Development and validation of a machine learning-based framework for assessing metabolic-associated fatty liver disease risk.

BACKGROUND: The existing predictive models for metabolic-associated fatty liver disease (MAFLD) possess certain limitations that render them unsuitable for extensive population-wide screening. This study is founded upon population health examination data and employs a comparison of eight distinct machine learning (ML) algorithms to construct the optimal screening model for identifying high-risk individuals with MAFLD in China. METHODS: We collected physical examination data from 5,171,392 adults residing in the northwestern region of China, during the year 2021. Feature selection was conducted through the utilization of the Least Absolute Shrinkage and Selection Operator (LASSO) regression. Additionally, class balancing parameters were incorporated into the models, accompanied by hyperparameter tuning, to effectively address the challenges posed by imbalanced datasets. This study encompassed the development of both tree-based ML models (including Classification and Regression Trees, Random Forest, Adaptive Boosting, Light Gradient Boosting Machine, Extreme Gradient Boosting, and Categorical Boosting) and alternative ML models (specifically, k-Nearest Neighbors and Artificial Neural Network) for the purpose of identifying individuals with MAFLD. Furthermore, we visualized the importance scores of each feature on the selected model. RESULTS: The average age (standard deviation) of the 5,171,392 participants was 51.12 (15.00) years, with 52.47% of the participants being females. MAFLD was diagnosed by specialized physicians. 20 variables were finally included for analyses after LASSO regression model. Following ten rounds of cross-validation and parameter optimization for each algorithm, the CatBoost algorithm exhibited the best performance, achieving an Area Under the Receiver Operating Characteristic Curve (AUC) of 0.862. The ranking of feature importance indicates that age, BMI, triglyceride, fasting plasma glucose, waist circumference, occupation, high density lipoprotein cholesterol, low density lipoprotein cholesterol, total cholesterol, systolic blood pressure, diastolic blood pressure, ethnicity and cardiovascular diseases are the top 13 crucial factors for MAFLD screening. CONCLUSION: This study utilized a large-scale, multi-ethnic physical examination data from the northwestern region of China to establish a more accurate and effective MAFLD risk screening model, offering a new perspective for the prediction and prevention of MAFLD.

A new neuroprotective candidate TJ1 targeting amyloidogenesis in 5xFAD Alzheimer's disease mice.

As one of the main pathmechanisms of Alzheimer's disease (AD), amyloid-ß (Aß) is widely considered to be the prime target for the development of AD therapy. Recently, imidazolylacetophenone oxime ethers or esters (IOEs) have shown neuroprotective effects against neuronal cells damage, suggesting their potential use in the prevention and treatment of AD. Thirty IOEs compounds from our lab in-house library were constructed and screened for the inhibitory effects on Aß42-induced cytotoxicity. Among them, TJ1, as a new IOEs hit, preliminarily showed the effect on inhibiting Aß42-induced cytotoxicity. Furthermore, the inhibitory effects of TJ1 on Aß42 aggregation were tested by ThT assays and TEM. The neuroprotective effects of TJ1 were evaluated in Aß42-stimulated SH-SY5Y cells, LPS-stimulated BV-2 cells, and H2O2- and RSL3-stimulated PC12 cells. The cognitive improvement of TJ1 was assessed in 5xFAD (C57BL/6J) transgenic mouse. These results showed that TJ1 had strong neuroprotective effects and high blood-brain barrier (BBB) permeability without obvious cytotoxicity. TJ1 impeded the self-accumulation process of Aß42 by acting on Aß oligomerization and fibrilization. Besides, TJ1 reversed Aß-, H2O2- and RSL3-induced neuronal cell damage and decreased neuroinflammation. In 5xFAD mice, TJ1 improved cognitive impairment, increased GSH level, reduced the level of Aß42 and Aß plaques, and attenuated the glia reactivation and inflammatory response in the brain,. Taken together, our results demonstrate that TJ1 improves cognitive impairments as a new neuroprotective candidate via targeting amyloidogenesis, which suggests the potential of TJ1 as a treatment for AD.

Herpotrichone A Exerts Neuroprotective Effects by Relieving Ferroptosis.

Inhibition of oxidative stress and ferroptosis is currently considered to be a promising therapeutic approach for neurodegenerative diseases. Herpotrichones, a class of compounds derived from insect symbionts, have shown potential for neuroprotective activity with low toxicity. However, the specific mechanisms through which herpotrichones exert their neuroprotective effects remain to be fully elucidated. In this study, the natural [4 + 2] adducts herpotrichone A (He-A) and its new analogues were isolated from the isopod-associated fungus Herpotrichia sp. SF09 and exhibited significantly protective effects in H2O2-, 6-OHDA-, and RSL3-stimulated PC12 cells and LPS-stimulated BV-2 cells. Moreover, He-A was able to relieve ferroptotic cell death in RSL3-stimulated PC12 cells and 6-OHDA-induced zebrafish larvae. Interestingly, He-A can activate antioxidant elements and modulate the SLC7A11 pathway without capturing oxidic free radical and chelating iron. These findings highlight He-A as a novel hit that protects against ferroptosis-like neuronal damage in the treatment of neurodegenerative diseases.

Accurate prediction of biliary atresia with an integrated model using MMP-7 levels and bile acids.

BACKGROUND: Biliary atresia (BA) is a rare fatal liver disease in children, and the aim of this study was to develop a method to diagnose BA early. METHODS: We determined serum levels of matrix metalloproteinase-7 (MMP-7), the results of 13 liver tests, and the levels of 20 bile acids, and integrated computational models were constructed to diagnose BA. RESULTS: Our findings demonstrated that MMP-7 expression levels, as well as the results of four liver tests and levels of ten bile acids, were significantly different between 86 BA and 59 non-BA patients (P < 0.05). The computational prediction model revealed that MMP-7 levels alone had a higher predictive accuracy [area under the receiver operating characteristic curve (AUC) = 0.966, 95% confidence interval (CI): 0.942, 0.989] than liver test results and bile acid levels. The AUC was 0.890 (95% CI 0.837, 0.943) for liver test results and 0.825 (95% CI 0.758, 0.892) for bile acid levels. Furthermore, bile levels had a higher contribution to enhancing the predictive accuracy of MMP-7 levels (AUC = 0.976, 95% CI 0.953, 1.000) than liver test results. The AUC was 0.983 (95% CI 0.962, 1.000) for MMP-7 levels combined with liver test results and bile acid levels. In addition, we found that MMP-7 levels were highly correlated with gamma-glutamyl transferase levels and the liver fibrosis score. CONCLUSION: The innovative integrated models based on a large number of indicators provide a noninvasive and cost-effective approach for accurately diagnosing BA in children. Video Abstract (MP4 142103 KB).

Measurement of MMP-7 in micro-volume peripheral blood: development of dried blood spot approach.

Purpose: Serum matrix metalloproteinase-7 (MMP-7) is significant in differentiating biliary atresia (BA). This study aims to develop a new peripheral blood quantitative collection device to detect MMP-7 levels via dried blood spot (DBS). Methods: This is a diagnostic accuracy test. Serum and DBS MMP-7 concentrations were measured using an ELISA kit. Intraoperative cholangiography and subsequent histological examinations were used to confirm BA diagnoses. Results: A total of 241 infants with obstructive jaundice were enrolled, among whom 168 were BA. Linear regression showed DBS MMP-7 correlated well with serum MMP-7 (R = 0.93, P < 0.001). The best cut-off value of serum MMP-7 for BA was 25.9 ng/ml, achieving the area under the ROC curve (AUC) of 0.962 (95% CI: 0.941, 0.983), and the sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were 86.9%, 94.5%, 97.3% and 75.8%, respectively. The best cut-off value of DBS MMP-7 for BA was 12.5 ng/ml, achieving the AUC of 0.922 (95% CI: 0.888, 0.956), and the sensitivity, specificity, PPV, and NPV were 86.9%, 89.0%, 94.8%, and 74.7%, respectively. The dried blood spots were intervened under different storage conditions, including 1-5 days at room temperature, 2 or 3 days at 30 °C and 2 or 3 days at 37 °C. The DBS MMP-7 concentration under different storage conditions had good correlation and consistency with that at -80 °C. Conclusions: Serum and DBS MMP-7 correlate well, both of which have high accuracy in the diagnosis of BA, while the requirements for the storage of DBS are low.

Integrated algorithm combining plasma biomarkers and cognitive assessments accurately predicts brain ß-amyloid pathology.

BACKGROUND: Accurate prediction of cerebral amyloidosis with easily available indicators is urgently needed for diagnosis and treatment of Alzheimer's disease (AD). METHODS: We examined plasma Aß42, Aß40, T-tau, P-tau181, and NfL, with APOE genotypes, cognitive test scores and key demographics in a large Chinese cohort (N = 609, aged 40 to 84 years) covering full AD spectrum. Data-driven integrated computational models were developed to predict brain ß-amyloid (Aß) pathology. RESULTS: Our computational models accurately predict brain Aß positivity (area under the ROC curves (AUC) = 0.94). The results are validated in Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. Particularly, the models have the highest prediction power (AUC = 0.97) in mild cognitive impairment (MCI) participants. Three levels of models are designed with different accuracies and complexities. The model which only consists of plasma biomarkers can predict Aß positivity in amnestic MCI (aMCI) patients with AUC = 0.89. Generally the models perform better in participants without comorbidities or family histories. CONCLUSIONS: The innovative integrated models provide opportunity to assess Aß pathology in a non-invasive and cost-effective way, which might facilitate AD-drug development, early screening, clinical diagnosis and prognosis evaluation.

The numbers of people with Alzheimer's disease are increasing. People with Alzheimer's disease have changes in the brain as well as cognitive impairment, which is when a person has difficulty remembering, learning, concentrating, or making decisions. Innovative medicines and new treatments all target people with early Alzheimer's disease. However, the methods used currently to diagnose Alzheimer's disease are expensive and can be unpleasant for patients. We studied Chinese people with no cognitive impairment, some cognitive decline, mild cognitive impairment, Alzheimer's disease and non-Alzheimer's disease dementia. We established a computational model that can predict the changes seen in the brain in people with Alzheimer's disease from information including results of blood and memory tests. This non-invasive and cost-effective approach might improve early identification of those with Alzheimer's disease.

Sleep Parameters and Plasma Biomarkers for Cognitive Impairment Evaluation in Patients With Cerebral Small Vessel Disease.

OBJECTIVES: Cognitive impairment caused by cerebrovascular disease accounts for more than half of vascular dementia. However, neuropsychological tests are limited by their subjectivity. Additional effective approaches to evaluate cognitive impairment in patients with cerebrovascular disease are necessary. METHOD: One hundred and thirty-two patients with cerebrovascular disease were recruited. One hundred participants met the criteria and completed neuropsychological scales. Sixty-nine participants proceeded with polysomnography, and 63 of them had their peripheral blood biomarkers measured. According to Mini-Mental State Examination scores, patients were divided into cognitively impaired and cognitively normal groups. The differences in biomarkers and sleep parameters between the groups were compared, and decision tree models were constructed to evaluate the evaluation ability of these indicators on cognitive decline. RESULTS: The integrated decision tree model of sleep parameters yielded an area under curve (AUC) of 0.952 (95% confidence interval [CI]: 0.911-0.993), while that of plasma biomarkers yielded an AUC of 0.872 (95% CI: 0.810-0.935) in the assessment of cognition status. Then the participants were automatically clustered into mild and severe cognitive impairment groups by multiple neuropsychological test results. The integrated plasma biomarker model showed an AUC of 0.928 (95% CI: 0.88-0.977), and the integrated sleep parameter model showed an AUC of 0.851 (95% CI: 0.783-0.919) in the assessment of mild/severe cognitive impairment. DISCUSSION: Integrated models which consist of sleep parameters and plasma biomarkers can accurately evaluate dementia status and cognitive impairment in patients with cerebral small vessel disease. This innovative study may facilitate drug development, early screening, clinical diagnosis, and prognosis evaluation of the disease.

Systematic evaluation of urinary formic acid as a new potential biomarker for Alzheimer's disease.

Introduction: The accumulation of endogenous formaldehyde is considered a pathogenic factor in Alzheimer's disease (AD). The purpose of this study was to investigate the relationship between urinary formic acid and plasma biomarkers in AD. Materials and methods: Five hundred and seventy-four participants were divided into five groups according to their diagnosis: 71 with normal cognitive (NC), 101 with subjective cognitive decline (SCD), 131 with cognitive impairment without mild cognitive impairment (CINM), 158 with mild cognitive impairment (MCI), and 113 with AD. Results: With the progression of the disease, urinary formic acid levels showed an overall upward trend. Urinary formic acid was significantly correlated with Mini-Mental State Examination (MMSE) scores, the Chinese version of Addenbrooke's Cognitive Examination III (ACE-III) scores, and Montreal Cognitive Assessment-Basic (MoCA-B) time. The areas under the receiver operating characteristic curves (AUC) of urinary formic acid in distinguishing NC from AD was 0.797, which was similar to that of plasma neurofilament light chain (NfL; AUC = 0.768) and better than other plasma biomarkers (Aß40, Aß42, Aß42/Aß40, T-tau, P-tau181, and P-tau181/T-tau). We also found that using urinary formic acid and formaldehyde levels could improve the accuracy of using plasma biomarkers to determine AD disease stage. Discussion: Our study revealed the possibility of urinary formic acid as a potential novel biomarker for the early diagnosis of AD.

Cognitive enhancement and neuroprotective effects of OABL, a sesquiterpene lactone in 5xFAD Alzheimer's disease mice model.

Alzheimer's disease (AD) is a neurodegenerative disease in which oxidative stress and neuroinflammation were demonstrated to be associated with neuronal loss and cognitive deficits. However, there are still no specific treatments that can prevent the progression of AD. In this study, a screening of anti-inflammatory hits from 4207 natural compounds of two different molecular libraries indicated 1,6-O,O-diacetylbritannilactone (OABL), a 1,10-seco-eudesmane sesquiterpene lactone isolated from the herb Inula britannica L., exhibited strong anti-inflammatory activity in vitro as well as favorable BBB penetration property. OABL reduced LPS-induced neuroinflammation in BV-2 microglial cells as assessed by effects on the levels of inflammatory mediators including NO, PGE2, TNF-α, iNOS, and COX-2, as well as the translocation of NF-κB. Besides, OABL also exhibited pronounced neuroprotective effects against oxytosis and ferroptosis in the rat pheochromocytoma PC12 cell line. For in vivo research, OABL (20 mg/kg B.W., i.p.) for 21 d attenuated the impairments in cognitive function observed in 6-month-old 5xFAD mice, as assessed with the Morris water maze test. OABL restored neuronal damage and postsynaptic density protein 95 (PSD95) expression in the hippocampus. OABL also significantly reduced the accumulation of amyloid plaques, the Aß expression, the phosphorylation of Tau protein, and the expression of BACE1 in AD mice brain. In addition, OABL attenuated the overactivation of microglia and astrocytes by suppressing the expressions of inflammatory cytokines, and increased glutathione (GSH) and reduced malondialdehyde (MDA) and super oxide dismutase (SOD) levels in the 5xFAD mice brain. In conclusion, these results highlight the beneficial effects of the natural product OABL as a novel treatment with potential application for drug discovery in AD due to its pharmacological profile.

Construction of MoS2 nanoarrays and MoO3 nanobelts: Two efficient adsorbents for removal of Pb(II), Au(III) and Methylene Blue.

Toxic heavy metal ions, valuable noble metal ions and organic dyes are significant concerns in wastewater treatment. In this work, MoO3 nanobelts (MoO3 NBs) prepared by solvothermal method and MoS2 nanoarrays (MoS2 NAs) constructed using MoO3 NBs precursor were proposed to effectively remove heavy/noble metal ions and organic dyes, such as Pb(II), Au(III) and Methylene Blue (MB). The two adsorbents exhibited the excellent adsorption capacity towards Pb(II), Au(III) and MB. The maximum removal capacity of Pb(II) and MB on MoO3 NBs was 684.93 mg/g and 1408 mg/g, respectively, whereas that of Au(III) and MB on MoS2 NAs was 1280.2 mg/g and 768 mg/g, respectively. Furthermore, the thermodynamic parameters were calculated from the temperature-dependent curves, suggesting that the removal of Pb(II) and Au(III) on both adsorbents was spontaneous and endothermic. The new adsorbents introduced here were high adsorption activity, ease of fabrication, high scalability, good chemical stability, great repeatability and abundant and cheap supply, which were highly attractive for wastewater treatment.

Profiling the genetic determinants of chromatin accessibility with scalable single-cell CRISPR screens.

CRISPR screens have been used to connect genetic perturbations with changes in gene expression and phenotypes. Here we describe a CRISPR-based, single-cell combinatorial indexing assay for transposase-accessible chromatin (CRISPR-sciATAC) to link genetic perturbations to genome-wide chromatin accessibility in a large number of cells. In human myelogenous leukemia cells, we apply CRISPR-sciATAC to target 105 chromatin-related genes, generating chromatin accessibility data for ~30,000 single cells. We correlate the loss of specific chromatin remodelers with changes in accessibility globally and at the binding sites of individual transcription factors (TFs). For example, we show that loss of the H3K27 methyltransferase EZH2 increases accessibility at heterochromatic regions involved in embryonic development and triggers expression of genes in the HOXA and HOXD clusters. At a subset of regulatory sites, we also analyze changes in nucleosome spacing following the loss of chromatin remodelers. CRISPR-sciATAC is a high-throughput, single-cell method for studying the effect of genetic perturbations on chromatin in normal and disease states.