Artificial descriptor

In contrast to that, molecular descriptors in the context of computational chemistry are valnes, vectors, or matrices that are calculated from one or more measured or calculated properties of a molecule. For ease of understanding, let us define those descriptors recorded as a result of an analytical technique as experimental descriptors. In contrast to that, we will talk about artificial descriptors when we refer to those that are calculated. 

Experimental descriptors emerge from a fixed experimental design, and their appearance is subject to the physical or chemical limitations of the measurement technique. The advantage of artificial descriptors is that they can be adjusted and fine-tuned easily to fit to a task due to their pure mathematical nature. The only limitation to this approach is the scientist s imagination. However, there are several constraints to be taken into account when selecting or constructing a molecular descriptor. Todeschini and Consonni pointed these out in their book Handbook of Molecular Descriptors [15]. Let us have a closer look at these constraints. 

Correlation with Other Molecular Descriptors — This applies mainly to artificial descriptors. A correlation with experimental descriptors is helpful to produce missing experimental data. 

Before we have a quick look at three of the most important transform methods, we should keep the following in mind. The mathematical theory of transformations is usually related to continuous phenomena for instance, Fourier transform is more exactly described as continuous Fourier transform (CFT). Experimental descriptors, such as signals resulting from instrumental analysis, as well as calculated artificial descriptors require an analysis on basis of discrete intervals. Transformations applied to such descriptors are usually indicated by the term discrete, such as the discrete Fourier transform (DFT). Similarly, efficient algorithms for computing those discrete transforms are typically indicated by the term fast, such as fast Fourier transform (FFT). We will focus in the following on the practical application — that is, on discrete transforms and fast transform algorithms. 

Artificial Descriptor is a molecular descriptor that is calculated from molecular properties. Due to its pure mathematical nature, it can be adjusted and fine-tuned to ht to a task. 

A challenging task in material science as well as in pharmaceutical research is to custom tailor a compound s properties. George S. Hammond stated that the most fundamental and lasting objective of synthesis is not production of new compounds, but production of properties (Norris Award Lecture, 1968). The molecular structure of an organic or inorganic compound determines its properties. Nevertheless, methods for the direct prediction of a compound s properties based on its molecular structure are usually not available (Figure 8-1). Therefore, the establishment of Quantitative Structure-Property Relationships (QSPRs) and Quantitative Structure-Activity Relationships (QSARs) uses an indirect approach in order to tackle this problem. In the first step, numerical descriptors encoding information about the molecular structure are calculated for a set of compounds. Secondly, statistical and artificial neural network models are used to predict the property or activity of interest based on these descriptors or a suitable subset. 

A structure descriptor is a mathematical representation of a molecule resulting from a procedure transforming the structural information encoded within a symbolic representation of a molecule. This mathematical representation has to be invariant to the molecule s size and number of atoms, to allow model building with statistical methods and artificial neural networks. 

Chirality codes are used to represent molecular chirality by a fixed number of de-.scriptors. Thc.se descriptors can then be correlated with molecular properties by way of statistical methods or artificial neural networks, for example. The importance of using descriptors that take different values for opposite enantiomers resides in the fact that observable properties are often different for opposite enantiomers. 

Aqueous solubility is selected to demonstrate the E-state application in QSPR studies. Huuskonen et al. modeled the aqueous solubihty of 734 diverse organic compounds with multiple linear regression (MLR) and artificial neural network (ANN) approaches [27]. The set of structural descriptors comprised 31 E-state atomic indices, and three indicator variables for pyridine, ahphatic hydrocarbons and aromatic hydrocarbons, respectively. The dataset of734 chemicals was divided into a training set ( =675), a vahdation set (n=38) and a test set (n=21). A comparison of the MLR results (training, r =0.94, s=0.58 vahdation r =0.84, s=0.67 test, r =0.80, s=0.87) and the ANN results (training, r =0.96, s=0.51 vahdation r =0.85, s=0.62 tesL r =0.84, s=0.75) indicates a smah improvement for the neural network model with five hidden neurons. These QSPR models may be used for a fast and rehable computahon of the aqueous solubihty for diverse orgarhc compounds. 

In the last decades not only thousands of chemical descriptors but also many advanced, powerful modeling algorithms have been made available, The older QSAR models were linear equations with one or a few parameters. Then, other tools have been introduced, such as artificial neural network, fuzzy logic, and data mining algorithms, making possible non linear models and automatic generation of mathematical solutions. 

A classical Hansch approach and an artificial neural networks approach were applied to a training set of 32 substituted phenylpiperazines characterized by their affinity for the 5-HTiA-R and the generic arAR [91]. The study was aimed at evaluating the structural requirements for the 5-HTiA/ai selectivity. Each chemical structure was described by six physicochemical parameters and three indicator variables. As electronic descriptors, the field and resonance constants of Swain and Lupton were used. Furthermore, the vdW volumes were employed as steric parameters. The hydrophobic effects exerted by the ortho- and meta-substituents were measured by using the Hansch 7t-ortho and n-meta constants [91]. The resulting models provided a significant correlation of electronic, steric and hydro-phobic parameters with the biological affinities. Moreover, it was inferred that the... 

This agrees to internal VolSurf models derived for PAMPA membrane transport [163] to understand passive transcellular transport across membranes. One of our internal models based on 29 compounds characterized by immobilized artificial membrane chromatography by Salminen etal. ]164] shows an of 0.81 and = 0.70 for two PLS components derived using VolSurf descriptors. This is one of the rare examples where ionized starting molecules led to slightly better PLS statistics, while the general chemical interpretation is not affected. 

Xu J, Chen B, Liang H (2008) Accurate prediction of theta (lower critical solution temperature) in polymer solutions based in 3D descriptors and artificial neural networks. Macromol Theory Simul 17 109-120... 

Recently, Jung et al. [42] developed two artificial neural network models to discriminate intestinal barrier-permeable heptapeptides identified by the peroral phage display experiments from randomly generated heptapeptides. There are two kinds of descriptors one is binary code of amino acid types (each position used 20 bits) and the other, which is called VHSE, is a property descriptor that characterizes the hydrophobic, steric, and electronic properties of 20 coded amino acids. Both types of descriptors produced statistically significant models and the predictive accuracy was about 70%. 

Key Words 2D-QSAR traditional QSAR 3D-QSAR nD-QSAR 4D-QSAR receptor-independent QSAR receptor-dependent QSAR high throughput screening alignment conformation chemometrics principal components analysis partial least squares artificial neural networks support vector machines Binary-QSAR selecting QSAR descriptors. 

Fig. 7. Artificial neural network model. Bioactivities and descriptor values are the input and a final model is the output. Numerical values enter through the input layer, pass through the neurons, and are transformed into output values the connections (arrows) are the numerical weights. As the model is trained on the Training Set, the system-dependent variables of the neurons and the weights are determined.

---