Chemoinformatic Classification Methods and their Applicability Domain

Abstract

Classification rules are often used in chemoinformatics to predict categorical properties of drug candidates related to bioactivity from explanatory variables, which encode the respective molecular structures (i.e. molecular descriptors). To avoid predictions with an unduly large error probability, the domain the classifier is applied to should be restricted to the domain covered by the training set objects. This latter domain is commonly referred to as applicability domain in chemoinformatics. Conceptually, the applicability domain defines the region in space where the “normal” objects are located. Defining the border of the applicability domain may then be viewed as detecting anomalous or novel objects or as detecting outliers. Currently two different types of measures are in use. The first one defines the applicability domain solely in terms of the molecular descriptor space, which is referred to as novelty detection. The second type defines the applicability domain in terms of the expected reliability of the predictions which is referred to as confidence estimation. Both types are systematically differentiated here and the most popular measures are reviewed. It will be shown that all common chemoinformatic classifiers have built‐in confidence scores. Since confidence estimation uses information of the class labels for computing the confidence scores, it is expected to be more efficient in reducing the error rate than novelty detection, which solely uses the information of the explanatory variables.

Predictive Models for Kinetic Parameters of Cycloaddition Reactions

“…Applicability Domain of the models . The “Fragment Control” procedure was chosen to delimit the general Applicability Domain (AD) of the approach, which corresponds to the bounding box encompassing the training set in fragment descriptor space. For each of the fragment associated to descriptor vector elements, a candidate molecule must not contain more of these than the richest representative of the training set, or less than the poorest one.…”

Visualization and Analysis of Complex Reaction Data: The Case of Tautomeric Equilibria

“…Generally, the AD defines an area of a chemical space where the model is presumably accurate . For external predictions, the applicability of each individual model for the current molecule was confined to a “bounding box” based on fragment counts.…”

Quimioinformática: Uma Introdução

“…113,114 O DA representa o espaço químico definido pelo conjunto de moléculas do conjunto de treinamento de determinado modelo de QSAR. Predições são consideradas confiáveis quando a molécula predita se insere dentro do DA do modelo em questão.…”