Steroids dataset

Himer, D.B., Willett, R, Ferguson, A.M. and Heritage, T.W. (1999). Evaluation of a Novel Molecular Vibration-Based Descriptor (EVA) for QSAR Studies 2. Model Validation Using a Benchmark Steroid Dataset. JComput.Aid.Molec.Des., 13,271-296. 

Let us start with a classic example. We had a dataset of 31 steroids. The spatial autocorrelation vector (more about autocorrelation vectors can be found in Chapter 8) stood as the set of molecular descriptors. The task was to model the Corticosteroid Ringing Globulin (CBG) affinity of the steroids. A feed-forward multilayer neural network trained with the back-propagation learning rule was employed as the learning method. The dataset itself was available in electronic form. More details can be found in Ref. [2]. 

Coats, E.A. The CoM FA steroids as a benchmark dataset for development of 3D-QSAR methods. In 3D QSAR in Drug Design, Vol. 3, Recent Advances, Kubinyi, H., Folkers, G., and Martin, Y.C. (Eds). Kluwer/ESCOM, Dordrecht, Netherlands, 1998, 199-213. 

The use of the Pathfinder descriptor for QSAR is exemplified here through application to two datasets taken from the literature (i) 31 steroids utilized in the original CoMFA study [3], since considered a benchmark for evaluating QSAR methods [4] (ii) 55 inhibitors of HIV-1 reverse transcriptase proposed by Chan and coworkers [5], interestingly this series could only be successfully correlated by means of a structure-based approach [6]. 

Tuppurainen, K., Viisas, M.. Perakyla, M. and Laatikainen, R. (2004) Ligand intramolecular motions in ligand-protein interaction ALPHA, a novel dynamic descriptor and a QSAR study widi extended steroid benchmark dataset. /. Comput. Aid. Mol. Des., 18, 175-187. 

It is appropriate to illustrate these concepts with a worked out example of a typical application of molecular quantum similarity ideas. The example addressed here involves the set of globulin bindings steroids used by Cramer et al. ° and subsequently in other studies to develop QSAR models. " This dataset has also been used by chemists in molecular quantum similarity studies and to develop quantum QSAR models. ° ° ... 

The confinement of the steroid and peptide datasets to ca. 40% of the bins demonstrates that particular structural types can be related to specific regions of the map. Thus, although the distributions are diffuse, it is possible to speak of the steroid region or the peptide region of the database. The steroid compounds provide another opportunity to compare the performance of the contemporary procedure against established knowledge in 1993, Kalman described a small set of steroid structures that display isostructural... 

---