Autocorrelation of Molecular Surface Properties for Modeling Corticosteroid Binding Globulin and Cytosolic Ah Receptor Activity by Neural Networks

Wagener, Markus; Sadowski, Jens; Gasteiger, Johann

doi:10.1021/ja00134a023

Cited by 304 publications

(282 citation statements)

References 2 publications

Supporting

Mentioning

275

Contrasting

Unclassified

Order By: Relevance

“…The entire procedure (fitting each compound 75 times to the template to find the best alignment, calculating the mean of the resultant FBSS similarities, carrying out the CoMFA analysis of the dataset using the set of FBSS-derived alignments, and noting the predictivity of the final FBSS similarity is appropriate for use in a 3D QSAR analysis; indeed, if a correlation is not observed then the dataset is not suitable for alignment using the whole-molecule procedure suggested here. The point marked by a circle in Figure 2 represents the similarity and q² values obtained for the manual alignments provided by Wagener et al [23], and it will be seen that this point fits well with the correlation obtained from the FBSS alignments.…”

Section: Datasetssupporting

confidence: 72%

See 1 more Smart Citation

Automatic generation of alignments for 3D QSAR analyses

Jewell

Turner

Willett

et al. 2001

Journal of Molecular Graphics and Modelling

View full text Add to dashboard Cite

Many 3D QSAR methods require the alignment of the molecules in a dataset, which can require a fair amount of manual effort in deciding upon a rational basis for the superposition. This paper describes the use of FBSS, a program for field-based similarity searching in chemical databases, for generating such alignments automatically. CoMFA and CoMSIA experiments with several literature datasets show that the QSAR models resulting from the FBSS alignments are broadly comparable in predictive performance with the models resulting from manual alignments.

show abstract

Section: Datasetssupporting

confidence: 72%

“…Specifically, we employed the 31 structures (a 21-compound training set and a 10-compound test set) reviewed by Wagener et al [23], with the exception of molecule-31…”

Section: Datasetsmentioning

confidence: 99%

Automatic generation of alignments for 3D QSAR analyses

Jewell

Turner

Willett

et al. 2001

Journal of Molecular Graphics and Modelling

View full text Add to dashboard Cite

show abstract

“…Another viable and convenient way for the derivation of descriptors for 3D-QSAR models was identified by Gasteiger and coworkers in the calculation of autocorrelation vectors of molecular electrostatic potentials (MEPs) mapped over the molecular surfaces of the ligands [45,46]. It is well accepted that MEPs considerably affect and govern molecular recognition.…”

Section: Ligand-based 3d-qsarmentioning

confidence: 99%

Ligand and structure-based methodologies for the prediction of the activity of G protein-coupled receptor ligands

Costanzi

Tikhonova

Harden

2008

J Comput Aided Mol Des

View full text Add to dashboard Cite

SummaryAccurate in silico models for the quantitative prediction of the activity of G protein-coupled receptor (GPCR) ligands would greatly facilitate the process of drug discovery and development. Several methodologies have been developed based on the properties of the ligands, the direct study of the receptor-ligand interactions, or a combination of both approaches. Ligand-based three-dimensional quantitative structure-activity relationships (3D-QSAR) techniques, not requiring knowledge of the receptor structure, have been historically the first to be applied to the prediction of the activity of GPCR ligands. They are generally endowed with robustness and good ranking ability; however they are highly dependent on training sets. Structure-based techniques generally do not provide the level of accuracy necessary to yield meaningful rankings when applied to GPCR homology models. However, they are essentially independent from training sets and have a sufficient level of accuracy to allow an effective discrimination between binders and nonbinders, thus qualifying as viable lead discovery tools. The combination of ligand and structure-based methodologies in the form of receptor-based 3D-QSAR and ligand and structure-based consensus models results in robust and accurate quantitative predictions. The contribution of the structure-based component to these combined approaches is expected to become more substantial and effective in the future, as more sophisticated scoring functions are developed and more detailed structural information on GPCRs is gathered.

show abstract

“…The performance of EVA_GA was evaluated using datasets for which external test sets were available and consist of a benchmark steroid dataset [4,18,19] and a set of melatonin receptor ligands [20]. The use of test sets must be considered essential for validating an EVA_GA QSAR model since the large number of adjustable parameters (NBINS) means a priori that there is great potential for training set overfit.…”

Section: Datasetsmentioning

confidence: 99%

“…The steroid CoMFA analysis has been described in some detail previously [3]; the structures and conformations are those of Wagener et al [19] and were aligned using an RMS fit of the 3, 5, 6, 13, 14 and 17 skeletal carbon atoms ( Figure 6) with deoxycortisol (H11) as a template. For the melatonin ligands the superposed conformations were obtained directly from the original authors [20].…”

Section: Comfa Analysesmentioning

confidence: 99%

Untitled

Turner

Willett

2000

Journal of Computer-Aided Molecular Design

View full text Add to dashboard Cite

SummaryThe EVA structural descriptor, based upon calculated fundamental molecular vibrational frequencies, has proved to be an effective descriptor for both QSAR and database similarity calculations. The descriptor is sensitive to 3D structure but has an advantage over fieldbased 3D-QSAR methods inasmuch as structural superposition is not required. The original technique involves a standardisation method wherein uniform Gaussians of fixed standard deviation (σ) are used to smear out frequencies projected onto a linear scale. This smearing function permits the overlap of proximal frequencies and thence the extraction of a fixed dimensional descriptor regardless of the number and precise values of the frequencies. It is proposed here that there exist optimal localised values of σ in different spectral regions; that is, the overlap of frequencies using uniform Gaussians may, at certain points in the spectrum, either be insufficient to pick up relationships where they exist or mix up information to such an extent that significant correlations are obscured by noise. A genetic algorithm is used to search for optimal localised σ values using crossvalidated PLS regression scores as the fitness score to be optimised. The resultant models are then validated against a previously unseen test set of compounds. The performance of EVA_GA is compared to that of EVA and analogous CoMFA studies.

show abstract

Autocorrelation of Molecular Surface Properties for Modeling Corticosteroid Binding Globulin and Cytosolic Ah Receptor Activity by Neural Networks

Cited by 304 publications

References 2 publications

Automatic generation of alignments for 3D QSAR analyses

Automatic generation of alignments for 3D QSAR analyses

Ligand and structure-based methodologies for the prediction of the activity of G protein-coupled receptor ligands

Untitled

Contact Info

Product

Resources

About