Liver disease carries significant healthcare burden and frequently requires a combination of blood tests, imaging, and invasive liver biopsy to diagnose. Distinguishing between inflammatory liver diseases, which may have similar clinical presentations, is particularly challenging. In this study, we implemented a machine learning pipeline for the identification of diagnostic gene expression biomarkers across several alcohol-associated and non-alcohol-associated liver diseases, using either liver tissue or blood-based samples. We collected peripheral blood mononuclear cells (PBMCs) and liver tissue samples from participants with alcohol-associated hepatitis (AH), alcohol-associated cirrhosis (AC), non-alcohol-associated fatty liver disease, chronic HCV infection, and healthy controls. We performed RNA sequencing (RNA-seq) on 137 PBMC samples and 67 liver tissue samples. Using gene expression data, we implemented a machine learning feature selection and classification pipeline to identify diagnostic biomarkers which distinguish between the liver disease groups. The liver tissue results were validated using a public independent RNA-seq dataset. The biomarkers were computationally validated for biological relevance using pathway analysis tools. Utilizing liver tissue RNA-seq data, we distinguished between AH, AC, and healthy conditions with overall accuracies of 90% in our dataset, and 82% in the independent dataset, with 33 genes. Distinguishing 4 liver conditions and healthy controls yielded 91% overall accuracy in our liver tissue dataset with 39 genes, and 75% overall accuracy in our PBMC dataset with 75 genes. Our machine learning pipeline was effective at identifying a small set of diagnostic gene biomarkers and classifying several liver diseases using RNA-seq data from liver tissue and PBMCs. The methodologies implemented and genes identified in this study may facilitate future efforts toward a liquid biopsy diagnostic for liver diseases. Distinguishing between inflammatory liver diseases without multiple tests can be challenging due to their clinically similar characteristics. To lay the groundwork for the development of a non-invasive blood-based diagnostic across a range of liver diseases, we compared samples from participants with alcohol-associated hepatitis, alcohol-associated cirrhosis, chronic hepatitis C infection, and non-alcohol-associated fatty liver disease. We used a machine learning computational approach to demonstrate that gene expression data generated from either liver tissue or blood samples can be used to discover a small set of gene biomarkers for effective diagnosis of these liver diseases.

Background: A limitation of traditional differential expression analysis on small datasets involves the possibility of false positives and false negatives due to sample variation. Considering the recent advances in deep learning (DL) based models, we wanted to expand the state-of-the-art in disease biomarker prediction from RNA-seq data using DL. However, application of DL to RNA-seq data is challenging due to absence of appropriate labels and smaller sample size as compared to number of genes. Deep learning coupled with transfer learning can improve prediction performance on novel data by incorporating patterns learned from other related data. With the emergence of new disease datasets, biomarker prediction would be facilitated by having a generalized model that can transfer the knowledge of trained feature maps to the new dataset. To the best of our knowledge, there is no Convolutional Neural Network (CNN)-based model coupled with transfer learning to predict the significant upregulating (UR) and downregulating (DR) genes from both trained and untrained datasets.Results: We implemented a CNN model, DEGnext, to predict UR and DR genes from gene expression data obtained from The Cancer Genome Atlas database. DEGnext uses biologically validated data along with logarithmic fold change values to classify differentially expressed genes (DEGs) as UR and DR genes. We applied transfer learning to our model to leverage the knowledge of trained feature maps to untrained cancer datasets. DEGnext’s results were competitive (ROC scores between 88 and 99 $$\%$$% ) with those of five traditional machine learning methods: Decision Tree, K-Nearest Neighbors, Random Forest, Support Vector Machine, and XGBoost. DEGnext was robust and effective in terms of transferring learned feature maps to facilitate classification of unseen datasets. Additionally, we validated that the predicted DEGs from DEGnext were mapped to significant Gene Ontology terms and pathways related to cancer.Conclusions: DEGnext can classify DEGs into UR and DR genes from RNA-seq cancer datasets with high performance. This type of analysis, using biologically relevant fine-tuning data, may aid in the exploration of potential biomarkers and can be adapted for other disease datasets.

Alcohol-associated hepatitis (AH) is often diagnosed at advanced stages, and severe AH usually carries poor prognosis and high short-term mortality. In addition, it is challenging to understand the molecular mechanisms of immune dysregulation and inflammation in AH due to the cellular complexity and heterogeneity. Using single-cell RNA sequencing, previous studies found that AH causes dysfunctional innate immune response in monocytes, involving activation of pattern recognition receptors (PRRs) and cytokine signaling pathways. To better understand the coordinated systemic immune response in AH patients, we performed combined single-cell transcriptome, cell-surface protein, and lymphocyte antigen receptor analysis of peripheral blood mononuclear cell (PBMC) samples. Our results showed inflammatory cytokines and chemokines were highly expressed in AH, including IL-2, IL-32, CXC3R1 and CXCL16 in monocytes and NK cells, whereas HLA-DR genes were reduced in monocytes. In addition, we also found altered differentiation of T-helper cells (T_H1 and T_H17), which could further lead to neutrophil recruitment and macrophage activation. Lastly, our results also suggest impaired NK-cell activation and differentiation in AH with reduced gene expression of KLRC2 and increased gene expression of KLRG1. Our findings indicate different mechanisms may be involved in impaired immune and inflammatory responses for the cellular subtypes of the PBMCs in AH.

Gene variants associated with longevity are also associated with protection against cognitive decline, dementia and Alzheimer's disease, suggesting that common physiologic pathways act at the interface of longevity and cognitive function. To test the hypothesis that variants in genes implicated in cognitive function may promote exceptional longevity, we performed a comprehensive 3‐stage study to identify functional longevity‐associated variants in ~700 candidate genes in up to 450 centenarians and 500 controls by target capture sequencing analysis. We found an enrichment of longevity‐associated genes in the nPKC and NF‐κB signaling pathways by gene‐based association analyses. Functional analysis of the top three gene variants (NFKBIA, CLU, PRKCH) suggests that non‐coding variants modulate the expression of cognate genes, thereby reducing signaling through the nPKC and NF‐κB. This matches genetic studies in multiple model organisms, suggesting that the evolutionary conservation of reduced PKC and NF‐κB signaling pathways in exceptional longevity may include humans.

Background: Fibrosis-4 (FIB4) is a recommended noninvasive test to assess hepatic fibrosis among patients with metabolic dysfunction–associated steatotic liver disease (MASLD). Here, we used FIB4 trajectory over time (ie, “slope” of FIB4) as a surrogate marker of liver fibrosis progression and examined if FIB4 slope is associated with clinical and genetic factors among individuals with clinically defined MASLD within the Million Veteran Program Cohort. Methods: In this retrospective cohort study, FIB4 slopes were estimated through linear regression for participants with clinically defined MASLD and FIB4 <2.67 at baseline. FIB4 slope was correlated with demographic parameters and clinical outcomes using logistic regression and Cox proportional hazard models. FIB4 slope as a quantitative phenotype was used in a genome-wide association analysis in ancestry-specific analysis and multiancestry meta-analysis using METAL. Results: FIB4 slopes, generated from 98,361 subjects with MASLD (16,045 African, 74,320 European, and 7996 Hispanic), showed significant associations with sex, ancestry, and cardiometabolic risk factors (p < 0.05). FIB4 slopes also correlated strongly with hepatic outcomes and were independently associated with time to cirrhosis. Five genetic loci showed genome-wide significant associations (p < 5 × 10⁻⁸) with FIB4 slope among European ancestry subjects, including 2 known (PNPLA3 and TM6SF2) and 3 novel loci (TERT 5.1 × 10⁻¹¹; LINC01088, 3.9 × 10⁻⁸; and MRC1, 2.9 × 10⁻⁹). Conclusions: Linear trajectories of FIB4 correlated significantly with time to progression to cirrhosis, with liver-related outcomes among individuals with MASLD and with known and novel genetic loci. FIB4 slope may be useful as a surrogate measure of fibrosis progression.