Highly Efficient Biosynthesis of Rebaudioside M8 through Structure-Guided Engineering of Glycosyltransferase UGT94E13.

Given the low-calorie, high-sweetness characteristics of steviol glycosides (SGs), developing SGs with improved taste profiles is a key focus. Rebaudioside M8 (Reb M8), a novel non-natural SG derivative obtained through glycosylation at the C-13 position of rebaudioside D (Reb D) using glycosyltransferase UGT94E13, holds promise for further development due to its enhanced sweetness. However, the low catalytic activity of UGT94E13 hampers further research and commercialization. This study aimed to improve the enzymatic activity of UGT94E13 through semirational design, and a variant UGT94E13-F169G/I185G was obtained with the catalytic activity improved by 13.90 times. A cascade reaction involving UGT94E13-F169G/I185G and sucrose synthase AtSuSy was established to recycle uridine diphosphate glucose, resulting in an efficient preparation of Reb M8 with a yield of 98%. Moreover, according to the analysis of the distances between the substrate Reb D and enzymes as well as between Reb D and the glucose donor through molecular dynamics simulations, it is found that the positive effect of shortening the distance on glycosylation reaction activity accounts for the improved catalytic activity of UGT94E13-F169G/I185G. Therefore, this study addresses the bottleneck in the efficient production of Reb M8 and provides a foundation for its widespread application in the food industry.

Lactate transported by MCT1 plays an active role in promoting mitochondrial biogenesis and enhancing TCA flux in skeletal muscle.

Once considered as a "metabolic waste," lactate is now recognized as a major fuel for tricarboxylic acid (TCA) cycle. Our metabolic flux analysis reveals that skeletal muscle mainly uses lactate to fuel TCA cycle. Lactate is transported through the cell membrane via monocarboxylate transporters (MCTs) in which MCT1 is highly expressed in the muscle. We analyzed how MCT1 affects muscle functions using mice with specific deletion of MCT1 in skeletal muscle. MCT1 deletion enhances running performance, increases oxidative fibers while decreasing glycolytic fibers, and enhances flux of glucose to TCA cycle. MCT1 deficiency increases the expression of mitochondrial proteins, augments cell respiration rate, and elevates mitochondrial activity in the muscle. Mechanistically, the protein level of PGC-1α, a master regulator of mitochondrial biogenesis, is elevated upon loss of MCT1 via increases in cellular NAD+ level and SIRT1 activity. Collectively, these results demonstrate that MCT1-mediated lactate shuttle plays a key role in regulating muscle functions by modulating mitochondrial biogenesis and TCA flux.

Identification of JUN gene and cellular microenvironment in response to PD-1 blockade treatment in lung cancer patients via single-cell RNA sequencing.

Exploring the molecular mechanisms of PD-1/PDL-1 blockade for non-small cell lung cancer (NSCLC) would facilitate understanding for tumor microenvironment (TME) and development of individualized medicine. To date, biomarkers of response to PD-1 blockade therapy were still limited. In this study, we hypothesize that cell type in the tumor microenvironment can influence the effect of PD-1 blockade immunotherapy through specific genes. Therefore, we re-analyze the single-cell RNA sequencing data and validation in tissue from lung adenocarcinoma patients. Dynamic changes of cellular subpopulation were observed after anti-PD-1 immunotherapy among TMEs between primary/metastasis or good/poor response patients. Non-exhausted CD8 T cells and dysregulated genes were observed in responsing patients from PD-1 blockade therapy. Among all changed genes, JUN, involved in PD-1 blockade immunotherapy pathway, and could be considered as a PD-1 responsing biomarker.

Development of an on-site diagnostic LAMP assay for rapid differentiation of the invasive pest Phthorimaea absoluta (Meyrick) using insect tissues.

BACKGROUND: The tomato leafminer, Phthorimaea absoluta (Meyrick) (Lepidoptera: Gelechiidae), is a destructive invasive pest that originated in South America and has spread within China since 2017. A rapid method for on-site identification of P. absoluta is urgently needed for interception of this pest across China. RESULTS: We developed a loop-mediated isothermal amplification (LAMP) technique to differentiate P. absoluta from Liriomyza sativae, Chromatomyia horticola, and Phthorimaea operculella using extracted genomic DNA, which was then refined to create an on-site LAMP diagnostic method that can be performed under field conditions without the need for laboratory equipment. CONCLUSION: In the present research, we developed an on-site diagnostic method for rapid differentiation of P. absoluta from other insects with similar morphology or damage characteristics in China. © 2024 Society of Chemical Industry.

One-Step Butadiene Purification in a Sulfonate-Functionalized Metal-Organic Framework through Synergistic Separation Mechanism.

Porous materials that could recognize specific molecules from complex mixtures are of great potential in improving the current energy-intensive multistep separation processes. However, due to the highly similar structures and properties of the mixtures, the design of desired porous materials remains challenging. Herein, a sulfonate-functionalized metal-organic framework ZU-609 with suitable pore size and pore chemistry is designed for 1,3-butadiene (C4H6) purification from complex C4 mixtures. The sulfonate anions decorated in the channel achieve selective recognition of C4H6 from other C4 olefins with subtle polarity differences through C-H⋅⋅⋅O-S interactions, affording recorded C4H6/trans-2-C4H8 selectivity (4.4). Meanwhile, the shrunken mouth of the channel with a suitable pore size (4.6 Å) exhibits exclusion effect to the larger molecules cis-2-C4H8, iso-C4H8, n-C4H10 and iso-C4H10. Benefiting from the moderate C4 olefins binding affinity exhibited by sulfonate anions, the adsorbed C4H6 could be easily regenerated near ambient conditions. Polymer-grade 1,3-butadiene (99.5 %) is firstly obtained from 7-component C4 mixtures via one adsorption-desorption cycle. The work demonstrates the great potential of synergistic recognition of size-sieving and thermodynamically equilibrium in dealing with complex mixtures.

Sulfonate Functional Ultramicroporous Materials with Suitable Pore Size and Layer-Stacked Structure for C4 Olefins Purification.

Selective recognition of 1,3-butadiene from complex olefin isomers is vital for 1,3-butadiene purification, but the lack of porous materials with suitable pore structures results in poor selectivity and low capacity in C4 olefin separation. Herein, two sulfonate-functionalized organic frameworks, ZU-601 and ZU-602, are designed and show impressive separation performance toward C4 olefins. Benefiting from the suitable aperture size caused by the flexibility of coordinated organic ligand, ZU-601, ZU-602 that are pillared with different sulfonate anions could discriminate C4 olefin isomers with high uptake ratio: 1,3-butadiene/1-butene (207), 1,3-butadiene/trans-2-butene (10.1). Meanwhile, their layer-stacked structure enables the utilization of both intra- and interlayer space, enhancing the accommodation of guest molecules. ZU-601 exhibits record high 1,3-butadiene adsorption capacity of 2.90 mmol g-1 (0.5 bar, 298 K) among the reported flexible porous materials with high 1,3-butadiene/1-butene selectivity. The breakthrough experiments confirm their superior separation ability even for all five C4 olefin isomers, and the molecular-level structural change is well elucidated via powder, crystal analysis, and simulation studies. The work provides ideas toward advanced materials design with simultaneous high separation capacity and high separation selectivity for challenging separations.

Selective sorting of hexane isomers by anion-functionalized metal-organic frameworks with optimal energy regulation.

Extensive efforts have been made to improve the separation selectivity of hydrocarbon isomers with nearly distinguishable boiling points; however, how to balance the high regeneration energy consumption remains a daunting challenge. Here we describe the efficient separation of hexane isomers by constructing and exploiting the rotational freedom of organic linkers and inorganic SnF62- anions within adaptive frameworks, and reveal the nature of flexible host-guest interactions to maximize the gas-framework interactions while achieving potential energy storage. This approach enables the discrimination of hexane isomers according to the degree of branching along with high capacity and record mono-/di-branched selectivity (6.97), di-branched isomers selectivity (22.16), and upgrades the gasoline to a maximum RON (Research Octane Number) of 105. Benefitting from the energy regulation of the flexible pore space, the material can be easily regenerated only through a simple vacuum treatment for 15 minutes at 25 °C with no temperature fluctuation, saving almost 45% energy compared to the commercialized zeolite 5 A. This approach could potentially revolutionize the whole scenario of alkane isomer separation processes.

Mitochondrial ATP generation is more proteome efficient than glycolysis.

Metabolic efficiency profoundly influences organismal fitness. Nonphotosynthetic organisms, from yeast to mammals, derive usable energy primarily through glycolysis and respiration. Although respiration is more energy efficient, some cells favor glycolysis even when oxygen is available (aerobic glycolysis, Warburg effect). A leading explanation is that glycolysis is more efficient in terms of ATP production per unit mass of protein (that is, faster). Through quantitative flux analysis and proteomics, we find, however, that mitochondrial respiration is actually more proteome efficient than aerobic glycolysis. This is shown across yeast strains, T cells, cancer cells, and tissues and tumors in vivo. Instead of aerobic glycolysis being valuable for fast ATP production, it correlates with high glycolytic protein expression, which promotes hypoxic growth. Aerobic glycolytic yeasts do not excel at aerobic growth but outgrow respiratory cells during oxygen limitation. We accordingly propose that aerobic glycolysis emerges from cells maintaining a proteome conducive to both aerobic and hypoxic growth.

Ultra-small, low-cost, and simple-to-control PSP projector based on SLCD technology.

Demand for ultra-small, inexpensive, and high-accurate 3D shape measurement devices is growing rapidly, especially in the industrial and consumer electronics sectors. Phase shifting profilometry (PSP) is a powerful candidate due to its advantages of high accuracy, great resolution, and insensitivity to ambient light. As a key component in PSP, the projector used to generate the phase-shifting sinusoidal fringes must be ultra-small (several millimeters), low-cost, and simple to control. However, existing projection methods make it difficult to meet these requirements simultaneously. In this paper, we present a modern technique that can be used to fabricate the desired projector. A specifically designed device based on segmented liquid crystal display (SLCD) technology is used to display the projected patterns, and a cylindrical lens is used as the projection lens. The SLCD device can display four sets of specific filled binary patterns, each yielding a sinusoidal fringe, and all four sinusoidal fringes satisfy the four-step phase shift relation. 3D shape measurement experiments verify the performance of the projector. Considering that the size of SLCD devices can be reduced to a few millimeters, the proposed technique can be easily used to manufacture ultra-small, low-cost, and simple-to-control PSP projectors.

Selective synthesis of rebaudioside M2 through structure-guided engineering of glycosyltransferase UGT94D1.

Rebaudioside M2 (Reb M2), a novel steviol glycoside derivative, has limited industrial applications due to its low synthetic yield and selectivity. Herein, we identify UGT94D1 as a selective glycosyltransferase for rebaudioside D (Reb D), leading to the production of a mono ß-1,6-glycosylated derivative, Reb M2. A variant UGT94D1-F119I/D188P was developed through protein engineering. This mutant exhibited a 6.33-fold improvement in catalytic efficiency, and produced Reb M2 with 92% yield. Moreover, molecular dynamics simulations demonstrated that UGT94D1-F119I/D188P exhibited a shorter distance between the nucleophilic oxygen (OH6) of the substrate Reb D and uridine diphosphate glucose, along with an increased Ophosphate-C1-Oacceptor angle, thus improving the catalytic activity of the enzyme. Therefore, this study provides an efficient method for the selective synthesis of Reb M2 and paves the way for its applications in various fields.

Development of a new cerebral ischemia reperfusion model of Mongolian gerbils and standardized evaluation system.

BACKGROUND: The Mongolian gerbil is an excellent laboratory animal for preparing the cerebral ischemia model due to its inherent deficiency in the circle of Willis. However, the low incidence and unpredictability of symptoms are caused by numerous complex variant types of the circle. Additionally, the lack of an evaluation system for the cerebral ischemia/reperfusion (I/R) model of gerbils has shackled the application of this model. METHODS: We created a symptom-oriented principle and detailed neurobehavioral scoring criteria. At different time points of reperfusion, we analyzed the alteration in locomotion by rotarod test and grip force score, infarct volume by triphenyltetrazolium chloride (TTC) staining, neuron loss using Nissl staining, and histological characteristics using hematoxylin-eosin (H&E) straining. RESULTS: With a successful model rate of 56%, 32 of the 57 gerbils operated by our method harbored typical features of cerebral I/R injury, and the mortality rate in the male gerbils was significantly higher than that in the female gerbils. The successfully prepared I/R gerbils demonstrated a significant reduction in motility and grip strength at 1 day after reperfusion; formed obvious infarction; exhibited typical pathological features, such as tissue edema, neuronal atrophy and death, and vacuolated structures; and were partially recovered with the extension of reperfusion time. CONCLUSION: This study developed a new method for the unilateral common carotid artery ligation I/R model of gerbil and established a standardized evaluation system for this model, which could provide a new cerebral I/R model of gerbils with more practical applications.

Reprogramming neuroblastoma by diet-enhanced polyamine depletion.

Neuroblastoma is a highly lethal childhood tumor derived from differentiation-arrested neural crest cells1,2. Like all cancers, its growth is fueled by metabolites obtained from either circulation or local biosynthesis3,4. Neuroblastomas depend on local polyamine biosynthesis, with the inhibitor difluoromethylornithine showing clinical activity5. Here we show that such inhibition can be augmented by dietary restriction of upstream amino acid substrates, leading to disruption of oncogenic protein translation, tumor differentiation, and profound survival gains in the TH-MYCN mouse model. Specifically, an arginine/proline-free diet decreases the polyamine precursor ornithine and augments tumor polyamine depletion by difluoromethylornithine. This polyamine depletion causes ribosome stalling, unexpectedly specifically at adenosine-ending codons. Such codons are selectively enriched in cell cycle genes and low in neuronal differentiation genes. Thus, impaired translation of these codons, induced by the diet-drug combination, favors a pro-differentiation proteome. These results suggest that the genes of specific cellular programs have evolved hallmark codon usage preferences that enable coherent translational rewiring in response to metabolic stresses, and that this process can be targeted to activate differentiation of pediatric cancers.

A molecular sieve with ultrafast adsorption kinetics for propylene separation.

The design of molecular sieves is vital for gas separation, but it suffers from a long-standing issue of slow adsorption kinetics due to the intrinsic contradiction between molecular sieving and diffusion within restricted nanopores. We report a molecular sieve ZU-609 with local sieving channels that feature molecular sieving gates and rapid diffusion channels. The precise cross-sectional cutoff of molecular sieving gates enables the exclusion of propane from propylene. The coexisting large channels constituted by sulfonic anions and helically arranged metal-organic architectures allow the fast adsorption kinetics of propylene, and the measured propylene diffusion coefficient in ZU-609 is one to two orders of magnitude higher than previous molecular sieves. Propylene with 99.9% purity is obtained through breakthrough experiments with a productivity of 32.2 L kg-1.

Direct prediction of gas adsorption via spatial atom interaction learning.

Physisorption relying on crystalline porous materials offers prospective avenues for sustainable separation processes, greenhouse gas capture, and energy storage. However, the lack of end-to-end deep learning model for adsorption prediction confines the rapid and precise screen of crystalline porous materials. Here, we present DeepSorption, a spatial atom interaction learning network that realizes accurate, fast, and direct structure-adsorption prediction with only information of atomic coordinate and chemical element types. The breakthrough in prediction is attributed to the awareness of global structure and local spatial atom interactions endowed by the developed Matformer, which provides the intuitive visualization of atomic-level thinking and executing trajectory in crystalline porous materials prediction. Complete adsorption curves prediction could be performed using DeepSorption with a higher accuracy than Grand canonical Monte Carlo simulation and other machine learning models, a 20-35% decline in the mean absolute error compared to graph neural network CGCNN and machine learning models based on descriptors. Since the established direct associations between raw structure and target functions are based on the understanding of the fundamental chemistry of interatomic interactions, the deep learning network is rationally universal in predicting the different physicochemical properties of various crystalline materials.

Eflornithine for chemoprevention in the high-risk population of colorectal cancer: a systematic review and meta-analysis with trial sequential analysis.

Objectives: To evaluate the efficacy of Difluoromethylornithine (DFMO) chemoprevention in the high-risk population for colorectal cancer (CRC). Methods: Meta-analysis was conducted to assess the caliber of the included literature by searching five databases for randomized controlled trials of DFMO chemoprevention in the high-risk population of CRC, with RevMan 5.4, Stata 15.0 and TSA 0.9.5.10 employed to statistically analyze the extracted data. Grade profiler 3.6 was employed for grading the evidence for the outcome indicators (disease progression and adenoma incidence). Results: Six trials were finally included in this research, with the collective data indicating that the DFMO combination therapy was efficacious in lowering the incidence of recurrent adenomas in patients who had experienced advanced CRC [RR 0.34, 95% CI 0.14 - 0.83, P < 0.05]. Meta-analysis showed that DFMO combined therapy had no statistical difference in disease progression in patients with familial adenomatous polyposis[RR 0.52, 95% CI 0.14 - 1.86, P > 0.05]; Trial Sequential Analysis reveals that the combination therapy of DFMO effectively diminishes the occurrence of recurrent adenomas in patients with a history of advanced colorectal tumors, displaying a Risk Ratio (RR) of 0.33 with a 95% Confidence Interval (CI) of 0.12 - 0.90 and a significance level of P < 0.05. This combination exhibits a statistically significant difference. Subgroup analysis demonstrates that, depending on the drug treatment regimen (DFMO+ Aspirin/DFMO+ Sulindac), the combination of DFMO and aspirin exhibits an effect comparable to a placebo in diminishing the occurrence of new adenomas in patients with a history of advanced colorectal tumors. However, the combination of DFMO and sulindac significantly mitigates the incidence of recurrent adenomas in this patient population. Conclusion: This meta-analysis indicates that the existing randomized controlled trials are adequate to ascertain the efficacy of DFMO combination therapy in diminishing the incidence of recurrent adenomas in patients who have previously encountered advanced colorectal tumors. However, further clinical trials need to be conducted to evaluate the optimum dosage and treatment course of prophylactic implementation of DFMO combination therapy in high-risk populations.

Activation of the integrated stress response rewires cardiac metabolism in Barth syndrome.

Barth Syndrome (BTHS) is an inherited cardiomyopathy caused by defects in the mitochondrial transacylase TAFAZZIN (Taz), required for the synthesis of the phospholipid cardiolipin. BTHS is characterized by heart failure, increased propensity for arrhythmias and a blunted inotropic reserve. Defects in Ca2+-induced Krebs cycle activation contribute to these functional defects, but despite oxidation of pyridine nucleotides, no oxidative stress developed in the heart. Here, we investigated how retrograde signaling pathways orchestrate metabolic rewiring to compensate for mitochondrial defects. In mice with an inducible knockdown (KD) of TAFAZZIN, and in induced pluripotent stem cell-derived cardiac myocytes, mitochondrial uptake and oxidation of fatty acids was strongly decreased, while glucose uptake was increased. Unbiased transcriptomic analyses revealed that the activation of the eIF2α/ATF4 axis of the integrated stress response upregulates one-carbon metabolism, which diverts glycolytic intermediates towards the biosynthesis of serine and fuels the biosynthesis of glutathione. In addition, strong upregulation of the glutamate/cystine antiporter xCT increases cardiac cystine import required for glutathione synthesis. Increased glutamate uptake facilitates anaplerotic replenishment of the Krebs cycle, sustaining energy production and antioxidative pathways. These data indicate that ATF4-driven rewiring of metabolism compensates for defects in mitochondrial uptake of fatty acids to sustain energy production and antioxidation.

Untargeted Metabolomics Reveals Alterations of Rhythmic Pulmonary Metabolism in IPF.

Idiopathic pulmonary fibrosis (IPF) is a chronic and progressive condition characterized by the impairment of alveolar epithelial cells. Despite continued research efforts, the effective therapeutic medication is still absent due to an incomplete understanding of the underlying etiology. It has been shown that rhythmic alterations are of significant importance in the pathophysiology of IPF. However, a comprehensive understanding of how metabolite level changes with circadian rhythms in individuals with IPF is lacking. Here, we constructed an extensive metabolite database by utilizing an unbiased reference system culturing with 13C or 15N labeled nutrients. Using LC-MS analysis via ESI and APCI ion sources, 1300 potential water-soluble metabolites were characterized and applied to evaluate the metabolic changes with rhythm in the lung from both wild-type mice and mice with IPF. The metabolites, such as glycerophospholipids and amino acids, in WT mice exhibited notable rhythmic oscillations. The concentrations of phospholipids reached the highest during the fast state, while those of amino acids reached their peak during fed state. Similar diurnal variations in the metabolite rhythm of amino acids and phospholipids were also observed in IPF mice. Although the rhythmic oscillation of metabolites in the urea cycle remained unchanged, there was a significant up-regulation in their levels in the lungs of IPF mice. 15N-ammonia in vivo isotope tracing further showed an increase in urea cycle activity in the lungs of mice with IPF, which may compensate for the reduced efficiency of the hepatic urea cycle. In sum, our metabolomics database and method provide evidence of the periodic changes in lung metabolites, thereby offering valuable insights to advance our understanding of metabolic reprogramming in the context of IPF.

DegU-mediated suppression of carbohydrate uptake in Listeria monocytogenes increases adaptation to oxidative stress.

The foodborne bacterial pathogen Listeria monocytogenes exhibits remarkable survival capabilities under challenging conditions, severely threatening food safety and human health. The orphan regulator DegU is a pleiotropic regulator required for bacterial environmental adaptation. However, the specific mechanism of how DegU participates in oxidative stress tolerance remains unknown in L. monocytogenes. In this study, we demonstrate that DegU suppresses carbohydrate uptake under stress conditions by altering global transcriptional profiles, particularly by modulating the transcription of the phosphoenolpyruvate-carbohydrate phosphotransferase system (PTS)-related genes, such as ptsH, ptsI, and hprK. Specifically, in the absence of degU, the transcripts of ptsI are significantly upregulated and those of hprK are significantly downregulated in response to copper ion-induced stress. Overexpression of ptsI significantly increases bacterial growth in vitro, while overexpression of hprK leads to a decrease in growth. We further demonstrate that DegU directly senses oxidative stress, downregulates ptsI transcription, and upregulates hprK transcription. Additionally, through an electrophoretic mobility shift assay, we demonstrate that DegU directly regulates the transcription of ptsI and hprK by binding to specific regions within their respective promoter sequences. Notably, the putative pivotal DegU binding sequence for ptsI is located from 38 to 68 base pairs upstream of the ptsH transcription start site (TSS), whereas for hprK, it is mapped from 36 to 124 base pairs upstream of the hprK TSS. In summary, we elucidate that DegU plays a significant role in suppressing carbohydrate uptake in response to oxidative stress through the direct regulation of ptsI and hprK.ImportanceUnderstanding the adaptive mechanisms employed by Listeria monocytogenes in harsh environments is of great significance. This study focuses on investigating the role of DegU in response to oxidative stress by examining global transcriptional profiles. The results highlight the noteworthy involvement of DegU in this stress response. Specifically, DegU acts as a direct sensor of oxidative stress, leading to the modulation of gene transcription. It downregulates ptsI transcription while it upregulates hprK transcription through direct binding to their promoters. Consequently, these regulatory actions impede bacterial growth, providing a defense mechanism against stress-induced damage. These findings gained from this study may have broader implications, serving as a reference for studying adaptive mechanisms in other pathogenic bacteria and aiding in the development of targeted strategies to control L. monocytogenes and ensure food safety.

Explore public concerns about environmental protection on Sina Weibo: evidence from text mining.

The increasingly serious problem of ecological environmental pollution warns the importance of human environmental protection behavior. However, public attention to environmental protection plays an important role in solving environmental problems. Therefore, in order to explore the environmental concerns of Chinese residents, the trends in time and space, the relationship between online retweets, and the extraction of environmental concerns, this study analyzed the data of Sina Weibo users and their comments on related posts. At the same time, we used the text mining analysis method to analyze the social media text data, and the results are as follows. In that analysis of concern about environmental protection, women show a stronger attitude and willingness to protect the environment than men, and the public in economically developed areas is more concerned. In order to further investigate the public's environmental concerns, this study also utilized the PageRank algorithm to further study the forwarding relationships between users. The study found that celebrities and some good media organizations can attract environmental attention. Finally, we use pyLDAvis technology to visualize and analyze popular environmental themes and propose reasonable countermeasures and suggestions to enhance public environmental awareness based on the research results.

Deep learning-based multiomics integration model for predicting axillary lymph node metastasis in breast cancer.

Aim: To develop a deep learning-based multiomics integration model. Materials & methods: Five types of omics data (mRNA, DNA methylation, miRNA, copy number variation and protein expression) were used to build a deep learning-based multiomics integration model via a deep neural network, incorporating an attention mechanism that adaptively considers the weights of multiomics features. Results: Compared with other methods, the deep learning-based multiomics integration model achieved remarkable results, with an area under the curve of 0.89 (95% CI: 0.863-0.910). Conclusion: The deep learning-based multiomics integration model achieved promising results and is an effective method for predicting axillary lymph node metastasis in breast cancer.