Background. Metabolic dysfunction‐associated steatohepatitis (MASH) has become the leading cause of chronic liver disease, but there has been no approved pharmacotherapy to date. Methods. We used a network analysis approach to delineate protein‐protein interactions that contribute to the transition from steatosis to MASH, in order to identify and target this transition as a potential pharmacotherapeutic strategy. Acyl‐CoA thioesterase 1 (ACOT1) was identified as a critical node in the protein‐protein interaction (PPI) network of the transition from steatosis to MASH in patient samples. ACOT1 overexpression and silencing effects were tested in vivo on C57BL/6 mice exposed to high‐fat diet (HFD) and inoculated with an adenoviral system to modulate ACOT1 expression. Transcriptomic and untargeted lipidomic profiles were performed on the mouse livers. Results. ACOT1 expression was 3‐fold higher in MASH as compared to steatosis. In patient samples, ACOT1 was significantly correlated with the severity of MASH as reflected by the nonalcoholic fatty liver disease score. Experimental validation showed that downregulation of ACOT1 resulted in decreased lipid accumulation and prevention of MASH in vivo. Conversely, upregulation of ACOT1 via an adenoviral vector resulted in development of MASH, whereas control mice only developed steatosis. Lipidomic analysis revealed glycerophospholipids to be especially abundant in MASH accelerated by ACOT1 upregulation. Conclusion. These results suggest that ACOT1 contributes to the transition from steatosis to MASH through modulation of glycerophospholipid accumulation and its potential as a novel therapeutic target in MASH. This trial is registered with NCT02148471.

The COVID-19 pandemic has underscored the importance of vaccines, especially for immunocompromised populations like solid organ transplant (SOT) recipients, who often have weaker immune responses. The purpose of this study was to compare deep learning architectures for predicting SARS-CoV-2 vaccine responses 12 months post-vaccination in this high-risk group. Utilizing data from 303 SOT recipients from a Canadian multicenter cohort, models were developed to forecast anti-receptor binding domain (RBD) antibody levels. The study compared traditional machine learning models-logistic regression, epsilon-support vector regression, random forest regressor, and gradient boosting regressor-and deep learning architectures, including long short-term memory (LSTM), recurrent neural networks, and a novel model, routed LSTM. This new model combines capsule networks with LSTM to reduce the need for large datasets. Demographic, clinical, and transplant-specific data, along with longitudinal antibody measurements, were incorporated into the models. The routed LSTM performed best, achieving a mean square error (MSE) of 0.02±0.02 and a Pearson correlation coefficient (PCC) of 0.79±0.24, outperforming all other models. Key factors influencing vaccine response included age, immunosuppression, breakthrough infection, BMI, sex, and transplant type. These findings suggest that AI could be a valuable tool in tailoring vaccine strategies, improving health outcomes for vulnerable transplant recipients.

Background. Liver transplantation is essential for many people with primary sclerosing cholangitis (PSC). People with PSC are less likely to receive a deceased donor liver transplant compared with other causes of chronic liver disease. This disparity may stem from the inaccuracy of the model for end-stage liver disease (MELD) in predicting waitlist mortality or dropout for PSC. The broad applicability of MELD across many causes comes at the expense of accuracy in prediction for certain causes that involve unique comorbidities. We aimed to develop a model that could more accurately predict dynamic changes in waitlist outcomes among patients with PSC while including complex clinical variables. Methods. We developed 3 machine learning architectures using data from 4666 patients with PSC in the Scientific Registry of Transplant Recipients (SRTR) and tested our models on our institutional data set of 144 patients at the University Health Network (UHN). We evaluated their time-dependent concordance index (C-index) for mortality prediction and compared it against MELD-sodium and MELD 3.0. Results. Random survival forest (RSF), a decision tree–based survival model, outperformed MELD-sodium and MELD 3.0 in both the SRTR and the UHN test data set using the same bloodwork variables and readily available demographic data. It achieved a C-index of 0.868 (SD 0.020) and 0.771 (SD 0.085) on the SRTR and UHN test data, respectively. Training a separate RSF model using the UHN data with PSC-specific achieved a C-index of 0.91. In addition to high MELD score, increased white blood cells, time on the waiting list, platelet count, presence of Autoimmune hepatitis-PSC overlap, aspartate aminotransferase, female sex, age, history of stricture dilation, and extremes of body weight were the top-ranked features predictive of the outcomes. Conclusions. Our RSF model offers more accurate waitlist outcome prediction in PSC. The significant performance improvement with the inclusion of PSC-specific variables highlights the importance of disease-specific variables for predicting trajectories of clinically distinct presentations. Export

Graft injury affects over 50% of liver transplant (LT) recipients, but non-invasive biomarkers to diagnose and guide treatment are currently limited. We aimed to develop a biomarker of graft injury by integrating serum metabolomic profiles with clinical variables. Serum from 55 LT recipients with biopsy confirmed metabolic dysfunction-associated steatohepatitis (MASH), T-cell mediated rejection (TCMR) and biliary complications was collected and processed using a combination of LC-MS/MS assay. The metabolomic profiles were integrated with clinical information using a multi-class Machine Learning (ML) classifier. The model’s efficacy was assessed through the Out-of-Bag (OOB) error estimate evaluation. Our ML model yielded an overall accuracy of 79.66% with an OOB estimate of the error rate at 19.75%. The model exhibited a maximum ability to distinguish MASH, with an OOB error estimate of 7.4% compared to 22.2% for biliary and 29.6% for TCMR. The metabolites serine and serotonin emerged as the topmost predictors. When predicting binary outcomes using three models: Biliary (biliary vs. rest), MASH (MASH vs. rest) and TCMR (TCMR vs. rest); the AUCs were 0.882, 0.972 and 0.896, respectively. Our ML tool integrating serum metabolites with clinical variables shows promise as a non-invasive, multi-class serum biomarker of graft pathology.

Graft injury affects over 50% of liver transplant (LT) recipients, but non-invasive biomarkers to diagnose and guide treatment are currently limited. We aimed to develop a biomarker of graft injury by integrating serum metabolomic profiles with clinical variables. Serum from 55 LT recipients with biopsy confirmed metabolic-dysfunction associated steatohepatitis (MASH), T-cell mediated rejection (TCMR) and biliary complications was collected and processed using a combination of LC-MS/MS assay. The metabolomic profiles were integrated with clinical information using a multi-class Machine Learning (ML) classifier. The efficacy of the model was assessed through the evaluation of the Out-of-Bag (OOB) error estimate. Our ML model yielded an overall accuracy of 79.66% with an OOB estimate of the error rate at 19.75%. The model exhibited a maximum ability to distinguish MASH, with an OOB error estimate of 7.4% compared to 22.2% for biliary and 29.6% for TCMR. The metabolites serine and serotonin emerged as the topmost predictors. When predicting binary outcomes using 3 models: Biliary (biliary vs. rest), MASH (MASH vs. rest) and TCMR (TCMR vs. rest), the AUCs were 0.882, 0.972 and 0.96 respectively. Our ML tool integrating serum metabolites with clinical variables shows promise as a non-invasive, multi-class serum biomarker of graft pathology.

Background/Objectives: Long-term survival among liver transplant (LT) recipients who live beyond one year has remained relatively stable over recent decades. However, reducing long-term morbidity is increasingly important, and metabolomics may enable risk-based, personalized immunosuppression. We aimed to evaluate and compare the serum metabolomic profiles of LT recipients treated with tacrolimus (TAC) versus sirolimus (SIR), to elucidate metabolic pathways associated with these regimens. Methods: Targeted metabolomic profiling of 894 metabolites was conducted on serum samples from 128 LT recipients using the Biocrates MxP^® Quant 500 kit. Data were analyzed with MetaboAnalyst 6.0, and multivariate analysis was performed using Partial Least Squares-Discriminant Analysis (PLS-DA). Metabolites with Variable Importance in Projection (VIP) scores > 1.5 underwent pathway enrichment in OmicsNet, incorporating Gene Ontology annotations and Kyoto Encyclopedia of Genes and Genomes (KEGG)-based network analysis. Results: Eighty-seven metabolites were significantly altered between groups. Phosphatidylcholines (PCs) and ceramides were elevated in TAC-treated patients, while di- and triacylglycerols were higher in the SIR group. Pathway enrichment implicated lipid metabolism, particularly glycerophospholipid, ether lipid, and sphingolipid pathways. Network analysis identified enriched modules related to metabolic regulation and immune response. Conclusions: Divergent metabolomic profiles distinguish TAC- and SIR-treated recipients, suggesting regimen-specific impacts on lipid metabolism with potential relevance to post-transplant complications.