Network pharmacology and computational analysis of berberine and kuwanon Z as possible natural antiviral compounds in COVID-19

Background:Global efforts to discover effective therapeutic agents for combating coronavirus disease 19(COVID-19)have intensified the exploration of natural compounds with potential antiviral properties.In this study,we utilized network pharmacology and computational analysis to investigate the antiviral effects of Berberine and Kuwanon Z against severe acute respiratory syndrome coronavirus 2,the viruses responsible for COVID-19.Method:Utilizing comprehensive network pharmacology approaches,we elucidated the complex interactions between these compounds and the host biological system,highlighting their multitarget mechanisms.Network pharmacology identifies COVID-19 targets and compounds through integrated protein‒protein interaction and KEGG pathway analyses.Molecular docking simulation studies were performed to assess the binding affinities and structural interactions of Berberine and Kuwanon Z with key viral proteins,shedding light on their potential inhibitory effects on viral replication and entry.Results:Network-based analyses revealed the modulation of crucial pathways involved in the host antiviral response.Compound-target network analysis revealed complex interactions(122 nodes,121 edges),with significant interactions and an average node degree of 1.37.KEGG analysis revealed pathways such as the COVID-19 pathway,chemokines and Jak-sat in COVID-19.Docking studies revealed that Kuwanon Z had binding energies of-10.5 kcal/mol for JAK2 and-8.1 kcal/mol for the main protease.Conclusion:The findings of this study contribute to the understanding of the pharmacological actions of Berberine and Kuwanon Z in the context of COVID-19,providing a basis for further experimental validation.These natural compounds exhibit promise as potential antiviral agents,offering a foundation for the development of novel therapeutic strategies in the ongoing battle against the global pandemic.

Dynamic adaptive spatio-temporal graph network for COVID-19 forecasting

Appropriately characterising the mixed space-time relations of the contagion process caused by hybrid space and time factors remains the primary challenge in COVID-19 forecasting.However,in previous deep learning models for epidemic forecasting,spatial and temporal variations are captured separately.A unified model is developed to cover all spatio-temporal relations.However,this measure is insufficient for modelling the complex spatio-temporal relations of infectious disease transmission.A dynamic adaptive spatio-temporal graph network(DASTGN)is proposed based on attention mechanisms to improve prediction accuracy.In DASTGN,complex spatio-temporal relations are depicted by adaptively fusing the mixed space-time effects and dynamic space-time dependency structure.This dual-scale model considers the time-specific,space-specific,and direct effects of the propagation process at the fine-grained level.Furthermore,the model characterises impacts from various space-time neighbour blocks under time-varying interventions at the coarse-grained level.The performance comparisons on the three COVID-19 datasets reveal that DASTGN achieves state-of-the-art results with a maximum improvement of 17.092%in the root mean-square error and 11.563%in the mean absolute error.Experimental results indicate that the mechanisms of designing DASTGN can effectively detect some spreading characteristics of COVID-19.The spatio-temporal weight matrices learned in each proposed module reveal diffusion patterns in various scenarios.In conclusion,DASTGN has successfully captured the dynamic spatio-temporal variations of COVID-19,and considering multiple dynamic space-time relationships is essential in epidemic forecasting.

Bioinformatics and network pharmacology identify the therapeutic role and potential targets of diosgenin in Alzheimer disease and COVID-19

Objective: This study aims to investigate the potential targets of diosgenin for the treatment of Alzheimer's disease (AD) and Coronavirus Disease 2019 (COVID-19) through the utilization of bioinformatics, network pharmacology, and molecular docking techniques. Methods: Differential expression genes (DEGs) shared by AD and COVID-19 were enriched by bioinformatics. Additionally, regulatory networks were analyzed to identify key genes in the Transcription Factor (TF) of both diseases. The networks were visualized using Cytoscape. Utilizing the DGIdb database, an investigation was conducted to identify potential drugs capable of treating both Alzheimer's disease (AD) and COVID-19. Subsequently, a Venn diagram analysis was performed using the drugs associated with AD and COVID-19 in the CTD database, leading to the identification of diosgenin as a promising candidate for the treatment of both AD and COVID-19.SEA, SuperPred, Swiss Target Prediction and TCMSP were used to predict the target of diosgenin in the treatment of AD and COVID-19, and the target of diosgenin in the treatment of AD and COVID-19 was determined by Wayne diagram intersection analysis with the differentially expressed genes of AD and COVID- 19. Their Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) were analyzed jointly. Genomes The Protein Protein Interaction (PPI) network of these drug targets was constructed, and core targets with the highest correlation were screened out. The binding of diosgenin to these core targets was analyzed by molecular docking. Results: Through enrichment and cluster analysis, it was found that the biological processes, pathways and diseases enriched by DEGs in AD and COVID-19 were all related to inflammation and immune regulation. These common DEGs and Trust databases were used to construct AD and COVID-19 TFs regulatory networks. Diosgenin was predicted as a potential drug for the treatment of AD and COVID-19 by network pharmacology, and 36 targets of diosgenin for the treatment of AD and 27 targets for COVID-19 were revealed. The six core targets with the highest correlation were selected for molecular docking with diosgenin using CytohHubba to calculate the scores. Conclusions: This study firstly revealed that the common TFs regulatory network of AD and COVID-19, and predicted and verified diosgenin as a potential drug for the treatment of AD and COVID-19. The binding of diosgenin to the core pharmacological targets for the treatment of AD and COVID-19 was determined by molecular docking, which provides a theoretical basis for developing a new approach to clinical treatment of AD and COVID-19.

Exploring the bioactive compounds of Feiduqing formula for the prevention and management of COVID-19 through network pharmacology and molecular docking

Background:To explore the effective chemical constituents of Feiduqing formula for prevention and treatment of coronavirus disease 2019(COVID-19).Methods:The compounds and action targets of twelve herbal medicines in Feiduqing formula were collected via Traditional Chinese Medicine Systems Pharmacology Database and Analytic Platform.The genes corresponding to the targets were queried through the UniProt database.The“herbal medicine-ingredient-target”network was established by Cytoscape software.The Gene Ontology function enrichment analysis and Kyoto Encyclopedia of Genes and Genomes pathway enrichment analysis were performed by Database for Annotation,Visualization and Integrated Discovery.Molecular docking was used to analyze the binding force of core active compounds of Feiduqing formula with PTGS2,HSP90AA1,SARS-CoV-23CL hydrolase and angiotensin converting enzyme II(ACE2).Results:The“herbal medicine-ingredient-target”network included 434 nodes and 1948 edges,including 222 components such as quercetin,kaempferol,luteolin,etc.The key targets are PTGS2,HSP90AA1,PTGS1,ESR1,AR,NOS2,etc.Gene Ontology function enrichment analysis revealed 2530 items,including RNA polymerase II-specific,response to oxidative stress,transcription factor activity,etc.Kyoto Encyclopedia of Genes and Genomes pathway enrichment screened 169 signal pathways,including Human cytomegalovirus infection,Kaposi sarcoma-associated herpesvirus infection,Hepatitis B,Hepatitis C,IL-17,TNF,etc.The results of molecular docking showed that quercetin,luteolin,β-sitosterol,stigmasterol and other core active compounds have a certain degree of affinity with PTGS2,HSP90AA1,SARS-CoV-23CL hydrolase and ACE2.Conclusion:The active compounds of Feiduqing formula may have a therapeutic effect on COVID-19 pneumonia through the action on PTGS2,HSP90AA1,SARS-CoV-23CL hydrolase and ACE2,and regulating many signaling pathways.

Contemporary Study for Detection of COVID-19 Using Machine Learning with Explainable AI

The prompt spread of COVID-19 has emphasized the necessity for effective and precise diagnostic tools.In this article,a hybrid approach in terms of datasets as well as the methodology by utilizing a previously unexplored dataset obtained from a private hospital for detecting COVID-19,pneumonia,and normal conditions in chest X-ray images(CXIs)is proposed coupled with Explainable Artificial Intelligence(XAI).Our study leverages less preprocessing with pre-trained cutting-edge models like InceptionV3,VGG16,and VGG19 that excel in the task of feature extraction.The methodology is further enhanced by the inclusion of the t-SNE(t-Distributed Stochastic Neighbor Embedding)technique for visualizing the extracted image features and Contrast Limited Adaptive Histogram Equalization(CLAHE)to improve images before extraction of features.Additionally,an AttentionMechanism is utilized,which helps clarify how the modelmakes decisions,which builds trust in artificial intelligence(AI)systems.To evaluate the effectiveness of the proposed approach,both benchmark datasets and a private dataset obtained with permissions from Jinnah PostgraduateMedical Center(JPMC)in Karachi,Pakistan,are utilized.In 12 experiments,VGG19 showcased remarkable performance in the hybrid dataset approach,achieving 100%accuracy in COVID-19 vs.pneumonia classification and 97%in distinguishing normal cases.Overall,across all classes,the approach achieved 98%accuracy,demonstrating its efficiency in detecting COVID-19 and differentiating it fromother chest disorders(Pneumonia and healthy)while also providing insights into the decision-making process of the models.

The potential mechanism of Isodon suzhouensis against COVID-19 via EGFR/TLR4 pathways

Corona Virus Disease 2019(COVID-19)has brought the new challenges to scientific research.Isodon suzhouensis has good anti-inflammatory and antioxidant stress effects,which is considered as a potential treatment for COVID-19.The possibility for the treatment of COVID-19 with I.suzhouensis and its potential mechanism of action were explored by employing molecular docking and network pharmacology.Network pharmacology and molecular docking were used to screen drug targets,and lipopolysaccharide(LPS)induced RAW264.7 and NR8383 cells inflammation model was used for experimental verification.Collectively a total of 209 possible linkages against 18 chemical components from I.suzhouensis and 1194 COVID-19 related targets were selected.Among these,164 common targets were obtained from the intersection of I.suzhouensis and COVID-19.Gene Ontology(GO)and Kyoto Encyclopedia of Genes and Genomes(KEGG)enriched 582 function targets and 87 target proteins pathways,respectively.The results from molecular docking studies revealed that rutin,vitexin,isoquercitrin and quercetin had significant binding ability with 3 chymotrypsin like protease(3CLpro)and angiotensin converting enzyme 2(ACE2).In vitro studies showed that I.suzhouensis extract(ISE)may inhibit the activation of PI3K/Akt pathway and the expression level of downstream proinflammatory factors by inhibiting the activation of epidermal growth factor receptor(EGFR)in RAW264.7 cells induced by LPS.In addition,ISE was able to inhibit the activation of TLR4/NF-κB signaling pathway in NR8383 cells exposed to LPS.Overall,the network pharmacology and in vitro studies conclude that active components from I.suzhouensis have strong therapeutic potential against COVID-19 through multi-target,multi-pathway dimensions and can be a promising candidate against COVID-19.

The basic core traditional C hinese medicine for the prevention and treatment of COVID-19 and its active mechanisms

Background:COVID-19 has had a dramatic impact on human health,economies,societies,and livelihoods around the world.Traditional Chinese medicine(TCM)formulae have played an important role in the prevention and treatment of COVID-19.WHO evaluated the role of TCM in treating of COVID-19 and encouraged other countries to promote the use of TCM formulae.However,the key is to find the basic core traditional Chinese medicine(BC-TCM)among those formulae.Methods:For the first time,we mined the data of TCM formulae in CNIPA and analyzed herb characteristics and association rules.We then determined the BC-TCM and screened main compounds and therapeutic targets.Finally,the potential molecular mechanisms were explored by using enrichment analyses and molecular docking.Results:This study screened 123 patented TCM formulae,including 312 herbs.According to frequency statistics and association rules,nine herbs(Gan Cao,Jin Yinhua,Guang Huoxiang,Fu Ling,Huang Qi,Jie Geng,Lian Qiao,Cang Zhu,Ku Xingren)were selected as the BC-TCM.The BC-TCM involved 166 main compounds and 48 therapeutic targets.The active compounds Hederagenin,Spinasterol,Beta-sitosterol,and Liquiritin had high binding activity to the COVID-19 targets 3CL,ACE2,and core targets RELA,HSP90AA1,STAT3,MAPK3,and TP53 according to molecular docking results.Interestingly,Hederagenin might be a potential compound for the prevention and treatment of COVID-19.Conclusion:Our research predicted and confirmed the preventive therapeutic effect of BC-TCM on COVID-19.This has the potential to broaden the scope of TCM,guide people in using clinical formulae,and provide valuable insights for future TCM discovery research.

Comparative Analysis of COVID-19 Detection Methods Based on Neural Network

In 2019,the novel coronavirus disease 2019(COVID-19)ravaged the world.As of July 2021,there are about 192 million infected people worldwide and 4.1365 million deaths.At present,the new coronavirus is still spreading and circulating in many places around the world,especially since the emergence of Delta variant strains has increased the risk of the COVID-19 pandemic again.The symptoms of COVID-19 are diverse,and most patients have mild symptoms,with fever,dry cough,and fatigue as the main manifestations,and about 15.7%to 32.0%of patients will develop severe symptoms.Patients are screened in hospitals or primary care clinics as the initial step in the therapy for COVID-19.Although transcription-polymerase chain reaction(PCR)tests are still the primary method for making the final diagnosis,in hospitals today,the election protocol is based on medical imaging because it is quick and easy to use,which enables doctors to diagnose illnesses and their effects more quickly3.According to this approach,individuals who are thought to have COVID-19 first undergo an X-ray session and then,if further information is required,a CT-scan session.This methodology has led to a significant increase in the use of computed tomography scans(CT scans)and X-ray pictures in the clinic as substitute diagnostic methods for identifying COVID-19.To provide a significant collection of various datasets and methods used to diagnose COVID-19,this paper provides a comparative study of various state-of-the-art methods.The impact of medical imaging techniques on COVID-19 is also discussed.

COVID-19 Detection Based on 6-Layered Explainable Customized Convolutional Neural Network

This paper presents a 6-layer customized convolutional neural network model(6L-CNN)to rapidly screen out patients with COVID-19 infection in chest CT images.This model can effectively detect whether the target CT image contains images of pneumonia lesions.In this method,6L-CNN was trained as a binary classifier using the dataset containing CT images of the lung with and without pneumonia as a sample.The results show that the model improves the accuracy of screening out COVID-19 patients.Compared to othermethods,the performance is better.In addition,the method can be extended to other similar clinical conditions.

A COVID-19 Detection Model Based on Convolutional Neural Network and Residual Learning

Amodel that can obtain rapid and accurate detection of coronavirus disease 2019(COVID-19)plays a significant role in treating and preventing the spread of disease transmission.However,designing such amodel that can balance the detection accuracy andweight parameters ofmemorywell to deploy a mobile device is challenging.Taking this point into account,this paper fuses the convolutional neural network and residual learning operations to build a multi-class classification model,which improves COVID-19 pneumonia detection performance and keeps a trade-off between the weight parameters and accuracy.The convolutional neural network can extract the COVID-19 feature information by repeated convolutional operations.The residual learning operations alleviate the gradient problems caused by stacking convolutional layers and enhance the ability of feature extraction.The ability further enables the proposed model to acquire effective feature information at a lowcost,which canmake ourmodel keep smallweight parameters.Extensive validation and comparison with other models of COVID-19 pneumonia detection on the well-known COVIDx dataset show that(1)the sensitivity of COVID-19 pneumonia detection is improved from 88.2%(non-COVID-19)and 77.5%(COVID-19)to 95.3%(non-COVID-19)and 96.5%(COVID-19),respectively.The positive predictive value is also respectively increased from72.8%(non-COVID-19)and 89.0%(COVID-19)to 88.8%(non-COVID-19)and 95.1%(COVID-19).(2)Compared with the weight parameters of the COVIDNet-small network,the value of the proposed model is 13 M,which is slightly higher than that(11.37 M)of the COVIDNet-small network.But,the corresponding accuracy is improved from 85.2%to 93.0%.The above results illustrate the proposed model can gain an efficient balance between accuracy and weight parameters.

Effect of Online Social Networking on Emotional Status and Its Interaction with Offline Reality during the Early Stage of the COVID-19 Pandemic in China

Background:During the early stages of the COVID-19 pandemic in China,social interactions shifted to online spaces due to lockdowns and social distancing measures.As a result,the impact of online social networking on users’emotional status has become stronger than ever.This study examines the association between online social networking and Internet users’emotional status and how offline reality affects this relationship.Methods:The study utilizes cross-sectional online survey data(n=3004)and Baidu Migration big data from the first 3 months of the pandemic.Two dimensions of online networking are measured:social support and information sources.Results:First,individuals’online social support(β=0.16,p<0.05)and information sources(β=0.08,p<0.01)are both positively associated to their emotional status during the epidemic.Second,these positive associations are moderated by social status and provincial pandemic control interventions.With regards to the moderation effect of social status,the constructive impact of information sources on emotional well-being is more pronounced among individuals from vulnerable groups compared to those who are not.With regard to the moderation effect of provincial interventions,online social support has the potential to alleviate the adverse repercussions of high rates of confirmed COVID-19 cases and strict lockdown measures while simultaneously augmenting the favorable effects of recovery.Conclusion:The various dimensions of social networking exert distinct effects on emotional status through diverse mechanisms,all of which must be taken into account when designing and adapting pandemic-control interventions.

Detection of COVID-19 and Pneumonia Using Deep Convolutional Neural Network

COVID-19 has created a panic all around the globe.It is a contagious dis-ease caused by Severe Acute Respiratory Syndrome Coronavirus 2(SARS-CoV-2),originated from Wuhan in December 2019 and spread quickly all over the world.The healthcare sector of the world is facing great challenges tackling COVID cases.One of the problems many have witnessed is the misdiagnosis of COVID-19 cases with that of healthy and pneumonia cases.In this article,we propose a deep Convo-lutional Neural Network(CNN)based approach to detect COVID+(i.e.,patients with COVID-19),pneumonia and normal cases,from the chest X-ray images.COVID-19 detection from chest X-ray is suitable considering all aspects in compar-ison to Reverse Transcription Polymerase Chain Reaction(RT-PCR)and Computed Tomography(CT)scan.Several deep CNN models including VGG16,InceptionV3,DenseNet121,DenseNet201 and InceptionResNetV2 have been adopted in this pro-posed work.They have been trained individually to make particular predictions.Empirical results demonstrate that DenseNet201 provides overall better performance with accuracy,recall,F1-score and precision of 94.75%,96%,95%and 95%respec-tively.After careful comparison with results available in the literature,we have found to develop models with a higher reliability.All the studies were carried out using a publicly available chest X-ray(CXR)image data-set.

Molecular mechanism of azvudine in the treatment of COVID-19 based on network pharmacology and molecular docking

Azvudine(FNC)is a nucleotide inhibitor with a wide antiviral drug.Azvudine was available for the treatment of HIV and corona virus disease(COVID-19)in 2019,but its efficacy and mechanism of action for the treatment of COVID-19 have not been evaluated.PharmMapper was used to predict 287 potentially relevant targets,and the OMIM and GeneCards databases yielded 2468 potential related targets.COVID-19 is linked to 72 FNC-related targets.Using gene ontology(GO)functional annotation and kyoto encyclopedia of genes and genomes(KEGG)pathway enrichment,binding protein-protein interaction(PPI)networks and cytoHubba plug-ins,10 relevant signaling pathways(Lipid and atherosclerosis,Pathways in cancer,Coronavirus disease COVID-19,T cell receptor signaling pathway,and so on.)and 10 hub genes were identified.FNC was shown to interact with MMP9,ALB,AKT1,EGFR,HRAS,MAPK14,MAPK8,PPARG,RHOA and NOS3 via molecular docking.This work investigated the key routes and targets of FNC in the treatment of COVID-19,as well as the possible anti-COVID-19 and anti-tumor targets and related signaling pathways of FNC,which provided references for us to locate and explore effective COVID-19 medications.

PSTCNN: Explainable COVID-19 diagnosis using PSO-guided self-tuning CNN

Since 2019,the coronavirus disease-19(COVID-19)has been spreading rapidly worldwide,posing an unignorable threat to the global economy and human health.It is a disease caused by severe acute respiratory syndrome coronavirus 2,a single-stranded RNA virus of the genus Betacoronavirus.This virus is highly infectious and relies on its angiotensin-converting enzyme 2-receptor to enter cells.With the increase in the number of confirmed COVID-19 diagnoses,the difficulty of diagnosis due to the lack of global healthcare resources becomes increasingly apparent.Deep learning-based computer-aided diagnosis models with high generalisability can effectively alleviate this pressure.Hyperparameter tuning is essential in training such models and significantly impacts their final performance and training speed.However,traditional hyperparameter tuning methods are usually time-consuming and unstable.To solve this issue,we introduce Particle Swarm Optimisation to build a PSO-guided Self-Tuning Convolution Neural Network(PSTCNN),allowing the model to tune hyperparameters automatically.Therefore,the proposed approach can reduce human involvement.Also,the optimisation algorithm can select the combination of hyperparameters in a targeted manner,thus stably achieving a solution closer to the global optimum.Experimentally,the PSTCNN can obtain quite excellent results,with a sensitivity of 93.65%±1.86%,a specificity of 94.32%±2.07%,a precision of 94.30%±2.04%,an accuracy of 93.99%±1.78%,an F1-score of 93.97%±1.78%,Matthews Correlation Coefficient of 87.99%±3.56%,and Fowlkes-Mallows Index of 93.97%±1.78%.Our experiments demonstrate that compared to traditional methods,hyperparameter tuning of the model using an optimisation algorithm is faster and more effective.

A Novel Edge-Assisted IoT-ML-Based Smart Healthcare Framework for COVID-19

The lack of modern technology in healthcare has led to the death of thousands of lives worldwide due to COVID-19 since its outbreak.The Internet of Things(IoT)along with other technologies like Machine Learning can revolutionize the traditional healthcare system.Instead of reactive healthcare systems,IoT technology combined with machine learning and edge computing can deliver proactive and preventive healthcare services.In this study,a novel healthcare edge-assisted framework has been proposed to detect and prognosticate the COVID-19 suspects in the initial phases to stop the transmission of coronavirus infection.The proposed framework is based on edge computing to provide personalized healthcare facilities with minimal latency,short response time,and optimal energy consumption.In this paper,the COVID-19 primary novel dataset has been used for experimental purposes employing various classification-based machine learning models.The proposed models were validated using kcross-validation to ensure the consistency of models.Based on the experimental results,our proposed models have recorded good accuracies with highest of 97.767%by Support Vector Machine.According to the findings of experiments,the proposed conceptual model will aid in the early detection and prediction of COVID-19 suspects,as well as continuous monitoring of the patient in order to provide emergency care in case of medical volatile situation.

SNELM:SqueezeNet-Guided ELM for COVID-19 Recognition

(Aim)The COVID-19 has caused 6.26 million deaths and 522.06 million confirmed cases till 17/May/2022.Chest computed tomography is a precise way to help clinicians diagnose COVID-19 patients.(Method)Two datasets are chosen for this study.The multiple-way data augmentation,including speckle noise,random translation,scaling,salt-and-pepper noise,vertical shear,Gamma correction,rotation,Gaussian noise,and horizontal shear,is harnessed to increase the size of the training set.Then,the SqueezeNet(SN)with complex bypass is used to generate SN features.Finally,the extreme learning machine(ELM)is used to serve as the classifier due to its simplicity of usage,quick learning speed,and great generalization performances.The number of hidden neurons in ELM is set to 2000.Ten runs of 10-fold cross-validation are implemented to generate impartial results.(Result)For the 296-image dataset,our SNELM model attains a sensitivity of 96.35±1.50%,a specificity of 96.08±1.05%,a precision of 96.10±1.00%,and an accuracy of 96.22±0.94%.For the 640-image dataset,the SNELM attains a sensitivity of 96.00±1.25%,a specificity of 96.28±1.16%,a precision of 96.28±1.13%,and an accuracy of 96.14±0.96%.(Conclusion)The proposed SNELM model is successful in diagnosing COVID-19.The performances of our model are higher than seven state-of-the-art COVID-19 recognition models.

A Network Pharmacology Study to Uncover the Multiple Molecular Mechanism of the Chinese Patent Medicine Toujiequwen Granules in the Treatment of Corona Virus Disease 2019(COVID-19)

Since the outbreak of the novel corona virus disease 2019(COVID-19)at the end of 2019,specific antiviral drugs have been lacking.A Chinese patent medicine Toujiequwen granules has been promoted in the treatment of COVID-19.The present study was designed to reveal the molecular mechanism of Toujiequwen granules against COVID-19.A network pharmacological method was applied to screen the main active ingredients of Toujiequwen granules.Network analysis of 149 active ingredients and 330 drug targets showed the most active ingredient interacting with many drug targets is quercetin.Drug targets most ffected by the active ingredients were PTGS2,PTGS1,and DPP4.Drug target disease enrichment analysis showed drug targets were significantly enriched in cardiovascular diseases and digestive tract diseases.An"active ingredient-target-disease"network showed that 57 active ingredients from Toujiequwen granules interacted with 15 key targets of COVID-19.There were 53 ingredients that could act on DPP4,suggesting that DPP4 may become a potential new key target for the treatment of COVID-19.GO analysis results showed that key targets were mainly enriched in the cellular response to lipopolysaccharide,cytokine activity and other functions.KEGG analysis showed they were mainly concentrated in viral protein interaction with cytokine and cytokine receptors and endocrine resistance pathway.The evidence suggests that Toujiequwen granules might play an effective role by improving the symptoms of underlying diseases in patients with COVID-19 and multi-target interventions against mutiple signaling pathways related to the pathogenesis of COVID-19.

COVID-19 Detection via a 6-Layer Deep Convolutional Neural Network

Many people around the world have lost their lives due to COVID-19.The symptoms of most COVID-19 patients are fever,tiredness and dry cough,and the disease can easily spread to those around them.If the infected people can be detected early,this will help local authorities control the speed of the virus,and the infected can also be treated in time.We proposed a six-layer convolutional neural network combined with max pooling,batch normalization and Adam algorithm to improve the detection effect of COVID-19 patients.In the 10-fold cross-validation methods,our method is superior to several state-of-the-art methods.In addition,we use Grad-CAM technology to realize heat map visualization to observe the process of model training and detection.

COVID TCL:A Joint Metric Loss Function for Diagnosing COVID-19 Patient in the Early and Incubation Period

Convolution Neural Networks(CNN)can quickly diagnose COVID-19 patients by analyzing computed tomography(CT)images of the lung,thereby effectively preventing the spread of COVID-19.However,the existing CNN-based COVID-19 diagnosis models do consider the problem that the lung images of COVID-19 patients in the early stage and incubation period are extremely similar to those of the non-COVID-19 population.Which reduces the model’s classification sensitivity,resulting in a higher probability of the model misdiagnosing COVID-19 patients as non-COVID-19 people.To solve the problem,this paper first attempts to apply triplet loss and center loss to the field of COVID-19 image classification,combining softmax loss to design a jointly supervised metric loss function COVID Triplet-Center Loss(COVID-TCL).Triplet loss can increase inter-class discreteness,and center loss can improve intra-class compactness.Therefore,COVID-TCL can help the CNN-based model to extract more discriminative features and strengthen the diagnostic capacity of COVID-19 patients in the early stage and incubation period.Meanwhile,we use the extreme gradient boosting(XGBoost)as a classifier to design a COVID-19 images classification model of CNN-XGBoost architecture,to further improve the CNN-based model’s classification effect and operation efficiency.The experiment shows that the classification accuracy of the model proposed in this paper is 97.41%,and the sensitivity is 97.61%,which is higher than the other 7 reference models.The COVID-TCL can effectively improve the classification sensitivity of the CNN-based model,the CNN-XGBoost architecture can further improve the CNN-based model’s classification effect.

Deep Rank-Based Average Pooling Network for Covid-19 Recognition

(Aim)To make a more accurate and precise COVID-19 diagnosis system,this study proposed a novel deep rank-based average pooling network(DRAPNet)model,i.e.,deep rank-based average pooling network,for COVID-19 recognition.(Methods)521 subjects yield 1164 slice images via the slice level selection method.All the 1164 slice images comprise four categories:COVID-19 positive;community-acquired pneumonia;second pulmonary tuberculosis;and healthy control.Our method firstly introduced an improved multiple-way data augmentation.Secondly,an n-conv rankbased average pooling module(NRAPM)was proposed in which rank-based pooling—particularly,rank-based average pooling(RAP)—was employed to avoid overfitting.Third,a novel DRAPNet was proposed based on NRAPM and inspired by the VGGnetwork.Grad-CAM was used to generate heatmaps and gave our AI model an explainable analysis.(Results)Our DRAPNet achieved a micro-averaged F1 score of 95.49%by 10 runs over the test set.The sensitivities of the four classes were 95.44%,96.07%,94.41%,and 96.07%,respectively.The precisions of four classes were 96.45%,95.22%,95.05%,and 95.28%,respectively.The F1 scores of the four classes were 95.94%,95.64%,94.73%,and 95.67%,respectively.Besides,the confusion matrix was given.(Conclusions)The DRAPNet is effective in diagnosing COVID-19 and other chest infectious diseases.The RAP gives better results than four other methods:strided convolution,l2-norm pooling,average pooling,and max pooling.