem, Arina Tkachuk, Kaitlynn McCay, Panwen Wang, Ying Li, Thomas D. Atwell, Krishan R. Jethwa, Caitlin Conboy, Nguyen H. Tran, Leslie A. Washburn, Melody Wu, Chen Wu, Andre De Menezes Silva Corraes, Rondell P. Graham, Jose Caetano Villasboas, Kevin Regan, Zuoyi Shao, Rayaan Kamal, Nathan R. Foster, Haidong Dong, Sean Park, Yi Lin, Lewis R. Roberts. Multimodal immunotherapy remodels the tumor microenvironment in hepatocellular carcinoma: Integrative spatial and transcriptomic profiling from a Phase II trial [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2026; Part 1 (Regular Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(7 Suppl):Abstract nr 7935.

Abstract Introduction: Liver cancer remains a leading cause of cancer mortality globally with limited treatment options for patients (pts) with unresectable hepatocellular carcinoma [HCC] and intrahepatic cholangiocarcinoma [iCCA][1,2,3,4]. We hypothesize that combining the intratumoral dendritic cell (DC) vaccination after external beam radiotherapy (EBRT) without (phase I) and with (phase II) systemic atezolizumab and bevacizumab (atezo/bev for HCC) would enhance tumor-specific immunity and improve clinical outcomes, and present preliminary results from our phase I/II trial (NCT03942328). Methods: Peripheral blood mononuclear cells (PBMCs) were collected at baseline (PRE), after radiation (EBRT), and after completion of DC without or with atezo/bev (POST). Single-cell RNA sequencing with TCR sequencing were analyzed using CellRanger v7.0.1, Immunopipe, Seurat v5.3.0, & Gene-set enrichment analysis (GSEA). Long EFS (EFS-L) is defined as &gt;=12 months (mo) for phase I and &gt;=18mo for phase II, and short EFS (EFS-S) below that. Results: Seventeen patients have been analyzed to date (Phase I: n=8 [4 HCC, 4 iCCA]; Phase II: n=9 HCC). 674,106 cells were sequenced (146,843 PRE; 168,838 EBRT; 114,437 POST). GSEA for EFS-L vs EFS-S were comparable at PRE, EBRT and POST between phase I and phase II. EFS-S was associated with enrichment of interferon alpha (IFNα; B naïve, monocytes, pDC, cDC2, NK, Treg, CD8 Tcm and Tem at PRE and POST; B intermediate, CD4 Tem and NK at EBRT) and reactive oxygen species (ROS; PRE: pDC, CD8 Tcm, Tem. EBRT: CD4 Tem. POST: CD8 T naïve Tem, CD4 Tcm & Tem, cDC2) pathways. In contrast, EFS-L was associated with enrichment of WNT-β-catenin (WNT; CD14 mono at EBRT & POST, B intermediate at EBRT), TGFb (PRE: NK; EBRT: B intermed, CD4 Tem; POST: monocytes, CD4 naïve & Tem, pDC, cDC2), and angiogenesis (EBRT: NK; POST: monocytes, cDC2) pathways. Interestingly, enrichment of protein secretion pathway in NK cells was associated with EFS-L, but among other cells were associated with EFS-S (PRE: CD16 mono, Treg; POST: CD16 mono, CD4 & D8 Tem). Compared to phase I, addition of atezo/bev in phase II pts was associated with a significant increase in Gini coefficient (p&lt;0.0001), suggesting expansion of certain TCR clones, along with a trend for increased Gini coefficient from Pre to Post in both phase I and II. Conclusions: Preliminary analysis of this study combining EBRT with intratumoral DC vaccination +/- PD-L1/VEGF blockade identified distinct treatment-related changes in systemic cellular immune profiles. Enhanced TCR clonal diversity in phase II suggests added immunologic benefit from PD-L1/VEGF blockade. As accrual continues, integrated analyses will identify systemic immune correlates of clinical benefit and resistance to this multimodal immunotherapy approach. Citation Format: Melody Wu, Panwen Wang, Chen Wu, Ying Li, Christopher L. Hallemeier, Thomas D. Atwell, Nguyen H. Tran, Andre de Menezes Silva Corraes, Kevin Regan, Zuoyi Shao, Rayaan Kamal, Haidong Dong, Lewis R. Roberts, Sean Park, Yi Lin, Lionel Aurelien Kankeu Fonkoua. Radiation-dendritic cell combination therapy drives systemic cellular immune shifts in liver cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2026; Part 1 (Regular Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(7 Suppl):Abstract nr 3741.

Abstract Prostate-specific membrane antigen (PSMA) is highly expressed in tumor-associated neovasculature in hepatocellular carcinoma (HCC), highlighting its promise as a theranostic target. This prospective study aimed to evaluate the utility of novel biomarkers derived from PSMA positron emission tomography computed tomography (PET/CT) to assess treatment response in advanced HCC patients (pts) receiving first line immune checkpoint inhibitors (ICI). Methods: This study (NCT05176223) enrolled unresectable, advanced HCC pts eligible for first-line ICI (atezolizumab/bevacizumab [A/B] or durvalumab/tremelimumab [D/T]) with measurable disease according to RECIST criteria. Primary endpoints: progression-free survival (PFS) per RECIST 1.1 and mRECIST; overall survival (OS); and best overall response. The survival distribution was estimated using the Kaplan-Meier method. Observed agreement is defined as the proportion of pts whose responses, as classified by PET/CT or CT, were concordant. Weighted kappa and Cohen’s kappa were used to quantify the strength of agreement between PET/CT and CT. Pts completed up to five 68Ga-PSMA PET/CT scans and blood collections. Results: Twenty-six pts were enrolled (25 evaluable) between Oct 2022 and Nov 2024. Median follow up was 22.1 months (m) (Q1, Q3: 14.5-23.7). Median age 68 yrs, 72% male, 88% White, 68% Child-Pugh [CP] A, 32% CP B, 32% Barcelona Clinic Liver Cancer [BCLC] stage B, 68% BCLC stage C, 36% with microvascular invasion; 56% received A/B and 40% received D/T treatment. PSMA was positive in 96% of pts at baseline with median SUVmax 14.3 (range 5.1-40.5) and median background liver SUVmax 3.9 (range 2.1-6.8). Median (95%CI) PFS was 5.6 m (4.6-12.5) by both RECIST and mRECIST. Median (95%CI) OS was 18.6 m (7.2-not estimable), with 56% deceased. The observed agreement between PET/CT adapted PERCIST criteria compared to RECIST and mRECIST in determining the best response was 46% and 50% and weighted kappa of 0.63 (95% CI: 0.37-0.90) and 0.66 (0.41-0.92), respectively. Observed agreement between PERCIST compared to RECIST and mRECIST for responders’ assessment was 67% and 71% with Cohen’s kappa of 0.36 (0.03-0.68) and 0.43 (0.11-0.76), respectively. Conclusion: In this cohort, PSMA PET/CT avidity was observed in all but one pt with advanced HCC, each demonstrating moderate to high SUVmax values. Median OS and PFS were consistent with outcomes reported in clinical trials. Response assessment using 68Ga-PSMA PET/CT according to PERCIST criteria showed good concordance with both RECIST and mRECIST standards. Analysis of immune biomarkers is ongoing. Citation Format: Nguyen H. Tran, Jacob Hirdler, Ajith Antony, Jacob Teske, Sudhakar K. Venkatesh, Amit Mahipal, Michael S. Torbenson, Scott M. Thompson, Thor R. Halfdanarson, Zhaohui Jin, Lionel Aurelien Kankeu Fonkoua, Leslie A. Washburn, Alexander Revzin, Haidong Dong, Robert R. Mcwilliams, Aminah Jatoi, Hani M. Babiker, Mitesh J. Borad, Tanios Bekaii-Saab, Gregory J. Gores, Lewis R. Roberts, Geoffrey B. Johnson, Ajit H. Goenka. Prospective evaluation of 68Ga-PSMA PET imaging in advanced hepatocellular carcinoma patients undergoing first line immunotherapy [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2026; Part 1 (Regular Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(7 Suppl):Abstract nr 2611.

Abstract Introduction: The prostate cancer (PCa) tumor microenvironment (TME) is immunosuppressive and resistant to immune checkpoint blockade (ICB). Based on multi-omic single cell correlatives of response to neoadjuvant Fc-enhanced (FcE) αCTLA-4 in high-risk localized PCa (NCT04301414), we explored how modulating the balance between regulatory T cells (Tregs) and dendritic cells (DCs) in the PCa TME affects sensitivity to ICB. Methods: We leveraged three single cell transcriptomic atlases of PCa to assess how Tregs and DC frequencies are dynamically regulated during PCa progression. To investigate responses to Treg depletion (via FcE-αCTLA-4) alongside DC expansion (via Flt3L-Ig) and stimulation (via STING agonist ADU-S100) in PCa, we employed the castration-sensitive MycCaP PCa model and 45-parameter spectral flow cytometry. To investigate novel direct mechanisms of DC stimulation by FcE-αCTLA-4 via Fcγ receptor (FcγR) engagement, we optimized reductionist in vitro assays involving bone marrow-derived DCs (BMDCs) from wild-type (WT) mice or mice deficient in activating FcγRs (Fcer1g-/-) or inhibitory FcγRIIb (Fcgr2b-/-). To validate this effect in vivo we established a tumor antigen-specific T cell priming assay with both flow cytometry and ex vivo 2-photon live cell imaging readouts. Results: In three independent single cell transcriptomic PCa atlases, we find cDC2 frequencies are significantly decreased in advanced PCa while effector Tregs (TNFRSF9+) increase in proportion. Hypothesizing that excessive Treg function and DC insufficiency drive ICB resistance in PCa, we find in vivo DC expansion (Flt3L-Ig) prior to hormonal therapy, Treg depletion (FcE-αCTLA-4), and in situ DC stimulation (ADU-S100) drives robust control of established MycCaP tumors, with 87% of animals tumor-free 40-days post-treatment (27/31). Using 45-parameter spectral flow cytometry we find FcE-αCTLA-4 drives DC activation prior to Treg depletion in the TME, supporting a novel direct mechanism of DC modulation by FcE-αCTLA-4. In vitro, we find cell-associated FcE-αCTLA-4 is sufficient to drive BMDC maturation in an FcγR-dependent manner. In vivo, FcE-αCTLA-4 augments DC-mediated T cell priming in an FcγR-dependent manner. Ongoing experiments are investigating how FcE-αCTLA-4 shapes DC-T cell interactions via FcγR engagement and how DC/Treg axis modulation can be optimized to improve long-term curative response rates in the MycCaP model. Conclusions: DC insufficiency and effector Treg differentiation are hallmarks of advanced PCa. Enhancing DC number and function concomitant with Treg depletion can drive effective antitumor immunity in a pre-clinical PCa model. Direct DC modulation via FcγR engagement represents a novel mechanism of response to CTLA-4-targeted ICB. These findings will inform ongoing translation of FcE-αCTLA-4 agents and development of novel immunotherapy strategies for PCa. Citation Format: Jessica C. Hill, Kade R. Copple, Collin Jugler, Phuong Nguyen, Nilika Bhattacharya, Jessica N. Lancaster, Casey R. Ager. Rewiring the dendritic cell: Regulatory T cell axis sensitizes prostate cancer to immunotherapy [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2026; Part 1 (Regular Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(7 Suppl):Abstract nr 166.

Background: Pancreatitis significantly alters the microbial composition of the oral and intestinal compartments, causing dysbiosis that may contribute to disease mechanisms and potentially serve as a basis for diagnosis or treatment. Objective: To determine whether the oral or gut microbial signature can classify chronic pancreatitis (CP). Methods: Stool samples (n=707) were collected from participants in the Prospective Evaluation of Chronic Pancreatitis for Epidemiologic and Translational Studies (PROCEED). Samples were distributed among 200 healthy (HC), 310 CP, 49 acute pancreatitis (AP), and 148 recurrent acute pancreatitis (RAP). In addition, saliva samples were collected for a subset of participants (n=156). Whole genome sequencing was performed to assess microbiome composition. Machine learning algorithms were utilized to identify a signature with microbial features predictive of CP. Results: Gut alpha diversity was significantly decreased in AP, RAP, and CP compared with HC, with CP exhibiting the lowest diversity. In contrast, oral microbial diversity showed no significant variation across groups. Beta diversity analysis revealed distinct gut microbiome compositions between HC and pancreatitis subtypes, with CP showing the most pronounced differences. Random forest models using gut microbial species demonstrated robust predictive performance for CP using a minimum of 10 species (Area under the curve—AUC: 0.834; accuracy: 0.774). Despite similarities in gut microbiome composition across pancreatitis subtypes, a unique gut microbial signature for CP was identified highlighting the microbiome’s potential in CP diagnosis. Conclusion: Our study reveals a gut microbial signature predictive of CP using machine learning models in a large US multi-institutional cohort.