Objective To develop a model based on a graph convolutional network(GCN)to achieve ef-ficient classification of the cold and hot medicinal properties of Chinese herbal medicines(CHMs).Methods After screening the datas...Objective To develop a model based on a graph convolutional network(GCN)to achieve ef-ficient classification of the cold and hot medicinal properties of Chinese herbal medicines(CHMs).Methods After screening the dataset provided in the published literature,this study includ-ed 495 CHMs and their 8075 compounds.Three molecular descriptors were used to repre-sent the compounds:the molecular access system(MACCS),extended connectivity finger-print(ECFP),and two-dimensional(2D)molecular descriptors computed by the RDKit open-source toolkit(RDKit_2D).A homogeneous graph with CHMs as nodes was constructed and a classification model for the cold and hot medicinal properties of CHMs was developed based on a GCN using the molecular descriptor information of the compounds as node features.Fi-nally,using accuracy and F1 score to evaluate model performance,the GCN model was ex-perimentally compared with the traditional machine learning approaches,including decision tree(DT),random forest(RF),k-nearest neighbor(KNN),Naïve Bayes classifier(NBC),and support vector machine(SVM).MACCS,ECFP,and RDKit_2D molecular descriptors were al-so adopted as features for comparison.Results The experimental results show that the GCN achieved better performance than the traditional machine learning approach when using MACCS as features,with the accuracy and F1 score reaching 0.8364 and 0.8453,respectively.The accuracy and F1 score have increased by 0.8690 and 0.8120,respectively,compared with the lowest performing feature combina-tion OMER(only the combination of MACCS,ECFP,and RDKit_2D).The accuracy and F1 score of DT,RF,KNN,NBC,and SVM are 0.5051 and 0.5018,0.6162 and 0.6015,0.6768 and 0.6243,0.6162 and 0.6071,0.6364 and 0.6225,respectively.Conclusion In this study,by introducing molecular descriptors as features,it is verified that molecular descriptors and fingerprints play a key role in classifying the cold and hot medici-nal properties of CHMs.Meanwhile,excellent classification performance was achieved using the GCN model,providing an important algorithmic basis for the in-depth study of the“struc-ture-property”relationship of CHMs.展开更多
A new method to test rock abrasiveness is proposed based upon the dependence of rock abrasiveness on their structural and physico-mechanical properties. The article describes the procedure of presentation of propertie...A new method to test rock abrasiveness is proposed based upon the dependence of rock abrasiveness on their structural and physico-mechanical properties. The article describes the procedure of presentation of properties that govern rock abrasiveness on a canonical scale by dimensionless components, and the integrated estimation of the properties by a generalized index. The obtained results are compared with the known classifications of rock abrasiveness.展开更多
The study of the relationship of local ground conditions with the parameters </span><span style="font-family:Verdana;">of seismic vibrations carried out by the section of engineering seismology&l...The study of the relationship of local ground conditions with the parameters </span><span style="font-family:Verdana;">of seismic vibrations carried out by the section of engineering seismology</span><span style="font-family:Verdana;"> called seismic microzonation. In</span><i> </i><span style="font-family:Verdana;">this branch of applied science radical changes have taken place at the end of the last century. The Commission on Seismic Safety of the National Institute of Building Sciences of the United States has developed new recommendations, which are significantly different from all that used in the world practice of anti-seismic construction. The main provisions of this NEHRP (National Earthquake Hazards Reduction Program) classifica</span><span style="font-family:Verdana;">tion adopted in many national building codes, including Eurocode 8. At the same time, a number of papers appeared in subsequent years criticizing the </span><span style="font-family:Verdana;">use of the NEHRP soil classification. This article examines in detail and, </span><span style="font-family:Verdana;">most</span><span style="font-family:Verdana;"> importantly, comprehensively the shortcomings of the NEHRP classification.展开更多
The curse of high-dimensionality has emerged in the statistical fields more and more frequently.Many techniques have been developed to address this challenge for classification problems. We propose a novel feature scr...The curse of high-dimensionality has emerged in the statistical fields more and more frequently.Many techniques have been developed to address this challenge for classification problems. We propose a novel feature screening procedure for dichotomous response data. This new method can be implemented as easily as t-test marginal screening approach, and the proposed procedure is free of any subexponential tail probability conditions and moment requirement and not restricted in a specific model structure. We prove that our method possesses the sure screening property and also illustrate the effect of screening by Monte Carlo simulation and apply it to a real data example.展开更多
基金Hunan Provincial Natural Science Foundation(2022JJ30438)Natural Science Foundation of Changsha(kq2202260)Hunan Province Traditional Chinese Medicine Research Project(B2023039).
文摘Objective To develop a model based on a graph convolutional network(GCN)to achieve ef-ficient classification of the cold and hot medicinal properties of Chinese herbal medicines(CHMs).Methods After screening the dataset provided in the published literature,this study includ-ed 495 CHMs and their 8075 compounds.Three molecular descriptors were used to repre-sent the compounds:the molecular access system(MACCS),extended connectivity finger-print(ECFP),and two-dimensional(2D)molecular descriptors computed by the RDKit open-source toolkit(RDKit_2D).A homogeneous graph with CHMs as nodes was constructed and a classification model for the cold and hot medicinal properties of CHMs was developed based on a GCN using the molecular descriptor information of the compounds as node features.Fi-nally,using accuracy and F1 score to evaluate model performance,the GCN model was ex-perimentally compared with the traditional machine learning approaches,including decision tree(DT),random forest(RF),k-nearest neighbor(KNN),Naïve Bayes classifier(NBC),and support vector machine(SVM).MACCS,ECFP,and RDKit_2D molecular descriptors were al-so adopted as features for comparison.Results The experimental results show that the GCN achieved better performance than the traditional machine learning approach when using MACCS as features,with the accuracy and F1 score reaching 0.8364 and 0.8453,respectively.The accuracy and F1 score have increased by 0.8690 and 0.8120,respectively,compared with the lowest performing feature combina-tion OMER(only the combination of MACCS,ECFP,and RDKit_2D).The accuracy and F1 score of DT,RF,KNN,NBC,and SVM are 0.5051 and 0.5018,0.6162 and 0.6015,0.6768 and 0.6243,0.6162 and 0.6071,0.6364 and 0.6225,respectively.Conclusion In this study,by introducing molecular descriptors as features,it is verified that molecular descriptors and fingerprints play a key role in classifying the cold and hot medici-nal properties of CHMs.Meanwhile,excellent classification performance was achieved using the GCN model,providing an important algorithmic basis for the in-depth study of the“struc-ture-property”relationship of CHMs.
文摘A new method to test rock abrasiveness is proposed based upon the dependence of rock abrasiveness on their structural and physico-mechanical properties. The article describes the procedure of presentation of properties that govern rock abrasiveness on a canonical scale by dimensionless components, and the integrated estimation of the properties by a generalized index. The obtained results are compared with the known classifications of rock abrasiveness.
文摘The study of the relationship of local ground conditions with the parameters </span><span style="font-family:Verdana;">of seismic vibrations carried out by the section of engineering seismology</span><span style="font-family:Verdana;"> called seismic microzonation. In</span><i> </i><span style="font-family:Verdana;">this branch of applied science radical changes have taken place at the end of the last century. The Commission on Seismic Safety of the National Institute of Building Sciences of the United States has developed new recommendations, which are significantly different from all that used in the world practice of anti-seismic construction. The main provisions of this NEHRP (National Earthquake Hazards Reduction Program) classifica</span><span style="font-family:Verdana;">tion adopted in many national building codes, including Eurocode 8. At the same time, a number of papers appeared in subsequent years criticizing the </span><span style="font-family:Verdana;">use of the NEHRP soil classification. This article examines in detail and, </span><span style="font-family:Verdana;">most</span><span style="font-family:Verdana;"> importantly, comprehensively the shortcomings of the NEHRP classification.
基金supported by Graduate Innovation Foundation of Shanghai University of Finance and Economics of China (Grant Nos. CXJJ-2014-459 and CXJJ-2015-430)National Natural Science Foundation of China (Grant No. 71271128), the State Key Program of National Natural Science Foundation of China (Grant No. 71331006), the State Key Program in the Major Research Plan of National Natural Science Foundation of China (Grant No. 91546202)+1 种基金National Center for Mathematics and Interdisciplinary Sciences, Key Laboratory of Random Complex Structures and Data Science, Academy of Mathematics and Systems Science, Chinese Academy of Sciences (Grant No. 2008DP173182)Innovative Research Team in Shanghai University of Finance and Economics (Grant No. IRT13077)
文摘The curse of high-dimensionality has emerged in the statistical fields more and more frequently.Many techniques have been developed to address this challenge for classification problems. We propose a novel feature screening procedure for dichotomous response data. This new method can be implemented as easily as t-test marginal screening approach, and the proposed procedure is free of any subexponential tail probability conditions and moment requirement and not restricted in a specific model structure. We prove that our method possesses the sure screening property and also illustrate the effect of screening by Monte Carlo simulation and apply it to a real data example.
