In:
PLOS ONE, Public Library of Science (PLoS), Vol. 15, No. 11 ( 2020-11-6), p. e0241838-
Abstract:
The rupture of an intracranial aneurysm (IA) causes devastating subarachnoid hemorrhages, yet most IAs remain undiscovered until they rupture. Recently, we found an IA RNA expression signature of circulating neutrophils, and used transcriptome data to build predictive models for unruptured IAs. In this study, we evaluate the feasibility of using whole blood transcriptomes to predict the presence of unruptured IAs. Methods We subjected RNA from peripheral whole blood of 67 patients (34 with unruptured IA, 33 without IA) to next-generation RNA sequencing. Model genes were identified using the least absolute shrinkage and selection operator (LASSO) in a random training cohort (n = 47). These genes were used to train a Gaussian Support Vector Machine (gSVM) model to distinguish patients with IA. The model was applied to an independent testing cohort (n = 20) to evaluate performance by receiver operating characteristic (ROC) curve. Gene ontology and pathway analyses investigated the underlying biology of the model genes. Results We identified 18 genes that could distinguish IA patients in a training cohort with 85% accuracy. This SVM model also had 85% accuracy in the testing cohort, with an area under the ROC curve of 0.91. Bioinformatics reflected activation and recruitment of leukocytes, activation of macrophages, and inflammatory response, suggesting that the biomarker captures important processes in IA pathogenesis. Conclusions Circulating whole blood transcriptomes can detect the presence of unruptured IAs. Pending additional testing in larger cohorts, this could serve as a foundation to develop a simple blood-based test to facilitate screening and early detection of IAs.
Type of Medium:
Online Resource
ISSN:
1932-6203
DOI:
10.1371/journal.pone.0241838
DOI:
10.1371/journal.pone.0241838.g001
DOI:
10.1371/journal.pone.0241838.g002
DOI:
10.1371/journal.pone.0241838.g003
DOI:
10.1371/journal.pone.0241838.t001
DOI:
10.1371/journal.pone.0241838.t002
DOI:
10.1371/journal.pone.0241838.t003
DOI:
10.1371/journal.pone.0241838.s001
DOI:
10.1371/journal.pone.0241838.s002
DOI:
10.1371/journal.pone.0241838.s003
DOI:
10.1371/journal.pone.0241838.s004
DOI:
10.1371/journal.pone.0241838.s005
DOI:
10.1371/journal.pone.0241838.s006
DOI:
10.1371/journal.pone.0241838.s007
DOI:
10.1371/journal.pone.0241838.r001
DOI:
10.1371/journal.pone.0241838.r002
DOI:
10.1371/journal.pone.0241838.r003
DOI:
10.1371/journal.pone.0241838.r004
Language:
English
Publisher:
Public Library of Science (PLoS)
Publication Date:
2020
detail.hit.zdb_id:
2267670-3
Permalink