BackgroundUnruptured intracranial aneurysms (IAs) are typically asymptomatic and undetected except for incidental discovery on imaging. Blood-based diagnostic biomarkers could lead to improvements in IA management. This exploratory study examined circulating neutrophils to determine whether they carry RNA expression signatures of IAs.MethodsBlood samples were collected from patients receiving cerebral angiography. Eleven samples were collected from patients with IAs and 11 from patients without IAs as controls. Samples from the two groups were paired based on demographics and comorbidities. RNA was extracted from isolated neutrophils and subjected to next-generation RNA sequencing to obtain differential expressions for identification of an IA-associated signature. Bioinformatics analyses, including gene set enrichment analysis and Ingenuity Pathway Analysis, were used to investigate the biological function of all differentially expressed transcripts.ResultsTranscriptome profiling identified 258 differentially expressed transcripts in patients with and without IAs. Expression differences were consistent with peripheral neutrophil activation. An IA-associated RNA expression signature was identified in 82 transcripts (p<0.05, fold-change ≥2). This signature was able to separate patients with and without IAs on hierarchical clustering. Furthermore, in an independent, unpaired, replication cohort of patients with IAs (n = 5) and controls (n = 5), the 82 transcripts separated 9 of 10 patients into their respective groups.ConclusionPreliminary findings show that RNA expression from circulating neutrophils carries an IA-associated signature. These findings highlight a potential to use predictive biomarkers from peripheral blood samples to identify patients with IAs.
BackgroundIntracranial aneurysms (IAs) are dangerous because of their potential to rupture and cause deadly subarachnoid hemorrhages. Previously, we found significant RNA expression differences in circulating neutrophils between patients with unruptured IAs and aneurysm-free controls. Searching for circulating biomarkers for unruptured IAs, we tested the feasibility of developing classification algorithms that use neutrophil RNA expression levels from blood samples to predict the presence of an IA.MethodsNeutrophil RNA extracted from blood samples from 40 patients (20 with angiography-confirmed unruptured IA, 20 angiography-confirmed IA-free controls) was subjected to next-generation RNA sequencing to obtain neutrophil transcriptomes. In a randomly-selected training cohort of 30 of the 40 samples (15 with IA, 15 controls), we performed differential expression analysis. Significantly differentially expressed transcripts (false discovery rate < 0.05, fold change ≥ 1.5) were used to construct prediction models for IA using four well-known supervised machine-learning approaches (diagonal linear discriminant analysis, cosine nearest neighbors, nearest shrunken centroids, and support vector machines). These models were tested in a testing cohort of the remaining 10 neutrophil samples from the 40 patients (5 with IA, 5 controls), and model performance was assessed by receiver-operating-characteristic (ROC) curves. Real-time quantitative polymerase chain reaction (PCR) was used to corroborate expression differences of a subset of model transcripts in neutrophil samples from a new, separate validation cohort of 10 patients (5 with IA, 5 controls).ResultsThe training cohort yielded 26 highly significantly differentially expressed neutrophil transcripts. Models using these transcripts identified IA patients in the testing cohort with accuracy ranging from 0.60 to 0.90. The best performing model was the diagonal linear discriminant analysis classifier (area under the ROC curve = 0.80 and accuracy = 0.90). Six of seven differentially expressed genes we tested were confirmed by quantitative PCR using isolated neutrophils from the separate validation cohort.ConclusionsOur findings demonstrate the potential of machine-learning methods to classify IA cases and create predictive models for unruptured IAs using circulating neutrophil transcriptome data. Future studies are needed to replicate these findings in larger cohorts.Electronic supplementary materialThe online version of this article (10.1186/s12967-018-1749-3) contains supplementary material, which is available to authorized users.
Background 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.
Background Intracranial aneurysms (IAs) are dangerous because of their potential to rupture. We previously found significant RNA expression differences in circulating neutrophils between patients with and without unruptured IAs and trained machine learning models to predict presence of IA using 40 neutrophil transcriptomes. Here, we aim to develop a predictive model for unruptured IA using neutrophil transcriptomes from a larger population and more robust machine learning methods. Methods Neutrophil RNA extracted from the blood of 134 patients (55 with IA, 79 IA-free controls) was subjected to next-generation RNA sequencing. In a randomly-selected training cohort (n = 94), the Least Absolute Shrinkage and Selection Operator (LASSO) selected transcripts, from which we constructed prediction models via 4 well-established supervised machine-learning algorithms (K-Nearest Neighbors, Random Forest, and Support Vector Machines with Gaussian and cubic kernels). We tested the models in the remaining samples (n = 40) and assessed model performance by receiver-operating-characteristic (ROC) curves. Real-time quantitative polymerase chain reaction (RT-qPCR) of 9 IA-associated genes was used to verify gene expression in a subset of 49 neutrophil RNA samples. We also examined the potential influence of demographics and comorbidities on model prediction. Results Feature selection using LASSO in the training cohort identified 37 IA-associated transcripts. Models trained using these transcripts had a maximum accuracy of 90% in the testing cohort. The testing performance across all methods had an average area under ROC curve (AUC) = 0.97, an improvement over our previous models. The Random Forest model performed best across both training and testing cohorts. RT-qPCR confirmed expression differences in 7 of 9 genes tested. Gene ontology and IPA network analyses performed on the 37 model genes reflected dysregulated inflammation, cell signaling, and apoptosis processes. In our data, demographics and comorbidities did not affect model performance. Conclusions We improved upon our previous IA prediction models based on circulating neutrophil transcriptomes by increasing sample size and by implementing LASSO and more robust machine learning methods. Future studies are needed to validate these models in larger cohorts and further investigate effect of covariates.
Our findings demonstrate the potential of machine learning approaches for classifying disease states and thus developing sensitive biomarkers that can be used to monitor pulmonary disease activity in CF.
Peripheral blood mononuclear cells (PBMCs) play an important role in the inflammation that accompanies intracranial aneurysm (IA) pathophysiology. We hypothesized that PBMCs have different transcriptional profiles in patients harboring IAs as compared to IA-free controls, which could be the basis for potential blood-based biomarkers for the disease. To test this, we isolated PBMC RNA from whole blood of 52 subjects (24 with IA, 28 without) and performed next-generation RNA sequencing to obtain their transcriptomes. In a randomly assigned discovery cohort of n = 39 patients, we performed differential expression analysis to define an IA-associated signature of 54 genes (q < 0.05 and an absolute fold-change ≥ 1.3). In the withheld validation dataset, these genes could delineate patients with IAs from controls, as the majority of them still had the same direction of expression difference. Bioinformatics analyses by gene ontology enrichment analysis and Ingenuity Pathway Analysis (IPA) demonstrated enrichment of structural regulation processes, intracellular signaling function, regulation of ion transport, and cell adhesion. IPA analysis showed that these processes were likely coordinated through NF-kB, cytokine signaling, growth factors, and TNF activity. Correlation analysis with aneurysm size and risk assessment metrics showed that 4/54 genes were associated with rupture risk. These findings highlight the potential to develop predictive biomarkers from PBMCs to identify patients harboring IAs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.