Shotgun mass spectrometry-based lipid profiling identifies and distinguishes between chronic inflammatory diseases

Neurolipidomic insights into anxiety disorders: Uncovering lipid dynamics for potential therapeutic advances

Anxiety disorders constitute a spectrum of psychological conditions affecting millions of individuals worldwide, imposing a significant health burden. Historically, the development of anxiolytic medications has been largely focused on neurotransmitter function and modulation. However, in recent years, neurolipids emerged as a prime target for understanding psychiatric pathogenesis and developing novel medications. Neurolipids influence various neural activities such as neurotransmission and cellular functioning, as well as maintaining cell membrane integrity. Therefore, this review aims to elucidate the alterations in neurolipids associated with an anxious mental state and explore their potential as targets of novel anxiolytic medications. Existing evidence tentatively associates dysregulated neurolipid levels with the etiopathology of anxiety disorders. Notably, preclinical investigations suggest that several neurolipids, including endocannabinoids and polyunsaturated fatty acids, may hold promise as potential pharmacological targets. Overall, the current literature tentatively suggests the involvement of lipids in the pathogenesis of anxiety disorders, hinting at potential prospects for future pharmacological interventions.

iLipidome: enhancing statistical power and interpretability using hidden biosynthetic interdependencies in the lipidome

Numerous biological processes and diseases are influenced by lipid composition. Advances in lipidomics are elucidating their roles, but analyzing and interpreting lipidomics data at the systems level remain challenging. To address this, we present iLipidome, a method for analyzing lipidomics data in the context of the lipid biosynthetic network, thus accounting for the interdependence of measured lipids. iLipidome enhances statistical power, enables reliable clustering and lipid enrichment analysis, and links lipidomic changes to their genetic origins. We applied iLipidome to investigate mechanisms driving changes in cellular lipidomes following supplementation of docosahexaenoic acid (DHA) and successfully identified the genetic causes of alterations. We further demonstrated how iLipidome can disclose enzyme-substrate specificity and pinpoint prospective glioblastoma therapeutic targets. Finally, iLipidome enabled us to explore underlying mechanisms of cardiovascular disease and could guide the discovery of early lipid biomarkers. Thus, iLipidome can assist researchers studying the essence of lipidomic data and advance the field of lipid biology.

Systemic lupus in the era of machine learning medicine

Artificial intelligence and machine learning applications are emerging as transformative technologies in medicine. With greater access to a diverse range of big datasets, researchers are turning to these powerful techniques for data analysis. Machine learning can reveal patterns and interactions between variables in large and complex datasets more accurately and efficiently than traditional statistical methods. Machine learning approaches open new possibilities for studying SLE, a multifactorial, highly heterogeneous and complex disease. Here, we discuss how machine learning methods are rapidly being integrated into the field of SLE research. Recent reports have focused on building prediction models and/or identifying novel biomarkers using both supervised and unsupervised techniques for understanding disease pathogenesis, early diagnosis and prognosis of disease. In this review, we will provide an overview of machine learning techniques to discuss current gaps, challenges and opportunities for SLE studies. External validation of most prediction models is still needed before clinical adoption. Utilisation of deep learning models, access to alternative sources of health data and increased awareness of the ethics, governance and regulations surrounding the use of artificial intelligence in medicine will help propel this exciting field forward.

Unraveling lipid and inflammation interplay in cancer, aging and infection for novel theranostic approaches

The synergistic relationships between Cancer, Aging, and Infection, here referred to as the CAIn Triangle, are significant determinants in numerous health maladies and mortality rates. The CAIn-related pathologies exhibit close correlations with each other and share two common underlying factors: persistent inflammation and anomalous lipid concentration profiles in the membranes of affected cells. This study provides a comprehensive evaluation of the most pertinent interconnections within the CAIn Triangle, in addition to examining the relationship between chronic inflammation and specific lipidic compositions in cellular membranes. To tackle the CAIn-associated diseases, a suite of complementary strategies aimed at diagnosis, prevention, and treatment is proffered. Our holistic approach is expected to augment the understanding of the fundamental mechanisms underlying these diseases and highlight the potential of shared features to facilitate the development of novel theranostic strategies.

Machine learning approaches to identify systemic lupus erythematosus in anti-nuclear antibody-positive patients using genomic data and electronic health records

BACKGROUND

Although the 2019 EULAR/ACR classification criteria for systemic lupus erythematosus (SLE) has required at least a positive anti-nuclear antibody (ANA) titer (≥ 1:80), it remains challenging for clinicians to identify patients with SLE. This study aimed to develop a machine learning (ML) approach to assist in the detection of SLE patients using genomic data and electronic health records.

METHODS

Participants with a positive ANA (≥ 1:80) were enrolled from the Taiwan Precision Medicine Initiative cohort. The Taiwan Biobank version 2 array was used to detect single nucleotide polymorphism (SNP) data. Six ML models, Logistic Regression, Random Forest (RF), Support Vector Machine, Light Gradient Boosting Machine, Gradient Tree Boosting, and Extreme Gradient Boosting (XGB), were used to identify SLE patients. The importance of the clinical and genetic features was determined by Shapley Additive Explanation (SHAP) values. A logistic regression model was applied to identify genetic variations associated with SLE in the subset of patients with an ANA equal to or exceeding 1:640.

RESULTS

A total of 946 SLE and 1,892 non-SLE controls were included in this analysis. Among the six ML models, RF and XGB demonstrated superior performance in the differentiation of SLE from non-SLE. The leading features in the SHAP diagram were anti-double strand DNA antibodies, ANA titers, AC4 ANA pattern, polygenic risk scores, complement levels, and SNPs. Additionally, in the subgroup with a high ANA titer (≥ 1:640), six SNPs positively associated with SLE and five SNPs negatively correlated with SLE were discovered.

CONCLUSIONS

ML approaches offer the potential to assist in diagnosing SLE and uncovering novel SNPs in a group of patients with autoimmunity.

Lipid metabolism analysis in esophageal cancer and associated drug discovery

Esophageal cancer is an upper gastrointestinal malignancy with a bleak prognosis. It is still being explored in depth due to its complex molecular mechanisms of occurrence and development. Lipids play a crucial role in cells by participating in energy supply, biofilm formation, and signal transduction processes, and lipid metabolic reprogramming also constitutes a significant characteristic of malignant tumors. More and more studies have found esophageal cancer has obvious lipid metabolism abnormalities throughout its beginning, progress, and treatment resistance. The inhibition of tumor growth and the enhancement of antitumor therapy efficacy can be achieved through the regulation of lipid metabolism. Therefore, we reviewed and analyzed the research results and latest findings for lipid metabolism and associated analysis techniques in esophageal cancer, and comprehensively proved the value of lipid metabolic reprogramming in the evolution and treatment resistance of esophageal cancer, as well as its significance in exploring potential therapeutic targets and biomarkers.

Cholesteryl Hemiazelate Present in Cardiovascular Disease Patients Causes Lysosome Dysfunction in Murine Fibroblasts

There is growing evidence supporting the role of fibroblasts in all stages of atherosclerosis, from the initial phase to fibrous cap and plaque formation. In the arterial wall, as with macrophages and vascular smooth muscle cells, fibroblasts are exposed to a myriad of LDL lipids, including the lipid species formed during the oxidation of their polyunsaturated fatty acids of cholesteryl esters (PUFA-CEs). Recently, our group identified the final oxidation products of the PUFA-CEs, cholesteryl hemiesters (ChE), in tissues from cardiovascular disease patients. Cholesteryl hemiazelate (ChA), the most prevalent lipid of this family, is sufficient to impact lysosome function in macrophages and vascular smooth muscle cells, with consequences for their homeostasis. Here, we show that the lysosomal compartment of ChA-treated fibroblasts also becomes dysfunctional. Indeed, fibroblasts exposed to ChA exhibited a perinuclear accumulation of enlarged lysosomes full of neutral lipids. However, this outcome did not trigger de novo lysosome biogenesis, and only the lysosomal transcription factor E3 (TFE3) was slightly transcriptionally upregulated. As a consequence, autophagy was inhibited, probably via mTORC1 activation, culminating in fibroblasts' apoptosis. Our findings suggest that the impairment of lysosome function and autophagy and the induction of apoptosis in fibroblasts may represent an additional mechanism by which ChA can contribute to the progression of atherosclerosis.

Cholesteryl hemiazelate identified in CVD patients causes in vitro and in vivo inflammation

Oxidation of PUFAs in LDLs trapped in the arterial intima plays a critical role in atherosclerosis. Though there have been many studies on the atherogenicity of oxidized derivatives of PUFA-esters of cholesterol, the effects of cholesteryl hemiesters (ChEs), the oxidation end products of these esters, have not been studied. Through lipidomics analyses, we identified and quantified two ChE types in the plasma of CVD patients and identified four ChE types in human endarterectomy specimens. Cholesteryl hemiazelate (ChA), the ChE of azelaic acid (n-nonane-1,9-dioic acid), was the most prevalent ChE identified in both cases. Importantly, human monocytes, monocyte-derived macrophages, and neutrophils exhibit inflammatory features when exposed to subtoxic concentrations of ChA in vitro. ChA increases the secretion of proinflammatory cytokines such as interleukin-1β and interleukin-6 and modulates the surface-marker profile of monocytes and monocyte-derived macrophage. In vivo, when zebrafish larvae were fed with a ChA-enriched diet, they exhibited neutrophil and macrophage accumulation in the vasculature in a caspase 1- and cathepsin B-dependent manner. ChA also triggered lipid accumulation at the bifurcation sites of the vasculature of the zebrafish larvae and negatively impacted their life expectancy. We conclude that ChA behaves as an endogenous damage-associated molecular pattern with inflammatory and proatherogenic properties.

Oxidized cholesteryl ester induces exocytosis of dysfunctional lysosomes in lipidotic macrophages

A key event in atherogenesis is the formation of lipid-loaded macrophages, lipidotic cells, which exhibit irreversible accumulation of undigested modified low-density lipoproteins (LDL) in lysosomes. This event culminates in the loss of cell homeostasis, inflammation, and cell death. Nevertheless, the exact chemical etiology of atherogenesis and the molecular and cellular mechanisms responsible for the impairment of lysosome function in plaque macrophages are still unknown. Here, we demonstrate that macrophages exposed to cholesteryl hemiazelate (ChA), one of the most prevalent products of LDL-derived cholesteryl ester oxidation, exhibit enlarged peripheral dysfunctional lysosomes full of undigested ChA and neutral lipids. Both lysosome area and accumulation of neutral lipids are partially irreversible. Interestingly, the dysfunctional peripheral lysosomes are more prone to fuse with the plasma membrane, secreting their undigested luminal content into the extracellular milieu with potential consequences for the pathology. We further demonstrate that this phenotype is mechanistically linked to the nuclear translocation of the MiT/TFE family of transcription factors. The induction of lysosome biogenesis by ChA appears to partially protect macrophages from lipid-induced cytotoxicity. In sum, our data show that ChA is involved in the etiology of lysosome dysfunction and promotes the exocytosis of these organelles. This latter event is a new mechanism that may be important in the pathogenesis of atherosclerosis.

Application of Machine Learning Models in Systemic Lupus Erythematosus

Systemic Lupus Erythematosus (SLE) is a systemic autoimmune disease and is extremely heterogeneous in terms of immunological features and clinical manifestations. This complexity could result in a delay in the diagnosis and treatment introduction, with impacts on long-term outcomes. In this view, the application of innovative tools, such as machine learning models (MLMs), could be useful. Thus, the purpose of the present review is to provide the reader with information about the possible application of artificial intelligence in SLE patients from a medical perspective. To summarize, several studies have applied MLMs in large cohorts in different disease-related fields. In particular, the majority of studies focused on diagnosis and pathogenesis, disease-related manifestations, in particular Lupus Nephritis, outcomes and treatment. Nonetheless, some studies focused on peculiar features, such as pregnancy and quality of life. The review of published data demonstrated the proposal of several models with good performance, suggesting the possible application of MLMs in the SLE scenario.

Machine Learning for Diagnosis of Systemic Lupus Erythematosus: A Systematic Review and Meta-Analysis

Background

Application of machine learning (ML) for identification of systemic lupus erythematosus (SLE) has been recently drawing increasing attention, while there is still lack of evidence-based support.

Methods

Systematic review and meta-analysis are conducted to evaluate its diagnostic accuracy and application prospect. PubMed, Embase, Cochrane Library, and Web of Science libraries are searched, in combination with manual searching and literature retrospection, for studies regarding machine learning for identifying SLE and neuropsychiatric systemic lupus erythematosus (NPSLE). Quality Assessment of Diagnostic Accuracy Studies (QUADA-2) is applied to assess the quality of included studies. Diagnostic accuracy of the SLE model and NPSLE model is assessed using the bivariate fixed-effect model, and the data are pooled. Summary receiver operator characteristic curve (SROC) is plotted, and area under the curve (AUC) is calculated.

Results

Eighteen (18) studies are included, in which ten (10) focused on SLE and eight (8) on NPSLE. The AUC of SLE identification is 0.95, the sensitivity is 0.90, the specificity is 0.89, the PLR is 8.4, the NLR is 0.12, and the DOR is 73. AUC of NPSLE identification is 0.89, the sensitivity is 0.83, the specificity is 0.83, the PLR is 5.0, the NLR is 0.20, and the DOR is 25.

Conclusion

Machine learning presented remarkable performance in identification of SLE and NPSLE. Based on the convenience for inclusion factor collection and non-invasiveness of detection, machine learning is expected to be widely applied in clinical practice to assist medical decision making.

Recent advances in the use of machine learning and artificial intelligence to improve diagnosis, predict flares, and enrich clinical trials in lupus

PURPOSE OF REVIEW

Machine learning is a computational tool that is increasingly used for the analysis of medical data and has provided the promise of more personalized care.

RECENT FINDINGS

The frequency with which machine learning analytics are reported in lupus research is comparable with that of rheumatoid arthritis and cancer, yet the clinical application of these computational tools has yet to be translated into better care. Considerable work has been applied to the development of machine learning models for lupus diagnosis, flare prediction, and classification of disease using histology or other medical images, yet few models have been tested in external datasets and independent centers. Application of machine learning has yet to be reported for lupus clinical trial enrichment and automated identification of eligible patients. Integration of machine learning into lupus clinical care and clinical trials would benefit from collaborative development between clinicians and data scientists.

SUMMARY

Although the application of machine learning to lupus data is at a nascent stage, initial results suggest a promising future.

Cholesteryl hemiazelate causes lysosome dysfunction impacting vascular smooth muscle cell homeostasis

In atherosclerotic lesions, vascular smooth muscle cells (VSMCs) represent half of the foam cell population, which is characterized by an aberrant accumulation of undigested lipids within lysosomes. Loss of lysosome function impacts VSMC homeostasis and disease progression. Understanding the molecular mechanisms underlying lysosome dysfunction in these cells is, therefore, crucial. We identify cholesteryl hemiazelate (ChA), a stable oxidation end-product of cholesteryl-polyunsaturated fatty acid esters, as an inducer of lysosome malfunction in VSMCs. ChA-treated VSMCs acquire a foam-cell-like phenotype, characterized by enlarged lysosomes full of ChA and neutral lipids. The lysosomes are perinuclear and exhibit degradative capacity and cargo exit defects. Lysosome luminal pH is also altered. Even though the transcriptional response machinery and autophagy are not activated by ChA, the addition of recombinant lysosomal acid lipase (LAL) is able to rescue lysosome dysfunction. ChA significantly affects VSMC proliferation and migration, impacting atherosclerosis. In summary, this work shows that ChA is sufficient to induce lysosomal dysfunction in VSMCs, that, in ChA-treated VSMCs, neither lysosome biogenesis nor autophagy are triggered, and, finally, that recombinant LAL can be a therapeutic approach for lysosomal dysfunction.