Neural networks applied to structure-activity relationships

Pattern recognition approach to classifying CYP 2C19 isoform

“…Support Vector Machine with a linear kernel(SVMl) and with a Gaussian Radial Basis kernel (SVMg) approaches were compared to the analysis of the same data set with neural networks (NN) [13] and linear Gaussian Process (GP). Classifiers were trained by the usage of ten fold cross-validation.…”

“…Since then there is an active group dedicated to this area [12]. One of the first work, which introduced the interdisciplinary application of machine learning techniques to the structure-activity modelling was [13]. Few years later a first summary paper, describing state-of-the-art in this field was printed [14].…”

Overview of Quantitative Structure–Activity Relationships (QSAR)

“…In the last decade, neural networks have emerged as the most useful way to overcome many of these shortcomings (see for example, Salt et al 1992;Tetko et al 1993;Burns and Whitesides 1993;Gasteiger and Zupan 1993;Aoyama et al 1990;Maggiora et al 1992). Neural networks (NNs) are computer-based mathematical models developed to have analogous functions to idealized simple biological nervous systems (illustrated in Figure 16.5).…”

<strong>DPPH&bull; Free Radical Scavenging Activity of Coumarin Derivatives.<em> In Silico </em>and<em> in Vitro </em>Approach</strong>

“…The QSAR studies assess mathematical associations between structural features of the molecules and biological properties. For the last two decades, Artificial Neural Networks (ANN) have increasingly found applicability in QSAR studies, thanks to their ability to map non-linear relations between structural characteristics of chemical compounds and their chemical / biological behavior [9]. The objective of this study was to develop an ANN model in order to relate the chemical compounds' scavenging ability of the DPPH• radical with the corresponding structural features, also known as molecular descriptors (MDs).…”