Fluorinated benzothiadiazole fluorescent probe based on ICT mechanism for highly selectivity and sensitive detection of fluoride ion.

Excessive fluoride ion (F-) in the environment can affect health and even endanger life when ingested by the human body. However, most fluoride probes have the disadvantages of low sensitivity and long detection time. Herein, fluorescent probe 3a is successfully synthesized by linking two acetylenyltrimethylsilyl groups at both ends of the fluorinated benzothiadiazole core. After the addition of F- to 3a, the emission at 436 nm is significantly quenched and slightly blue-shifted. It is confirmed by electrospray ionization high-resolution mass spectrometry (ESI-HRMS) and density functional theory calculations (DFT) that these changes are due to the F- triggered Si-C bond cleavage and the subsequent inactivation of intramolecular charge transfer (ICT). The detection limit and response time of probe 3a for F- are 10-8 mol/L and 25 s, respectively. Importantly, fluorescent material 3a can be processed into portable test tools for the visual detection of fluoride ion.

Clinical validation of automated depth camera-based measurement of the Fugl-Meyer assessment for upper extremity.

OBJECTIVE: Depth camera-based measurement has demonstrated efficacy in automated assessment of upper limb Fugl-Meyer Assessment for paralysis rehabilitation. However, there is a lack of adequately sized studies to provide clinical support. Thus, we developed an automated system utilizing depth camera and machine learning, and assessed its feasibility and validity in a clinical setting. DESIGN: Validation and feasibility study of a measurement instrument based on single cross-sectional data. SETTING: Rehabilitation unit in a general hospital. PARTICIPANTS: Ninety-five patients with hemiparesis admitted for inpatient rehabilitation unit (2021-2023). MAIN MEASURES: Scores for each item, excluding those related to reflexes, were computed utilizing machine learning models trained on participant videos and readouts from force test devices, while the remaining reflex scores were derived through regression algorithms. Concurrent criterion validity was evaluated using sensitivity, specificity, percent agreement and Cohen's Kappa coefficient for ordinal scores of individual items, as well as correlations and intraclass correlation coefficients for total scores. Video-based manual assessment was also conducted and compared to the automated tools. RESULT: The majority of patients completed the assessment without therapist intervention. The automated scoring models demonstrated superior validity compared to video-based manual assessment across most items. The total scores derived from the automated assessment exhibited a high coefficient of 0.960. However, the validity of force test items utilizing force sensing resistors was relatively low. CONCLUSION: The integration of depth camera technology and machine learning models for automated Fugl-Meyer Assessment demonstrated acceptable validity and feasibility, suggesting its potential as a valuable tool in rehabilitation assessment.

Aquaporins alteration revealed kidney damages in cerebral ischemia/reperfusion rats.

Background: Restoration of blood supply is a desired goal for the treatment of acute ischemic stroke. However, the restoration often leads to cerebral ischemia-reperfusion injury (CIR/I), which greatly increases the risk of non-neural organ damage. In particular, the acute kidney injury might be one of the most common complications. Aims: The study aimed to understand the damage occurred and the potential molecular mechanisms. Methods: The study was explored on the CIR/I rats generated by performing middle cerebral artery occlusion/reperfusion (MCAO/Reperfusion). The rats were evaluated with injury on the brains, followed by the non-neural organs including kidneys, livers, colons and stomachs. They were examined further with histopathological changes, and gene expression alterations by using RT-qPCR of ten aquaporins (Aqps) subtypes including Aqp1～Aqp9 and Aqp11. Furthermore, the Aqps expression profiles were constructed for each organ and analyzed by performing Principle Component Analysis. In addition, immunohistochemistry was explored to look at the protein expression of Aqp1, Aqp2, Aqp3 and Aqp4 in the rat kidneys. Results: There was a prominent down-regulation profile in the MCAO/Reperfusion rat kidneys. The protein expression of Aqp1, Aqp2, Aqp3 and Aqp4 was decreased in the kidneys of the MCAO/Reperfusion rats. We suggested that the kidney was in the highest risk to be damaged following the CIR/I. Down-regulation of Aqp2, Aqp3 and Aqp4 was involved in the acute kidney injury induced by the CIR/I.

Microwave-assisted and methanol/acetic acid-free method for rapid staining of proteins in SDS-PAGE gels.

We describe a microwave-assisted, methanol and acetic acid-free, inexpensive method for rapid staining of SDS-PAGE proteins. Only citric acid, benzoic acid, and Coomassie brilliant blue G-250 (CBG) were used. Microwave irradiation reduced the detection duration, and proteins in a clear background were visualized within 30 min of destaining, after 2 min of fixing and 12 min of staining. By using this protocol, comparable band intensities were obtained to the conventional methanol/acetic acid method.

Discovery of novel coumarin-based KRAS-G12C inhibitors from virtual screening and Rational structural optimization.

KRAS-G12C inhibitors has been made significant progress in the treatment of KRAS-G12C mutant cancers, but their clinical application is limited due to the adaptive resistance, motivating development of novel structural inhibitors. Herein, series of coumarin derivatives as KRAS-G12C inhibitors were found through virtual screening and rational structural optimization. Especially, K45 exhibited strong antiproliferative potency on NCI-H23 and NCI-H358 cancer cells harboring KRAS-G12C with the IC50 values of 0.77 µM and 1.50 µM, which was 15 and 11 times as potent as positive drug ARS1620, respectively. Furthermore, K45 reduced the phosphorylation of KRAS downstream effectors ERK and AKT by reducing the active form of KRAS (KRAS GTP) in NCI-H23 cells. In addition, K45 induced cell apoptosis by increasing the expression of anti-apoptotic protein BAD and BAX in NCI-H23 cells. Docking studies displayed that the 3-naphthylmethoxy moiety of K45 extended into the cryptic pocket formed by the residues Gln99 and Val9, which enhanced the interaction with the KRAS-G12C protein. These results indicated that K45 was a potent KRAS-G12C inhibitor worthy of further study.

Stepwise structural evolution toward robust carboranealkynyl-protected copper nanocluster catalysts for nitrate electroreduction.

Atomically precise metal nanoclusters (NCs) are emerging as idealized model catalysts for imprecise metal nanoparticles to unveil their structure-activity relationship. However, the directional synthesis of robust metal NCs with accessible catalytic active sites remains a great challenge. In this work, we achieved bulky carboranealkynyl-protected copper NCs, the monomer Cu13·3PF6 and nido-carboranealkynyl bridged dimer Cu26·4PF6, with fair stability as well as accessible open metal sites step by step through external ligand shell modification and metal-core evolution. Both Cu13·3PF6 and Cu26·4PF6 demonstrate remarkable catalytic activity and selectivity in electrocatalytic nitrate (NO3-) reduction to NH3 reaction, with the dimer Cu26·4PF6 displaying superior performance. The mechanism of this catalytic reaction was elucidated through theoretical computations in conjunction with in situ FTIR spectra. This study not only provides strategies for accessing desired copper NC catalysts but also establishes a platform to uncover the structure-activity relationship of copper NCs.

A prospective single-center, single-arm, open-label, phase II study of sintilimab and anlotinib combined with chemotherapy in neoadjuvant treatment of resectable esophageal cancer.

BACKGROUND: Antiangiogenic treatment and immunochemotherapy effectively treat patients with advanced esophageal cancer. However, there remains a dearth of studies concerning neoadjuvant therapy for resectable esophageal cancer. METHODS: The study focused on patients with T2-4NxM0 resectable esophageal carcinoma. Neoadjuvant treatment involved administering anlotinib (10 mg orally, once a day, 2 weeks on and 1 week off) for antiangiogenesis and sintilimab (200 mg) and chemotherapy for three cycles. Surgical treatment was performed 4-6 weeks after the last chemotherapy cycle was completed. The primary endpoints assessed were pathological complete response (pCR) and safety. RESULTS: Out of the 34 screened patients, 17 were successfully enrolled in the study, and 14 completed the entire treatment process. The pCR was 35.3% (6/17). However, two patients experienced mortality. The occurring rate of grade 3 or higher complications after the surgery was 78.6% (11/14) according to Clavien-Dindo classification. Specifically, anastomotic leakage was observed in 57.1% (8/14) of the patients. CONCLUSION: Compared to neoadjuvant chemotherapy, the current regimen demonstrated improved pCR. However, it did not show significant improvement compared to immunochemotherapy. It is essential to exercise caution when using this treatment approach in patients with esophageal cancer as it might increase postoperative complications, especially anastomotic leakage.

Isolation, Identification, Genomic Diversity, and Antimicrobial Resistance Analysis of Streptococcus suis in Hubei Province of China from 2021 to 2023.

Streptococcus suis (S. suis) is a zoonotic pathogen capable of causing severe diseases in humans and pigs, including meningitis, sepsis, polyserositis, arthritis, and endocarditis. This study aimed to investigate the biological characteristics of 19 strains of S. suis isolated from diseased pigs in Hubei Province between 2021 and 2023. Through bioinformatics analysis, we investigated the serotype, MLST, pan-genome characteristics, SNP, AMR, and ICE of the 19 S. suis isolates. Among the 19 S. suis strains, ten serotypes were identified, and serotype 9 was the most prevalent (21.05%). Ten new alleles and nine new sequence types (STs) were discovered, with ST28 and ST243 emerging as the predominant STs. The results of the pan-genomic analysis of S. suis indicate that there are 943 core genes, 2259 shell genes, and 5663 cloud genes. Through SNP evolutionary analysis, we identified a strong genetic similarity between SS31 and the reference genome P1/7. The analysis of antibiotic resistance genes revealed widespread presence of erm(B) and tet(O) genes among 19 strains of S. suis. This association may be linked to the high resistance of S. suis to lincosamides, macrolides, and tetracyclines. Integrative and conjugative elements (ICEs) and integrative and mobilizable elements (IMEs) were identified in 16 strains, with a carriage rate of 84.21%, and resistance genes were identified within the ICE/IME elements of 8 strains. Antimicrobial susceptibility testing revealed that all strains showed sensitivity to vancomycin and lincomycin but resistance to tilmicosin, tiamulin, amoxicillin, and doxycycline. This study contributes to our understanding of the genomic diversity of S. suis in Hubei Province of China, providing essential data for the comprehensive prevention and control of S. suis infections in China.

Single-Shot 3D Reconstruction via Nonlinear Fringe Transformation: Supervised and Unsupervised Learning Approaches.

The field of computer vision has been focusing on achieving accurate three-dimensional (3D) object representations from a single two-dimensional (2D) image through deep artificial neural networks. Recent advancements in 3D shape reconstruction techniques that combine structured light and deep learning show promise in acquiring high-quality geometric information about object surfaces. This paper introduces a new single-shot 3D shape reconstruction method that uses a nonlinear fringe transformation approach through both supervised and unsupervised learning networks. In this method, a deep learning network learns to convert a grayscale fringe input into multiple phase-shifted fringe outputs with different frequencies, which act as an intermediate result for the subsequent 3D reconstruction process using the structured-light fringe projection profilometry technique. Experiments have been conducted to validate the practicality and robustness of the proposed technique. The experimental results demonstrate that the unsupervised learning approach using a deep convolutional generative adversarial network (DCGAN) is superior to the supervised learning approach using UNet in image-to-image generation. The proposed technique's ability to accurately reconstruct 3D shapes of objects using only a single fringe image opens up vast opportunities for its application across diverse real-world scenarios.

Boosting 2000-Fold Hypergolic Ignition Rate of Carborane by Substitutes Migration in Metal Clusters.

Hypergolic propellants rely on fuel and oxidizer that spontaneously ignite upon contact, which fulfill a wide variety of mission roles in launch vehicles and spacecraft. Energy-rich carboranes are promising hypergolic fuels, but triggering their energy release is quite difficult because of their ultrastable aromatic cage structure. To steer the development of carborane-based high-performance hypergolic material, carboranylthiolated compounds integrated with atomically precise copper clusters are presented, yielding two distinct isomers, Cu14B-S and Cu14C-S, both possessing similar ligands and core structures. With the migration of thiolate groups from carbon atoms to boron atoms, the ignition delay (ID) time shortened from 6870 to 3 ms when contacted with environmentally benign oxidizer high-test peroxide (HTP, with a H2O2 concentration of 90%). The extraordinarily short ignition ID time of Cu14B-S is ranking among the best of HTP-active hypergolic materials. The experimental and theoretical findings reveal that benefitting from the migration of thiolate groups, Cu14B-S, characterized by an electron-rich metal kernel, displays enhanced reducibility and superior charge transfer efficiency. This results in exceptional activation rates with HTP, consequently inducing carborane combustion and the simultaneous release of energy. This fundamental investigation shed light on the development of advanced green hypergolic propulsion systems.

Adsorption of Pyrene and Arsenite by Micro/Nano Carbon Black and Iron Oxide.

Polycyclic aromatic hydrocarbons (PAHs) and arsenic (As) are common pollutants co-existing in the environment, causing potential hazards to the ecosystem and human health. How their behaviors are affected by micro/nano particles in the environment are still not very clear. Through a series of static adsorption experiments, this study investigated the adsorption of pyrene and arsenite (As (III)) using micro/nano carbon black and iron oxide under different conditions. The objectives were to determine the kinetics and isotherms of the adsorption of pyrene and As (III) using micro/nano carbon black and iron oxide and evaluate the impact of co-existing conditions on the adsorption. The microstructure of micro/nano carbon black (C 94.03%) is spherical-like, with a diameter of 100-200 nm. The micro/nano iron oxide (hematite) has irregular rod-shaped structures, mostly about 1 µm long and 100-200 nm wide. The results show that the micro/nano black carbon easily adsorbed the pyrene, with a pseudo-second-order rate constant of 0.016 mg/(g·h) and an adsorption capacity of 283.23 µg/g at 24 h. The micro/nano iron oxide easily adsorbed As (III), with a pseudo-second-order rate constant of 0.814 mg/(g·h) and an adsorption capacity of 3.45 mg/g at 24 h. The mechanisms of adsorption were mainly chemical reactions. Micro/nano carbon black hardly adsorbed As (III), but its adsorption capability for pyrene was reduced by the presence of As (III), and this effect increased with an increase in the As (III) concentration. The adsorbed pyrene on the micro/nano black carbon could hardly be desorbed. On the other hand, the micro/nano iron oxide could hardly adsorb the pyrene, but its adsorption capability for As (III) was increased by the presence of pyrene, and this effect increased with an increase in the pyrene concentration. The results of this study provide guidance for the risk management and remediation of the environment when there is combined pollution of PAHs and As.

Multi-Functional Nano-Doped Hollow Fiber from Microfluidics for Sensors and Micromotors.

Nano-doped hollow fiber is currently receiving extensive attention due to its multifunctionality and booming development. However, the microfluidic fabrication of nano-doped hollow fiber in a simple, smooth, stable, continuous, well-controlled manner without system blockage remains challenging. In this study, we employ a microfluidic method to fabricate nano-doped hollow fiber, which not only makes the preparation process continuous, controllable, and efficient, but also improves the dispersion uniformity of nanoparticles. Hydrogel hollow fiber doped with carbon nanotubes is fabricated and exhibits superior electrical conductivity (15.8 S m-1), strong flexibility (342.9%), and versatility as wearable sensors for monitoring human motions and collecting physiological electrical signals. Furthermore, we incorporate iron tetroxide nanoparticles into fibers to create magnetic-driven micromotors, which provide trajectory-controlled motion and the ability to move through narrow channels due to their small size. In addition, manganese dioxide nanoparticles are embedded into the fiber walls to create self-propelled micromotors. When placed in a hydrogen peroxide environment, the micromotors can reach a top speed of 615 µm s-1 and navigate hard-to-reach areas. Our nano-doped hollow fiber offers a broad range of applications in wearable electronics and self-propelled machines and creates promising opportunities for sensors and actuators.

Multifunctional Hydrogel of Recombinant Humanized Collagen Loaded with MSCs and MnO2 Accelerates Chronic Diabetic Wound Healing.

Chronic wound repair is a clinical treatment challenge. The development of multifunctional hydrogels is of great significance in the key aspects of treating chronic wounds, including reducing oxidative stress, promoting angiogenesis, and improving the natural remodeling of extracellular matrix and immune regulation. In this study, we prepared a composite hydrogel, sodium alginate (SA)@MnO2/recombinant humanized collagen III (RHC)/mesenchymal stem cells (MSCs), composed of SA, MnO2 nanoparticles, RHC, and MSCs. The hydrogel has high mechanical properties and good biocompatibility. In vitro, SA@MnO2/RHC/MSCs hydrogel effectively enhanced the formation of intricate tubular structures and angiogenesis and showed synergistic effects on cell proliferation and migration. In vivo, the SA@MnO2/RHC/MSCs hydrogel enhanced diabetes wound healing, rapid re-epithelization, favorable collagen deposition, and abundant wound angiogenesis. These findings demonstrated that the combined effects of SA, MnO2, RHC, and MSCs synergistically accelerate healing, resulting in a reduced healing time. These observed healing effects demonstrated the potential of this multifunctional hydrogel to transform chronic wound care and improve patient outcomes.

An endometrial biomimetic extracellular matrix (ECM) for enhanced endometrial regeneration using hyaluronic acid hydrogel containing recombinant human type III collagen.

Endometrial injury poses a significant challenge in tissue regeneration, with type III collagen (COL III) playing a pivotal role in maintaining endometrial integrity and facilitating repair. Our study explored the utility of recombinant human type III collagen (RHC) as an intervention for endometrial damage. To address the challenges associated with the inherent instability and rapid degradation of COL III in vivo, we developed an RHC-HA hydrogel by conjugating RHC with hyaluronic acid (HA), thus ensuring a more stable and sustained delivery. Our findings suggested that the RHC-HA hydrogel significantly promoted endometrial regeneration and restored fertility. The hydrogel facilitated prolonged retention of RHC in the uterus, leading to a substantial improvement in the repair process. The synergistic interaction between RHC and HA greatly enhances cell proliferation and adhesion, surpassing the efficacy of HA or RHC alone. Additionally, the RHC-HA hydrogel demonstrated notable anti-fibrotic effects, which are crucial for preventing abnormalities during endometrial healing. These findings suggested that the RHC-HA hydrogel presented a therapeutic strategy in the treatment of uterine endometrial injuries, which may improve female reproductive health.

Periodic magnetic modulation enhanced electrochemical analysis for highly sensitive determination of genomic DNA methylation.

DNA methylation aberrations have a strong correlation with cancer in early detection, diagnosis, and prognosis, which make them possible candidate biomarkers. Electrochemical biosensors offer rapid protocols for detecting DNA methylation status with minimal pretreatment of samples. However, the inevitable presence of background current in the time domain, including electrochemical noise and variations, limits the detection performance of these biosensors, especially for low concentration analytes. Here, we propose an ultrasensitive frequency-domain electrochemical analysis strategy to effectively separate the weak signals from background current. To achieve this, we employed periodic magnetic field modulation of magnetic beads (MBs) on and off the electrode surface to generate a periodic electrochemical signal for subsequent frequency-domain analysis. By capturing labeled MBs with as low as 0.5 pg of DNA, we successfully demonstrated a highly sensitive electrochemical method for determination of genome-wide DNA methylation levels. We also validated the effectiveness of this methodology using DNA samples extracted from three types of hepatocellular carcinoma (HCC) cell lines. The results revealed varying genomic methylation levels among different HCC cell lines, indicating the potential application of this approach for early-stage cancer detection in terms of DNA methylation status.

Polyethylene glycol crosslinked modified chitosan/halloysite nanotube composite aerogel microspheres for efficient adsorption of melanoidin.

Melanoidins are widely present in molasses wastewater and are dark-colored macromolecules that are hazardous to the environment. Currently, adsorption methods can effectively remove melanoidins from wastewater. However, existing adsorbents have shown unsatisfactory removal efficiency for melanoidins, making practical application challenging. Polyethylene glycol crosslinked modified chitosan/halloysite nanotube composite aerogel microspheres (PCAM@HNTs) were developed as a highly efficient adsorbent for melanoidins. The removal rate of PCAM@HNTs for melanoidins was 98.53 % at adsorbent dosage 0.4 mg/mL, pH 7, temperature 303 K and 450 mg/L initial melanoidins concentration, and the corresponding equilibrium adsorption capacity was 1108.49 mg/g. The analysis results indicate that the adsorption of melanoidins by PCAM@HNTs is a spontaneous and endothermic process. It fits well with pseudo-second-order kinetic models and the Freundlich isotherm equation. The adsorption of PCAM@HNT on melanoidins is primarily attributed to electrostatic and hydrogen bonding interactions. Furthermore, PCAM@HNTs exhibit excellent biocompatibility and are nonhazardous. Therefore, PCAM@HNTs proved to be an ideal adsorbent for the decolorization of molasses wastewater.

Loss-of-function variants in GLMN are associated with generalized skin hyperpigmentation with or without glomuvenous malformation.

BACKGROUNDS: Inherited hyperpigmented skin disorders comprise a group of entities with considerable clinical and genetic heterogenicity. The genetic basis of a majority of these disorders remains to be elucidated. OBJECTIVES: This study aimed to identify the underlying gene for an unclarified disorder of autosomal-dominant generalized skin hyperpigmentation with or without glomuvenous malformation. METHODS: Whole-exome sequencing was performed in five unrelated families with autosomal-dominant generalized skin hyperpigmentation. Variants were confirmed using Sanger sequencing and a minigene assay was employed to evaluate the splicing alteration. Immunofluorescence and transmission electron microscopy (TEM) were used to determine the quantity of melanocytes and melanosomes in hyperpigmented skin lesions. GLMN knockdown by siRNA assays was performed in human MNT-1 cells to examine melanin concentration and the underlying molecular mechanism. RESULTS: We identified five variants in GLMN in five unrelated families, including c.995_996insAACA(p.Ser333Thrfs*11), c.632 + 4delA, c.1470_1473dup(p.Thr492fs*12), c.1319G > A(p.Trp440*), and c.1613_1614insTA(Thr540*). The minigene assay confirmed that the c.632 + 4delA mutant resulted in an abolishment of the canonical donor splice site. Although the number of melanocytes remained unchanged in skin lesions as demonstrated by immunofluorescent staining of tyrosinase and premelanosome protein (PMEL), TEM revealed an increased quantity of melanosomes in the skin lesion of a patient. The GLMN-knockdown MNT-1 cells demonstrated a higher melanin concentration, a higher proportion of stage III and IV melanosomes, upregulation of MITF and tyrosinase, and downregulation of phosphorylated p70S6 K, compared to mock-transfected cells. CONCLUSIONS: We found loss-of-function variants in GLMN are associated with generalized skin hyperpigmentation with or without glomuvenous malformation. Our study implicates a potential role of glomulin in human skin melanogenesis, in addition to vascular morphogenesis.

Strategies for using magnetic beads in enhanced deep eutectic solvent-mechanochemical extraction of natural products from orange peels.

To address the challenges of low recovery, prolonged extraction times, and environmental pollution caused by toxic solvents in traditional extraction methods, magnetic bead-enhanced deep eutectic solvent mechanochemical extraction was developed for extracting natural products from orange peels. The extraction efficiencies of deep eutectic solvents were experimentally evaluated, and theoretical methods were used to guide solvent selection. Choline chloride-ethylene glycol demonstrated the highest efficiency under the optimal extraction conditions: a molar ratio of 1:2, no water content, a solid-liquid ratio of 0.08 g/mL, and an extraction time of 60 s. The synergy between the deep eutectic solvent and magnetic bead-enhanced the mechanochemical extraction efficiencies. The study also examined the effects of different magnetic bead types and orange peel powder particle sizes on extraction efficiency, finding that a 0.11 mm particle size combined with CIP@SiO2 yielded the best results. Overall, this study holds promise as an environmentally friendly and efficient extraction method.

Multi-channel high-order network representation learning research.

The existing network representation learning algorithms mainly model the relationship between network nodes based on the structural features of the network, or use text features, hierarchical features and other external attributes to realize the network joint representation learning. Capturing global features of the network allows the obtained node vectors to retain more comprehensive feature information during training, thereby enhancing the quality of embeddings. In order to preserve the global structural features of the network in the training results, we employed a multi-channel learning approach to perform high-order feature modeling on the network. We proposed a novel algorithm for multi-channel high-order network representation learning, referred to as the Multi-Channel High-Order Network Representation (MHNR) algorithm. This algorithm initially constructs high-order network features from the original network structure, thereby transforming the single-channel network representation learning process into a multi-channel high-order network representation learning process. Then, for each single-channel network representation learning process, the novel graph assimilation mechanism is introduced in the algorithm, so as to realize the high-order network structure modeling mechanism in the single-channel network representation learning. Finally, the algorithm integrates the multi-channel and single-channel mechanism of high-order network structure joint modeling, realizing the efficient use of network structure features and sufficient modeling. Experimental results show that the node classification performance of the proposed MHNR algorithm reaches a good order on Citeseer, Cora, and DBLP data, and its node classification performance is better than that of the comparison algorithm used in this paper. In addition, when the vector length is optimized, the average classification accuracy of nodes of the proposed algorithm is up to 12.24% higher than that of the DeepWalk algorithm. Therefore, the node classification performance of the proposed algorithm can reach the current optimal order only based on the structural features of the network under the condition of no external feature supplementary modeling.

Extraction of Lilium davidii var. unicolor Planting Information Based on Deep Learning and Multi-Source Data.

Accurate extraction of crop acreage is an important element of digital agriculture. This study uses Sentinel-2A, Sentinel-1, and DEM as data sources to construct a multidimensional feature dataset encompassing spectral features, vegetation index, texture features, terrain features, and radar features. The Relief-F algorithm is applied for feature selection to identify the optimal feature dataset. And the combination of deep learning and the random forest (RF) classification method is utilized to identify lilies in Qilihe District and Yuzhong County of Lanzhou City, obtain their planting structure, and analyze their spatial distribution characteristics in Gansu Province. The findings indicate that terrain features significantly contribute to ground object classification, with the highest classification accuracy when the number of features in the feature dataset is 36. The precision of the deep learning classification method exceeds that of RF, with an overall classification accuracy and kappa coefficient of 95.9% and 0.934, respectively. The Lanzhou lily planting area is 137.24 km2, and it primarily presents a concentrated and contiguous distribution feature. The study's findings can serve as a solid scientific foundation for Lanzhou City's lily planting structure adjustment and optimization and a basis of data for local lily yield forecasting, development, and application.