Network Pharmacology and Experimental Verification Reveal the Regulatory Mechanism of Chuanbeimu in Treating Chronic Obstructive Pulmonary Disease.

Background: Chronic obstructive pulmonary disease (COPD) is a common respiratory disorder in pulmonology. Chuanbeimu (CBM) is a traditional Chinese medicinal herb for treating COPD and has been widely utilized in clinical practice. However, the mechanism of CBM in the treatment of COPD remains incompletely understood. This study aims to investigate the underlying therapeutic mechanism of CBM for COPD using network pharmacology and experimental approaches. Methods: Active ingredients and their targets were obtained from the Traditional Chinese Medicine Systems Pharmacology database. COPD-associated targets were retrieved from the GeneCards database. The common targets for CBM and COPD were identified through Venn diagram analysis. Protein-protein interaction (PPI) networks and disease-herb-ingredient-target networks were constructed. Subsequently, the results of the network pharmacology were validated by molecular docking and in vitro experiments. Results: Seven active ingredients and 32 potential targets for CBM were identified as closely associated with COPD. The results of the disease-herb-ingredient-target network and PPI network showed that peimisine emerged as the core ingredient, and SRC, ADRB2, MMP2, and NOS3 were the potential targets for CBM in treating COPD. Molecular docking analysis confirmed that peimisine exhibited high binding affinity with SRC, ADRB2, MMP2, and NOS3. In vitro experiments demonstrated that peimisine significantly upregulated the expression of ADRB2 and NOS3 and downregulated the expression of SRC and MMP2. Conclusion: These findings indicate that CBM may modulate the expression of SRC, ADRB2, MMP2, and NOS3, thereby exerting a protective effect against COPD.

PGKD-Net: Prior-guided and Knowledge Diffusive Network for Choroid Segmentation.

The thickness of the choroid is considered to be an important indicator of clinical diagnosis. Therefore, accurate choroid segmentation in retinal OCT images is crucial for monitoring various ophthalmic diseases. However, this is still challenging due to the blurry boundaries and interference from other lesions. To address these issues, we propose a novel prior-guided and knowledge diffusive network (PGKD-Net) to fully utilize retinal structural information to highlight choroidal region features and boost segmentation performance. Specifically, it is composed of two parts: a Prior-mask Guided Network (PG-Net) for coarse segmentation and a Knowledge Diffusive Network (KD-Net) for fine segmentation. In addition, we design two novel feature enhancement modules, Multi-Scale Context Aggregation (MSCA) and Multi-Level Feature Fusion (MLFF). The MSCA module captures the long-distance dependencies between features from different receptive fields and improves the model's ability to learn global context. The MLFF module integrates the cascaded context knowledge learned from PG-Net to benefit fine-level segmentation. Comprehensive experiments are conducted to evaluate the performance of the proposed PGKD-Net. Experimental results show that our proposed method achieves superior segmentation accuracy over other state-of-the-art methods. Our code is made up publicly available at: https://github.com/yzh-hdu/choroid-segmentation.

Salvianolic Acid B Alleviates Liver Injury by Regulating Lactate-Mediated Histone Lactylation in Macrophages.

Salvianolic acid B (Sal B) is the primary water-soluble bioactive constituent derived from the roots of Salvia miltiorrhiza Bunge. This research was designed to reveal the potential mechanism of Sal B anti-liver injury from the perspective of macrophages. In our lipopolysaccharide-induced M1 macrophage model, Sal B showed a clear dose-dependent gradient of inhibition of the macrophage trend of the M1 type. Moreover, Sal B downregulated the expression of lactate dehydrogenase A (LDHA), while the overexpression of LDHA impaired Sal B's effect of inhibiting the trend of macrophage M1 polarization. Additionally, this study revealed that Sal B exhibited inhibitory effects on the lactylation process of histone H3 lysine 18 (H3K18la). In a ChIP-qPCR analysis, Sal B was observed to drive a reduction in H3K18la levels in the promoter region of the LDHA, NLRP3, and IL-1ß genes. Furthermore, our in vivo experiments showed that Sal B has a good effect on alleviating CCl4-induced liver injury. An examination of liver tissues and the Kupffer cells isolated from those tissues proved that Sal B affects the M1 polarization of macrophages and the level of histone lactylation. Together, our data reveal that Sal B has a potential mechanism of inhibiting the histone lactylation of macrophages by downregulating the level of LDHA in the treatment of liver injury.

Hsa_circ_0008833 promotes COPD progression via inducing pyroptosis in bronchial epithelial cells.

Purpose: Chronic obstructive pulmonary disease (COPD) is a common respiratory disorder. Pyroptosis represents a distinctive form of inflammatory cell death that is mediated through the activation of Caspase-1 and inflammasomes. CircRNAs have emerged as a novel class of biomolecules with implications in various human diseases. This study aims to investigate the circRNAs profile of in COPD progression and identify pivotal circRNAs associated with the development of this disease. Methods: he expression profiles of circRNAs in peripheral blood mononuclear cells of COPD patients were assessed by circRNA microarray. Furthermore, flag-labeled vectors were constructed to assess the potential protein-coding capacity of has-circ-0008833. 16HBE cells were stably transfected with lentivirus approach, and cell proliferation and death were assessed to clarify the functional roles of has-circ-0008833 and its encoded protein circ-0008833aa. Additionally, western blot analysis was furthered performed to determine the level of Caspase-1, IL-18, IL-1ß, NLRP3, ASC, and cleaved GSDMD regulated by has-circ-0008833 and circ-0008833-57aa. Results: Initially, we screened the expression profiles of human circRNAs in peripheral blood mononuclear cells of COPD patients, and found that has-circ-0008833 exhibited a significant increase in COPD mononuclear cells. Subsequently, we demonstrated that has-circ-0008833 carried an open reading frame (ORF), which encoded a functional protein, referred to as circ-0008833-57aa. By employing gain-of-function approaches, our results suggested that both circ-0008833 and circ-0008833-57aa inhibited proliferation, but accelerated the rate of 16HBE cell death. Finally, we discovered that circ-0008833 and circ-0008833-57aa promoted the expression of Caspase-1, IL-18, IL-1ß, NLRP3, ASC, and cleaved GSDMD in 16HBE cells. Conclusions: Upregulation of circ-0008833 might promote COPD progression by inducing pyroptosis of bronchial epithelial cells through the encoding of a 57-amino acid peptide.

The Study of the Influence of IL5RA Variants on Chronic Obstructive Pulmonary Disease.

Chronic obstructive pulmonary disease (COPD) is a complex disease, and its pathogenesis is influenced by genetic factors. This study aimed to evaluate the role of IL5RA genetic variation in the risk of COPD. In this study, 498 patients with COPD and 498 normal controls were recruited. Subsequently, five SNPs (rs3804795, rs2290610, rs13097407, rs334782, and rs3856850) in the IL5RA gene were genotyped. Logistic analysis examined the association of five single nucleotide polymorphisms (SNPs) in IL5RA with the risk of COPD under various genetic models. Furthermore, the association between IL5RA and susceptibility to COPD was comprehensively analyzed with stratification based on age, sex, smoking, and alcohol consumption. Our study showed that IL5RA rs13097407 reduced susceptibility to COPD (OR = 0.43, p < 0.001, p (FDR)< 0.001). On the other hand, rs3856850 was associated with an increased risk of COPD (OR = 1.71, p = 0.002, p (FDR) = 0.002). Interestingly, the effect of IL5RA SNPs on susceptibility to COPD was found to be influenced by factors such as sex and smoking. IL5RA gene variants were significantly associated with susceptibility to COPD.

The mechanisms of multidrug resistance of breast cancer and research progress on related reversal agents.

Chemotherapy is the mainstay in the treatment of breast cancer. However, many drugs that are commonly used in clinical practice have a high incidence of side effects and multidrug resistance (MDR), which is mainly caused by overexpression of drug transporters and related enzymes in breast cancer cells. In recent years, researchers have been working hard to find newer and safer drugs to overcome MDR in breast cancer. In this review, we provide the molecule mechanism of MDR in breast cancer, categorize potential lead compounds that inhibit single or multiple drug transporter proteins, as well as related enzymes. Additionally, we have summarized the structure-activity relationship (SAR) based on potential breast cancer MDR modulators with lower side effects. The development of novel approaches to suppress MDR is also addressed. These lead compounds hold great promise for exploring effective chemotherapy agents to overcome MDR, providing opportunities for curing breast cancer in the future.

A Review on the Mechanism and Structure-activity Relationship of Resveratrol Heteroaryl Analogues.

Resveratrol is one of the most interesting naturally-occurring nonflavonoid phenolic compounds with various biological activities, such as anticancer, neuroprotection, antibacterial, and anti-inflammatory. However, there is no clinical usage of resveratrol due to either its poor activity or poor pharmacokinetic properties. Heteroarenes-modified resveratrol is one pathway to improve its biological activities and bioavailability, and form more modification sites. In this review, we present the progress of heteroaryl analogues of resveratrol with promising biological activities in the latest five years, ranging from the synthesis to the structure-activity relationship and mechanism of actions. Finally, introducing heteroarenes into resveratrol is an effective strategy, which focuses on the selectivity of structure-activity relationship in vivo.

The m6A reader MhYTP2 regulates the stability of its target mRNAs contributing to low nitrogen tolerance in apple (Malus domestica).

Studies have shown that the m6A reader primarily affects genes expression by participating in the regulation of mRNA localization, splicing, degradation, translation, and other metabolic processes. Previously, we discovered that the apple (Malus domestica) m6A reader MhYTP2 bound with and destabilized m6A-modified MdMLO19 mRNA. In addition, it enhanced the translation efficiency of m6A-modified mRNA of MdGDH1L, encoding a glutamate dehydrogenase, which confers resistance to powdery mildew. In this study, we report the function of MhYTP2 in the regulation of resistance to low nitrogen (N). The overexpression of MhYTP2 enhances the resistance of apple to low N. We show that MhYTP2 binds with and stabilizes the mRNAs of MdALN, which participates in the allantoin catabolic process and cellular response to N starvation in apple; MdPIDL, which participates in root hair elongation; MdTTG1, which is involved in the differentiation process of trichomes; and MdATG8A, which is a core participant in the regulation of autophagy. In addition, MhYTP2 accelerates the degradation of MdRHD3 mRNA, which regulates root development. RNA immunoprecipitation-seq and electrophoretic mobility shift assays show that the mRNAs of MdALN, MdATG8A, MdPIDL, MdTTG1, and MdRHD3 are the direct targets of MhYTP2. Overexpressing or knocking down the above genes in MhYTP2 overexpressing plants dismisses the function of MhYTP2 under low N, suggesting the role of MhYTP2 is dependent on those genes. Together, these results demonstrate that MhYTP2 enhances the resistance of apple to N deficiency by affecting the stability of the bound mRNAs.

The m6 A reader MhYTP2 negatively modulates apple Glomerella leaf spot resistance by binding to and degrading MdRGA2L mRNA.

Glomerella leaf spot (GLS), caused by the fungal pathogen Colletotrichum fructicola, significantly threatens apple production. Some resistances to plant disease are mediated by the accumulation of nucleotide-binding site and leucine-rich repeat (NBS-LRR) proteins that are encoded by a major class of plant disease resistance genes (R genes). However, the R genes that confer resistance to GLS in apple remain largely unclear. Malus hupehensis YT521-B homology domain-containing protein 2 (MhYTP2) was identified as an N6 -methyladenosine RNA methylation (m6 A) modified RNA reader in our previous study. However, whether MhYTP2 binds to mRNAs without m6 A RNA modifications remains unknown. In this study, we discovered that MhYTP2 exerts both m6 A-dependent and -independent functions by analysing previously obtained RNA immunoprecipitation sequencing results. The overexpression of MhYTP2 significantly reduced the resistance of apple to GLS and down-regulated the transcript levels of some R genes whose transcripts do not contain m6 A modifications. Further analysis indicated that MhYTP2 binds to and reduces the stability of MdRGA2L mRNA. MdRGA2L positively regulates resistance to GLS by activating salicylic acid signalling. Our findings revealed that MhYTP2 plays an essential role in the regulation of resistance to GLS and identified a promising R gene, MdRGA2L, for use in developing apple cultivars with GLS resistance.

Clustering analysis and prognostic model based on PI3K/AKT-related genes in pancreatic cancer.

Background: Pancreatic cancer is one of most aggressive malignancies with a dismal prognosis. Activation of PI3K/AKT signaling is instrumental in pancreatic cancer tumorigenesis. The aims of this study were to identify the molecular clustering, prognostic value, relationship with tumor immunity and targeting of PI3K/AKT-related genes (PARGs) in pancreatic cancer using bioinformatics. Methods: The GSEA website was searched for PARGs, and pancreatic cancer-related mRNA data and clinical profiles were obtained through TCGA downloads. Prognosis-related genes were identified by univariate Cox regression analysis, and samples were further clustered by unsupervised methods to identify significant differences in survival, clinical information and immune infiltration between categories. Next, a prognostic model was constructed using Lasso regression analysis. The model was well validated by univariate and multivariate Cox regression analyses, Kaplan-Meier survival analysis and ROC curves, and correlations between risk scores and patient pathological characteristics were identified. Finally, GSEA, drug prediction and immune checkpoint protein analyses were performed. Results: Pancreatic cancers were divided into Cluster 1 (C1) and Cluster 2 (C1) according to PARG mRNA expression. C1 exhibited longer overall survival (OS) and higher immune scores and CTLA4 expression, whereas C2 exhibited more abundant PD-L1. A 6-PARG-based prognostic model was constructed to divide pancreatic cancer patients into a high-risk score (HRS) group and a low-risk score (LRS) group, where the HRS group exhibited worse OS. The risk score was defined as an independent predictor of OS. The HRS group was significantly associated with pancreatic cancer metastasis, aggregation and immune score. Furthermore, the HRS group exhibited immunosuppression and was sensitive to radiotherapy and guitarbine chemotherapy. Multidrug sensitivity prediction analysis indicated that the HRS group may be sensitive to PI3K/AKT signaling inhibitors (PIK-93, GSK2126458, CAL-101 and rapamycin) and ATP concentration regulators (Thapsigargin). In addition, we confirmed the oncogenic effect of protein phosphatase 2 regulatory subunit B'' subunit alpha (PPP2R3A) in pancreatic cancer in vitro and in vivo. Conclusions: PARGs predict prognosis, tumor immune profile, radiotherapy and chemotherapy drug sensitivity and are potential predictive markers for pancreatic cancer treatment that can help clinicians make decisions and personalize treatment.

Identification of Mycoplasma pneumoniae by DNA-modified gold nanomaterials in a colorimetric assay.

Mycoplasma pneumoniae is a highly infectious bacterium and the major cause of pneumonia especially in school-going children. Mycoplasma pneumoniae affects the respiratory tract, and 25% of patients experience health-related problems. It is important to have a suitable method to detect M. pneumoniae, and gold nanoparticle (GNP)-based colorimetric biosensing was used in this study to identify the specific target DNA for M. pneumoniae. The color of GNPs changes due to negatively charged GNPs in the presence of positively charged monovalent (Na+ ) ions from NaCl. This condition is reversed in the presence of a single-stranded oligonucleotide, as it attracts GNPs but not in the presence of double-stranded DNA. Single standard capture DNA was mixed with optimal target DNA that cannot be adsorbed by GNPs; under this condition, GNPs are not stabilized and aggregate at high ionic strength (from 100 mM). Without capture DNA, the GNPs that were stabilized by capture DNA (from 1 µM) became more stable under high ionic conditions and retaining their red color. The GNPs turned blue in the presence of target DNA at concentrations of 1 pM, and the GNPs retained a red color when there was no target in the solution. This method is useful for the simple, easy, and accurate identification of M. pneumoniae target DNA at higher discrimination and without involving sophisticated equipment, and this method provides a diagnostic for M. pneumoniae.

Anticancer activity of oleanolic acid and its derivatives modified at A-ring and C-28 position.

Oleanolic acid (OA) is a five-ring triterpenoid compound, which is widely present in plants. Due to a wide range of pharmacological activities, oleanolic acid has attracted more and more attention. However, oleanolic acid is insoluble in water and has low bioavailability, which limits its clinical application. In this review, we focus on summarizing the anti-cancer activity and mechanism of the A ring or C-28 carboxyl modified derivatives of OA since 2015, to determine the strength of its anti-cancer effectiveness and evaluate whether it could be used as a clinical anti-cancer drug.

Smartphone-based microplate reader for high-throughput quantitation of disease markers in serum.

Herein, a smartphone-based portable reader with integrated optics for standard microtiter plates (96 wells) has been designed and demonstrated for high-throughput quantitation of validated biomarkers in serum. The customized optical attachment was simply constructed with a convex lens and a light source, by which the transmitted light through a 96-well microtiter plate was converged for imaging with a smartphone, so that accurate and wide-range reading of the plate can be achieved. More importantly, relying on the digitized colorimetric analysis of the obtained images, concentrations of various biomarkers can be determined directly using the customized mobile app. A set of validated biomarkers for inflammation and infection, C-reactive protein (CRP), serum amyloid A (SAA), and procalcitonin (PCT) have been quantitated with this new system; both the response ranges and limits of detection meet the requirement of clinical tests. The consistency with the results obtained using a commercial microplate reader proves its reliability and precision, augments its potential as a point-of-care diagnostic device for on-site testing or resource-limited settings.

Recent Advances of Curcumin Derivatives in Breast Cancer.

Curcumin is a potential plant-derived drug for the treatment of breast cancer. Poor solubility and bioavailability are the main factors that limit its clinical application. Various structural modification strategies have been developed to improve the anti-breast cancer activity of curcumin. This review focuses on the difference of modification sites and heterocyclic/non-heterocyclic modifications to systematically summarize curcumin derivatives with better anti-breast cancer activity.

Pd-Catalyzed Aerobic Intermolecular 1,2-Diamination of Conjugated Dienes: Regio- and Chemoselective Synthesis of Piperazines and 2-Piperazinones.

Dinitrogen heterocycles are among the most important molecular structures, and the synthesis of these types of structures through intermolecular 1,2-diamination of olefins is a direct and efficient method. However, the types of nitrogen sources are mostly derived from ureas or arylamines, and nitrogen sources from aliphatic amines are still limited due to their distinct electronic and steric effects. Herein, we report a palladium-catalyzed aerobic intermolecular 1,2-diamination of conjugated dienes, using ethanediamine and α-amino amide derivatives as nitrogen sources respectively, for the synthesis of piperazines and 2-piperazinones in good yields (up to 95 %) and with high regio- and chemoselectivities.

Design, Synthesis, and Anti-Breast Cancer Activity of Novel Fluorinated 7-O-Modified Genistein Derivatives.

BACKGROUND: Genistein has been limited in clinical application due to its low bioavailability, extremely poor liposolubility, and fast glycosylation rate, though it possesses anti-breast cancer activity. Therefore, the discovery of novel genistein derivatives is an urgency. OBJECTIVE: To enhance the anti-breast cancer activity of genistein, a series of novel fluorinated genistein derivatives were synthesized. METHODS: Their in vitro antitumor activity was investigated by the MTT assay against three cancer cell lines, via, MDA-MB-231, MCF-7, and MDA-MB-435, respectively. RESULTS: Analogs 1d, 2b, and 3b showed remarkable anticancer activities compared to tamoxifen, a clinical anti-breast cancer drug on the market. CONCLUSION: The activities against breast cancer of genistein were enhanced by introducing the 7- alkoxyl group and fluorine atom into the B-ring. Therefore, these compounds may be potential candidates for treating breast cancer.

Prevalence of Carbapenem-Resistant Hypervirulent Klebsiella pneumoniae and Hypervirulent Carbapenem-Resistant Klebsiella pneumoniae in China Determined via Mouse Lethality Tests.

Objective: To investigate the epidemiology of carbapenem-resistant hypervirulent Klebsiella pneumoniae (CR-HvKP) and hypervirulent carbapenem-resistant Klebsiella pneumoniae (Hv-CRKP). Methods: Totally 436 K. pneumoniae strains were collected from 7 hospitals in mainland China between 2017.01 and 2018.02. Sequence types, serotypes, antimicrobial-resistance and virulence genes were analyzed. Additionally, string test, capsule stain, Periodic Acid Schiff stain, fitness analysis, quantitative real-time PCR and mouse lethality test were also performed. Molecular combinations were used to screen putative blaKPC(+)-HvKP and Hv-blaKPC(+)-KP, followed by the confirmation of mouse lethality test. Results: Diverse detection rates were found for the virulence genes, ranging from c-rmpA (0.0%) to entB (100.0%). According to the molecular criteria, 127, 186, 9 and 26 strains were putatively denoted as HvKP, blaKPC(+)-KP, blaKPC(+)-HvKP and Hv-blaKPC(+)-KP. Mouse lethality test confirmed 2 blaKPC(+)-HvKP strains (JS184 and TZ20) and no Hv-blaKPC(+)-KP. JS184 showed K2 serotype, thin capsule, positive exopolysaccharid and string test. TZ20 presented K20 serotype, thin capsule, negative exopolysaccharide and string test. Compared with the positive control NTUH-K2044, equal galF expression and growth curves were confirmed for JS184 and TZ20. Conclusions: Molecular determination of CR-HvKP and Hv-CRKP brings remarkable bias compared with mouse lethality test. The exact prevalence of CR-HvKP is less than 1.0%, which of Hv-CRKP is much lower.

A curriculum learning-based fully automated system for quantification of the choroidal structure in highly myopic patients.

Objective.An automated tool for choroidal segmentation and quantitative analysis under pathological conditions is currently lacking, hindering the exploration of choroidal structural changes in fundus diseases. This study aims to create a fully automated deep learning system for the quantitative analysis of the choroid with pathological changes, and to apply the system in analyzing the correlation between the choroidal structure and the severity of high myopia.Approach. A total of 2590 optical coherence tomography B-scan images of 1424 eyes of 1029 patients of high myopia from 3 hospitals were collected. We developed a curriculum learning-based system, including a two-stage U-net (TSU-net) and a post-process module for segmentation of the choroid, to calculate mean choroidal thickness (MCT) and choroidal vascularity index (CVI). The output of the images was statistically analyzed to explore the associations among MCT, CVI and the clinical characteristics of the patients.Main results. The Dice coefficient and IoU measures of choroid segmentation were 0.9221 and 0.8575, respectively. In a human-machine comparison, the system performed faster and better than a senior ophthalmologist. Statistical analysis demonstrated that, MCT is correlated with age, scan region, axial length, maculopathy type, and CVI, and CVI is correlated with scan region and MCT.Significance. A fully automated choroidal structural quantification system was developed. Clinical evaluation demonstrated that severity of high myopia is closely related to MCT but shows only a low correlation with CVI, suggesting that CVI may have little applicability in eyes with large anatomical structural variations. Future quantitative analysis of choroidal structure of large samples will enable exploration of the pathogenesis of additional fundus diseases.

The m6 A reader MhYTP2 regulates MdMLO19 mRNA stability and antioxidant genes translation efficiency conferring powdery mildew resistance in apple.

N6 -methyladenosine (m6 A) reader protein plays an important role in trichome morphology, developmental timing and morphogenesis in Arabidopsis. However, the function of m6 A readers in plant-microbe interaction remains unclear. Here, a Malus YTH-domain family protein MhYTP2 was initially characterized as an m6 A reader. MhYTP2 overexpression increased mRNA m6 A modification level and translation efficiency. The m6 A in the exon regions appeared to destabilize the mRNAs, whereas m6 A in the untranslated regions positively correlated with the associated mRNA abundance. MhYTP2 overexpression enhanced apple powdery mildew resistance, possibly by rapidly degrading the bound mRNAs of MdMLO19 and MdMLO19-X1 and improving the translation efficiency of the antioxidant genes. To conclude, the results shed light on the apple m6 A profile, the effect of MhYTP2 on m6 A profile, and the m6 A roles in MdMLO19 and MdMLO19-X1 mRNAs stability and glutamate dehydrogenase 1-like MdGDH1L mRNA translation efficiency.

Self-Supervision-Augmented Deep Autoencoder for Unsupervised Visual Anomaly Detection.

Deep autoencoder (AE) has demonstrated promising performances in visual anomaly detection (VAD). Learning normal patterns on normal data, deep AE is expected to yield larger reconstruction errors for anomalous samples, which is utilized as the criterion for detecting anomalies. However, this hypothesis cannot be always tenable since the deep AE usually captures the low-level shared features between normal and abnormal data, which leads to similar reconstruction errors for them. To tackle this problem, we propose a self-supervised representation-augmented deep AE for unsupervised VAD, which can enlarge the gap of anomaly scores between normal and abnormal samples by introducing autoencoding transformation (AT). Essentially, AT is introduced to facilitate AE to learn the high-level visual semantic features of normal images by introducing a self-supervision task (transformation reconstruction). In particular, our model inputs the original and transformed images into the encoder for obtaining latent representations; afterward, they are fed to the decoder for reconstructing both the original image and applied transformation. In this way, our model can utilize both image and transformation reconstruction errors to detect anomaly. Extensive experiments indicate that the proposed method outperforms other state-of-the-art methods, which demonstrates the validity and advancement of our model.