ABSTRACT Recent studies have shown that deep neural networks are vulnerable to adversarial attacks. In the field of 3D point cloud classification, transfer‐based black‐box attack strategies have been explored to address the challenge of limited knowledge about the model in practical scenarios. However, existing approaches typically rely excessively on network structure, resulting in poor transferability of the generated adversarial examples. To address the above problem, the authors propose AEattack , an adversarial attack method capable of generating highly transferable adversarial examples. Specifically, AEattack employs an autoencoder (AE) to extract features from the point cloud data and reconstruct the adversarial point cloud based on these features. Notably, the AE does not require pre‐training, and its parameters are jointly optimised using a loss function during the process of generating adversarial point clouds. The method makes the generated adversarial point cloud not overly dependent on the network structure, but more concerned with the data distribution. Moreover, this design endows AEattack with a broader potential for application. Extensive experiments on the ModelNet40 dataset show that AEattack is capable of generating highly transferable adversarial point clouds, with up to 61.8% improvement in transferability compared to state‐of‐the‐art adversarial attacks.

3D point cloud classifiers exhibit vulnerability to imperceptible perturbations, which poses a serious threat to the security and reliability of deep learning models in practical applications, making the robustness evaluation of deep 3D point cloud models increasingly important. Due to the difficulty in obtaining model parameters, black-box attacks have become a mainstream means of assessing the adversarial robustness of 3D classification models. The core of improving the transferability of adversarial examples generated by black-box attacks is to generate better generalized adversarial examples, where data augmentation has become one of the popular approaches. In this article, we employ five mainstream attack methods and combine six data augmentation strategies, namely point dropping, flipping, rotating, scaling, shearing, and translating, in order to comprehensively explore the impact of these strategies on the transferability of adversarial examples. Our research reveals that data augmentation methods generally improve the transferability of the adversarial examples, and the effect is better when the methods are stacked. The interaction between data augmentation methods, model characteristics, attack, and defense strategies collectively determines the transferability of adversarial examples. In order to comprehensively understand and improve the effectiveness of adversarial examples, it is necessary to comprehensively consider these complex interrelationships.

Purpose: Analyzing the medication pattern of Chinese medicine for asthma based on data mining technology. Method: We searched the relevant prescriptions for the treatment of asthma included in the Cloud Platform of Ancient and Modern Medical Cases since its establishment, screened the literature according to the inclusion and exclusion criteria, and used Microsoft Excel 2010 to carry out the frequency statistics of single medicines and drug combinations, and the Apriori algorithm of IBM SPSS Modeler 18.0 statistical software to analyze the association rules and compounding patterns of Chinese medicines. The high frequency Chinese medicines were analyzed by using IBM SPSS Statistics 26.0 for cluster analysis. Results: A total of 418 prescriptions were included, involving 395 flavors of traditional Chinese medicine (TCM), with a cumulative frequency of 5425 times, among which the top 20 drugs in terms of frequency of use had a cumulative frequency of 2280 times, and those with a frequency of use of ⩾ 115 times were, from highest to lowest, as follows: Licorice (274), Ephedra (200), Almond (179), Banxia (176), Skullcap (117), Tuckahoe (116). The four qi were dominated by warm (35.03%) and cold (34.01%); the five flavors were dominated by pleasant (30.77%) and bitter (29.60%); and the attributed meridians were dominated by the lung meridian (21.43%) and the liver meridian (18.44%).The association analysis yielded six sets of core pairs, of which those with ⩾ 15% support and ⩾ 80% confidence were (Licorice - Almond + Ephedra), (Ephedra - Assarium), (Licorice - Tangerine peel), (Licorice - White peony), ( Licorice - Cinnamon branches), (Ephedra - Assarium + Licorice). Conclusion: The prescription of Chinese medicine for bronchial asthma is based on resolving phlegm and calming asthma, warming the lungs and resolving drinks, clearing the lungs and relieving cough, tonifying the lungs and the spleen, restoring wind and relieving spasm, and dispelling blood stasis and clearing the channels.

Objective: Using data mining technology to explore the medication law of chronic cholecystitis. Methods: We searched the literature of all acupuncture prescriptions for treating menstrual headache since the establishment of the Chinese Journal Full-text Database (CNKI), Wanfang Data Resource System Library (WF), Chinese Biomedical Literature Database (CBM), and Wipo Journal Full-text Database (VIP) databases, extracted the valid prescriptions according to the exclusion criteria, import Microsoft Office Excel 2021 to establish the database of traditional Chinese medicine in the treatment of chronic cholecystitis and used Excel 2021, IBM SPSS Modeler18.0, and IBM SPSS Statistics 27.0 to analyze the database of menstrual acupoint frequency analysis, acupoint attribution analysis, association rule analysis, and cluster analysis. Results: There was a total of 501 prescriptions, designed for 193 flavours of Chinese medicine, with a total application frequency of 5292 times, and the highest frequency of single flavour use was for Radix Bupleuri, Licorice, and Radix Paeoniae Alba, which were mainly used with cold, warm, bitter, and pungent medicines, and there was a total of 10 groups of core pairs of medicines, with 3 classes obtained through clustering.

As an emerging interdisciplinary discipline, Traditional Chinese Medicine Informatics (TCMI) faces the challenges of improving its training mode, adjusting its curriculum, and optimizing teaching resources during its development. In this study, the academic master's degree students of TCMI jointly cultivated by the School of Pharmaceutical Information of Changchun University of Traditional Chinese Medicine and the Institute of Traditional Chinese Medicine Information of China Academy of Traditional Chinese Medicine are selected as the research object to explore the new mode of joint training of academic postgraduates between the universities and the institute. With the help of an Internet platform, a "self-organized" learning platform is constructed to guide students to realize self-management and self-improvement, and a new "student-led" cultivation mode is gradually built on this basis. We hope to provide innovative methods for developing discipline, valuable ideas, and inspiration for improving the cultivation mode

Background: In recent years, with the rapid development of China’s economy, lifestyle changes, and the exacerbation of the aging population, cardiovascular disease has emerged as the leading cause of mortality in China. The incidence and mortality rates of myocardial infarction have been progressively increasing year by year. Xuefu Zhuyu Tang, a classic traditional Chinese medicine formula known for its efficacy in promoting blood circulation and resolving stasis, has shown notable effectiveness in alleviating clinical symptoms and enhancing the prognosis of myocardial infarction. Methods: Information on the active ingredients and targets of the Xuefu Zhuyu Tang drug group was acquired from the Traditional Chinese medicine systems pharmacology database. Subsequently, we conducted data screening from GeneCards, OMIM, PharmaGkb, and DrugBank disease databases to identify common targets between drugs and diseases. A "drug component target" network was constructed using Cytoscape software, and potential target protein interaction networks were developed through the protein-protein interaction database (STRING). Core targets were identified using Cytoscape’s CytoNCA plugin, and Gene Ontology function and KEGG enrichment analyses of these targets were performed using R statistical software. Results: The drug group was composed of Peach kernel, safflower, Angelica sinensis, Rehmannia glutinosa, Achyranthis bidentata Radix, Ligusticum chuanxiong, Platycodon grandiflorum, Radix Paeoniae Rubra, Fructus Aurantii, Licorice, and Bupleurum chinense. From this group, we screened 10 effective ingredients and identified 29 core targets. The mechanism of action is associated with 130 significantly enriched pathways, encompassing cancer, lipid and atherosclerosis, diabetes complications AGE-RAGE signaling pathway, tumor necrosis factor signaling pathway, and interleukin-17 signaling pathway. Conclusion: This study explored into the primary active ingredients, targets, and pertinent pathways involved in Xuefu Zhuyu Tang’s efficacy in treating myocardial infarction. This study assessed the effect of Xuefu Zhuyu Tang on myocardial infarction from the perspective of network pharmacology, providing theoretical basis for subsequent studies on traditional Chinese medicine interventions for myocardial infarction treatment.

Background:The emergence of novel coronavirus pneumonia has seriously affected people’s normal life and health. Cold-dampness epidemic prescription has a good effect in the prevention and treatment of novel coronavirus pneumonia. Methods:TCMSP, PubChem, Swiss Target Prediction, PharmMapper database and related literatures were used to retrieve and predict the main chemical components and corresponding targets of Traditional Chinese Medicine (TCM)TCM. GeneCard, OMIM, NCBI and TTD databases were used to collect disease targets. Uniprot disease database was used to standardize target names. Cytoscape3.8.2 software was used to establish the “active components-action target” network. Protein interaction (PPI) network was established by using protein interaction database (STRING), and core genes were screened by CytoNCA plug-in of Cytoscape3.8.2 software.GO enrichment analysis and KEGG pathway enrichment analysis were carried out through DAVID network database, and Hiplot network platform was used for visualization. Molecular docking technology was used to verify the docking between core components and targets. Results:After preliminary screening, 102 effective components, 255 potential targets and 2230 COVID-19 disease targets were obtained, and it was speculated that the mechanism might be related to 177 pathways such as TNF signaling pathway, IL-17 signaling pathway and AGE-RAGE signaling pathway in diabetic complications. The absolute values of docking binding energy between active components such as quercetin, luteolin and wogonin and targets such as PTGS2, AR, TP53 and CASP3 were greater than 5.0 Kcal/mol, and the docking results were good. Conclusion:Cold-dampness epidemic prescription has the characteristics of multiple components, multiple targets and multiple pathways in the prevention and treatment of COVID-19, and may play a therapeutic role through anti-inflammatory, antiviral and immune regulation.

Background: Lung abscess is a purulent infection of the lung tissue that is caused by one or more pathogens. Traditional Chinese medicine (TCM) can effectively treat lung abscess and has certain advantages compared to antibiotics. Methods: The prescriptions for lung carbuncle in Zhong Hua Yi Fang were organized using Excel 2016, and the core drugs were identified on the basis of ancient and modern medical records. The effective compounds and targets of the core drug pairs were retrieved from TCMSP database, and the disease targets of lung abscess were retrieved from the Genecard, PharmGkb, OMIM and DrugBank databases. The drug-compound-target network was constructed using Cytoscape, and the intersecting targets of drugs and diseases were obtained using R. The protein-protein interaction (PPI) network was constructed using the STRING database and Cytoscape, and the core targets were obtained. The latter were functionally annotated by GO enrichment analysis and KEGG pathway analysis. AutoDockTools was used for molecular docking simulation. The results were visualized by Pymol software and TBtools software. Results: A total of 182 prescriptions for the treatment of lung abscess were identified, including 240 TCM formulations. The top 10 most frequently used drugs were licorice, Platycodon grandiflorum, Fritillaria, Panax ginseng, Semen Armeniacae Amarum, Mori Cortex, Coix seed, Poria cocos, Aster tataricus and Ophiopogon japonicus. The core drugs were licorice and P. grandiflorum. In addition, 99 active compounds of the core drug pair were screened, corresponding to 124 targets of lung abscess, and 23 core targets were identified, including MMP9, CASP3, PPARG and MYC among others. The core targets were enriched in 2150 biological processes, 52 cell components and 164 molecular functions in the GO analysis. Furthermore, KEGG enrichment analysis revealed that the core targets were associated with 174 pathways. Molecular docking of quercetin, luteolin and kaempferol with the core targets showed good binding activity. Conclusions: Licorice and P. grandiflorum inhibit inflammation, promote cell growth and regulate apoptosis in lung abscess by targeting the PI3K-Akt and AGE – RAGE signaling pathways, specifically CASP3, VEGFA, JUN, TP53, AKTI, etc. Our study provides theoretical reference for subsequent studies on the therapeutic effects of TCM on lung abscess.

Background: Mumps is a highly infectious acute respiratory infectious disease caused by mumps virus, which mainly occurs in children and adolescents. Traditional Chinese Medicine (TCM) effectively alleviates the symptoms of mumps. Methods: Relevant literature on TCM for treating mumps was collected from the China National Knowledge Infrastructure (CNKI), and data mining tools identified the core drug group. The TCMSP database retrieved the active ingredients and targets of the core drug group and through screening data from GeneCard, OMIM, PharmGkb, Drug Bank, and Uniprot disease databases to obtain common targets for drug and disease. The Cytooscape software constructed the “ingredients-targets” network. Meanwhile, the protein interaction database (STRING) constructed the potential target protein interaction network. The CytoNCA plug-in of Cytoscape screened the core targets. GO functional, and KEGG enrichment analyses of intersection targets were performed using the R statistical software. The molecular docking technology verified the relationship between the core ingredients and targets. Result: A total of 177 prescriptions were extracted from the CNKI literature, including 138 Chinese medicines. Forsythia suspensa, Isatidis Radix, and Scutellariae Radix were selected as the core drug group. Preliminary screening obtained 60 active ingredients and 23 common genes. The mechanism of action is related to the 94 significantly enriched pathway, including Fluid shear stress and atherosclerosis, Lipid and atherosclerosis, TNF signaling pathway, AGE-RAGE signaling pathway in diabetic complications, and NOD-like receptor signaling pathway. The molecular docking results revealed that most of the combinations of the active components and core targets could form stable structures. Conclusions: The main active ingredients, action targets, and related pathways for treating mumps using Forsythia suspensa, Isatidis Radix, and Scutellariae Radix is discussed. The study confirmed the effects of Forsythia suspensa, Isatidis Radix, and Scutellariae Radix for treating mumps, providing a reference for clinical practice.

Background:Polycystic ovary syndrome (PCOS) is the most common endocrine and metabolic disease in women of childbearing age worldwide. Traditional Chinese Medicine (TCM) effectively alleviates the clinical symptoms of PCOS. Methods: Relevant literature on TCM for treating PCOS was collected from the China National Knowledge Infrastructure (CNKI), and data mining tools identified the core drug group. The TCMSP database retrieved the active ingredients and targets of the core drug group and through screening data from GeneCard, OMIM, PharmGkb, DrugBank, and Uniprot disease databases to obtain common targets for drugs and diseases. The Cytoscape software constructed the “ingredients-targets” network. Meanwhile, the protein interaction database (STRING) constructed the potential target protein interaction network. The CytoNCA plug-in of Cytoscape screened the core targets. GO functional, and KEGG enrichment analyses of intersection targets were performed using the R statistical software. The molecular docking technology verified the relationship between the core ingredients and targets. Results: A total of 175 prescriptions were extracted from the CNKI literature, including 212 Chinese medicinals. Angelica sinensis, Cuscuta chinensis, and Rehmannia root were selected as the core drug group. Preliminary screening obtained 13 active ingredients and 446 potential targets. The mechanism of action is related to the 175 significantly enriched pathways, including lipid and atherosclerosis, fluid shear stress and atherosclerosis, AGE-RAGE signaling pathway in diabetic complications, MAPK, TNF, and PI3K-Akt signaling pathways. The absolute value of binding energies of quercetin, kaempferol, and isorhamnetin with NCOA2, PGR, and PTGS2 were over 5.0 Kcal / mol, indicating good docking results. Conclusions: The main active ingredients, action targets, and related pathways for treating PCOS using Angelica sinensis, Cuscuta chinensis, and Rehmannia root is discussed. The study confirmed the effects of Angelica sinensis, Cuscuta chinensis, and Rehmannia root for treating PCOS, providing a reference for clinical practice.