Blocking of amino acid transporter OsAAP7 promoted tillering and yield by determining basic and neutral amino acids accumulation in rice.

BACKGROUND: Amino acids are not only the main form of N in rice, but also are vital for its growth and development. These processes are facilitated by amino acid transporters within the plant. Despite their significance, only a few AAP amino acid transporters have been reported. RESULTS: In this study, we observed that there were differences in the expression of amino acid transporter OsAAP7 among 521 wild cultivated rice varieties, and it directly negatively correlated with tillering and grain yield per plant. We revealed that OsAAP7 protein was localized to the endoplasmic reticulum and had absorption and transport affinity for amino acids such as phenylalanine (Phe), lysine (Lys), leucine (Leu), and arginine (Arg) using subcellular localization, yeast substrate testing, fluorescent amino acid uptake, and amino acid content determination. Further hydroponic studies showed that exogenous application of amino acids Phe, Lys and Arg inhibited the growth of axillary buds in the overexpression lines, and promoted the elongation of axillary buds in the mutant lines. Finally, RNA-seq analysis showed that the expression patterns of genes related to nitrogen, auxin and cytokinin pathways were changed in axillary buds of OsAAP7 transgenic plants. CONCLUSIONS: This study revealed the gene function of OsAAP7, and found that blocking of amino acid transporter OsAAP7 with CRISPR/Cas9 technology promoted tillering and yield by determining basic and neutral amino acids accumulation in rice.

Nlrp6 protects from corticosterone-induced NSPC ferroptosis by modulating RIG-1/MAVS-mediated mitophagy.

Hippocampal neural stem/progenitor cells (NSPCs) are highly vulnerable to different stress stimuli, resulting in adult neurogenesis decline and eventual cognitive defects. Our previous study demonstrated that NOD-like receptor family pyrin domain-containing 6 (Nlrp6) highly expressed in NSPCs played a critical role in sustaining hippocampal neurogenesis to resist stress-induced depression, but the underlying mechnistms are still unclear. Here, we found that Nlrp6 depletion led to cognitive defects and hippocampal NSPC loss in mice. RNA-sequencing analysis of the primary NSPCs revealed that Nlrp6 deficiency altered gene expression profiles of mitochondrial energy generation and ferroptotic process. Upon siNlrp6 transfection, as well as corticosterone (CORT) exposure, downregulation of Nlrp6 suppressed retinoic acid-inducible gene I (RIG-1)/mitochondrial antiviral signaling proteins (MAVS)-mediated autophagy, but drove NSPC ferroptotic death. More interesting, short chain fatty acids (SCFAs) upregulated Nlrp6 expression and promoted RIG-1/MAVS-mediated mitophagy, preventing CORT-induced NSPC ferroptosis. Our study further demonstrates that Nlrp6 should be a sensor for RIG-1/MAVS-mediated mitophagy and play a critical role in maintain mitochondrial homeostasis of hippocampal NSPCs. These results suggests that Nlrp6 should be a potential drug target to combat neurodegenerative diseases relative with chronic stress.

Strain-Induced Self-Assembly at Interface of Two-Dimensional Heterostructures Boosts CO2 Reduction to Methanol by H2O.

CO2 conversion with pure H2O into CH3OH and O2 driven by solar energy can supply fuels and life-essential substances for extraterrestrial exploration. However, the effective production of CH3OH is significantly challenging. Here we report an organozinc complex/MoS2 heterostructure linked by well-defined zinc-sulfur covalent bonds derived by the structural deformation and intensive coupling of dx2 - y2(Zn)-p(S) orbitals at the interface, resulting in distinctive charge transfer behaviors and excellent redox capabilities as revealed by experimental characterizations and first-principle calculations. The synthesis strategy is further generalized to more organometallic compounds, achieving various heterostructures for CO2 photoreduction. The optimal catalyst delivers a promising CH3OH yield of 2.57 mmol gcat-1 h-1 and selectivity of more than 99.5%. The reverse water gas shift mechanism is identified for methanol formation. Meanwhile, energy-unfavorable adsorption of methanol on MoS2, where the photogenerated holes accumulate, ensures the selective oxidation of water over methanol.

Immunomodulation in non-alcoholic fatty liver disease: exploring mechanisms and applications.

Non-alcoholic fatty liver disease (NAFLD) exhibits increased lipid enrichment in hepatocytes. The spectrum of this disease includes stages such as nonalcoholic simple fatty liver (NAFL), nonalcoholic steatohepatitis (NASH), and liver fibrosis. Changes in lifestyle behaviors have been a major factor contributing to the increased cases of NAFLD patients globally. Therefore, it is imperative to explore the pathogenesis of NAFLD, identify therapeutic targets, and develop new strategies to improve the clinical management of the disease. Immunoregulation is a strategy through which the organism recognizes and eliminates antigenic foreign bodies to maintain physiological homeostasis. In this process, multiple factors, including immune cells, signaling molecules, and cytokines, play a role in governing the evolution of NAFLD. This review seeks to encapsulate the advancements in research regarding immune regulation in NAFLD, spanning from underlying mechanisms to practical applications.

Hepatotoxic of polystyrene microplastics in aged mice: Focus on the role of gastrointestinal transformation and AMPK/FoxO pathway.

Microplastic (MP) toxicity has attracted widespread attention, whereas before triggering hepatotoxicity, ingested MPs first undergo transportation and digestion processes in the gastrointestinal tract, possibly interacting with the gastrointestinal contents (GIC). More alarming is the need for more understanding of how this process may impact the liver health of aged animals. This study selected old mice. Firstly, we incubated polystyrene microplastics (PS-MPs, 1 µm) with GIC extract. The results of SEM/EDS indicated a structural alteration in PS-MPs. Additionally, impurities resembling corona, rich in heteroatoms (O, N, and S), were observed. This resulted in an enhanced aggregating phenomenon of MPs. We conducted a 10-day experiment exposing aged mice to four concentrations of PS-MPs, ranging from 1 × 103 to 1 × 1012 particles/L. Subsequent measurements of tissue pathology and body and organ weights were conducted, revealing alterations in liver structure. In the liver, 12 crucial metabolites were found by LC-MS technology, including purines, lipids, and amino acids. The AMPK/FoxO pathway was enriched, activated, and validated in western blotting results. We also comprehensively examined the innate immune system, inflammatory factors, and oxidative stress indicators. The results indicated decreased C3 levels, stable C4 levels, inflammatory factors (IL-6 and IL-8), and antioxidant enzymes were increased to varying degrees. PS-MPs also caused DNA oxidative damage. These toxic effects exhibited a specific dose dependence. Overall, after the formation of the gastrointestinal corona, PS-MPs subsequently impact various cellular processes, such as cycle arrest (p21), leading to hepatic and health crises in the elderly. The presence of gastrointestinal coronas also underscores the MPs' morphology and characteristics, which should be distinguished after ingestion.

2,2-Dichloroacetamide exposure induces behavior and memory disorders in mice: Detrimental effects of long-term dietary restriction on neurotoxicity.

2, 2-dichloroacetamide (DCAcAm), a nitrogen-containing disinfection byproduct (DBPs), is commonly found in potable water. This study aimed to compare the neurotoxicity of DCAcAm in C57/BL6 mice at both environmentally relevant and higher doses through oral exposure over a 28-day period. Furthermore, the potential effects of dietary restriction (DR) on the cerebral toxicity induced by 20 ppb DCAcAm were examined. The findings indicated that DCAcAm exposure and DR treatment resulted in reduced memory retention and cognitive adaptability in mice. Additionally, higher doses of DCAcAm exposure induced severe brain inflammation and oxidative stress. Metabolic profiling revealed disruptions in fatty acid, energy, and amino acid metabolism in the brain. Remarkably, the negative impacts of 20 ppb DCAcAm on the mice brain were worsened by DR treatment. Analysis of 16S rRNA sequencing revealed notable changes in the composition and structure of intestinal microorganisms after exposure to DCAcAm. This study discovered that DCAcAm has both direct effects on the brain and indirect effects through the microbial-brain-intestinal axis, which collectively result in neurotoxicity and dietary restriction exacerbates these effects. This study provides emerging views on the assessment of the toxicity of nitrogen containing DBPs.

Novel insights into perfluorinated compound-induced hepatotoxicity: Chronic dietary restriction exacerbates the effects of PFBS on hepatic lipid metabolism in mice.

Perfluorobutane sulfonates (PFBS) have garnered extensive utilization because of their distinctive physicochemical properties. The liver acts as a key target organ for toxicity within the body and is vital for regulating metabolic processes, particularly lipid metabolism. However, there is currently a significant research gap regarding the influences of PFBS on hepatic lipid metabolism, especially in individuals with different dietary statuses. Here, the objective of this research was to examine the effects of PFBS on hepatic function under different dietary conditions. The results suggested that the levels of liver injury biomarkers were significantly upregulated, e.g., transaminase (GPT, GOT), while liver lipid levels were downregulated after exposure to PFBS at concentration of 50 µg/L for 42 days. Moreover, restricted diet further intensified the adverse effects of PFBS on the liver. Metabolomics analysis identified significant alterations in lipid-related metabolites in PFBS-induced hepatotoxicity, PFBS exposure induced a decrease in lysophosphatidylethanolamine and lysophosphatidylcholine. PFBS exposure caused an increase in aldosterone and prostaglandin f2alpha under restricted diet. In PFBS treatment group, histidine metabolism, beta-alanine metabolism, and arginine biosynthesis were the main pathway for PFBS toxicity. Aldosterone-regulated sodium reabsorption as a vital factor in inducing PFBS toxicity in the RD-PFBS treatment group. The analysis of 16S rRNA sequencing revealed that exposure to PFBS resulted in imbalance of gut microbial communities. PFBS exposure induced a decrease in Akkermansia and Lactobacillus, but an increase in Enterococcus. PFBS exposure caused the abundance of Lachnospiraceae_NK4A136_group was significantly elevated under restricted diet. Additionally, disruptions in the expression of genes involved in lipid production and consumption may significantly contribute to lipid imbalance in the liver. This study underscores the importance of recognizing the harmful impact of PFBS on liver function, along with the biotoxicity of contaminant influenced by dietary habits.

Intelligent Early Fault Diagnosis of Space Flywheel Rotor System.

Three frequently encountered problems-a variety of fault types, data with insufficient labels, and missing fault types-are the common challenges in the early fault diagnosis of space flywheel rotor systems. Focusing on the above issues, this paper proposes an intelligent early fault diagnosis method based on the multi-channel convolutional neural network with hierarchical branch and similarity clustering (HB-SC-MCCNN). First, a similarity clustering (SC) method is integrated into the parameter-shared dual MCCNN architecture to set up as the basic structural block. The hierarchical branch model and additional loss are then added to SC-MCCNN to form a hierarchical branch network, which simplifies the problem of fault multi-classification into binary classification with multi-steps. Based on the self-learning characteristics of the proposed model, the unlabeled data and the missing fault types in the training set are re-labeled to realize the re-training of the network. The results of the experiments for comparing the abilities between the proposed method and several advanced deep learning models confirm that on the established early fault dataset of the space flywheel rotor system, the proposed method successfully achieves the hierarchical diagnosis and presents stronger competitiveness in the case of insufficient labeled data and missing fault types at the same time.

Adversarial robustness in deep neural networks based on variable attributes of the stochastic ensemble model.

Deep neural networks (DNNs) have been shown to be susceptible to critical vulnerabilities when attacked by adversarial samples. This has prompted the development of attack and defense strategies similar to those used in cyberspace security. The dependence of such strategies on attack and defense mechanisms makes the associated algorithms on both sides appear as closely processes, with the defense method being particularly passive in these processes. Inspired by the dynamic defense approach proposed in cyberspace to address endless arm races, this article defines ensemble quantity, network structure, and smoothing parameters as variable ensemble attributes and proposes a stochastic ensemble strategy based on heterogeneous and redundant sub-models. The proposed method introduces the diversity and randomness characteristic of deep neural networks to alter the fixed correspondence gradient between input and output. The unpredictability and diversity of the gradients make it more difficult for attackers to directly implement white-box attacks, helping to address the extreme transferability and vulnerability of ensemble models under white-box attacks. Experimental comparison of ASR-vs.-distortion curves with different attack scenarios under CIFAR10 preliminarily demonstrates the effectiveness of the proposed method that even the highest-capacity attacker cannot easily outperform the attack success rate associated with the ensemble smoothed model, especially for untargeted attacks.

Suspicious Object Detection for Millimeter-Wave Images With Multi-View Fusion Siamese Network.

Millimeter-wave (MMW) imaging techniques have been widely used in the public security industries for their under-controlled privacy concerns and no health hazards. However, since MMW images are low resolution and most objects are small, reflection-weak, diverse, suspicious object detection in the MMW images is a very challenging task. This paper develops a robust suspicious object detector for the MMW images based on the Siamese network integrated with the pose estimation and image segmentation, which estimates the coordinates of human joints and segments the complete human images into symmetrical body part images. Unlike most existing detectors, which detect and recognize suspicious objects in MMW images and require a complete training set with correct annotations, our proposed model aims to learn the similarity between two symmetrical human body part images segmented from the complete MMW images. Furthermore, to decrease the misdetection caused by the restricted field of view, we further fuse the multi-view MMW images observed from the same person by designing a decision-level fusion strategy and feature-level fusion strategy based on the attention mechanism. Experimental results on the measured MMW images show that our proposed models have favorable detection accuracy and speed in practical application and thus prove their effectiveness.

A Bioinspired Injectable, Adhesive, and Self-Healing Hydrogel with Dual Hybrid Network for Neural Regeneration after Spinal Cord Injury.

Hydrogel-based regenerated scaffolds show promise as a platform for neural regeneration following spinal cord injury (SCI). Nevertheless, the persistent problem of poor mechanical strength and limited integration with the host tissue still exists. In this study, a bioinspired hydrogel with highly sophisticated features for neural regeneration after SCI is developed. The hydrogel is composed of dihydroxyphenylalanine (DOPA)-grafted chitosan and a designer peptide, offering a unique set of qualities such as being injectable, having self-healing abilities, and adhering to tissues. Compared to conventional hydrogels, this hydrogel ensures a significant promotion of immune response modulation and axon regrowth while featuring synapse formation of various neurotransmitters and myelin regeneration. Subsequently, functional recoveries are enhanced, including motor function, sensory function, and particularly bladder defect repair. These positive findings demonstrate that the hydrogel has great potential as a strategy for repairing SCI. Moreover, the versatility of this strategy goes beyond neural regeneration and holds promise for tissue regeneration in other contexts. Overall, this proposed hydrogel represents an innovative and multifaceted tool for engineering structures in the biomedical field.

Dual Atom Catalysts for Energy and Environmental Applications.

The pursuit of high metal utilization in heterogeneous catalysis has triggered the burgeoning interest of various atomically dispersed catalysts. Our aim in this review is to assess key recent findings in the synthesis, characterization, structure-property relationship and computational studies of dual-atom catalysts (DACs), which cover the full spectrum of applications in thermocatalysis, electrocatalysis and photocatalysis. In particular, combination of qualitative and quantitative characterization with cooperation with DFT insights, synergies and superiorities of DACs compare to counterparts, high-throughput catalyst exploration and screening with machine-learning algorithms are highlighted. Undoubtably, it would be wise to expect more fascinating developments in the field of DACs as tunable catalysts.

Cooperative assembly of a designer peptide and silk fibroin into hybrid nanofiber gels for neural regeneration after spinal cord injury.

Local reconstruction of a permissive environment with biomaterials is a promising strategy to treat spinal cord injury (SCI). We reported a hybrid hydrogel fabricated from a small functional self-assembling peptide (F-SAP) and large silk fibroin (SF). The diffusion of SF micelles into F-SAP solution was driven by the dynamic synergy between osmotic pressure and F-SAP/SF electrostatic interactions, resulting in the rearrangement of SF micelles and the formation of rod-like filaments with axes nearly perpendicular to F-SAP nanofibers. Spectroscopy analysis, including circular dichroism, Raman and fluorescence, indicated conformation changes of SF from random coil to ß sheet, which contributed to enhanced mechanical properties of the resultant hybrid hydrogel. Furthermore, the F-SAP/SF hybrid hydrogel coupled with controlled release of NT-3 provided a permissive environment for neural regeneration by providing nanofibrous substrates for regenerating axons, inflammatory modulation and remyelination, consequently resulting in improved locomotion and electrophysiological properties. This hydrogel could be used as a long-term stent in vivo for the treatment of SCI.

Emvirus: An embedding-based neural framework for human-virus protein-protein interactions prediction.

Human-virus protein-protein interactions (PPIs) play critical roles in viral infection. For example, the spike protein of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) binds primarily to human angiotensin-converting enzyme 2 (ACE2) protein to infect human cells. Thus, identifying and blocking these PPIs contribute to controlling and preventing viruses. However, wet-lab experiment-based identification of human-virus PPIs is usually expensive, labor-intensive, and time-consuming, which presents the need for computational methods. Many machine-learning methods have been proposed recently and achieved good results in predicting human-virus PPIs. However, most methods are based on protein sequence features and apply manually extracted features, such as statistical characteristics, phylogenetic profiles, and physicochemical properties. In this work, we present an embedding-based neural framework with convolutional neural network (CNN) and bi-directional long short-term memory unit (Bi-LSTM) architecture, named Emvirus, to predict human-virus PPIs (including human-SARS-CoV-2 PPIs). In addition, we conduct cross-viral experiments to explore the generalization ability of Emvirus. Compared to other feature extraction methods, Emvirus achieves better prediction accuracy.

Assessment of DNA mutagenicity induced by He-Ne laser using Salmonella typhimurium strains.

Helium-neon (He-Ne) laser mutagenesis is widely used in microbiology and plant breeding. In this study, two frameshift mutant representative strains of Salmonella typhimurium TA97a and TA98 and two base pair substitution types TA100 and TA102 were employed as model microorganisms to assess DNA mutagenicity induced by He-Ne laser (3 J·cm-2·s-1, 632.8 nm) for 10, 20, and 30 min. The results revealed that the optimal laser application was 6 h in the mid-logarithmic growth stage. Low-power He-Ne laser for short treatment inhibited cell growth, and continued treatment stimulated the metabolism. The effects of the laser on TA98 and TA100 were the most prominent. Sequencing results from 1500 TA98 revertants showed that there were 88 insertion and deletion (InDel) types in the hisD3052 gene, of which the InDels unique to laser were 21 more than that of the control. Sequencing results from 760 TA100 revertants indicated that laser treatment created Pro (CCC) in the product of the hisG46 gene more likely to be replaced by His (CAC) or Ser (TCC) than by Leu (CTC). Two unique non-classical base substitutions, CCC → TAC and CCC → CAA, also appeared in the laser group. These findings will provide a theoretical basis for further exploration of laser mutagenesis breeding. KEY POINTS: • Salmonella typhimurium served as model organism for laser mutagenesis study. • Laser promoted the occurrence of InDels in the hisD3052 gene of TA98. • Laser promoted the occurrence of base substitution in the hisG46 gene of TA100.

Atomically Dispersed Electron Traps in Cu Doped BiOBr Boosting CO2 Reduction to Methanol by Pure H2 O.

Overall photocatalytic conversion of CO2 and pure H2 O driven by solar irradiation into methanol provides a sustainable approach for extraterrestrial synthesis. However, few photocatalysts exhibit efficient production of CH3 OH. Here, BiOBr nanosheets supporting atomic Cu catalysts for CO2 reduction are reported. The investigation of charge dynamics demonstrates a strong built-in electric field established by isolated Cu sites as electron traps to facilitate charge transfer and stabilize charge carriers. As result, the catalysts exhibit a substantially high catalytic performance with methanol productivity of 627.66 µmol gcatal -1 h-1 and selectivity of ≈90% with an apparent quantum efficiency of 12.23%. Mechanism studies reveal that the high selectivity of methanol can be ascribed to energy-favorable hydrogenation of *CO intermediate giving rise to *CHO. The unfavorable adsorption on Cu1 @BiOBr prevents methanol from being oxidized by photogenerated holes. This work highlights the great potential of single-atom photocatalysts in chemical transformation and energy storage reactions.

Studies on ultrasound-mediated insertion-deletion polymorphisms of DNA and underlying mechanisms based on Ames tester strains.

Low-lethality ultrasound technology has received more and more attention in regulating microorganisms of fermentation industry. Herein, two representative Ames tester strains TA97a and TA98 as model organisms were used to explore the effects of ultrasound on insertion-deletion (InDel) polymorphisms of microbial DNA and its underlying mechanisms. Results revealed that a promotion was observed in the reversion mutation of TA98 upon sonication. Sequencing results from 1752 TA98 revertants showed that there was a total of 127 InDels, of which the InDels unique to ultrasound were 36 more than that of the control. Compared with the control, ultrasound-mediated InDels of DNA displayed additional -29 bp deletion and +7 âˆ¼ +43 bp insertions of direct repeat sequences. Combined with the analysis of transcriptomics and prediction of secondary structure of single-stranded DNA from InDels core region (No. 832 âˆ¼ 915 bp) in hisD3052 gene of TA98 strain, ultrasound-mediated "thermal breathing" mechanism was proposed based on the formation of DNA hairpin structure with micro-homologous sequence. This finding implied that low-intensity ultrasound is expected to be developed a new low-lethal mutagenic technology for continuous mutagenesis.

Nexuses Between the Chemical Design and Performance of Small Molecule Dopant-Free Hole Transporting Materials in Perovskite Solar Cells.

Perovskite solar cells (PSCs) have grabbed much attention of researchers owing to their quick rise in power conversion efficiency (PCE). However, long-term stability remains a hurdle in commercialization, partly due to the inclusion of necessary hygroscopic dopants in hole transporting materials, enhancing the complexity and total cost. Generally, the efforts in designing dopant-free hole transporting materials (HTMs) are devoted toward small molecule and polymeric HTMs, where small molecule based HTMs (SM-HTMs) are dominant due to their reproducibility, facile synthesis, and low cost. Still, the state-of-art dopant-free SM-HTM has not been achieved yet, mainly because of the knowledge gap between device engineering and molecular designs. From a molecular engineering perspective, this article reviews dopant-free SM-HTMs for PSCs, outlining analyses of chemical structures with promising properties toward achieving effective, low-cost, and scalable materials for devices with higher stability. Finally, an outlook of dopant-free SM-HTMs toward commercial application and insight into the development of long-term stability PSCs devices is provided.

A portable analog front-end system for label-free sensing of proteins using nanowell array impedance sensors.

Proteins are useful biomarkers for a wide range of applications such as cancer detection, discovery of vaccines, and determining exposure to viruses and pathogens. Here, we present a low-noise front-end analog circuit interface towards development of a portable readout system for the label-free sensing of proteins using Nanowell array impedance sensing with a form factor of approximately 35cm2. The electronic interface consists of a low-noise lock-in amplifier enabling reliable detection of changes in impedance as low as 0.1% and thus detection of proteins down to the picoMolar level. The sensitivity of our system is comparable to that of a commercial bench-top impedance spectroscope when using the same sensors. The aim of this work is to demonstrate the potential of using impedance sensing as a portable, low-cost, and reliable method of detecting proteins, thus inching us closer to a Point-of-Care (POC) personalized health monitoring system. We have demonstrated the utility of our system to detect antibodies at various concentrations and protein (45 pM IL-6) in PBS, however, our system has the capability to be used for assaying various biomarkers including proteins, cytokines, virus molecules and antibodies in a portable setting.

Development of Machine Learning Tools for Predicting Coronary Artery Disease in the Chinese Population.

Purpose: Coronary artery disease (CAD) is one of the major cardiovascular diseases and the leading cause of death globally. Blood lipid profile is associated with CAD early risk. Therefore, we aim to establish machine learning models utilizing blood lipid profile to predict CAD risk. Methods: In this study, 193 non-CAD controls and 2001 newly-diagnosed CAD patients (1647 CAD patients who received lipid-lowering therapy and 354 who did not) were recruited. Clinical data and the result of routine blood lipids tests were collected. Moreover, low-density lipoprotein cholesterol (LDL-C) subfractions (LDLC-1 to LDLC-7) were classified and quantified using the Lipoprint system. Six predictive models (k-nearest neighbor classifier (KNN), logistic regression (LR), support vector machine (SVM), decision tree (DT), multilayer perceptron (MLP), and extreme gradient boosting (XGBoost)) were established and evaluated by the confusion matrix, area under the receiver operating characteristic (ROC) curve (AUC), recall (sensitivity), accuracy, precision, and F1 score. The selected features were analyzed and ranked. Results: While predicting the CAD development risk of the CAD patients without lipid-lowering therapy in the test set, all models obtained AUC values above 0.94, and the accuracy, precision, recall, and F1 score were above 0.84, 0.85, 0.92, and 0.88, respectively. While predicting the CAD development risk of all CAD patients in the test set, all models obtained AUC values above 0.91, and the accuracy, precision, recall, and F1 score were above 0.87, 0.94, 0.87, and 0.92, respectively. Importantly, small dense LDL-C (sdLDL-C) and LDLC-4 play pivotal roles in predicting CAD risk. Conclusions: In the present study, machine learning tools combining both clinical data and blood lipid profile showed excellent overall predictive power. It suggests that machine learning tools are suitable for predicting the risk of CAD development in the near future.