Hotspot mutations in the structured ENL YEATS domain link aberrant transcriptional condensates and cancer.

Growing evidence suggests prevalence of transcriptional condensates on chromatin, yet their mechanisms of formation and functional significance remain largely unclear. In human cancer, a series of mutations in the histone acetylation reader ENL create gain-of-function mutants with increased transcriptional activation ability. Here, we show that these mutations, clustered in ENL's structured acetyl-reading YEATS domain, trigger aberrant condensates at native genomic targets through multivalent homotypic and heterotypic interactions. Mechanistically, mutation-induced structural changes in the YEATS domain, ENL's two disordered regions of opposing charges, and the incorporation of extrinsic elongation factors are all required for ENL condensate formation. Extensive mutagenesis establishes condensate formation as a driver of oncogenic gene activation. Furthermore, expression of ENL mutants beyond the endogenous level leads to non-functional condensates. Our findings provide new mechanistic and functional insights into cancer-associated condensates and support condensate dysregulation as an oncogenic mechanism.

Antimicrobial peptide-producing dermal preadipocytes defend against Candida albicans skin infection via the FGFR-MEK-ERK pathway.

Dermal fibroblasts (dFBs) defend against deep bacterial skin infections by differentiating into preadipocytes (pAds) that produce the antimicrobial peptide cathelicidin; this differentiation is known as the dermal reactive adipogenesis response. However, the role of dFBs in fungal infection remains unknown. Here, we found that cathelicidin-producing pAds were present in high numbers in skin lesions from patients with cutaneous Candida granulomas. Second, we showed that dermal Candida albicans (C. albicans) infection in mice robustly triggered the dermal reactive adipogenesis response and induced cathelicidin expression, and inhibition of adipogenesis with pharmacological inhibitors of peroxisome proliferator-activated receptor γ (PPARγ) impaired skin resistance to C. albicans. In vitro, C. albicans products induced cathelicidin expression in pAds, and differentiating pAds markedly suppressed the growth of C. albicans by producing cathelicidin. Finally, we showed that C. albicans induced an antimicrobial response in pAds through the FGFR-MEK-ERK pathway. Together, our data reveal a previously unknown role of dFBs in the defense against skin infection caused by C. albicans.

DLBCL-associated NOTCH2 mutations escape ubiquitin-dependent degradation and promote chemoresistance.

Diffuse large B-cell lymphoma (DLBCL) is the most common subtype of non-Hodgkin lymphoma. Up to 40% of patients with DLBCL display refractory disease or relapse after standard chemotherapy treatment (rituximab, cyclophosphamide, doxorubicin, vincristine, and prednisone [R-CHOP]), leading to significant morbidity and mortality. The molecular mechanisms of chemoresistance in DLBCL remain incompletely understood. Using a cullin-really interesting new gene (RING) ligase-based CRISPR-Cas9 library, we identify that inactivation of the E3 ubiquitin ligase KLHL6 promotes DLBCL chemoresistance. Furthermore, proteomic approaches helped identify KLHL6 as a novel master regulator of plasma membrane-associated NOTCH2 via proteasome-dependent degradation. In CHOP-resistant DLBCL tumors, mutations of NOTCH2 result in a protein that escapes the mechanism of ubiquitin-dependent proteolysis, leading to protein stabilization and activation of the oncogenic RAS signaling pathway. Targeting CHOP-resistant DLBCL tumors with the phase 3 clinical trial molecules nirogacestat, a selective γ-secretase inhibitor, and ipatasertib, a pan-AKT inhibitor, synergistically promotes DLBCL destruction. These findings establish the rationale for therapeutic strategies aimed at targeting the oncogenic pathway activated in KLHL6- or NOTCH2-mutated DLBCL.

Preparation of Cobalt-Nitrogen Co-Doped Carbon Nanotubes for Activated Peroxymonosulfate Degradation of Carbamazepine.

Cobalt-nitrogen co-doped carbon nanotubes (Co3@NCNT-800) were synthesized via a facile and economical approach to investigate the efficient degradation of organic pollutants in aqueous environments. This material demonstrated high catalytic efficiency in the degradation of carbamazepine (CBZ) in the presence of peroxymonosulfate (PMS). The experimental data revealed that at a neutral pH of 7 and an initial CBZ concentration of 20 mg/L, the application of Co3@NCNT-800 at 0.2 g/L facilitated a degradation rate of 64.7% within 60 min. Mechanistic investigations indicated that the presence of pyridinic nitrogen and cobalt species enhanced the generation of reactive oxygen species. Radical scavenging assays and electron spin resonance spectroscopy confirmed that radical and nonradical pathways contributed to CBZ degradation, with the nonradical mechanism being predominant. This research presents the development of a novel PMS catalyst, synthesized through an efficient and stable method, which provides a cost-effective solution for the remediation of organic contaminants in water.

Long Noncoding RNA GMAN, Up-regulated in Gastric Cancer Tissues, Is Associated With Metastasis in Patients and Promotes Translation of Ephrin A1 by Competitively Binding GMAN-AS.

BACKGROUND & AIMS: We aimed to identify long noncoding RNAs (lncRNAs) that are up-regulated in gastric cancer tissues from patients and study their function in gastric tumor metastasis. METHODS: We collected gastric tumor and nontumor tissues from patients in China and analyzed levels of lncRNAs by microarray analysis, proteins by immunohistochemistry, and RNAs by quantitative reverse-transcription polymerase chain reaction; we compared these with survival times of patients and tumor progression. RNA levels were knocked down or knocked out in BGC-823, SGC-7901, and MKN45 cell lines using small interfering or short hairpin RNAs or clustered regularly interspaced short palindromic repeats (ie, CRISPR)/CRISPR associated protein 9 (ie, Cas9) vectors. Genes were overexpressed from transfected plasmids in HGC-27 cells. Cells were analyzed by Northern blot and immunoblot, polysome profiling assay, and cell invasion assay. Cells were injected into the tail veins or spleens of nude mice or SCID mice; lung and liver tissues were collected, and metastases were counted. lncRNAs were cloned by using rapid amplification of complementary DNA ends. Their interactions with other genes were determined by RNA pulldown and mapping assays. RESULTS: In microarray analyses, we identified 151 lncRNAs expressed at significantly higher levels in gastric tumor vs nontumor tissues. Levels of an lncRNA that we called gastric cancer metastasis associated long noncoding RNA (GMAN) were increased in gastric tumor tissues, compared with nontumor tissues; its up-regulation was associated with tumor metastasis and shorter survival times of patients. The GMAN gene overlaps with the ephrin A1 gene (EFNA1) and was highly expressed in BGC-823 and MKN45 cells. Knockdown of GMAN in these cells did not affect proliferation, colony formation, or adhesion but did reduce their invasive activity in Transwell assays. Ectopic expression of GMAN increased the invasive activity of HGC-27 cells. BGC-823 and MKN45 cells with knockdown of GMAN formed fewer metastases after injection into tail veins of nude mice. Knockdown or knockout of GMAN also reduced levels of ephrin A1 protein in cells. We found that GMAN promoted translation of ephrin A1 messenger RNA into protein by binding to the antisense GMAN RNA (GMAN-AS)-this antisense sequence is also complementary to that of ephrin A1 mRNA. Levels of ephrin A1 protein were also increased in gastric tumors from patients with metastases than in those without metastases. Knockout of ephrin A1 in BGC-823 cells reduced their invasive activity in Transwell assays and ability to form metastases after injection into SCID mice. Ectopic expression of ephrin A1 in BGC-823 cells with knockdown or knockout of GMAN restored their invasive activities and ability form metastases in nude or SCID mice. A CRISPR/Cas9-based strategy to disrupt the GMAN gene significantly reduced the numbers of metastases formed from SGC-7901 cells in mice. CONCLUSIONS: We identified an lncRNA, which we call GMAN, that is increased in gastric tumors from patients and associated with survival and formation of metastases. It regulates translation of ephrin A1 mRNA by binding competitively to GMAN-AS. Knockdown or knockout of GMAN or ephrin A1 in gastric cancer cell lines reduces their invasive activity and ability to form metastases after injection into mice. These genes might be targeted to prevent or reduce gastric cancer metastasis.

A Current Sensing Biosensor for BOD Rapid Measurement.

In order to improve the practicality of the rapid biochemical oxygen demand (BOD) method, a highly sensitive rapid detection method for BOD that is based on establishing the correlation between current and dissolved oxygen (DO) was developed. In this experiment, Bacillus subtilis was used as the test microorganism, and the embedding method was used to achieve quantitative fixation of microorganisms, which could increase the content of microorganisms and prolong the service life of the biological element. The conductivity (COND) probe is used as a sensing element, so that the testing value can be read every second. In the program, the moving average method is used to process the collected data so that the value can be read every minute. National standard samples were detected to test the accuracy and stability of the method. The results showed that relative error and analytical standard deviations were less than 5%. Different polluted water was tested to evaluate its application range. The results showed that relative error was less than 5%. The results of the method are consistent with the results of the wastewater sample obtained by the BOD5 standard method. The proposed rapid BOD current sensing biosensor method should be promising in practical application of wastewater monitoring.

Insights into Uptake, Translocation, and Transformation Mechanisms of Perfluorophosphinates and Perfluorophosphonates in Wheat (Triticum aestivum L.).

As emerging alternatives of legacy perfluoroalkyl substances, perfluorophosphinates (PFPiAs) and perfluorophosphonates (PFPAs) are widely applied in industrial and agricultural fields and are supposed to be large partitioned to soil and highly persistent. It is of particular interest to understand their transfer from roots to shoots and transformation in plants, such as wheat. The results of hydroponic experiments indicated that C6/C6 PFPiA, C8/C8 PFPiA, perfluorooctanophosphonic acid (PFOPA), and perfluorohexaphosphonic acid (PFHxPA) were quickly adsorbed on the epidermis of wheat root (Triticum aestivum L.), which was driven by their hydrophobicity. A small fraction of the accumulated PFPiAs and PFPAs in the wheat root was subjected to absorption via an active process dependent on H+-ATPase. PFHxPA, which has the smallest molecular weight and medium hydrophilicity (log Kow < 4), displayed the strongest absorption efficiency via the water and anion channels and had the highest translocation potential from roots to shoots in wheat. C6/C6 and C8/C8 PFPiAs experienced phase I metabolism in wheat, although at a low rate, to form more persistent PFHxPA and PFOPA, respectively, as well as 1H-perfluorohexane (1H-PFHx) and 1H-perfluorooctane (1H-PFO), which were regulated by cytochrome P450 in wheat root. As a result, exposure to PFPiAs in roots ultimately caused the accumulation of more persistent PFPAs in the above-ground parts of plants, raising concerns on their potential risks on human health.

Magnetically Powered Shape-Transformable Liquid Metal Micromotors.

Shape-transformable liquid metal (LM) micromachines have attracted the attention of the scientific community over the past 5 years, but the inconvenience of transfer routes and the use of corrosive fuels have limited their potential applications. In this work, a shape-transformable LM micromotor that is fabricated by a simple, versatile ice-assisted transfer printing method is demonstrated, in which an ice layer is employed as a "sacrificial" substrate that can enable the direct transfer of LM micromotors to arbitrary target substrates conveniently. The resulting LM microswimmers display efficient propulsion of over 60 µm s-1 (≈3 bodylength s-1 ) under elliptically polarized magnetic fields, comparable to that of the common magnetic micro/nanomotors with rigid bodies. Moreover, these LM micromotors can undergo dramatic morphological transformation in an aqueous environment under the irradiation of an alternating magnetic field. The ability to transform the shape and efficiently propel LM microswimmers holds great promise for chemical sensing, controlled cargo transport, materials science, and even artificial intelligence in ways that are not possible with rigid-bodies microrobots.

Magnetically Powered Annelid-Worm-Like Microswimmers.

A bioinspired magnetically powered microswimmer is designed and experimentally demonstrated by mimicking the morphology of annelid worms. The structural parameters of the microswimmer, such as the surface wrinkling, can be controlled by applying prestrain on substrate for the precise fabrication and consistent performance of the microswimmers. The resulting annelid-worm-like microswimmers display efficient propulsion under an oscillating magnetic field, reaching a peak speed of ≈100 µm s-1 . The speed and directionality of the microswimmer can be readily controlled by changing the parameters of the field inputs. Additionally, it is demonstrated that the microswimmers are able to transport microparticles toward a predefined destination, although the translation velocity is inevitably reduced due to the additional hydrodynamic resistance of the microparticles. These annelid-worm-like microswimmers have excellent mobility, good maneuverability, and strong transport capacity, and they hold considerable promise for diverse biomedical, chemical sensing, and environmental applications.

The sacred lotus genome provides insights into the evolution of flowering plants.

Sacred lotus (Nelumbo nucifera) is an ornamental plant that is also used for food and medicine. This basal eudicot species is especially important from an evolutionary perspective, as it occupies a critical phylogenetic position in flowering plants. Here we report the draft genome of a wild strain of sacred lotus. The assembled genome is 792 Mb, which is approximately 85-90% of genome size estimates. We annotated 392 Mb of repeat sequences and 36,385 protein-coding genes within the genome. Using these sequence data, we constructed a phylogenetic tree and confirmed the basal location of sacred lotus within eudicots. Importantly, we found evidence for a relatively recent whole-genome duplication event; any indication of the ancient paleo-hexaploid event was, however, absent. Genomic analysis revealed evidence of positive selection within 28 embryo-defective genes and one annexin gene that may be related to the long-term viability of sacred lotus seed. We also identified a significant expansion of starch synthase genes, which probably elevated starch levels within the rhizome of sacred lotus. Sequencing this strain of sacred lotus thus provided important insights into the evolution of flowering plant and revealed genetic mechanisms that influence seed dormancy and starch synthesis.

Dysregulation of transcriptional condensates in human disease: mechanisms, biological functions, and open questions.

Precise gene expression, crucial for normal development and health, depends on the co-ordinated assembly and function of various factors within the crowded nucleus. Recent evidence suggests that this process is in part regulated by mesoscale compartmentalization and concentration of transcriptional components within condensates, offering a new perspective on gene regulation. Dysregulation of transcriptional condensates is increasingly associated with diseases, indicating a potential role in pathogenesis. In this mini-review, we provide a concise overview of the current understanding of the formation and function of transcriptional condensates, with a specific focus on recent advances in their dysregulation and implications in diseases, notably cancer. We also address limitations in the field and highlight open questions for future research.

Controlling the Collective Behaviors of Ultrasound-Driven Nanomotors via Frequency Regulation.

Controlling the collective behavior of micro/nanomotors with ultrasound may enable new functionality in robotics, medicine, and other engineering disciplines. Currently, various collective behaviors of nanomotors, such as assembly, reconfiguration, and disassembly, have been explored by using acoustic fields with a fixed frequency, while regulating their collective behaviors by varying the ultrasound frequency still remains challenging. In this work, we designed an ultrasound manipulation methodology that allows nanomotors to exhibit different collective behaviors by regulating the applied ultrasound frequency. The experimental results and FEM simulations demonstrate that the secondary ultrasonic waves produced from the edge of the sample cell lead to the formation of complex acoustic pressure fields and microfluidic patterns, which causes these collective behaviors. This work has important implications for the design of artificial actuated nanomotors and optimize their performances.

Clinical evidence and potential mechanisms of traditional Chinese medicine for refractory heart failure: a literature review and perspectives.

Refractory heart failure (RHF), or end-stage heart failure, has a poor prognosis and high case fatality rate, making it one of the therapeutic difficulties in the cardiovascular field. Despite the continuous abundance of methods and means for treating RHF in modern medicine, it still cannot meet the clinical needs of patients with RHF. How to further reduce the mortality rate and readmission rate of patients with RHF and improve their quality of life is still a difficult point in current research. In China, traditional Chinese medicine (TCM) has been widely used and has accumulated rich experience in the treatment of RHF due to its unique efficacy and safety advantages. Based on this, we comprehensively summarized and analyzed the clinical evidence and mechanism of action of TCM in the treatment of RHF and proposed urgent scientific issues and future research strategies for the treatment of RHF with TCM, to provide reference for the treatment of RHF.

Combining quantitative and qualitative analysis for scoring pleural line in lung ultrasound.

Objective.Accurate assessment of pleural line is crucial for the application of lung ultrasound (LUS) in monitoring lung diseases, thereby aim of this study is to develop a quantitative and qualitative analysis method for pleural line.Approach.The novel cascaded deep learning model based on convolution and multilayer perceptron was proposed to locate and segment the pleural line in LUS images, whose results were applied for quantitative analysis of textural and morphological features, respectively. By using gray-level co-occurrence matrix and self-designed statistical methods, eight textural and three morphological features were generated to characterize the pleural lines. Furthermore, the machine learning-based classifiers were employed to qualitatively evaluate the lesion degree of pleural line in LUS images.Main results.We prospectively evaluated 3770 LUS images acquired from 31 pneumonia patients. Experimental results demonstrated that the proposed pleural line extraction and evaluation methods all have good performance, with dice and accuracy of 0.87 and 94.47%, respectively, and the comparison with previous methods found statistical significance (P< 0.001 for all). Meanwhile, the generalization verification proved the feasibility of the proposed method in multiple data scenarios.Significance.The proposed method has great application potential for assessment of pleural line in LUS images and aiding lung disease diagnosis and treatment.

Photodetectors Based on ZrS3/MoS2 Heterostructures.

High-performance photodetectors with the detection capability of linearly polarized light have broad applications in both military and civilian fields. Quasi-one-dimensional ZrS3 as an emerging anisotropic two-dimensional material has come under the spotlight owing to its intriguing properties. However, the performance of the ZrS3 photodetector is seriously restricted by its low responsivity. Herein, a novel high-performance photodetector based on the van der Waals ZrS3/MoS2 heterostructure is proposed. Attributed to the charge trapping-assisted photogating effect, interlayer carrier transitions, and fast spatial separation of the photogenerated electron-hole pairs, the device displays superior photoresponse characteristics ranging from the ultraviolet to the visible spectrum in terms of high responsivity up to 212 A/W, an extraordinary external quantum efficiency of 8.5 × 104%, and a prompt rise/decay time of 0.19/0.38 ms. In addition, owing to the profound birefringence and dichroism effects in ZrS3 together with strong light-matter interactions in the heterostructure, profound linear-polarization sensitivity is demonstrated with a dichroic ratio of about 2.8. Overall, this photodetector not only is integrated with the excellent properties of ZrS3 and monolayer MoS2 but also further enhances the advantages through interlayer couplings, which demonstrate the strong potential of the ZrS3-based devices for high-performance, ultrafast, and polarization-sensitive photodetection.

Atrial Septal Defect Detection in Children Based on Ultrasound Video Using Multiple Instances Learning.

Thoracic echocardiography (TTE) can provide sufficient cardiac structure information, evaluate hemodynamics and cardiac function, and is an effective method for atrial septal defect (ASD) examination. This paper aims to study a deep learning method based on cardiac ultrasound video to assist in ASD diagnosis. We chose four standard views in pediatric cardiac ultrasound to identify atrial septal defects; the four standard views were as follows: subcostal sagittal view of the atrium septum (subSAS), apical four-chamber view (A4C), the low parasternal four-chamber view (LPS4C), and parasternal short-axis view of large artery (PSAX). We enlist data from 300 children patients as part of a double-blind experiment for five-fold cross-validation to verify the performance of our model. In addition, data from 30 children patients (15 positives and 15 negatives) are collected for clinician testing and compared to our model test results (these 30 samples do not participate in model training). In our model, we present a block random selection, maximal agreement decision, and frame sampling strategy for training and testing respectively, resNet18 and r3D networks are used to extract the frame features and aggregate them to build a rich video-level representation. We validate our model using our private dataset by five cross-validation. For ASD detection, we achieve 89.33 ± 3.13 AUC, 84.95 ± 3.88 accuracy, 85.70 ± 4.91 sensitivity, 81.51 ± 8.15 specificity, and 81.99 ± 5.30 F1 score. The proposed model is a multiple instances learning-based deep learning model for video atrial septal defect detection which effectively improves ASD detection accuracy when compared to the performances of previous networks and clinical doctors.

Condensate-promoting ENL mutation drives tumorigenesis in vivo through dynamic regulation of histone modifications and gene expression.

Gain-of-function mutations in the histone acetylation 'reader' ENL, found in AML and Wilms tumor, are known to drive condensate formation and gene activation in cellular systems. However, their role in tumorigenesis remains unclear. Using a conditional knock-in mouse model, we show that mutant ENL perturbs normal hematopoiesis, induces aberrant expansion of myeloid progenitors, and triggers rapid onset of aggressive AML. Mutant ENL alters developmental and inflammatory gene programs in part by remodeling histone modifications. Mutant ENL forms condensates in hematopoietic stem/progenitor cells at key leukemogenic genes, and disrupting condensate formation via mutagenesis impairs its chromatin and oncogenic function. Moreover, treatment with an acetyl-binding inhibitor of mutant ENL displaces these condensates from target loci, inhibits mutant ENL-induced chromatin changes, and delays AML initiation and progression in vivo. Our study elucidates the function of ENL mutations in chromatin regulation and tumorigenesis, and demonstrates the potential of targeting pathogenic condensates in cancer treatment.

Lead Optimization of Small Molecule ENL YEATS Inhibitors to Enable In Vivo Studies: Discovery of TDI-11055.

Eleven-nineteen leukemia (ENL) is an epigenetic reader protein that drives oncogenic transcriptional programs in acute myeloid leukemia (AML). AML is one of the deadliest hematopoietic malignancies, with an overall 5-year survival rate of 27%. The epigenetic reader activity of ENL is mediated by its YEATS domain that binds to acetyl and crotonyl marks on histone tails and colocalizes with promoters of actively transcribed genes that are essential for leukemia. Prior to the discovery of TDI-11055, existing inhibitors of ENL YEATS showed in vitro potency, but had not shown efficacy in in vivo animal models. During the course of the medicinal chemistry campaign described here, we identified ENL YEATS inhibitor TDI-11055 that has an improved pharmacokinetic profile and is appropriate for in vivo evaluation of the ENL YEATS inhibition mechanism in AML.

Unraveling the role of VLDL in the relationship between type 2 diabetes and coronary atherosclerosis: a Mendelian randomization analysis.

Background: The causal link between Type 2 diabetes (T2D) and coronary atherosclerosis has been established through wet lab experiments; however, its analysis with Genome-wide association studies (GWAS) data remains unexplored. This study aims to validate this relationship using Mendelian randomization analysis and explore the potential mediation of VLDL in this mechanism. Methods: Employing Mendelian randomization analysis, we investigated the causal connection between T2D and coronary atherosclerosis. We utilized GWAS summary statistics from European ancestry cohorts, comprising 23,363 coronary atherosclerosis patients and 195,429 controls, along with 32,469 T2D patients and 183,185 controls. VLDL levels, linked to SNPs, were considered as a potential mediating causal factor that might contribute to coronary atherosclerosis in the presence of T2D. We employed the inverse variance weighted (IVW), Egger regression (MR-Egger), weighted median, and weighted model methods for causal effect estimation. A leave-one-out sensitivity analysis was conducted to ensure robustness. Results: Our Mendelian randomization analysis demonstrated a genetic association between T2D and an increased coronary atherosclerosis risk, with the IVW estimate at 1.13 [95% confidence interval (CI): 1.07-1.20]. Additionally, we observed a suggestive causal link between T2D and VLDL levels, as evidenced by the IVW estimate of 1.02 (95% CI: 0.98-1.07). Further supporting lipid involvement in coronary atherosclerosis pathogenesis, the IVW-Egger estimate was 1.30 (95% CI: 1.06-1.58). Conclusion: In conclusion, this study highlights the autonomous contributions of T2D and VLDL levels to coronary atherosclerosis development. T2D is linked to a 13.35% elevated risk of coronary atherosclerosis, and within T2D patients, VLDL concentration rises by 2.49%. Notably, each standard deviation increase in VLDL raises the likelihood of heart disease by 29.6%. This underscores the significant role of lipid regulation, particularly VLDL, as a mediating pathway in coronary atherosclerosis progression.

LOANet: a lightweight network using object attention for extracting buildings and roads from UAV aerial remote sensing images.

Semantic segmentation for extracting buildings and roads from uncrewed aerial vehicle (UAV) remote sensing images by deep learning becomes a more efficient and convenient method than traditional manual segmentation in surveying and mapping fields. In order to make the model lightweight and improve the model accuracy, a lightweight network using object attention (LOANet) for buildings and roads from UAV aerial remote sensing images is proposed. The proposed network adopts an encoder-decoder architecture in which a lightweight densely connected network (LDCNet) is developed as the encoder. In the decoder part, the dual multi-scale context modules which consist of the atrous spatial pyramid pooling module (ASPP) and the object attention module (OAM) are designed to capture more context information from feature maps of UAV remote sensing images. Between ASPP and OAM, a feature pyramid network (FPN) module is used to fuse multi-scale features extracted from ASPP. A private dataset of remote sensing images taken by UAV which contains 2431 training sets, 945 validation sets, and 475 test sets is constructed. The proposed basic model performs well on this dataset, with only 1.4M parameters and 5.48G floating point operations (FLOPs), achieving excellent mean Intersection-over-Union (mIoU). Further experiments on the publicly available LoveDA and CITY-OSM datasets have been conducted to further validate the effectiveness of the proposed basic and large model, and outstanding mIoU results have been achieved. All codes are available on https://github.com/GtLinyer/LOANet.