| Attributs | Valeurs |
|---|
| type
| |
| Is Part Of
| |
| Subject
| |
| Title
| - QSAR − How Good Is It in Practice? Comparison of Descriptor Sets on an UnbiasedCross Section of Corporate Data Sets
|
| has manifestation of work
| |
| related by
| |
| Author
| |
| Abstract
| - The quality of QSAR (Quantitative Structure−Activity Relationships) predictions depends on a large numberof factors including the descriptor set, the statistical method, and the data sets used. Here we study thequality of QSAR predictions mainly as a function of the data set and descriptor type using partial leastsquares as the statistical modeling method. The study makes use of the fact that we have access to a largenumber of data sets and to a variety of different QSAR descriptors. The main conclusions are that thequality of the predictions depends both on the data set and the descriptor used. The quality of the predictionscorrelates positively with the size of the data set and the range of biological activities. There is no cleardependence of the quality of the predictions on the complexity of the data set. All of the descriptors testedproduced useful predictions for some of the data sets. None of the descriptors is best for all data sets; it istherefore necessary to test in each individual case, which descriptor produces the best model. In our tests,2D fragment based descriptors usually performed better than simpler descriptors based on augmented atomtypes. Possible reasons for these observations are discussed.
|
| article type
| |
| is part of this journal
| |
