Jasmonic acid(JA)plays an important role in regulating leaf senescence.However,the molecular mechanisms of leaf senescence in apple(Malus domestica)remain elusive.In this study,we found that MdZAT10,a C2H2-type zinc f...Jasmonic acid(JA)plays an important role in regulating leaf senescence.However,the molecular mechanisms of leaf senescence in apple(Malus domestica)remain elusive.In this study,we found that MdZAT10,a C2H2-type zinc finger transcription factor(TF)in apple,markedly accelerates leaf senescence and increases the expression of senescence-related genes.To explore how MdZAT10 promotes leaf senescence,we carried out liquid chromatography/mass spectrometry screening.We found that MdABI5 physically interacts with MdZAT10.MdABI5,an important positive regulator of leaf senescence,significantly accelerated leaf senescence in apple.MdZAT10 was found to enhance the transcriptional activity of MdABI5 for MdNYC1 and MdNYE1,thus accelerating leaf senescence.In addition,we found that MdZAT10 expression was induced by methyl jasmonate(MeJA),which accelerated JA-induced leaf senescence.We also found that the JA-responsive protein MdBT2 directly interacts with MdZAT10 and reduces its protein stability through ubiquitination and degradation,thereby delaying MdZAT10-mediated leaf senescence.Taken together,our results provide new insight into the mechanisms by which MdZAT10 positively regulates JA-induced leaf senescence in apple.展开更多
Introduction China is a country with a low morbidity of prostate carcinoma.The in-cidence of prostate carcinoma in China is 1.6/100,000,which is muchlower than the rate in the United States,i.e.,119.9/100,000.Dueto ch...Introduction China is a country with a low morbidity of prostate carcinoma.The in-cidence of prostate carcinoma in China is 1.6/100,000,which is muchlower than the rate in the United States,i.e.,119.9/100,000.Dueto changes of lifestyle and improved measurement of serum展开更多
Objective:To validate two proposed coronavirus disease 2019(COVID-19)prognosis models,analyze the characteristics of different models,consider the performance of models in predicting different outcomes,and provide new...Objective:To validate two proposed coronavirus disease 2019(COVID-19)prognosis models,analyze the characteristics of different models,consider the performance of models in predicting different outcomes,and provide new insights into the development and use of artificial intelligence(AI)predictive models in clinical decision-making for COVID-19 and other diseases.Materials and Methods:We compared two proposed prediction models for COVID-19 prognosis that use a decision tree and logistic regression modeling.We evaluated the effectiveness of different model-building strategies using laboratory tests and/or clinical record data,their sensitivity and robustness to the timings of records used and the presence of missing data,and their predictive performance and capabilities in single-site and multicenter settings.Results:The predictive accuracies of the two models after retraining were improved to 93.2% and 93.9%,compared with that of the models directly used,with accuracies of 84.3% and 87.9%,indicating that the prediction models could not be used directly and require retraining based on actual data.In addition,based on the prediction model,new features obtained by model comparison and literature evidence were transferred to integrate the new models with better performance.Conclusions:Comparing the characteristics and differences of datasets used in model training,effective model verification,and a fusion of models is necessary in improving the performance of AI models.展开更多
Since Bitcoin came into the world,modelling and analyzing the underlying characteristics of Bitcoin has attracted increasing attention.This paper uses a framework including decomposition,reconstruction and extraction ...Since Bitcoin came into the world,modelling and analyzing the underlying characteristics of Bitcoin has attracted increasing attention.This paper uses a framework including decomposition,reconstruction and extraction method(DRE)to analyze price fluctuations based on ultra-high-frequency data from Dec.1,2019,to Nov.30,2021.First,the ensemble mode decomposition(EMD)is employed to decompose the Bitcoin hourly spot price into 13 intrinsic mode functions(IMF)plus a residual.Second,the IMFs are reconstructed into high-frequency components,low-frequency components and a trend based on fine-to-coarse reconstruction.Furthermore,the intraday volatility analysis based on LM test is applied on 15-minutes frequency data to detect discontinuous jump arrivals and extract jump from realized quadratic variation.Empirical results show that three components of reconstruction can be identified as short term fluctuations process caused by microstructure noise,the shocks affected by major events,and a long-term trend based on inelastic supply and rigid demand.We find that approximately 40%of jumps can be matched with the news from the public news database(Factiva),and the jump sizes are larger than that of stock markets.This finding indicates that the Bitcoin market has more irregularly noise and unforeseen shocks from unscheduled events.展开更多
OBJECTIVE: To evaluate the efficacy of Banxiaxiexin Tang compared with Western Medicine in the treatment of functional dyspepsia(FD) through Meta-analysis.METHODS: Literature was searched in the following databases: M...OBJECTIVE: To evaluate the efficacy of Banxiaxiexin Tang compared with Western Medicine in the treatment of functional dyspepsia(FD) through Meta-analysis.METHODS: Literature was searched in the following databases: MEDLINE, Excerpta Medica Database, Chinese Medical Current Contents, China Science and Technology Database, Chinese Biomedical Literature Database, and China National Knowledge Infrastructure. Randomized controlled trials evaluating the efficacy of Banxiaxiexin Tang for the treatment of FD were selected according to certain standards including clear general situation of patients, specific diagnostic criteria, definite clinical outcomes, etc. Articles were evaluated with quality assessment standards in the Cochrane Handbook for Systematic Reviews of Interventions. Meta-analysis was conducted with RevMan 5.0.23 software.RESULTS: Ten articles with a total of 972 patients were included. The comparison of efficacy between Banxiaxiexin Tang and Western Medicine showed a combined effect size [OR=2.75, 95% CI(1.86-4.07)]andcombinedeffectofvalueofZ=5.07(P<0.000 01),suggesting a significant difference between the groups.CONCLUSION: Banxiaxiexin Tang was more effective thanWestern Medicine in treating FD.展开更多
In this paper,a bioinspired path planning approach for mobile robots is proposed.The approach is based on the sparrow search algorithm,which is an intelligent optimization algorithm inspired by the group wisdom,foragi...In this paper,a bioinspired path planning approach for mobile robots is proposed.The approach is based on the sparrow search algorithm,which is an intelligent optimization algorithm inspired by the group wisdom,foraging,and anti-predation behaviors of sparrows.To obtain high-quality paths and fast convergence,an improved sparrow search algorithm is proposed with three new strategies.First,a linear path strategy is proposed,which can transform the polyline in the corner of the path into a smooth line,to enable the robot to reach the goal faster.Then,a new neighborhood search strategy is used to improve the fitness value of the global optimal individual,and a new position update function is used to speed up the convergence.Finally,a new multi-index comprehensive evaluation method is designed to evaluate these algorithms.Experimental results show that the proposed algorithm has a shorter path and faster convergence than other state-ofthe-art studies.展开更多
With the recent upsurge of studies in the field of microbiology,we have learned more about the complexity of the gastrointestinal microecosystem.More than 30 genera and 1000 species of gastrointestinal microflora have...With the recent upsurge of studies in the field of microbiology,we have learned more about the complexity of the gastrointestinal microecosystem.More than 30 genera and 1000 species of gastrointestinal microflora have been found.The structure of the normal microflora is relatively stable,and is in an interdependent and restricted dynamic equilibrium with the body.In recent years,studies have shown that there is a potential relationship between gastrointestinal microflora imbalance and gastric cancer(GC)and precancerous lesions.So,restoring the balance of gastrointestinal microflora is of great significance.Moreover,intervention in gastric premalignant condition(GPC),also known as precancerous lesion of gastric cancer(PLGC),has been the focus of current clinical studies.The holistic view of traditional Chinese medicine(TCM)is consistent with the microecology concept,and oral TCM can play a two-way regulatory role directly with the microflora in the digestive tract,restoring the homeostasis of gastrointestinal microflora to prevent canceration.However,large gaps in knowledge remain to be addressed.This review aims to provide new ideas and a reference for clinical practice.展开更多
Foreword Note:Some of the document contents may involve certain patents,the identification of which is not the responsibility of the institution that releases the document.Main drafting organizations:Tsinghua Universi...Foreword Note:Some of the document contents may involve certain patents,the identification of which is not the responsibility of the institution that releases the document.Main drafting organizations:Tsinghua University,Specialty Committee of Network Pharmacology of World Federation of Chinese Medicine Societies(WFCMS).展开更多
Determining effective traditional Chinese medicine （TCM） treatments for specific disease conditions or particular patient groups is a difficult issue that necessitates investigation because of the complicated person...Determining effective traditional Chinese medicine （TCM） treatments for specific disease conditions or particular patient groups is a difficult issue that necessitates investigation because of the complicated personalized manifestations in real-world patients and the individualized combination therapies prescribed in clinical settings. In this study, a multistage analysis method that integrates propensity case matching, complex network analysis, and herb set enrichment analysis was proposed to identify effective herb prescriptions for particular diseases （e.g., insomnia）. First, propensity case matching was applied to match clinical cases. Then, core network extraction and herb set enrichment were combined to detect core effective herb prescriptions. Effectiveness-based mutual information was used to detect strong herb symptom relationships. This method was applied on a TCM clinical data set with 955 patients collected from well-designed observational studies. Results revealed that groups of herb prescriptions with higher effectiveness rates （76.9% vs. 42.8% for matched samples; 94.2% vs. 84.9% for all samples） compared with the original prescriptions were found. Particular patient groups with symptom manifestations were also identified to help investigate the indications of the effective herb prescriptions.展开更多
Vascular endothelial growth factor(VEGF)is the main regulator of physiological angiogenesis during embryonic development,bone growth,and reproductive function,and it also participates in a series of pathological chang...Vascular endothelial growth factor(VEGF)is the main regulator of physiological angiogenesis during embryonic development,bone growth,and reproductive function,and it also participates in a series of pathological changes.Traditional Chinese medicine(TCM),with a history of more than 2000 years,has been widely used in clinical practice,while the exploration of its mechanisms has only begun.This review summarizes the research of recent years on the influence of TCM on VEGF.It is found that many Chinese medicines and recipes have a regulatory effect on VEGF,indicating that Chinese medicine has broad prospects as a complementary and alternative therapy,providing new treatment ideas for clinical applications and the theoretical basis for research on the mechanisms of TCM.展开更多
Emerging single-cell technologies create new opportunities for unraveling tumor heterogeneity.However,the development of high-content phenotyping platform is still at its infancy.Here,we develop a microfluidic chip fo...Emerging single-cell technologies create new opportunities for unraveling tumor heterogeneity.However,the development of high-content phenotyping platform is still at its infancy.Here,we develop a microfluidic chip for two-dimensional(2D)profiling of tumor chemotactic and molecular features at single cell resolution.Individual cells were captured by the triangular micropillar arrays in the cell-loading channel,facilitating downstream single-cell analysis.For 2D phenotyping,the chemotactic properties of tumor cells were visualized through cellular migratory behavior in microchannels,while their protein expression was profiled with multiplex surface enhanced Raman scattering(SERS)nanovectors,in which Raman reporter-embedded gold@silver core-shell nanoparticles(Au@Ag REPs)were modified with DNA aptamers targeting cellular surface proteins.As a proof of concept,breast cancer cells with diverse phenotypes were tested on the chip,demonstrating the capability of this platform for simultaneous chemotactic and molecular analysis.The chip is expected to provide a powerful tool for investigating tumor heterogeneity and promoting clinical precision medicine.展开更多
Imaging through a time-varying water surface exhibits severe non-rigid geometric distortions and motion blur.Theoretically,although the water surface possesses smoothness and temporal periodicity,random fluctuations a...Imaging through a time-varying water surface exhibits severe non-rigid geometric distortions and motion blur.Theoretically,although the water surface possesses smoothness and temporal periodicity,random fluctuations are inevitable in an actual video sequence.Meanwhile,considering the distribution of information,the image structure contributes more to the restoration.In this paper,a new two-stage restoration method for distorted underwater video sequences is presented.During the first stage,salient feature points,which are selected through multiple methods,are tracked across the frames,and the motion fields at all pixels are estimated using a compressive sensing solver to remove the periodic distortions.During the second stage,the combination of a guided filter algorithm and an image registration method is applied to remove the structural-information-oriented residual distortions.Finally,the experiment results show that the method outperforms other state-of-the-art approaches in terms of the recovery effect and time.展开更多
Due to the large-scale spread of COVID-19,which has a significant impact on human health and social economy,developing effective antiviral drugs for COVID-19 is vital to saving human lives.Various biomedical associati...Due to the large-scale spread of COVID-19,which has a significant impact on human health and social economy,developing effective antiviral drugs for COVID-19 is vital to saving human lives.Various biomedical associations,e.g.,drug-virus and viral protein-host protein interactions,can be used for building biomedical knowledge graphs.Based on these sources,large-scale knowledge reasoning algorithms can be used to predict new links between antiviral drugs and viruses.To utilize the various heterogeneous biomedical associations,we proposed a fusion strategy to integrate the results of two tensor decomposition-based models(i.e.,CP-N3 and Compl Ex-N3).Sufficient experiments indicated that our method obtained high performance(MRR=0.2328).Compared with CP-N3,the mean reciprocal rank(MRR)is increased by 3.3%and compared with Compl Ex-N3,the MRR is increased by 3.5%.Meanwhile,we explored the relationship between the performance and relationship types,which indicated that there is a negative correlation(PCC=0.446,P-value=2.26 e-194)between the performance of triples predicted by our method and edge betweenness.展开更多
基金This research was supported by the National Natural Science Foundation of China(31772288)Shandong Natural Science Major Basic Research Foundation(ZR2020ZD43).
文摘Jasmonic acid(JA)plays an important role in regulating leaf senescence.However,the molecular mechanisms of leaf senescence in apple(Malus domestica)remain elusive.In this study,we found that MdZAT10,a C2H2-type zinc finger transcription factor(TF)in apple,markedly accelerates leaf senescence and increases the expression of senescence-related genes.To explore how MdZAT10 promotes leaf senescence,we carried out liquid chromatography/mass spectrometry screening.We found that MdABI5 physically interacts with MdZAT10.MdABI5,an important positive regulator of leaf senescence,significantly accelerated leaf senescence in apple.MdZAT10 was found to enhance the transcriptional activity of MdABI5 for MdNYC1 and MdNYE1,thus accelerating leaf senescence.In addition,we found that MdZAT10 expression was induced by methyl jasmonate(MeJA),which accelerated JA-induced leaf senescence.We also found that the JA-responsive protein MdBT2 directly interacts with MdZAT10 and reduces its protein stability through ubiquitination and degradation,thereby delaying MdZAT10-mediated leaf senescence.Taken together,our results provide new insight into the mechanisms by which MdZAT10 positively regulates JA-induced leaf senescence in apple.
文摘Introduction China is a country with a low morbidity of prostate carcinoma.The in-cidence of prostate carcinoma in China is 1.6/100,000,which is muchlower than the rate in the United States,i.e.,119.9/100,000.Dueto changes of lifestyle and improved measurement of serum
基金financially supported by the Natural Science Foundation of Beijing(No.M21012)National Natural Science Foundation of China(No.82174533)Key Technologies R and D Program of the China Academy of Chinese Medical Sciences(No.CI2021A00920).
文摘Objective:To validate two proposed coronavirus disease 2019(COVID-19)prognosis models,analyze the characteristics of different models,consider the performance of models in predicting different outcomes,and provide new insights into the development and use of artificial intelligence(AI)predictive models in clinical decision-making for COVID-19 and other diseases.Materials and Methods:We compared two proposed prediction models for COVID-19 prognosis that use a decision tree and logistic regression modeling.We evaluated the effectiveness of different model-building strategies using laboratory tests and/or clinical record data,their sensitivity and robustness to the timings of records used and the presence of missing data,and their predictive performance and capabilities in single-site and multicenter settings.Results:The predictive accuracies of the two models after retraining were improved to 93.2% and 93.9%,compared with that of the models directly used,with accuracies of 84.3% and 87.9%,indicating that the prediction models could not be used directly and require retraining based on actual data.In addition,based on the prediction model,new features obtained by model comparison and literature evidence were transferred to integrate the new models with better performance.Conclusions:Comparing the characteristics and differences of datasets used in model training,effective model verification,and a fusion of models is necessary in improving the performance of AI models.
基金Supported by the National Natural Science Foundation of China(72073126,71988101,72091212)Young Elite Scientists Sponsorship Program by CAST(YESS20200072)。
文摘Since Bitcoin came into the world,modelling and analyzing the underlying characteristics of Bitcoin has attracted increasing attention.This paper uses a framework including decomposition,reconstruction and extraction method(DRE)to analyze price fluctuations based on ultra-high-frequency data from Dec.1,2019,to Nov.30,2021.First,the ensemble mode decomposition(EMD)is employed to decompose the Bitcoin hourly spot price into 13 intrinsic mode functions(IMF)plus a residual.Second,the IMFs are reconstructed into high-frequency components,low-frequency components and a trend based on fine-to-coarse reconstruction.Furthermore,the intraday volatility analysis based on LM test is applied on 15-minutes frequency data to detect discontinuous jump arrivals and extract jump from realized quadratic variation.Empirical results show that three components of reconstruction can be identified as short term fluctuations process caused by microstructure noise,the shocks affected by major events,and a long-term trend based on inelastic supply and rigid demand.We find that approximately 40%of jumps can be matched with the news from the public news database(Factiva),and the jump sizes are larger than that of stock markets.This finding indicates that the Bitcoin market has more irregularly noise and unforeseen shocks from unscheduled events.
文摘OBJECTIVE: To evaluate the efficacy of Banxiaxiexin Tang compared with Western Medicine in the treatment of functional dyspepsia(FD) through Meta-analysis.METHODS: Literature was searched in the following databases: MEDLINE, Excerpta Medica Database, Chinese Medical Current Contents, China Science and Technology Database, Chinese Biomedical Literature Database, and China National Knowledge Infrastructure. Randomized controlled trials evaluating the efficacy of Banxiaxiexin Tang for the treatment of FD were selected according to certain standards including clear general situation of patients, specific diagnostic criteria, definite clinical outcomes, etc. Articles were evaluated with quality assessment standards in the Cochrane Handbook for Systematic Reviews of Interventions. Meta-analysis was conducted with RevMan 5.0.23 software.RESULTS: Ten articles with a total of 972 patients were included. The comparison of efficacy between Banxiaxiexin Tang and Western Medicine showed a combined effect size [OR=2.75, 95% CI(1.86-4.07)]andcombinedeffectofvalueofZ=5.07(P<0.000 01),suggesting a significant difference between the groups.CONCLUSION: Banxiaxiexin Tang was more effective thanWestern Medicine in treating FD.
基金supported by the National Key R&D Program of China(Grant No.2018YFB1309200)the Opening Project of Shanghai Robot Industry R&D and Transformation Functional Platform.
文摘In this paper,a bioinspired path planning approach for mobile robots is proposed.The approach is based on the sparrow search algorithm,which is an intelligent optimization algorithm inspired by the group wisdom,foraging,and anti-predation behaviors of sparrows.To obtain high-quality paths and fast convergence,an improved sparrow search algorithm is proposed with three new strategies.First,a linear path strategy is proposed,which can transform the polyline in the corner of the path into a smooth line,to enable the robot to reach the goal faster.Then,a new neighborhood search strategy is used to improve the fitness value of the global optimal individual,and a new position update function is used to speed up the convergence.Finally,a new multi-index comprehensive evaluation method is designed to evaluate these algorithms.Experimental results show that the proposed algorithm has a shorter path and faster convergence than other state-ofthe-art studies.
基金This work was supported by the Tianjin Sci-Tech Projects(No.16YFZCSY01070),China.
文摘With the recent upsurge of studies in the field of microbiology,we have learned more about the complexity of the gastrointestinal microecosystem.More than 30 genera and 1000 species of gastrointestinal microflora have been found.The structure of the normal microflora is relatively stable,and is in an interdependent and restricted dynamic equilibrium with the body.In recent years,studies have shown that there is a potential relationship between gastrointestinal microflora imbalance and gastric cancer(GC)and precancerous lesions.So,restoring the balance of gastrointestinal microflora is of great significance.Moreover,intervention in gastric premalignant condition(GPC),also known as precancerous lesion of gastric cancer(PLGC),has been the focus of current clinical studies.The holistic view of traditional Chinese medicine(TCM)is consistent with the microecology concept,and oral TCM can play a two-way regulatory role directly with the microflora in the digestive tract,restoring the homeostasis of gastrointestinal microflora to prevent canceration.However,large gaps in knowledge remain to be addressed.This review aims to provide new ideas and a reference for clinical practice.
文摘Foreword Note:Some of the document contents may involve certain patents,the identification of which is not the responsibility of the institution that releases the document.Main drafting organizations:Tsinghua University,Specialty Committee of Network Pharmacology of World Federation of Chinese Medicine Societies(WFCMS).
文摘Determining effective traditional Chinese medicine （TCM） treatments for specific disease conditions or particular patient groups is a difficult issue that necessitates investigation because of the complicated personalized manifestations in real-world patients and the individualized combination therapies prescribed in clinical settings. In this study, a multistage analysis method that integrates propensity case matching, complex network analysis, and herb set enrichment analysis was proposed to identify effective herb prescriptions for particular diseases （e.g., insomnia）. First, propensity case matching was applied to match clinical cases. Then, core network extraction and herb set enrichment were combined to detect core effective herb prescriptions. Effectiveness-based mutual information was used to detect strong herb symptom relationships. This method was applied on a TCM clinical data set with 955 patients collected from well-designed observational studies. Results revealed that groups of herb prescriptions with higher effectiveness rates （76.9% vs. 42.8% for matched samples; 94.2% vs. 84.9% for all samples） compared with the original prescriptions were found. Particular patient groups with symptom manifestations were also identified to help investigate the indications of the effective herb prescriptions.
基金supported by the Tianjin Sci-Tech Project(No.16YFZCSY01070),China。
文摘Vascular endothelial growth factor(VEGF)is the main regulator of physiological angiogenesis during embryonic development,bone growth,and reproductive function,and it also participates in a series of pathological changes.Traditional Chinese medicine(TCM),with a history of more than 2000 years,has been widely used in clinical practice,while the exploration of its mechanisms has only begun.This review summarizes the research of recent years on the influence of TCM on VEGF.It is found that many Chinese medicines and recipes have a regulatory effect on VEGF,indicating that Chinese medicine has broad prospects as a complementary and alternative therapy,providing new treatment ideas for clinical applications and the theoretical basis for research on the mechanisms of TCM.
基金This study was supported by the National Science Fund for Excellent Young Scholars(No.61822503)the National Natural Science Foundation of China(Nos.62175030 and 62175027)+3 种基金China Postdoctoral Science Foundation(No.2021TQ0147)Jiangsu Innovation and Entrepreneurship Program(No.JSSCBS20210126)Nanjing Science and Technology Innovation Project for Returned Overseas Chinese Scholars(No.1106000308)the Fundamental Research Funds for the Central Universities(Nos.3206002104D and 3206002108A1).
文摘Emerging single-cell technologies create new opportunities for unraveling tumor heterogeneity.However,the development of high-content phenotyping platform is still at its infancy.Here,we develop a microfluidic chip for two-dimensional(2D)profiling of tumor chemotactic and molecular features at single cell resolution.Individual cells were captured by the triangular micropillar arrays in the cell-loading channel,facilitating downstream single-cell analysis.For 2D phenotyping,the chemotactic properties of tumor cells were visualized through cellular migratory behavior in microchannels,while their protein expression was profiled with multiplex surface enhanced Raman scattering(SERS)nanovectors,in which Raman reporter-embedded gold@silver core-shell nanoparticles(Au@Ag REPs)were modified with DNA aptamers targeting cellular surface proteins.As a proof of concept,breast cancer cells with diverse phenotypes were tested on the chip,demonstrating the capability of this platform for simultaneous chemotactic and molecular analysis.The chip is expected to provide a powerful tool for investigating tumor heterogeneity and promoting clinical precision medicine.
基金supported by the National Key R&D Program of China(Grant No.2018YFB1309200).
文摘Imaging through a time-varying water surface exhibits severe non-rigid geometric distortions and motion blur.Theoretically,although the water surface possesses smoothness and temporal periodicity,random fluctuations are inevitable in an actual video sequence.Meanwhile,considering the distribution of information,the image structure contributes more to the restoration.In this paper,a new two-stage restoration method for distorted underwater video sequences is presented.During the first stage,salient feature points,which are selected through multiple methods,are tracked across the frames,and the motion fields at all pixels are estimated using a compressive sensing solver to remove the periodic distortions.During the second stage,the combination of a guided filter algorithm and an image registration method is applied to remove the structural-information-oriented residual distortions.Finally,the experiment results show that the method outperforms other state-of-the-art approaches in terms of the recovery effect and time.
基金partially supported by Beijing Natural Science Foundation(No.M21012)National Key Research and Development Program of China(No.2017YFC1703506,No.2018AAA0100302)National Natural Science Foundation of China(No.82174533)
文摘Due to the large-scale spread of COVID-19,which has a significant impact on human health and social economy,developing effective antiviral drugs for COVID-19 is vital to saving human lives.Various biomedical associations,e.g.,drug-virus and viral protein-host protein interactions,can be used for building biomedical knowledge graphs.Based on these sources,large-scale knowledge reasoning algorithms can be used to predict new links between antiviral drugs and viruses.To utilize the various heterogeneous biomedical associations,we proposed a fusion strategy to integrate the results of two tensor decomposition-based models(i.e.,CP-N3 and Compl Ex-N3).Sufficient experiments indicated that our method obtained high performance(MRR=0.2328).Compared with CP-N3,the mean reciprocal rank(MRR)is increased by 3.3%and compared with Compl Ex-N3,the MRR is increased by 3.5%.Meanwhile,we explored the relationship between the performance and relationship types,which indicated that there is a negative correlation(PCC=0.446,P-value=2.26 e-194)between the performance of triples predicted by our method and edge betweenness.
