Vector descriptor

For each property, an autocorrelation vector of length 17 was calculated. This yielded a descriptor vector which contained 136 (8 x 17) individual descriptors. 

The simplest and fastest techniques for grouping molecules are partitioning methods. Every molecule is represented by a point in an n-dimensional space, the axes of which are defined by the n components of the descriptor vector. The range of values for each component is then subdivided into a set of subranges (or bins). As a result, the entire multidimensional space is partitioned into a number of hypercubes (or cells) of fixed size, and every molecule (represented as a point in this space) falls into one of these cells [57]. 

Mathematically, the model is a function that predicts the learned property from the descriptor vector. Building the model means finding the optimal prediction function... 

A polynomial function is applied to return the inner products of descriptor vectors and the separating hyperplane is defined as... 

The descriptor matrix formed by the uniform descriptor vectors for all the training set structures, as well as the experimental activity values, serves as the source data for the statistical analysis and construction of the QSAR model. 

Figure 5.3 Formation of a uniform descriptor vector for a structure by superimposing it onto the MSG.

Computational methods applied in diversity computations for building blocks can be much more compHcated and more precise, because the number of processed structures is much smaUer. If a combinatorial Hbrary utilizes three building block Hbraries which contain 50,100 and 200 reactants, the virtual Hbrary consists of one milHon structures. To describe the entire virtual Hbrary, one milHon descriptor vectors are needed. In contrast, the sum of building blocks to be described is just 350. 

Moreover, because all the selected properties, except for molar refractivity, contain both positive and negative values, these are treated as different properties and cross-correlation terms are also calculated between positive and negative values of each property. Therefore, 7 autocorrelation terms and 12 cross-correlation terms constitute the final TMACC descriptor vector. 

VSW descriptor (Vector of principal component Scores for WHIMs) is a vectorial descriptor derived from Principal Component Analysis on the 99 WHIM descriptors calculated for the... 

The probability density p(Y=l X = x)ofa compound, represented by the descriptor vector x, to be active is calculated according to... 

First, the atom types within a molecule are assigned then, n-centered groups are searched for, n varying from 1 to 4, and the occurrence frequency of each is recorded in the final descriptor vector. 

Givehchi, A. and Schneider, G. (2004) Impact of descriptor vector scaling on the classification of drugs and nondrugs with artificial neural networks./. Mol. Model., 10, 204—211. 

Let the moduli nij (f) e 0, 1 V f > 0, y = 1,..., Hs, of the Us switching MTFs be grouped into a vector m t), the outputs Zi of all storage elements in integral causality, the inputs Zd of all storage elements in derivative causality and the outputs of resistors and switches be grouped into a descriptor vector x. The outputs of all modulated sinks activated at switching events are combined into a vector X. Let denote the vector of all system inputs. 

Now, let Ax denote variations of the states of all storage elements in integral causality, AxJ the variations of the non-states of all energy stores in differential causality in the incremental bond graph of the inverse model, and Ax the descriptor vector Ax = [Ax A ff. Furthermore, may A denote the vector of parameter variations. Then, matrices can be built so that... 

---