The Pharmacophore Network: A Computational Method for Exploring Structure–Activity Relationships from a Large Chemical Data Set

In this article, Quantitative Structure Activity Relationships (QSAR) were generated to link the structure of over 120 heterogeneous drugs to rat hepatotoxicity. Existing studies, performed on the same data set, could not highlight relevant structure-activity relationships, and suggested models for the prediction of hepatotoxicity based on genomic data. Binary activity responses were used for the development of classification QSARs using theoretical molecular descriptors calculated with the software PaDEL-Descriptor. A statistically powerful QSAR based on six descriptors was generated by using k-Nearest Neighbour (k-NN) method and by applying the Genetic Algorithm (GA) as variable selection procedure. The new k-NN QSAR outperforms published models by providing better accuracy and less false negatives. This model is a valid alternative to approaches based on genomic descriptors, which cannot be used in virtual screening of new compounds (pre- or post-synthesis) without experimental data.

Download Full-text

Automated Structure–Activity Relationship Mining

CrossRef Listing of Deleted DOIs ◽

10.1177/1087057114530783 ◽

2014 ◽

Vol 19 (5) ◽

pp. 738-748 ◽

Cited By ~ 12

Author(s):

Mathias J. Wawer ◽

David E. Jaramillo ◽

Vlado Dančík ◽

Daniel M. Fass ◽

Stephen J. Haggarty ◽

...

Keyword(s):

Small Molecules ◽

Histone Deacetylase Inhibitors ◽

Biological Response ◽

Binding Constants ◽

Structural Features ◽

Computational Method ◽

High Dimensional ◽

Data Set ◽

Structure Activity ◽

Small Molecule Profiling

Understanding the structure–activity relationships (SARs) of small molecules is important for developing probes and novel therapeutic agents in chemical biology and drug discovery. Increasingly, multiplexed small-molecule profiling assays allow simultaneous measurement of many biological response parameters for the same compound (e.g., expression levels for many genes or binding constants against many proteins). Although such methods promise to capture SARs with high granularity, few computational methods are available to support SAR analyses of high-dimensional compound activity profiles. Many of these methods are not generally applicable or reduce the activity space to scalar summary statistics before establishing SARs. In this article, we present a versatile computational method that automatically extracts interpretable SAR rules from high-dimensional profiling data. The rules connect chemical structural features of compounds to patterns in their biological activity profiles. We applied our method to data from novel cell-based gene-expression and imaging assays collected on more than 30,000 small molecules. Based on the rules identified for this data set, we prioritized groups of compounds for further study, including a novel set of putative histone deacetylase inhibitors.

Download Full-text

The Role of Structure-activity Relationships and Expert Systems in Alternative Strategies for the Determination of Skin Sensitisation, Skin Corrosivity and Eye Irritation

Alternatives to Laboratory Animals ◽

10.1177/026119299502300114 ◽

1995 ◽

Vol 23 (1) ◽

pp. 111-122 ◽

Cited By ~ 2

Author(s):

Martin D. Barratt

Keyword(s):

Principal Components ◽

Early Stage ◽

Skin Irritation ◽

Data Sets ◽

Data Set ◽

Eye Irritation ◽

Structure Activity Relationships ◽

Structure Activity ◽

Skin Sensitisation ◽

Key Factor

A historical database containing the results of 294 defined single substances tested in the guinea-pig maximisation test, carried out according to a single protocol, was used to derive a set of structural alerts for skin sensitisation, which have been incorporated into the expert system, DEREK. Together with an assessment of percutaneous absorption, this system forms an integral part of a strategic approach to the identification of contact allergens. Quantitative structure-activity relationships (QSARs) were derived for the skin corrosivity of organic acids and bases, and for the eye irritation potential of neutral organic chemicals. The independent variables used for these analyses were selected on the basis of the putative mechanisms for skin irritation or corrosivity and for eye irritation, respectively. Data sets were analysed using principal components analysis; plots of the first two principal components for each data set showed that the analyses were able to discriminate well between chemicals with different classifications of toxicological activity. The derived QSARs are expected to give useful predictions of skin corrosivity and eye irritancy for new or untested chemicals in these classes. Although the development of these techniques is still at a very early stage, they are already able to play an important part in proposed strategies for the reduction of experimental animal usage. In the long term, it should be possible to conduct safety evaluations using fewer experimental animals or no animals at all. However, acceptance by regulatory authorities will be a key factor in realising the full benefits of the approach.

Download Full-text