ObjectiveThis paper aims to verify the therapeutic effect of Cranial Painkiller pills' extract powder prepared by the new process on the rat's trigeminal neuralgia model caused by infraorbital injection of Talci Pulvis， evaluate its potential clinical application value， and compare the therapeutic effect with that of Cranial Painkiller granules， so as to provide data support for the application of the Cranial Painkiller pills' extract powder and precise treatment. MethodsThe rat's trigeminal neuralgia model was constructed by infraorbital injection of Talci Pulvis， and the rats were randomly divided into the normal group， model group， carbamazepine group （60 mg·kg^-1）， Cranial Painkiller granules group （2.70 g·kg^-1）， and low， medium， and high dosage groups of Cranial Painkiller pills' extract powder （1.35， 2.70， 5.40 g·kg^-1） according to the basal mechanical pain thresholds， and there were 10 rats in each group. The drug was administered by gavage to each group 2 h after modeling， and distilled water was given by gavage to the normal and model groups under the same conditions once a day for 10 d. Von Frey brushes were used to measure mechanical pain thresholds in rats. Hematoxylin-eosin （HE） staining was used to detect pathological changes in the trigeminal ganglion， and enzyme-linked immunosorbent assay （ELISA） was used to detect the inflammatory factors interleukin-1 （IL-1）， interleukin-6 （IL-6）， interleukin-8 （IL-8）， and tumor necrosis factor-α （TNF-α） levels in rat serum， as well as neuropeptide substance P （SP） and β-endorphin （β-EP） levels in rat brain tissue. Western blot technique was used to detect the levels of NLRP3， ASC， Caspase-1， and OTULIN proteins in rat brain tissue. ResultsCompared with the normal group， the pain threshold of rats in the model group showed a continuous significant decrease （P<0.01）. The pathological damage of brain tissue was significant （P<0.01）， and the inflammatory levels of IL-1， IL-6， IL-8， and TNF-α in serum were significantly elevated （P<0.01）. The level of the SP in the brain tissue was significantly elevated （P<0.01）， and the level of β-EP was significantly reduced （P<0.01）， while the level of OTULIN was significantly reduced， and NLRP3， ASC， and Caspase-1 protein levels were significantly elevated （P<0.01）. After administration of the drug， compared with the model group， the pain threshold of each dose group of the Cranial Painkiller pills' extract powder and the Cranial Painkiller granules group significantly increased （P<0.01）. The inflammatory levels of IL-1， IL-6， IL-8， and TNF-α and SP levels significantly decreased （P<0.01）， and the β-EP levels were significantly elevated （P<0.01）， while the levels of OTULIN protein were significantly elevated （P<0.05， P<0.01）， and the levels of NLRP3， ASC proteins were decreased （P<0.01）in high dose Cranial Painkiller pills' extract powder. Meanwhile， compared with those in the model group， the trigeminal ganglion lesions of rats in the Cranial Painkiller pills' extract powder and Cranial Painkiller granules groups showed different degrees of improvement （P<0.05， P<0.01）. ConclusionThe Cranial Painkiller pills' extract powder has significant therapeutic effects on the rat model of trigeminal neuralgia induced by infraorbital injection of Talci Pulvis， and its mechanism is related to the improvement of OTULIN-regulated neuroinflammation.

ObjectiveTo investigate the protective effect and mechanism of verbenalin on mouse mononuclear macrophage leukemia cells （RAW264.7） damaged by human coronavirus （HCoV）-229E infection， thereby providing experimental evidence for its development and application. MethodsRAW264.7 macrophages were infected with different concentrations of HCoV-229E to establish a coronavirus-induced macrophage injury model using the cell counting kit-8 （CCK-8） assay for assessing cell proliferation and viability. Cells were randomly divided into four groups： normal control， verbenalin group （125 μmol·L^-1）， model group （HCoV-229E）， and HCoV-229E + verbenalin group （HCoV-229E + 125 μmol·L^-1 verbenalin）. Cell viability was measured using the CCK-8 assay， and the maximum non-toxic concentration （CC₀）， half-maximal cytotoxic concentration （CC₅₀）， half-maximal effective concentration （EC₅₀）， and selectivity index （SI） of verbenalin were calculated. Calcein/PI double staining was used to assess cell viability and cytotoxicity， and JC-1 staining was applied to evaluate changes in mitochondrial membrane potential （MMP）. mito-Keima adenovirus labeling was used to assess mitophagy levels in each group. ResultsA macrophage infection model was successfully established by infecting RAW264.7 cells with the original concentration of HCoV-229E for 36 h. The CC₀ of verbenalin was 125 μmol·L^-1. The CC₅₀ was 448.25 μmol·L^-1. The EC₅₀ against HCoV-229E-infected cells was 46.28 μmol·L^-1， and the SI was 9.68. Compared with the normal group， the model group showed significantly reduced cell survival rate （P<0.01）， increased cell death rate （P<0.01）， decreased MMP （P<0.01）， and suppressed mitophagy （P<0.01）. In contrast， verbenalin treatment significantly improved cell survival rate （P<0.01）， reduced cell death rate （P<0.01）， alleviated MMP loss （P<0.01）， and enhanced mitophagy levels （P<0.01） compared with the model group. ConclusionVerbenalin can enhance the survival rate of macrophages following HCoV-229E infection. The underlying mechanism may be associated with the activation of mitophagy， maintenance of MMP stability， and alleviation of mitochondrial damage.

ObjectiveTo explore the effects of the Tibetan medicine Sanwei Doukoutang （SWDK） on cognitive dysfunction in mice suffering from Alzheimer's disease （AD） and its related mechanism. MethodsFifty SPF 5 × FAD mice were randomly divided into model group， total ginsenoside group（0.04 g·kg^-1）， high-， medium-， and low-dose groups of SWDK （32.60， 16.30， 8.15 g·kg^-1）， with 10 mice in each group， and ten wild-type mice of the same age were used as the normal group， male and female in 1∶1. Gavage administration was performed once daily for 8 weeks. The Morris water maze test and contextual fear memory experiment were used to observe learning and memory function. Hematoxylin-eosin （HE） staining was utilized to observe the changes in the pathomorphology of brain tissue in mice. The levels of synaptophysin （SYP） and postsynaptic dense substance 95 （PSD95） in mice serum were detected by enzyme-linked immunosorbent assay （ELISA）. The positive expression of brain-derived neurotrophic factor（BDNF） in the dentate gyrus （DG） region of mouse brain tissue was observed by immunohistochemistry （IHC）. The protein levels of BDNF， Wnt family member 3A（Wnt3a）， and β-catenin were detected in the hippocampus of mice by Western blot. ResultsCompared with the normal group of mice， the model group of mice had significantly more complex swimming routes and lower swimming speed （P<0.01）， significantly lower percentage of time spent in the target quadrant （P<0.01）， and a significantly lower percentage of freezing time （P<0.05）. The number of neurons in the hippocampal region of mice was obviously reduced and unevenly arranged. The levels of SYP and PSD95（P<0.01） in the serum of mice were reduced， and the positive expression of BDNF in the DG region of the brain tissue of mice was reduced. The levels of hippocampal BDNF， Wnt3a， and β-catenin proteins in the hippocampus of mice were obviously reduced （P<0.05， P<0.01）. Compared with the model group， the mice in the SWDK group and the total ginsenoside group had significantly shorter swimming routes， the high- and medium- dose SWDK groups significantly higher swimming speeds （P<0.01）， significantly higher percentage of time spent in the target quadrant （P<0.01）， obviously higher percentage of Freezing time （P<0.05）， and obviously more neurons in the hippocampal region of the mice with tighter arrangement. The mice had elevated levels of serum SYP （P<0.05， P<0.01）， PSD95 （P<0.01）， increased BDNF-positive cells in the DG region of brain tissue， and obviously elevated levels of BDNF， Wnt3a， and β-catenin proteins in the hippocampus of mice （P<0.05， P<0.01）. ConclusionSWDK can significantly improve the cognitive dysfunction of AD mice， and its mechanism may be related to regulating the Wnt/β-catenin signaling pathway， which promotes BDNF expression and thereby enhances synaptic plasticity， allowing neuronal signaling to be restored.

ObjectiveThis paper aims to verify the therapeutic effect of Cranial Painkiller pills' extract powder prepared by the new process on the rat's trigeminal neuralgia model caused by infraorbital injection of Talci Pulvis， evaluate its potential clinical application value， and compare the therapeutic effect with that of Cranial Painkiller granules， so as to provide data support for the application of the Cranial Painkiller pills' extract powder and precise treatment. MethodsThe rat's trigeminal neuralgia model was constructed by infraorbital injection of Talci Pulvis， and the rats were randomly divided into the normal group， model group， carbamazepine group （60 mg·kg^-1）， Cranial Painkiller granules group （2.70 g·kg^-1）， and low， medium， and high dosage groups of Cranial Painkiller pills' extract powder （1.35， 2.70， 5.40 g·kg^-1） according to the basal mechanical pain thresholds， and there were 10 rats in each group. The drug was administered by gavage to each group 2 h after modeling， and distilled water was given by gavage to the normal and model groups under the same conditions once a day for 10 d. Von Frey brushes were used to measure mechanical pain thresholds in rats. Hematoxylin-eosin （HE） staining was used to detect pathological changes in the trigeminal ganglion， and enzyme-linked immunosorbent assay （ELISA） was used to detect the inflammatory factors interleukin-1 （IL-1）， interleukin-6 （IL-6）， interleukin-8 （IL-8）， and tumor necrosis factor-α （TNF-α） levels in rat serum， as well as neuropeptide substance P （SP） and β-endorphin （β-EP） levels in rat brain tissue. Western blot technique was used to detect the levels of NLRP3， ASC， Caspase-1， and OTULIN proteins in rat brain tissue. ResultsCompared with the normal group， the pain threshold of rats in the model group showed a continuous significant decrease （P<0.01）. The pathological damage of brain tissue was significant （P<0.01）， and the inflammatory levels of IL-1， IL-6， IL-8， and TNF-α in serum were significantly elevated （P<0.01）. The level of the SP in the brain tissue was significantly elevated （P<0.01）， and the level of β-EP was significantly reduced （P<0.01）， while the level of OTULIN was significantly reduced， and NLRP3， ASC， and Caspase-1 protein levels were significantly elevated （P<0.01）. After administration of the drug， compared with the model group， the pain threshold of each dose group of the Cranial Painkiller pills' extract powder and the Cranial Painkiller granules group significantly increased （P<0.01）. The inflammatory levels of IL-1， IL-6， IL-8， and TNF-α and SP levels significantly decreased （P<0.01）， and the β-EP levels were significantly elevated （P<0.01）， while the levels of OTULIN protein were significantly elevated （P<0.05， P<0.01）， and the levels of NLRP3， ASC proteins were decreased （P<0.01）in high dose Cranial Painkiller pills' extract powder. Meanwhile， compared with those in the model group， the trigeminal ganglion lesions of rats in the Cranial Painkiller pills' extract powder and Cranial Painkiller granules groups showed different degrees of improvement （P<0.05， P<0.01）. ConclusionThe Cranial Painkiller pills' extract powder has significant therapeutic effects on the rat model of trigeminal neuralgia induced by infraorbital injection of Talci Pulvis， and its mechanism is related to the improvement of OTULIN-regulated neuroinflammation.

ObjectiveTo investigate the protective effect and mechanism of verbenalin on mouse mononuclear macrophage leukemia cells （RAW264.7） damaged by human coronavirus （HCoV）-229E infection， thereby providing experimental evidence for its development and application. MethodsRAW264.7 macrophages were infected with different concentrations of HCoV-229E to establish a coronavirus-induced macrophage injury model using the cell counting kit-8 （CCK-8） assay for assessing cell proliferation and viability. Cells were randomly divided into four groups： normal control， verbenalin group （125 μmol·L^-1）， model group （HCoV-229E）， and HCoV-229E + verbenalin group （HCoV-229E + 125 μmol·L^-1 verbenalin）. Cell viability was measured using the CCK-8 assay， and the maximum non-toxic concentration （CC₀）， half-maximal cytotoxic concentration （CC₅₀）， half-maximal effective concentration （EC₅₀）， and selectivity index （SI） of verbenalin were calculated. Calcein/PI double staining was used to assess cell viability and cytotoxicity， and JC-1 staining was applied to evaluate changes in mitochondrial membrane potential （MMP）. mito-Keima adenovirus labeling was used to assess mitophagy levels in each group. ResultsA macrophage infection model was successfully established by infecting RAW264.7 cells with the original concentration of HCoV-229E for 36 h. The CC₀ of verbenalin was 125 μmol·L^-1. The CC₅₀ was 448.25 μmol·L^-1. The EC₅₀ against HCoV-229E-infected cells was 46.28 μmol·L^-1， and the SI was 9.68. Compared with the normal group， the model group showed significantly reduced cell survival rate （P<0.01）， increased cell death rate （P<0.01）， decreased MMP （P<0.01）， and suppressed mitophagy （P<0.01）. In contrast， verbenalin treatment significantly improved cell survival rate （P<0.01）， reduced cell death rate （P<0.01）， alleviated MMP loss （P<0.01）， and enhanced mitophagy levels （P<0.01） compared with the model group. ConclusionVerbenalin can enhance the survival rate of macrophages following HCoV-229E infection. The underlying mechanism may be associated with the activation of mitophagy， maintenance of MMP stability， and alleviation of mitochondrial damage.

ObjectiveTo explore the effects of the Tibetan medicine Sanwei Doukoutang （SWDK） on cognitive dysfunction in mice suffering from Alzheimer's disease （AD） and its related mechanism. MethodsFifty SPF 5 × FAD mice were randomly divided into model group， total ginsenoside group（0.04 g·kg^-1）， high-， medium-， and low-dose groups of SWDK （32.60， 16.30， 8.15 g·kg^-1）， with 10 mice in each group， and ten wild-type mice of the same age were used as the normal group， male and female in 1∶1. Gavage administration was performed once daily for 8 weeks. The Morris water maze test and contextual fear memory experiment were used to observe learning and memory function. Hematoxylin-eosin （HE） staining was utilized to observe the changes in the pathomorphology of brain tissue in mice. The levels of synaptophysin （SYP） and postsynaptic dense substance 95 （PSD95） in mice serum were detected by enzyme-linked immunosorbent assay （ELISA）. The positive expression of brain-derived neurotrophic factor（BDNF） in the dentate gyrus （DG） region of mouse brain tissue was observed by immunohistochemistry （IHC）. The protein levels of BDNF， Wnt family member 3A（Wnt3a）， and β-catenin were detected in the hippocampus of mice by Western blot. ResultsCompared with the normal group of mice， the model group of mice had significantly more complex swimming routes and lower swimming speed （P<0.01）， significantly lower percentage of time spent in the target quadrant （P<0.01）， and a significantly lower percentage of freezing time （P<0.05）. The number of neurons in the hippocampal region of mice was obviously reduced and unevenly arranged. The levels of SYP and PSD95（P<0.01） in the serum of mice were reduced， and the positive expression of BDNF in the DG region of the brain tissue of mice was reduced. The levels of hippocampal BDNF， Wnt3a， and β-catenin proteins in the hippocampus of mice were obviously reduced （P<0.05， P<0.01）. Compared with the model group， the mice in the SWDK group and the total ginsenoside group had significantly shorter swimming routes， the high- and medium- dose SWDK groups significantly higher swimming speeds （P<0.01）， significantly higher percentage of time spent in the target quadrant （P<0.01）， obviously higher percentage of Freezing time （P<0.05）， and obviously more neurons in the hippocampal region of the mice with tighter arrangement. The mice had elevated levels of serum SYP （P<0.05， P<0.01）， PSD95 （P<0.01）， increased BDNF-positive cells in the DG region of brain tissue， and obviously elevated levels of BDNF， Wnt3a， and β-catenin proteins in the hippocampus of mice （P<0.05， P<0.01）. ConclusionSWDK can significantly improve the cognitive dysfunction of AD mice， and its mechanism may be related to regulating the Wnt/β-catenin signaling pathway， which promotes BDNF expression and thereby enhances synaptic plasticity， allowing neuronal signaling to be restored.

ObjectiveTo investigate the mechanism of Huangqin Tang （HQT） in regulating metabolic reprogramming during the inflammation-cancer transformation in colitis-associated colorectal cancer （CAC）. MethodsCAC mouse model was established using the carcinogen azoxymethane （AOM） combined with the inflammatory agent dextran sulfate sodium （DSS）. HQT treatment was adopted. Serum metabolomics analysis was performed at three stages （inflammation， proliferation， and tumor formation） using liquid chromatography-tandem mass spectrometry （LC-MS/MS） untargeted metabolomics coupled with multivariate statistical analysis to explore the mechanism of HQT intervention in metabolism in CAC. ResultsThe results revealed that HQT significantly reversed the disturbance of key metabolites in CAC mice. A total of 52， 67， and 45 differential metabolites were identified in the model group， compared to the normal group， during inflammation， proliferation， and tumor stages， respectively. Lactate， linoleic acid， oleic acid， elaidic acid， and betaine were characteristic metabolites persistently enriched throughout colitis-cancer transformation. Pathway enrichment analysis of differential metabolites showed that linoleic acid metabolism and arachidonic acid metabolism were the most significantly disturbed in CAC pathogenesis. The proliferation stage featured expanded amino acid metabolic networks， while the tumor stage uniquely exhibited two new pathways of nicotinate and nicotinamide metabolism and phosphoinositide metabolism. HQT exerted stage-specific regulatory effects： targeting arachidonic acid metabolism in the inflammation stage， correcting the dysregulation of choline-carnitine metabolism in the proliferation stage， and rescuing nicotinamide and tryptophan metabolic collapse in the tumor stage. ConclusionHQT exerts regulatory effects on metabolic disorders at various stages of the colitis-cancer transformation process， thereby effectively slowing the progression from colitis to cancer. The study also reveals the dynamic metabolic characteristics of colorectal "inflammation-cancer transformation，"providing new insights for research on the targeted mechanisms of traditional Chinese medicine in anti-tumor therapy based on metabolic reprogramming.

ObjectiveTo evaluate the pharmacological effects of verbenalin on both in vitro and in vivo infection models of human coronavirus 229E （HCoV-229E） and to preliminarily explore the antiviral mechanism of verbenalin through proteomic analysis. MethodsIn vitro， the cell counting kit-8 （CCK-8） for cell proliferation and viability assessment was used to establish a model of HCoV-229E-induced injury in human lung adenocarcinoma cells（A549）. A549 cells were divided into five groups： normal group， model group， and three verbenalin treatment groups （125， 62.5， and 31.25 μmol·L^-1）. The cell protective activity of verbenalin was evaluated through cell viability assay and immunofluorescence staining. In vivo， 30 BALB/c mice were randomly divided into normal group， model group， chloroquine group， and high-dose， low-dose verbenalin groups （40 and 20 mg·kg^-1）， with six mice per group. An HCoV-229E-induced mouse lung injury model was established to evaluate the therapeutic effects of verbenalin. Lung injury was assessed by detecting the lung index and lung inhibition rate. The severity of pulmonary inflammation cytokines was measured by enzyme-linked immunosorbent assay （ELISA）， while the lung morphology and structure were analyzed by micro-computed tomography （Micro-CT）. Hematoxylin and eosin （HE） staining was used to assess histopathological changes in lung tissue. Additionally， four-dimensional data-independent acquisition （4D-DIA） proteomics was employed to preliminarily explore the potential mechanisms of verbenalin in treating HCoV-229E-induced lung injury in mice， through differential protein expression screening， functional annotation， enrichment analysis， and protein-protein interaction network analysis. ResultsThe A549 cells were infected with HCoV-229E at the original viral titer for 36 hours to establish an in vitro infection model. The maximum non-toxic concentration of verbenalin was 125 μmol·L^-1， and the half-maximal cytotoxic concentration （CC₅₀） was 288.8 μmol·L^-1. Compared with the normal group， the model group showed a significant decrease in cell viability （P<0.01）， a significant increase in the proportion of dead cells （P<0.01）， mitochondrial damage， and a significant reduction in mitochondrial membrane potential （P<0.01）. After treatment with different concentrations of verbenalin （125， 62.5， and 31.25 μmol·L^-1）， cell viability was significantly increased （P<0.01）， and the proportion of dead cells was reduced （P<0.01）， with mitochondrial membrane potential restored （P<0.01）. In vivo experiments further confirmed the therapeutic effect of verbenalin on HCoV-229E-infected mice. Compared to the normal group， the model group showed a significant increase in the lung index （P<0.01）， severe lung tissue injury， lung volume enlargement， and a significant increase in the expression of inflammatory cytokines， including interleukin-6 （IL-6） and tumor necrosis factor-α （TNF-α） （P<0.01）. In contrast， in the verbenalin treatment groups， these pathological changes were significantly improved， with a reduction in the lung index （P<0.01）， alleviation of lung tissue injury， reduced lung volume enlargement， and a significant decrease in inflammatory cytokine expression （P<0.01）. Proteomics analysis revealed that， compared to the normal group， the model group showed enrichment in several antiviral immune-related signaling pathways， including the nuclear factor-κB （NF-κB） signaling pathway （P<0.05）. Compared to the model group， the verbenalin treatment group showed enrichment in several signaling pathways related to inflammatory response and autophagy （P<0.05）， suggesting that verbenalin may exert its antiviral and anti-inflammatory effects by regulating these pathways. ConclusionVerbenalin demonstrates significant therapeutic effects in both in vitro and in vivo HCoV-229E infection models， with its mechanism likely related to the NOD-like receptor protein 3 （NLRP3） inflammasome pathway and mitochondrial autophagy.

Objective:This study aims to analyze the performance of five automatic cell type annotation methods in single cell RNA sequencing (scRNA-seq) data.Methods:Simulated data were generated using the Splatter package in R language, taking into account two data characteristics: the number of cells and the number of genes. The actual data came from the GSE10245 scRNA seq dataset of non-small cell lung cancer in Gene Expression Omnibus (GEO) database, the data had been pre-processed and batch effects had been eliminated. The automatic cell type recognition (ACTINN) of neural networks, the single-cell type annotation method based on deep learning (scDeepSort), the reference batch transcriptome annotation scRNA seq R-package (SingleR), the cross platform and cross species scRNA seq data classifier (SingleCellNet), and the cross scRNA seq dataset projection (scMap-cell) were implemented using the Tensorflow library in Python. The performance evaluation indicators for cell type annotation included accuracy (ACC), F1-score, and Matthews correlation coefficient (MCC). Each method was validated using ten fold cross validation, and the average value was taken after 50 repeated runs for performance comparison between methods. The Dunnett's t-test in the DescTools package of R language was used for multiple comparisons between ACTINN and other four methods. Results:Under 12 different scenarios (3 levels of cell numbers × 4 levels of gene numbers), simulated data analysis showed that compared with scDeepSort, SingleR, SingleCellNet, and scMap-cell, the percentage increase in ACC value of ACTINN ranged from 3.31% to 14.59%, 1.38% to 13.03%, 12.98% to 25.25%, and 20.72% to 29.62%, respectively; the range of F1 score improvement percentages were 2.75% - 22.74%, 2.46% - 23.68%, 5.07% - 27.47%, and 10.27% - 31.47%, respectively; the percentage increase ranges for MCC values were 3.42% - 9.75%, 2.26% - 7.61%, 5.41% - 11.11%, and 8.27% - 15.22%, respectively. Actual data analysis showed that the ACC value of ACTINN was 81.0%, which was increased by 2.1%, 5.2%, 7.9%, and 8.9% compared with the above four methods, respectively; the F1-score value was 80.5%, which was increased by 2.3%, 5.9%, 2.4%, and 6.0%, respectively; the MCC value was 83.3%, which was increased by 0.9%, 2.5%, 3.4%, and 11.2%, respectively. The results of Dunnett's t-test showed that the difference was not statistically significant in ACC values between scDeepSort and ACTINN ( P = 0.821), in F1-score values between scDeepSort and ACTINN ( P = 0.498), and in MCC values between scDeepSort, SingleCellNet and ACTINN ( P = 0.904, 0.134). However, the differences were statistically significant in other multiple comparisons ( P < 0.05). Conclusions:ACTINN and scDeepSort have good performance in cell type annotation, with ACTINN showing outstanding performance and SingleR showing robust performance, while SingleCellNet and scMap-cell have relatively limited performance. This suggests that self-attention mechanism algorithm based on Transformer framework is expected to promote further development of automatic cell annotation methods.

Objective:This study aims to analyze the performance of five automatic cell type annotation methods in single cell RNA sequencing (scRNA-seq) data.Methods:Simulated data were generated using the Splatter package in R language, taking into account two data characteristics: the number of cells and the number of genes. The actual data came from the GSE10245 scRNA seq dataset of non-small cell lung cancer in Gene Expression Omnibus (GEO) database, the data had been pre-processed and batch effects had been eliminated. The automatic cell type recognition (ACTINN) of neural networks, the single-cell type annotation method based on deep learning (scDeepSort), the reference batch transcriptome annotation scRNA seq R-package (SingleR), the cross platform and cross species scRNA seq data classifier (SingleCellNet), and the cross scRNA seq dataset projection (scMap-cell) were implemented using the Tensorflow library in Python. The performance evaluation indicators for cell type annotation included accuracy (ACC), F1-score, and Matthews correlation coefficient (MCC). Each method was validated using ten fold cross validation, and the average value was taken after 50 repeated runs for performance comparison between methods. The Dunnett's t-test in the DescTools package of R language was used for multiple comparisons between ACTINN and other four methods. Results:Under 12 different scenarios (3 levels of cell numbers × 4 levels of gene numbers), simulated data analysis showed that compared with scDeepSort, SingleR, SingleCellNet, and scMap-cell, the percentage increase in ACC value of ACTINN ranged from 3.31% to 14.59%, 1.38% to 13.03%, 12.98% to 25.25%, and 20.72% to 29.62%, respectively; the range of F1 score improvement percentages were 2.75% - 22.74%, 2.46% - 23.68%, 5.07% - 27.47%, and 10.27% - 31.47%, respectively; the percentage increase ranges for MCC values were 3.42% - 9.75%, 2.26% - 7.61%, 5.41% - 11.11%, and 8.27% - 15.22%, respectively. Actual data analysis showed that the ACC value of ACTINN was 81.0%, which was increased by 2.1%, 5.2%, 7.9%, and 8.9% compared with the above four methods, respectively; the F1-score value was 80.5%, which was increased by 2.3%, 5.9%, 2.4%, and 6.0%, respectively; the MCC value was 83.3%, which was increased by 0.9%, 2.5%, 3.4%, and 11.2%, respectively. The results of Dunnett's t-test showed that the difference was not statistically significant in ACC values between scDeepSort and ACTINN ( P = 0.821), in F1-score values between scDeepSort and ACTINN ( P = 0.498), and in MCC values between scDeepSort, SingleCellNet and ACTINN ( P = 0.904, 0.134). However, the differences were statistically significant in other multiple comparisons ( P < 0.05). Conclusions:ACTINN and scDeepSort have good performance in cell type annotation, with ACTINN showing outstanding performance and SingleR showing robust performance, while SingleCellNet and scMap-cell have relatively limited performance. This suggests that self-attention mechanism algorithm based on Transformer framework is expected to promote further development of automatic cell annotation methods.