Machine learning analysis of volatolomic profiles in breath can identify non-invasive biomarkers of liver disease: A pilot study.
Ontology highlight
ABSTRACT:
SUBMITTER: Thomas JN
PROVIDER: S-EPMC8631657 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Non-alcoholic fatty liver disease (NAFLD) is a chronic liver disease that presents a great challenge for treatment and prevention.. This study aims to implement a machine learning approach that employs such datasets to identify potential biomarker targets. We developed a pipeline to identify potential biomarkers for NAFLD that includes five major processes, namely, a pre-processing step, a feature selection and a generation of a random forest model and, finally, a downstream feature analysis and a provision of a potential biological interpretation. The pre-processing step includes data normalising and variable extraction accompanied by appropriate annotations. A feature selection based on a differential gene expression analysis is then conducted to identify significant features and then employ them to generate a random forest model whose performance is assessed based on a receiver operating characteristic curve. Next, the features are subjected to a downstream analysis, such as univariate analysis, a pathway enrichment analysis, a network analysis and a generation of correlation plots, boxplots and heatmaps. Once the results are obtained, the biological interpretation and the literature validation is conducted over the identified features and results. We applied this pipeline to transcriptomics and lipidomic datasets and concluded that the C4BPA gene could play a role in the development of NAFLD. The activation of the complement pathway, due to the downregulation of the C4BPA gene, leads to an increase in triglyceride content, which might further render the lipid metabolism. This approach identified the C4BPA gene, an inhibitor of the complement pathway, as a potential biomarker for the development of NAFLD.
| S-EPMC8615894 | biostudies-literature
Project description:Weight gain is a metabolic disorder that often culminates in the development of obesity and other comorbidities such as diabetes. Obesity is characterized by the development of a chronic, subclinical systemic inflammation, and is regarded as a remarkably important factor that contributes to the development of such comorbidities. Therefore, laboratory methods that allow the identification of subjects at higher risk for severe weight-associated morbidity are of utter importance, considering the health, and safety of populations. This contribution analyzed the plasma of 180 Brazilian individuals, equally divided into a eutrophic control group and case group, to assess the presence of biomarkers related to weight gain, aiming at characterizing the phenotype of this population. Samples were analyzed by mass spectrometry and most discriminant features were determined by a machine learning approach using Random Forest algorithm. Five biomarkers related to the pathogenesis and chronicity of inflammation in weight gain were identified. Two metabolites of arachidonic acid were upregulated in the case group, indicating the presence of inflammation, as well as two other molecules related to dysfunctions in the cycle of nitric oxide (NO) and increase in superoxide production. Finally, a fifth case group marker observed in this study may indicate the trigger for diabetes in overweight and obesity individuals. The use of mass spectrometry combined with machine learning analyses to prospect and characterize biomarkers associated with weight gain will pave the way for elucidating potential therapeutic and prognostic targets.
| S-EPMC6993102 | biostudies-literature
Project description:Background & aimsFontan-associated liver disease (FALD) has emerged as an important morbidity following surgical palliation of single ventricle congenital heart disease. In this study, non-invasive biomarkers that may be associated with severity of FALD were explored.MethodsA retrospective cohort of paediatric patients post-Fontan who underwent liver biopsy at a high volume at a paediatric congenital heart disease centre was reviewed.ResultsAmong 106 patients, 66% were male and 69% were Hispanic. The mean age was 14.4 ± 3.5 years, and biopsy was performed 10.8 ± 3.6 years post-Fontan. The mean BMI was 20.8 ± 5 kg/m2, with 27.4% meeting obesity criteria. Bridging fibrosis was observed in 35% of patients, and 10.4% of all patients had superimposed steatosis. Bridging fibrosis was associated with lower platelet counts (168.3 ± 58.4 vs. 203.9 ± 65.8 K/μl for congestive hepatic fibrosis score [CHFS] 0-2b, p = 0.009), higher bilirubin (1.7 ± 2.2 vs. 0.9 ± 0.7 mg/dl, p = 0.0090), higher aspartate aminotransferase-to-platelet ratio index [APRI] and fibrosis-4 [FIB-4] scores (APRI: 0.5 ± 0.3 vs. 0.4 ± 0.1, p <0.01 [AUC: 0.69] and FIB-4: 0.6 ± 0.4 vs. 0.4 ± 0.2, p <0.01 [AUC: 0.69]), and worse overall survival (median 2 years follow-up post-biopsy, p = 0.027). Regression modelling of temporal changes in platelet counts before and after biopsy correlated with fibrosis severity (p = 0.005).ConclusionsIn this large, relatively homogeneous adolescent population in terms of age, ethnicity, and Fontan duration, bridging fibrosis was observed in 35% of patients within the first decade post-Fontan. Bridging fibrosis was associated with worse survival. Changes in platelet counts, even years before biopsy, and APRI/FIB-4 scores had modest discriminatory power in identifying patients with advanced fibrosis. Steatosis may represent an additional risk factor for disease progression in obese patients. Further prospective studies are necessary to develop strategies to screen for FALD in the adolescent population.Lay summaryIn this study, the prevalence of Fontan-associated liver disease (FALD) in the young adult population and clinical variables that may be predictive of fibrosis severity or adverse outcomes were explored. Several lab-based, non-invasive markers of bridging fibrosis in FALD were identified, suggesting that these values may be followed as a prognostic biomarker for FALD progression in the adolescent population.
| S-EPMC8517550 | biostudies-literature
Project description:IntroductionThe search for non-invasive diagnostic methods of lung cancer (LC) has led to new avenues of research, including the exploration of the exhaled breath. Previous studies have shown that LC can, in principle, be detected through exhaled-breath analysis. This study evaluated the potential of exhaled-breath analysis for the distinction of benign and malignant pulmonary nodules (PNs).MethodsBreath samples were taken from 72 patients with PNs in a prospective trial. Profiles of volatile organic compounds were determined by (1) gas chromatography/mass spectrometry (GC-MS) combined with solid-phase microextraction and (2) a chemical nanoarray.ResultsFifty-three PNs were malignant and 19 were benign with similar smoking histories and comorbidities. Nodule size (mean ± SD) was 2.7 ± 1.7 versus 1.6 ± 1.3 cm (p = 0.004), respectively. Within the malignant group, 47 were non-small-cell lung cancer and six were small-cell lung cancer. Thirty patients had early-stage disease and 23 had advanced disease. Gas chromatography/mass spectrometry analysis identified a significantly higher concentration of 1-octene in the breath of LC, and the nanoarray distinguished significantly between benign versus malignant PNs (p < 0.0001; accuracy 88 ± 3%), between adeno- and squamous-cell carcinomas [LINE SEPARATOR](p < 0.0001; 88 ± 3%) and between early stage and advanced disease (p < 0.0001; 88 ± 2%).ConclusionsIn this pilot study, breath analysis discriminated benign from malignant PNs in a high-risk cohort based on LC-related volatile organic compound profiles. Furthermore, it discriminated adeno- and squamous-cell carcinoma and between early versus advanced disease. Further studies are required to validate this noninvasive approach, using a larger cohort of patients with PNs detected by computed tomography.
| S-EPMC3444531 | biostudies-literature
Project description:Diabetic nephropathy (DN), a multifaceted disease with various contributing factors, presents challenges in understanding its underlying causes. Uncovering biomarkers linked to this condition can shed light on its pathogenesis and support the creation of new diagnostic and treatment methods. Gene expression data were sourced from accessible public databases, and Weighted Gene Co-expression Network Analysis (WGCNA)was employed to pinpoint gene co-expression modules relevant to DN. Subsequently, various machine learning techniques, such as random forest, lasso regression algorithm (LASSO), and support vector machine-recursive feature elimination (SVM-REF), were utilized for distinguishing DN cases from controls using the identified gene modules. Additionally, functional enrichment analyses were conducted to explore the biological roles of these genes. Our analysis revealed 131 genes showing distinct expression patterns between controlled and uncontrolled groups. During the integrated WCGNA, we identified 61 co-expressed genes encompassing both categories. The enrichment analysis highlighted involvement in various immune responses and complex activities. Techniques like Random Forest, LASSO, and SVM-REF were applied to pinpoint key hub genes, leading to the identification of VWF and DNASE1L3. In the context of DN, they demonstrated significant consistency in both expression and function. Our research uncovered potential biomarkers for DN through the application of WGCNA and various machine learning methods. The results indicate that 2 central genes could serve as innovative diagnostic indicators and therapeutic targets for this disease. This discovery offers fresh perspectives on the development of DN and could contribute to the advancement of new diagnostic and treatment approaches.
| S-EPMC11309603 | biostudies-literature
Project description:BackgroundKnee osteoarthritis (KOA) is a common degenerative joint disease. In this study, we aimed to identify new biomarkers of KOA to improve the accuracy of diagnosis and treatment.MethodsGSE98918 and GSE51588 were downloaded from the Gene Expression Omnibus database as training sets, with a total of 74 samples. Gene differences were analyzed by Gene Ontology, Kyoto Encyclopedia of Genes and Genomes pathway, and Disease Ontology enrichment analyses for the differentially expressed genes (DEGs), and GSEA enrichment analysis was carried out for the training gene set. Through least absolute shrinkage and selection operator regression analysis, the support vector machine recursive feature elimination algorithm, and gene expression screening, the range of DEGs was further reduced. Immune infiltration analysis was carried out, and the prediction results of the combined biomarker logistic regression model were verified with GSE55457.ResultsIn total, 84 DEGs were identified through differential gene expression analysis. The five biomarkers that were screened further showed significant differences in cartilage, subchondral bone, and synovial tissue. The diagnostic accuracy of the model synthesized using five biomarkers through logistic regression was better than that of a single biomarker and significantly better than that of a single clinical trait.ConclusionsCX3CR1, SLC7A5, ARL4C, TLR7, and MTHFD2 might be used as novel biomarkers to improve the accuracy of KOA disease diagnosis, monitor disease progression, and improve the efficacy of clinical treatment.
| S-EPMC9246600 | biostudies-literature
Project description:Exhaled breath condensate (EBC) analysis is a developing field with tremendous promise to advance personalized, non-invasive health diagnostics as new analytical instrumentation platforms and detection methods are developed. Multiple commercially-available and researcher-built experimental samplers are reported in the literature. However, there is very limited information available to determine an effective breath sampling approach, especially regarding the dependence of breath sample metabolomic content on the collection device design and sampling methodology. This lack of an optimal standard procedure results in a range of reported results that are sometimes contradictory. Here, we present a design of a portable human EBC sampler optimized for collection and preservation of the rich metabolomic content of breath. The performance of the engineered device is compared to two commercially available breath collection devices: the RTube™ and TurboDECCS. A number of design and performance parameters are considered, including: condenser temperature stability during sampling, collection efficiency, condenser material choice, and saliva contamination in the collected breath samples. The significance of the biological content of breath samples, collected with each device, is evaluated with a set of mass spectrometry methods and was the primary factor for evaluating device performance. The design includes an adjustable mass-size threshold for aerodynamic filtering of saliva droplets from the breath flow. Engineering an inexpensive device that allows efficient collection of metalomic-rich breath samples is intended to aid further advancement in the field of breath analysis for non-invasive health diagnostic. EBC sampling from human volunteers was performed under UC Davis IRB protocol 63701-3 (09/30/2014-07/07/2017).
| S-EPMC5447364 | biostudies-literature
Project description:The burden of liver disease in the UK has risen dramatically and there is a need for improved diagnostics.To determine which breath volatiles are associated with the cirrhotic liver and hence diagnostically useful.A two-stage biomarker discovery procedure was used. Alveolar breath samples of 31 patients with cirrhosis and 30 healthy controls were mass spectrometrically analysed and compared (stage 1). 12 of these patients had their breath analysed after liver transplant (stage 2). Five patients were followed longitudinally as in-patients in the post-transplant period.Seven volatiles were elevated in the breath of patients versus controls. Of these, five showed statistically significant decrease post-transplant: limonene, methanol, 2-pentanone, 2-butanone and carbon disulfide. On an individual basis limonene has the best diagnostic capability (the area under a receiver operating characteristic curve (AUROC) is 0.91), but this is improved by combining methanol, 2-pentanone and limonene (AUROC curve 0.95). Following transplant, limonene shows wash-out characteristics.Limonene, methanol and 2-pentanone are breath markers for a cirrhotic liver. This study raises the potential to investigate these volatiles as markers for early-stage liver disease. By monitoring the wash-out of limonene following transplant, graft liver function can be non-invasively assessed.
| S-EPMC4588000 | biostudies-literature
Project description:Screening agrochemicals and pharmaceuticals for potential liver toxicity is required for regulatory approval and is an expensive and time-consuming process. The identification and utilization of early exposure gene signatures and robust predictive models in regulatory toxicity testing has the potential to reduce time and costs substantially. In this study, comparative supervised machine learning approaches were applied to the rat liver TG-GATEs dataset to develop feature selection and predictive testing. We identified ten gene biomarkers using three different feature selection methods that predicted liver necrosis with high specificity and selectivity in an independent validation dataset from the Microarray Quality Control (MAQC)-II study. Nine of the ten genes that were selected with the supervised methods are involved in metabolism and detoxification (Car3, Crat, Cyp39a1, Dcd, Lbp, Scly, Slc23a1, and Tkfc) and transcriptional regulation (Ablim3). Several of these genes are also implicated in liver carcinogenesis, including Crat, Car3 and Slc23a1. Our biomarker gene signature provides high statistical accuracy and a manageable number of genes to study as indicators to potentially accelerate toxicity testing based on their ability to induce liver necrosis and, eventually, liver cancer.
| S-EPMC7645727 | biostudies-literature
Project description:BackgroundImproved detection of hepatocellular carcinoma (HCC) is needed, as current detection methods, such as alpha fetoprotein (AFP) and ultrasound, suffer from poor sensitivity. MicroRNAs (miRNAs) are small, non-coding RNAs that regulate many cellular functions and impact cancer development and progression. Notably, miRNAs are detectable in saliva and have shown potential as non-invasive biomarkers for a number of cancers including breast, oral, and lung cancers. Here, we present, to our knowledge, the first report of salivary miRNAs in HCC and compare these findings to patients with cirrhosis, a high-risk cohort for HCC.MethodsWe performed small RNA sequencing in 20 patients with HCC and 19 with cirrhosis. Eleven patients with HCC had chronic liver disease, and analyses were performed with these samples combined and stratified by the presence of chronic liver disease. P values were adjusted for multiple comparisons using a false discovery rate (FDR) approach and miRNA with FDR P < 0.05 were considered statistically significant. Differential expression of salivary miRNAs was compared to a previously published report of miRNAs in liver tissue of patients with HCC vs cirrhosis. Support vector machines and leave-one-out cross-validation were performed to determine if salivary miRNAs have predictive potential for detecting HCC.ResultsA total of 4,565 precursor and mature miRNAs were detected in saliva and 365 were significantly different between those with HCC compared to cirrhosis (FDR P < 0.05). Interestingly, 283 of these miRNAs were significantly downregulated in patients with HCC. Machine-learning identified a combination of 10 miRNAs and covariates that accurately classified patients with HCC (AUC = 0.87). In addition, we identified three miRNAs that were differentially expressed in HCC saliva samples and in a previously published study of miRNAs in HCC tissue compared to cirrhotic liver tissue.ConclusionsThis study demonstrates, for the first time, that miRNAs relevant to HCC are detectable in saliva, that salivary miRNA signatures show potential to be highly sensitive and specific non-invasive biomarkers of HCC, and that additional studies utilizing larger cohorts are needed.
| S-EPMC8742548 | biostudies-literature