Machine learning reveals serum sphingolipids as cholesterol-independent biomarkers of coronary artery disease

Poss, Annelise M; Maschek, J. Alan; Cox, James E.; Hauner, Benedikt J; Hopkins, Paul N.; Hunt, Steven C.; Holland, William L.; Summers, Scott A.; Playdon, Mary C.

doi:10.1172/jci131838

Cited by 165 publications

(153 citation statements)

References 71 publications

(88 reference statements)

Supporting

Mentioning

146

Contrasting

Unclassified

Order By: Relevance

“…Dots and lines in red represent significant association biomarkers for various conditions including cancer, neurodegenerative, metabolic, autoimmune. and vascular diseases [25,[44][45][46][47][48][49][50]. In the current study, we observed alterations of plasma sphingosine-1-phosphate (S1P) species in a cohort of aged cognitively normal subjects as well as people with vascular cognitive impairment (VCI) and Alzheimer's disease (AD).…”

Section: Discussionmentioning

confidence: 84%

Immunomodulatory sphingosine-1-phosphates as plasma biomarkers of Alzheimer’s disease and vascular cognitive impairment

et al. 2020

View full text Add to dashboard Cite

Background There has been ongoing research impetus to uncover novel blood-based diagnostic and prognostic biomarkers for Alzheimer’s disease (AD), vascular dementia (VaD), and related cerebrovascular disease (CEVD)-associated conditions within the spectrum of vascular cognitive impairment (VCI). Sphingosine-1-phosphates (S1Ps) are signaling lipids which act on the S1PR family of cognate G-protein-coupled receptors and have been shown to modulate neuroinflammation, a process known to be involved in both neurodegenerative and cerebrovascular diseases. However, the status of peripheral S1P in AD and VCI is at present unclear. Methods We obtained baseline bloods from individuals recruited into an ongoing longitudinal cohort study who had normal cognition (N = 80); cognitive impairment, no dementia (N = 160); AD (N = 113); or VaD (N = 31), along with neuroimaging assessments of cerebrovascular diseases. Plasma samples were processed for the measurements of major S1P species: d16:1, d17:1, d18:0, and d18:1, along with pro-inflammatory cytokines interleukin (IL)-6, IL-8, and tumor necrosis factor (TNF). Furthermore, in vitro effects of S1Ps on cytokine expression were also studied in an astrocytoma cell line and in rodent primary astrocytes. Results Of the S1Ps species measured, only d16:1 S1P was significantly reduced in the plasma of VaD, but not AD, patients, while the d18:1 to d16:1 ratios were increased in all cognitive subgroups (CIND, AD, and VaD). Furthermore, d18:1 to d16:1 ratios correlated with levels of IL-6, IL-8, and TNF. In both primary astrocytes and an astroglial cell line, treatment with d16:1 or d18:1 S1P resulted in the upregulation of mRNA transcripts of pro-inflammatory cytokines, with d18:1 showing a stronger effect than d16:1. Interestingly, co-treatment assays showed that the addition of d16:1 reduced the extent of d18:1-mediated gene expression, indicating that d16:1 may function to “fine-tune” the pro-inflammatory effects of d18:1. Conclusion Taken together, our data suggest that plasma d16:1 S1P may be useful as a diagnostic marker for VCI, while the d18:1 to d16:1 S1P ratio is an index of dysregulated S1P-mediated immunomodulation leading to chronic inflammation-associated neurodegeneration and cerebrovascular damage.

show abstract

Section: Discussionmentioning

confidence: 84%

Immunomodulatory sphingosine-1-phosphates as plasma biomarkers of Alzheimer’s disease and vascular cognitive impairment

et al. 2020

View full text Add to dashboard Cite

show abstract

“…A new approach to identify associations between serum ceramides and coronary artery disease (CAD) was introduced by Poss et al ( 50 ). They performed targeted lipidomics on serum samples from individuals with familial CAD ( n = 462) and population-based controls ( n = 212) to study the association between serum sphingolipids and CAD, using unbiased machine learning to find sphingolipids related with CAD.…”

Section: Ceramide Score As the Clinical Solutionmentioning

confidence: 99%

Ceramides and Ceramide Scores: Clinical Applications for Cardiometabolic Risk Stratification

et al. 2020

View full text Add to dashboard Cite

Ceramides are bioactive lipids that have an important role in many cellular functions such as apoptosis and inflammation. During the past decade emerging clinical data have shown that ceramides are not only of great biochemical interest but may also have diagnostic utility. Ceramides have shown independent predictive value for negative cardiovascular outcomes as well as for the onset of type 2 diabetes. Based on abundant published data, risk score using the concentrations of circulating ceramides have been developed and adapted for routine clinical practice. Currently serum ceramides are used clinically as efficient risk stratifiers for primary and secondary prevention of atherosclerotic cardiovascular disease (CVD). A direct cause-effect relationship between CVD and ceramide has not been established to date. As ceramide-specific medications are being developed, conventional strategies such as lipid lowering agents and lifestyle interventions can be used to reduce overall risk. Ceramides can identify a very high-risk coronary heart disease category of patients in need for more intense medical attention, specifically those patients at higher risk as highlighted in the 2019 European Society of Cardiology guidelines for stable chronic coronary syndrome patients. In addition, the ceramide risk score may be used as a decision-making tool in primary prevention patients with moderate CVD risk. Finally, the ceramide risk score may have a unique utility as a motivational tool to increase patient's adherence to medical therapy and lifestyle changes.

show abstract

“…In addition to the intrinsic biological complexity, lack of big cohorts due to limitations in sample gathering or high analytical costs, and intragroup variability of measurements further complicate these studies. In this context, recent works have shown that implementation of artificial intelligence approaches can help to unravel disease-specific markers and pathological mechanisms even in data-limited regimes [48][49][50][51][52]. Therefore, using a novel approach, we have combined metabolomic and proteomic measurements with machine intelligence modeling and synthetic data generation [51,53,54] to identify molecular patterns that can discriminate malignant from benign biliary strictures.…”

Section: Introductionmentioning

confidence: 99%

Pilot Multi-Omic Analysis of Human Bile from Benign and Malignant Biliary Strictures: A Machine-Learning Approach

Urmán

Herranz

Uriarte

et al. 2020

Cancers

View full text Add to dashboard Cite

Cholangiocarcinoma (CCA) and pancreatic adenocarcinoma (PDAC) may lead to the development of extrahepatic obstructive cholestasis. However, biliary stenoses can also be caused by benign conditions, and the identification of their etiology still remains a clinical challenge. We performed metabolomic and proteomic analyses of bile from patients with benign (n = 36) and malignant conditions, CCA (n = 36) or PDAC (n = 57), undergoing endoscopic retrograde cholangiopancreatography with the aim of characterizing bile composition in biliopancreatic disease and identifying biomarkers for the differential diagnosis of biliary strictures. Comprehensive analyses of lipids, bile acids and small molecules were carried out using mass spectrometry (MS) and nuclear magnetic resonance spectroscopy (1H-NMR) in all patients. MS analysis of bile proteome was performed in five patients per group. We implemented artificial intelligence tools for the selection of biomarkers and algorithms with predictive capacity. Our machine-learning pipeline included the generation of synthetic data with properties of real data, the selection of potential biomarkers (metabolites or proteins) and their analysis with neural networks (NN). Selected biomarkers were then validated with real data. We identified panels of lipids (n = 10) and proteins (n = 5) that when analyzed with NN algorithms discriminated between patients with and without cancer with an unprecedented accuracy.

show abstract

Machine learning reveals serum sphingolipids as cholesterol-independent biomarkers of coronary artery disease

Cited by 165 publications

References 71 publications

Immunomodulatory sphingosine-1-phosphates as plasma biomarkers of Alzheimer’s disease and vascular cognitive impairment

Immunomodulatory sphingosine-1-phosphates as plasma biomarkers of Alzheimer’s disease and vascular cognitive impairment

Ceramides and Ceramide Scores: Clinical Applications for Cardiometabolic Risk Stratification

Pilot Multi-Omic Analysis of Human Bile from Benign and Malignant Biliary Strictures: A Machine-Learning Approach

Contact Info

Product

Resources

About