In QSAR, a statistical model is generated from a training set of molecules (represented by chemical descriptors) and their biological activities. We will call this traditional type of QSAR model an "activity model". The activity model can be used to predict the activities of molecules not in the training set. A relatively new subfield for QSAR is domain applicability. The aim is to estimate the reliability of prediction of a specific molecule on a specific activity model. A number of different metrics have been proposed in the literature for this purpose. It is desirable to build a quantitative model of reliability against one or more of these metrics. We can call this an "error model". A previous publication from our laboratory (Sheridan J. Chem. Inf. Model., 2012, 52, 814-823.) suggested the simultaneous use of three metrics would be more discriminating than any one metric. An error model could be built in the form of a three-dimensional set of bins. When the number of metrics exceeds three, however, the bin paradigm is not practical. An obvious solution for constructing an error model using multiple metrics is to use a QSAR method, in our case random forest. In this paper we demonstrate the usefulness of this paradigm, specifically for determining whether a useful error model can be built and which metrics are most useful for a given problem. For the ten data sets and for the seven metrics we examine here, it appears that it is possible to construct a useful error model using only two metrics (TREE_SD and PREDICTED). These do not require calculating similarities/distances between the molecules being predicted and the molecules used to build the activity model, which can be rate-limiting.

qsar statist model generat train set molecul repres chemic descriptor biolog activ will call tradit type qsar model activ model activ model can use predict activ molecul train set relat new subfield qsar domain applic aim estim reliabl predict specif molecul specif activ model number differ metric propos literatur purpos desir build quantit model reliabl one metric can call error model previous public laboratori sheridan j chem inf model suggest simultan use three metric discrimin one metric error model built form threedimension set bin number metric exceed three howev bin paradigm practic obvious solut construct error model use multipl metric use qsar method case random forest paper demonstr use paradigm specif determin whether use error model can built metric use given problem ten data set seven metric examin appear possibl construct use error model use two metric treesd predict requir calcul similaritiesdist molecul predict molecul use build activ model can ratelimit