Predictive models molecular descriptors

The series editors wish this book a wide distribution. It is up to the reader to find out which of the properties and descriptors might be most suitable for describing the data. However, the early warnings by Corwin Hansch, John Topliss, and others should not be forgotten make your model as simple as possible test and include only a few parameters try to achieve an understanding of your model use a test set to check the external predictivity of your model. Molecular descriptors are powerful tools in QSAR studies - but their abuse may lead nowhere. May this book further contribute to their selective and proper use ... 

Modeling Approach is a specific method for deriving the molecular structure from an infrared spectrum by predicting a molecular descriptor from an artificial neural network, searching for the most similar descriptor in a structure database, and using an iterative method for structure adaptation until its descriptor matches the predicted one. 

The method of building predictive models in QSPR/QSAR can also be applied to the modeling of materials without a unique, clearly defined structure. Instead of the connection table, physicochemical data as well as spectra reflecting the compound s structure can be used as molecular descriptors for model building,... 

These pharmacophore techniques are different in format from the traditional pharmacophore definitions. They can not be easily visualized and mapped to the molecular structures rather, they are encoded as keys or topological/topographical descriptors. Nonetheless, they capture the same idea as the classic pharmacophore concept. Furthermore, this formalism is quite useful in building quantitative predictive models that can be used to classify and predict biological activities. 

Li H, Yap CW, Ung CY, Xue Y, Cao ZW and Chen YZ Effect of selection of molecular descriptors on the prediction of blood-brain barrier penetrating and nonpenetrating agents by statistical learning methods. J Chem Inf Model 2005 45 1376-1384. 

Raevsky, O. A., Dearden, J. C. Creation of predictive models of aquatic toxicity of environmental pollutants with different mechanisms of action on the basis of molecular similarity and HYBOT descriptors. SAR QSAR Environ. Res. 2004, 15, 433-448. 

After all the careful filtering, there was neither a single molecular property from the profiles discussed above which could effectively discriminate the two classes nor a predictive model obtained from all those property descriptors. Only after... 

The VolSurf method was used to produce molecular descriptors, and PLS discriminant analysis (DA) was applied. The statistical model showed two significant latent variables after cross-validation. The 2D PLS score model offers a discrimination between the permeable and less permeable compounds. When the spectrum color is active (Fig. 17.2), red points refer to high permeability, whereas blue points indicate low permeability. There is a region in the central part of the plot with both red and blue compounds. In this region, and in between the two continuous lines, the permeability prediction is less reliable. The permeability model... 

Flexible optimal descriptors have been defined as specific modifications of adjacency matrix, by means of utilization of nonzero diagonal elements (Randic and Basak, 1999, 2001 Randic and Pompe, 2001a, b). These nonzero values of matrix elements change vertex degrees and consequently the values of molecular descriptors. As a rule, these modifications are aimed to change topological indices. The values of these diagonal elements must provide minimum standard error of estimation for predictive model (that is based on the flexible descriptor) of property/activity of interest. 

The predictive performance of majority of the log BB models developed so far is 0.4 log units, despite the great diversity of molecular descriptors employed and the variations in the composition of the training sets. This seems like a large error in comparison to the range of log BB determined by experiment ( -2 to +1.5, i.e. 3.5 log units). However, it should be remembered that the experimental error in log BB measurements can be around 0.3 log units, and so this value provides a limit to the accuracy of in silico methods. 

---