首页 | 本学科首页   官方微博 | 高级检索  
     


Correlation ranking and stepwise regression procedures in principal components artificial neural networks modeling with application to predict toxic activity and human serum albumin binding affinity
Authors:Omar Deeb
Affiliation:
  • Faculty of Pharmacy, Al-Quds University, P.O. Box 20002, Jerusalem, Palestine
  • Abstract:
    Keywords:ANN  artificial neural networks  CR  correlation ranking  CR-PC-ANN  correlation ranking principal components artificial neural networks  CR-PC-ANN(C)  correlation ranking principal components artificial neural networks based on the combined approach  CR-PC-ANN(I)  stepwise regression principal components artificial neural networks based on the individual approach  FE  feature extraction  FS  feature selection  HOMO  highest occupied molecular orbital  HSA  human serum albumin  log IC50  logarithm of half maximal inhibitory concentration  LMO-CV  leave-many-out cross validation  log K'hsa  logarithm of HSA binding affinity  LUMO  lowest unoccupied molecular orbital  MLR  multiple linear regression  PC  principal component  PC-ANN  principal components artificial neural networks  PCA  principal components analysis  PCA(C)  principal components analysis based on the combined approach  PCA(I)  principal components analysis based on the individual approach  PCR  principal component regression  R2  coefficient of determination  R2CV  cross-validation coefficient of determination  RMSE  root mean square error  R2p  square of the correlation coefficient between the predicted and actual activities  SR  stepwise regression  SR-PC-ANN  stepwise regression principal components artificial neural networks  SR-PC-ANN(C)  stepwise regression principal components artificial neural networks based on the combined approach  SR-PC-ANN(I)  stepwise regression principal components artificial neural networks based on the individual approach  SVD  singular value decomposition
    本文献已被 ScienceDirect 等数据库收录!
    设为首页 | 免责声明 | 关于勤云 | 加入收藏

    Copyright©北京勤云科技发展有限公司  京ICP备09084417号