Differentiating between liver diseases by applying multiclass machine learning approaches to transcriptomics of liver tissue or blood-based samples

Alterations in the hepatic microenvironment following direct-acting antiviral therapy for chronic hepatitis C

Background and aims. The first direct-acting antivirals (DAAs) to treat the viral hepatitis C (HCV) became available in 2011. Despite numerous clinical studies of patient outcomes after treatment, few have evaluated changes in the liver microenvironment. Despite achieving sustained virologic response (SVR), patients may still experience adverse outcomes like cirrhosis and hepatocellular carcinoma. By comparing gene and protein expression in liver biopsies collected before and after treatment, we sought to determine whether specific signatures correlated with disease progression and adverse clinical outcomes. Methods. Biopsies were collected from 22 patients before and after DAA treatment. We measured ∼770 genes and used multispectral imaging with custom machine learning algorithms to analyze phenotypes of intrahepatic macrophages (CD68, CD14, CD16, MAC387, CD163) and T cells (CD3, CD4, CD8, CD45, FoxP3). Results. Before DAA treatment, patients showed two distinct gene expression patterns: one with high pro-inflammatory and antiviral gene expression and another with weaker expression. Patients with adverse outcomes exhibited significantly (p<0.05) more inflammatory activity and had more advanced fibrosis stages in their baseline biopsies than those with liver disease resolution. Patients who achieved SVR had significantly decreased liver enzymes, reduced inflammatory scores, and restored type 1 interferon pathways similar to controls. However, after DAA treatment, patients with persistently high gene expression (67%, pre-hot) still had significantly worse outcomes (p<0.049) despite achieving SVR. A persistent lymphocytic infiltrate was observed in a subset of these patients (76.5%). After therapy, anti-inflammatory macrophages (CD16+, CD16+CD163+, CD16+CD68+) increased, and T cell heterogeneity was more pronounced, showing a predominance of helper and memory T cells (CD3+CD45RO+, CD4+CD45RO+, CD3+CD4+CD45RO+). Conclusions. Patients who have more inflamed livers and more advanced fibrosis before DAA treatment should be closely followed for the development of adverse outcomes, even after achieving SVR. We can enhance patient risk stratification by integrating gene and protein expression profiles with clinical data. This could identify those who may benefit from more intensive monitoring or alternative therapeutic approaches, inspiring a new era of personalized patient care.

Lay Summary

Direct-acting antiviral (DAA) therapy has dramatically improved the treatment of chronic HCV, making it curable for most people. This study determined gene and protein expression differences in the liver before and after treatment of HCV. These results will lead to a deeper understanding of the changes in the hepatic immune microenvironment with and without the virus present in the liver in hopes of improving patient surveillance, prognosis, and outcome in the future.

Insights into ALD and AUD diagnosis and prognosis: Exploring AI and multimodal data streams

The rapid evolution of artificial intelligence and the widespread embrace of digital technologies have ushered in a new era of clinical research and practice in hepatology. Although its potential is far from realization, these significant strides have generated new opportunities to address existing gaps in the delivery of care for patients with liver disease. In this review, we discuss how artificial intelligence and opportunities for multimodal data integration can improve the diagnosis, prognosis, and management of alcohol-associated liver disease. An emphasis is made on how these approaches will also benefit the detection and management of alcohol use disorder. Our discussion encompasses challenges and limitations, concluding with a glimpse into the promising future of these advancements.

Alcohol-associated liver disease

Alcohol-associated liver disease (ALD) is a major cause of chronic liver disease worldwide, and comprises a spectrum of several different disorders, including simple steatosis, steatohepatitis, cirrhosis, and superimposed hepatocellular carcinoma. Although tremendous progress has been made in the field of ALD over the last 20 years, the pathogenesis of ALD remains obscure, and there are currently no FDA-approved drugs for the treatment of ALD. In this Review, we discuss new insights into the pathogenesis and therapeutic targets of ALD, utilizing the study of multiomics and other cutting-edge approaches. The potential translation of these studies into clinical practice and therapy is deliberated. We also discuss preclinical models of ALD, interplay of ALD and metabolic dysfunction, alcohol-associated liver cancer, the heterogeneity of ALD, and some potential translational research prospects for ALD.

Identification of integrated proteomics and transcriptomics signature of alcohol-associated liver disease using machine learning

Distinguishing between alcohol-associated hepatitis (AH) and alcohol-associated cirrhosis (AC) remains a diagnostic challenge. In this study, we used machine learning with transcriptomics and proteomics data from liver tissue and peripheral mononuclear blood cells (PBMCs) to classify patients with alcohol-associated liver disease. The conditions in the study were AH, AC, and healthy controls. We processed 98 PBMC RNAseq samples, 55 PBMC proteomic samples, 48 liver RNAseq samples, and 53 liver proteomic samples. First, we built separate classification and feature selection pipelines for transcriptomics and proteomics data. The liver tissue models were validated in independent liver tissue datasets. Next, we built integrated gene and protein expression models that allowed us to identify combined gene-protein biomarker panels. For liver tissue, we attained 90% nested-cross validation accuracy in our dataset and 82% accuracy in the independent validation dataset using transcriptomic data. We attained 100% nested-cross validation accuracy in our dataset and 61% accuracy in the independent validation dataset using proteomic data. For PBMCs, we attained 83% and 89% accuracy with transcriptomic and proteomic data, respectively. The integration of the two data types resulted in improved classification accuracy for PBMCs, but not liver tissue. We also identified the following gene-protein matches within the gene-protein biomarker panels: CLEC4M-CLC4M, GSTA1-GSTA2 for liver tissue and SELENBP1-SBP1 for PBMCs. In this study, machine learning models had high classification accuracy for both transcriptomics and proteomics data, across liver tissue and PBMCs. The integration of transcriptomics and proteomics into a multi-omics model yielded improvement in classification accuracy for the PBMC data. The set of integrated gene-protein biomarkers for PBMCs show promise toward developing a liquid biopsy for alcohol-associated liver disease.

Microbiome and Metabolomics in Liver Cancer: Scientific Technology

Primary liver cancer is a heterogeneous disease. Liver cancer metabolism includes both the reprogramming of intracellular metabolism to enable cancer cells to proliferate inappropriately and adapt to the tumor microenvironment and fluctuations in regular tissue metabolism. Currently, metabolomics and metabolite profiling in liver cirrhosis, liver cancer, and hepatocellular carcinoma (HCC) have been in the spotlight in terms of cancer diagnosis, monitoring, and therapy. Metabolomics is the global analysis of small molecules, chemicals, and metabolites. Metabolomics technologies can provide critical information about the liver cancer state. Here, we review how liver cirrhosis, liver cancer, and HCC therapies interact with metabolism at the cellular and systemic levels. An overview of liver metabolomics is provided, with a focus on currently available technologies and how they have been used in clinical and translational research. We also list scalable methods, including chemometrics, followed by pathway processing in liver cancer. We conclude that important drivers of metabolomics science and scientific technologies are novel therapeutic tools and liver cancer biomarker analysis.