Breast cancer is presently one of the most common malignancies worldwide,with a higher fatality rate.In this study,a quantitative structure-activity relationship(QSAR)model of compound biological activity and ADMET(Ab...Breast cancer is presently one of the most common malignancies worldwide,with a higher fatality rate.In this study,a quantitative structure-activity relationship(QSAR)model of compound biological activity and ADMET(Absorption,Distribution,Metabolism,Excretion,Toxicity)properties prediction model were performed using estrogen receptor alpha(ERα)antagonist information collected from compound samples.We first utilized grey relation analysis(GRA)in conjunction with the random forest(RF)algorithm to identify the top 20 molecular descriptor variables that have the greatest influence on biological activity,and then we used Spearman correlation analysis to identify 16 independent variables.Second,a QSAR model of the compound were developed based on BP neural network(BPNN),genetic algorithm optimized BP neural network(GA-BPNN),and support vector regression(SVR).The BPNN,the SVR,and the logistic regression(LR)models were then used to identify and predict the ADMET properties of substances,with the prediction impacts of each model compared and assessed.The results reveal that a SVR model was used in QSAR quantitative prediction,and in the classification prediction of ADMET properties:the SVR model predicts the Caco-2 and hERG(human Ether-a-go-go Related Gene)properties,the LR model predicts the cytochrome P450 enzyme 3A4 subtype(CYP3A4)and Micronucleus(MN)properties,and the BPNN model predicts the Human Oral Bioavailability(HOB)properties.Finally,information entropy theory is used to validate the rationality of variable screening,and sensitivity analysis of the model demonstrates that the constructed model has high accuracy and stability,which can be used as a reference for screening probable active compounds and drug discovery.展开更多
Direct coal liquefaction(DCL)is an important and effective method of converting coal into high-valueadded chemicals and fuel oil.In DCL,heating the direct coal liquefaction solvent(DCLS)from low to high temperature an...Direct coal liquefaction(DCL)is an important and effective method of converting coal into high-valueadded chemicals and fuel oil.In DCL,heating the direct coal liquefaction solvent(DCLS)from low to high temperature and pre-hydrogenation of the DCLS are critical steps.Therefore,studying the dissolution of hydrogen in DCLS under liquefaction conditions gains importance.However,it is difficult to precisely determine hydrogen solubility only by experiments,especially under the actual DCL conditions.To address this issue,we developed a prediction model of hydrogen solubility in a single solvent based on the machine-learning quantitative structure–property relationship(ML-QSPR)methods.The results showed that the squared correlation coefficient R^(2)=0.92 and root mean square error RMSE=0.095,indicating the model’s good statistical performance.The external validation of the model also reveals excellent accuracy and predictive ability.Molecular polarization(a)is the main factor affecting the dissolution of hydrogen in DCLS.The hydrogen solubility in acyclic alkanes increases with increasing carbon number.Whereas in polycyclic aromatics,it decreases with increasing ring number,and in hydrogenated aromatics,it increases with hydrogenation degree.This work provides a new reference for the selection and proportioning of DCLS,i.e.,a solvent with higher hydrogen solubility can be added to provide active hydrogen for the reaction and thus reduce the hydrogen pressure.Besides,it brings important insight into the theoretical significance and practical value of the DCL.展开更多
There are 9.56 million accountants in China, who are working in different size firms and nonprofit organizations. The objective of this article is to examine the quantitative relationship between the firm size and the...There are 9.56 million accountants in China, who are working in different size firms and nonprofit organizations. The objective of this article is to examine the quantitative relationship between the firm size and the quantity of accountants working for the firm. In this paper, the employees, sales revenues, and total assets in a firm are employed to measure firm size. The authors collect and analyze the data of 436 listed firms from the Chinese Shenzhen Stock Exchange. The result of this study indicates there is a positive relationship between the firm size and the quantity of accountants employed by the firm. The study also establishes the multiple regression equation, which can be used to predict the quantity of accountants of listed firms. And it provides a way to predict the quantity of accountants of legal organizations.展开更多
The rock uniaxial compressive strength(UCS)is the basic parameter for support designs in underground engineering.In particular,the rock UCS should be obtained rapidly for underground engineering with complex geologica...The rock uniaxial compressive strength(UCS)is the basic parameter for support designs in underground engineering.In particular,the rock UCS should be obtained rapidly for underground engineering with complex geological conditions,such as soft rock,fracture areas,and high stress,to adjust the excavation and support plan and ensure construction safety.To solve the problem of obtaining real-time rock UCS at engineering sites,a rock UCS forecast idea is proposed using digital core drilling.The digital core drilling tests and uniaxial compression tests are performed based on the developed rock mass digital drilling system.The results indicate that the drilling parameters are highly responsive to the rock UCS.Based on the cutting and fracture characteristics of the rock digital core drilling,the mechanical analysis of rock cutting provides the digital core drilling strength,and a quantitative relationship model(CDP-UCS model)for the digital core drilling parameters and rock UCS is established.Thus,the digital core drilling-based rock UCS forecast method is proposed to provide a theoretical basis for continuous and quick testing of the surrounding rock UCS.展开更多
Based on the identical group as a pseudo atom instead of a typical atom, a novel modified molecular dis-tance-edge (MDE) vector μ was developed in our laboratory to characterize chemical structure of polychlorinated ...Based on the identical group as a pseudo atom instead of a typical atom, a novel modified molecular dis-tance-edge (MDE) vector μ was developed in our laboratory to characterize chemical structure of polychlorinated diben-zofurans (PCDFs) congeners and/or isomers. Quantitative structure-retention relationships (QSRRs) between the new VMDE parameters and gas chromatographic (GC) retention behavior of PCDFs were then generated by multiple linear regression (MLR) method for non-polar, moderately polar, and polar stationary phases. Four excellent models with high correlation coefficients, R=0.984-0.995, were proposed for non-polar columns (DB-5, SE-54, OV-101). For the moder-ately polar columns (OV-1701), the correlation coefficient of the developed good model is only 0.958. For the polar col-umns (SP-2300), the QSRR model is poor with R=0.884. Then cross validation with leave-one out of procedure (CV) is performed in high correlation with the non-polar (Rcv=992-0.974) and weakly polar (Rcv=921) columns and in little cor-relation (Rcv=0.834) with the polar columns. These results show that the new μ vector is suitable for describing the re-tention behaviors of PCDFs on non-polar and moderately polar stationary phases and not for the various gas chroma-tographic retention behaviors of PCDFs on the different po-larity-varying stationary phases.展开更多
目的利用机器学习方法,基于定量构效关系建立并验证中草药心脏毒性预测模型,为中草药的安全性评价和临床合理用药提供参考。方法利用比例失衡法筛选并收集美国食品药品监督管理局(Food and Drug Administration,FDA)不良事件报告系统(Ad...目的利用机器学习方法,基于定量构效关系建立并验证中草药心脏毒性预测模型,为中草药的安全性评价和临床合理用药提供参考。方法利用比例失衡法筛选并收集美国食品药品监督管理局(Food and Drug Administration,FDA)不良事件报告系统(Adverse Event Reporting System,FAERS)数据库中具有潜在心脏风险的活性成分,作为主分析数据,随机划分为训练集和验证集,分别通过随机森林(RF)、决策树(DT)、K-最近邻分类法(KNN)和极端梯度提升法(XGBoost)构建预测模型及内部验证,使用曲线下面积(AUC)、准确率、精确度等多个指标评估模型的性能,选出最优模型;并通过检索相关数据库建库至2025年1月1日的文献收集具有心脏毒性的中草药活性成分,从自发报告系统数据库挖掘出可能具有心脏风险的中草药,并从TCMSP数据库中筛查其活性成分,作为测试集,对构建的最优模型进行外部验证。结果预测性能最佳的模型为KNN,训练集AUC=0.684,验证集AUC=0.718;通过文献筛选出24种具有心脏毒性的中草药活性成分,自发报告系统数据库中筛查出怀疑中草药11种,经外部验证后18种中草药活性成分以及10种中草药预测出心脏风险。结论模型预测的整体准确率达80%,可以用于中草药活性成分的心脏毒性预测。展开更多
基金Supported by the Postgraduate Research&Practice Innovation Program of Jiangsu Province(KYCX23_0082)
文摘Breast cancer is presently one of the most common malignancies worldwide,with a higher fatality rate.In this study,a quantitative structure-activity relationship(QSAR)model of compound biological activity and ADMET(Absorption,Distribution,Metabolism,Excretion,Toxicity)properties prediction model were performed using estrogen receptor alpha(ERα)antagonist information collected from compound samples.We first utilized grey relation analysis(GRA)in conjunction with the random forest(RF)algorithm to identify the top 20 molecular descriptor variables that have the greatest influence on biological activity,and then we used Spearman correlation analysis to identify 16 independent variables.Second,a QSAR model of the compound were developed based on BP neural network(BPNN),genetic algorithm optimized BP neural network(GA-BPNN),and support vector regression(SVR).The BPNN,the SVR,and the logistic regression(LR)models were then used to identify and predict the ADMET properties of substances,with the prediction impacts of each model compared and assessed.The results reveal that a SVR model was used in QSAR quantitative prediction,and in the classification prediction of ADMET properties:the SVR model predicts the Caco-2 and hERG(human Ether-a-go-go Related Gene)properties,the LR model predicts the cytochrome P450 enzyme 3A4 subtype(CYP3A4)and Micronucleus(MN)properties,and the BPNN model predicts the Human Oral Bioavailability(HOB)properties.Finally,information entropy theory is used to validate the rationality of variable screening,and sensitivity analysis of the model demonstrates that the constructed model has high accuracy and stability,which can be used as a reference for screening probable active compounds and drug discovery.
基金the financial support from the National Key Research and Development Program of China(2022YFB4101302-01)the National Natural Science Foundation of China(22178243)the science and technology innovation project of China Shenhua Coal to Liquid and Chemical Company Limited(MZYHG-22-02).
文摘Direct coal liquefaction(DCL)is an important and effective method of converting coal into high-valueadded chemicals and fuel oil.In DCL,heating the direct coal liquefaction solvent(DCLS)from low to high temperature and pre-hydrogenation of the DCLS are critical steps.Therefore,studying the dissolution of hydrogen in DCLS under liquefaction conditions gains importance.However,it is difficult to precisely determine hydrogen solubility only by experiments,especially under the actual DCL conditions.To address this issue,we developed a prediction model of hydrogen solubility in a single solvent based on the machine-learning quantitative structure–property relationship(ML-QSPR)methods.The results showed that the squared correlation coefficient R^(2)=0.92 and root mean square error RMSE=0.095,indicating the model’s good statistical performance.The external validation of the model also reveals excellent accuracy and predictive ability.Molecular polarization(a)is the main factor affecting the dissolution of hydrogen in DCLS.The hydrogen solubility in acyclic alkanes increases with increasing carbon number.Whereas in polycyclic aromatics,it decreases with increasing ring number,and in hydrogenated aromatics,it increases with hydrogenation degree.This work provides a new reference for the selection and proportioning of DCLS,i.e.,a solvent with higher hydrogen solubility can be added to provide active hydrogen for the reaction and thus reduce the hydrogen pressure.Besides,it brings important insight into the theoretical significance and practical value of the DCL.
文摘There are 9.56 million accountants in China, who are working in different size firms and nonprofit organizations. The objective of this article is to examine the quantitative relationship between the firm size and the quantity of accountants working for the firm. In this paper, the employees, sales revenues, and total assets in a firm are employed to measure firm size. The authors collect and analyze the data of 436 listed firms from the Chinese Shenzhen Stock Exchange. The result of this study indicates there is a positive relationship between the firm size and the quantity of accountants employed by the firm. The study also establishes the multiple regression equation, which can be used to predict the quantity of accountants of listed firms. And it provides a way to predict the quantity of accountants of legal organizations.
基金the Natural Science Foundation of China(Nos.51874188,51927807,41941018 and 51704125)the State Key Laboratory for GeoMechanics and Deep Underground Engineering,China University of Mining&Technology(No.SKLGDUEK1717)+1 种基金the Major Scientific and Technological Innovation Project of Shandong Province,China(No.2019SDZY04)the Project of Shandong Province Higher Educational Youth Innovation Science and Technology Program(No.2019KJG013).
文摘The rock uniaxial compressive strength(UCS)is the basic parameter for support designs in underground engineering.In particular,the rock UCS should be obtained rapidly for underground engineering with complex geological conditions,such as soft rock,fracture areas,and high stress,to adjust the excavation and support plan and ensure construction safety.To solve the problem of obtaining real-time rock UCS at engineering sites,a rock UCS forecast idea is proposed using digital core drilling.The digital core drilling tests and uniaxial compression tests are performed based on the developed rock mass digital drilling system.The results indicate that the drilling parameters are highly responsive to the rock UCS.Based on the cutting and fracture characteristics of the rock digital core drilling,the mechanical analysis of rock cutting provides the digital core drilling strength,and a quantitative relationship model(CDP-UCS model)for the digital core drilling parameters and rock UCS is established.Thus,the digital core drilling-based rock UCS forecast method is proposed to provide a theoretical basis for continuous and quick testing of the surrounding rock UCS.
基金This work was supported by the Chunhui Project Fund of the Ministry of Education(Grant No.SCPF99-4-4+37)Fok Ying-Tung Educational Foundation(Grant No.FYTF98-7-6)+1 种基金Chongqing Applied Science Fund(Grant No,CASF01-3-6)Chongqing University ZYXT Innovation Fund(Grant No.CUIF03-5-6+04-10-10).
文摘Based on the identical group as a pseudo atom instead of a typical atom, a novel modified molecular dis-tance-edge (MDE) vector μ was developed in our laboratory to characterize chemical structure of polychlorinated diben-zofurans (PCDFs) congeners and/or isomers. Quantitative structure-retention relationships (QSRRs) between the new VMDE parameters and gas chromatographic (GC) retention behavior of PCDFs were then generated by multiple linear regression (MLR) method for non-polar, moderately polar, and polar stationary phases. Four excellent models with high correlation coefficients, R=0.984-0.995, were proposed for non-polar columns (DB-5, SE-54, OV-101). For the moder-ately polar columns (OV-1701), the correlation coefficient of the developed good model is only 0.958. For the polar col-umns (SP-2300), the QSRR model is poor with R=0.884. Then cross validation with leave-one out of procedure (CV) is performed in high correlation with the non-polar (Rcv=992-0.974) and weakly polar (Rcv=921) columns and in little cor-relation (Rcv=0.834) with the polar columns. These results show that the new μ vector is suitable for describing the re-tention behaviors of PCDFs on non-polar and moderately polar stationary phases and not for the various gas chroma-tographic retention behaviors of PCDFs on the different po-larity-varying stationary phases.
文摘目的利用机器学习方法,基于定量构效关系建立并验证中草药心脏毒性预测模型,为中草药的安全性评价和临床合理用药提供参考。方法利用比例失衡法筛选并收集美国食品药品监督管理局(Food and Drug Administration,FDA)不良事件报告系统(Adverse Event Reporting System,FAERS)数据库中具有潜在心脏风险的活性成分,作为主分析数据,随机划分为训练集和验证集,分别通过随机森林(RF)、决策树(DT)、K-最近邻分类法(KNN)和极端梯度提升法(XGBoost)构建预测模型及内部验证,使用曲线下面积(AUC)、准确率、精确度等多个指标评估模型的性能,选出最优模型;并通过检索相关数据库建库至2025年1月1日的文献收集具有心脏毒性的中草药活性成分,从自发报告系统数据库挖掘出可能具有心脏风险的中草药,并从TCMSP数据库中筛查其活性成分,作为测试集,对构建的最优模型进行外部验证。结果预测性能最佳的模型为KNN,训练集AUC=0.684,验证集AUC=0.718;通过文献筛选出24种具有心脏毒性的中草药活性成分,自发报告系统数据库中筛查出怀疑中草药11种,经外部验证后18种中草药活性成分以及10种中草药预测出心脏风险。结论模型预测的整体准确率达80%,可以用于中草药活性成分的心脏毒性预测。
