Dataset Information

Discovery of stroke-related blood biomarkers from gene expression network models.

ABSTRACT:

Background

Identifying molecular biomarkers characteristic of ischemic stroke has the potential to aid in distinguishing stroke cases from stroke mimicking symptoms, as well as advancing the understanding of the physiological changes that underlie the body's response to stroke. This study uses machine learning-based analysis of gene co-expression to identify transcription patterns characteristic of patients with acute ischemic stroke.

Methods

Mutual information values for the expression levels among 13,243 quantified transcripts were computed for blood samples from 82 stroke patients and 68 controls to construct a co-expression network of genes (separately) for stroke and control samples. Page rank centrality scores were computed for every gene; a gene's significance in the network was assessed according to the differences in their network's pagerank centrality between stroke and control expression patterns. A hybrid genetic algorithm - support vector machine learning tool was used to classify samples based on gene centrality in order to identify an optimal set of predictor genes for stroke while minimizing the number of genes in the model.

Results

A predictive model with 89.6% accuracy was identified using 6 network-central and differentially expressed genes (ID3, MBTPS1, NOG, SFXN2, BMX, SLC22A1), characterized by large differences in association network connectivity between stroke and control samples. In contrast, classification models based solely on individual genes identified by significant fold-changes in expression level provided lower predictive accuracies: ConclusionsNetwork-based models have the potential to identify a more statistically robust pattern of gene expression typical of acute ischemic stroke and to generate hypotheses about possible interactions among functionally relevant genes, leading to the identification of more informative biomarkers.

SUBMITTER: Theofilatos K

PROVIDER: S-EPMC6686563 | biostudies-literature | 2019 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Discovery of stroke-related blood biomarkers from gene expression network models.

Theofilatos Konstantinos K Korfiati Aigli A Mavroudi Seferina S Cowperthwaite Matthew C MC Shpak Max M

BMC medical genomics 20190807 1

<h4>Background</h4>Identifying molecular biomarkers characteristic of ischemic stroke has the potential to aid in distinguishing stroke cases from stroke mimicking symptoms, as well as advancing the understanding of the physiological changes that underlie the body's response to stroke. This study uses machine learning-based analysis of gene co-expression to identify transcription patterns characteristic of patients with acute ischemic stroke.<h4>Methods</h4>Mutual information values for the expr ...[more]

PMID: 31391037

Similar Datasets

Project description:Background and purposesRecent developments in high-throughput proteomic approach have shown the potential to discover biomarkers for diagnosing acute stroke and to elucidate the pathomechanisms specific to different stroke subtypes. We aimed to determine blood-based protein biomarkers to diagnose total stroke (IS+ICH) from healthy controls, ischemic stroke (IS) from healthy controls, and intracerebral hemorrhage (ICH) from healthy control subjects within 24 h using a discovery-based SWATH-MS proteomic approach.MethodsIn this discovery phase study, serum samples were collected within 24 h from acute stroke (IS & ICH) patients and healthy controls and were subjected to SWATH-MS-based untargeted proteomics. For protein identification, a high-pH fractionated peptide library for human serum proteins (obtained from SCIEX) comprising of 465 proteins was used. Significantly differentially expressed (SDE) proteins were selected using the following criteria: >1.5-fold change for upregulated, < 0.67 for downregulated, p-value < 0.05, and confirmed/tentative selection using Boruta random forest. Protein-protein interaction network analysis and the functional enrichment analysis were conducted using STRING 11 online tool, g:Profiler tool and Cytoscape 3.9.0 software. The statistical analyses were conducted in R version 3.6.2.ResultsOur study included 40 stroke cases (20 IS, 20 ICH) within 24 h and 40 age-, sex-, hypertension-, and diabetes-matched healthy controls. We quantified 375 proteins between the stroke cases and control groups through SWATH-MS analysis. We observed 31 SDE proteins between total stroke and controls, 16 SDE proteins between IS and controls, and 41 SDE proteins between ICH and controls within 24 h. Four proteins [ceruloplasmin, alpha-1-antitrypsin (SERPINA1), von Willebrand factor (vWF), and coagulation factor XIII B chain (F13B)] commonly differentiated total stroke, IS, and ICH from healthy control subjects. The most common significant pathways in stroke cases involved complement and coagulation cascades, platelet degranulation, immune-related processes, acute phase response, lipid-related processes, and pathways related to extracellular space and matrix.ConclusionOur discovery phase study identified potential protein biomarker candidates for the diagnosis of acute stroke and highlighted significant pathways associated with different stroke subtypes. These potential biomarker candidates warrant further validation in future studies with a large cohort of stroke patients to investigate their diagnostic performance.

Dataset Information

Discovery of stroke-related blood biomarkers from gene expression network models.

Background

Methods

Results

Publications

Discovery of stroke-related blood biomarkers from gene expression network models.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets