Martyn G. Ford

Unsupervised forward selection: a method for eliminating redundant variables

An unsupervised learning method is proposed for variable selection and its performance assessed using three typical QSAR data sets. The aims of this procedure are to generate a subset of descriptors from any given data set in which the resultant variables are relevant, redundancy is eliminated, and multicollinearity is reduced. Continuum regression, an algorithm encompassing ordinary least squares regression, regression on principal components, and partial least squares regression, was used to construct models from the selected variables. The variable selection routine is shown to produce simple, robust, and easily interpreted models for the chosen data sets.

Use of Automatic Relevance Determination in QSAR Studies Using Bayesian Neural Networks

We describe the use of Bayesian regularized artificial neural networks (BRANNs) coupled with automatic relevance determination (ARD) in the development of quantitative structure-activity relationship (QSAR) models. These BRANN-ARD networks have the potential to solve a number of problems which arise in QSAR modeling such as the following: choice of model; robustness of model; choice of validation set; size of validation effort; and optimization of network architecture. The ARD method ensures that irrelevant or highly correlated indices used in the modeling are neglected as well as showing which are the most important variables in modeling the activity data. The application of the methods to QSAR of compounds active at the benzodiazepine and muscarinic receptors as well as some toxicological data of the effect of substituted benzenes on Tetetrahymena pyriformis is illustrated.

Simultaneous prediction of aqueous solubility and octanol/water partition coefficient based on descriptors derived from molecular structure

It has been shown that water solubility and octanol/water partition coefficient for a large diverse set of compounds can be predicted simultaneously using molecular descriptors derived solely from a two dimensional representation of molecular structure. These properties have been modelled using multiple linear regression, artificial neural networks and a statistical method known as canonical correlation analysis. The neural networks give slightly better models both in terms of fitting and prediction presumably due to the fact that they include non-linear terms. The statistical methods, on the other hand, provide information concerning the explanation of variance and allow easy interrogation of the models. Models were fitted using a training set of 552 compounds, a validation set and test set each containing 68 molecules and two separate literature test sets for solubility and partition.

Biological data mining with neural networks: implementation and application of a flexible decision tree extraction algorithm to genomic problem domains

In the past, neural networks have been viewed as classification and regression systems whose internal representations were extremely difficult to interpret. It is now becoming apparent that algorithms can be designed which extract understandable representations from trained neural networks, enabling them to be used for data mining, i.e. the discovery and explanation of previously unknown relationships present in data. This paper reviews existing algorithms for extracting comprehensible representations from neural networks and describes research to generalize and extend the capabilities of one of these algorithms. The algorithm has been generalized for application to bioinformatics datasets, including the prediction of splice site junctions in Human DNA sequences. Results generated on this datasets are compared with those generated by a conventional data mining technique (C5) and conclusions drawn.

Separation and analysis of the diastereomers and enantiomers of cypermethrin and related compounds

Abstract The diastereomers of cypermethrin and permethrin have been resolved on an irregular silica column. Complete separation of three of the four enantiomeric pairs of cypermethrin was achieved with reasonable retention times (

An investigation of the ionophoric characteristics of destruxin A

Destruxin A, a cyclohexadepsipeptide related to the enniatins and beauvericin, exhibits ionophoric properties. Calcium ion mobilization across liposomal membrane barriers, for example, has been demonstrated using the calcium ion-sensitive dyes Arsenazo III and Fura-2. Initial molecular mechanics/molecular dynamics calculations indicate the potential for destruxin A to form a coordination complex with calcium in which the divalent cation is bound at the center of a sandwich formed by two molecules of destruxin A. This novel calcium ion binding may help explain the diverse biological effects exhibited by the destruxins.

Structure-activity relationships of pyrethroid insecticides. Part 2. The use of molecular dynamics for conformation searching and average parameter calculation

SummaryMolecular dynamics simulations have been performed on a number of conformationally flexible pyrethroid insecticides. The results indicate that molecular dynamics is a suitable tool for conformational searching of small molecules given suitable simulation parameters. The structures derived from the simulations are compared with the static conformation used in a previous study. Various physicochemical parameters have been calculated for a set of conformations selected from the simulations using multivariate analysis. The averaged values of the parameters over the selected set (and the factors derived from them) are compared with the single conformation values used in the previous study.

Optimising the EVA descriptor for prediction of biological activity

EVA is a multivariate molecular descriptor for use in QSAR studies. It is constructed from vibrational eigenvalues derived from either a quantum theoretical or molecular mechanical treatment of molecular structure. This paper applies the method to biological-activity data using measures of the inotropic potential of a range of Calcium channel agonists. The performance of the descriptor, as both an explanatory and a predictive tool, is analysed in relation to the way in which it is constructed using a rigorous statistical treatment. Its capabilities are examined in relation to those of previously published methodology which used a composite descriptor. It is shown to have improved performance and several procedural advantages, such as ease of calculation and operation. It is a 3-D structural descriptor which does not require prior co-alignment of structures for a QSAR study.

The role of cuticular waxes and surface roughness in determining the insecticidal efficacy of deltamethrin and dimethoate applied as emulsifiable concentrates to leaf surfaces

Abstract Previous work has shown that insecticide residual toxicity to arthropods on foliage varies strongly with leaf type. Although several aspects of leaf morphology could influence insecticide toxicity, the possible role of leaf waxes, which could influence bioavailability, has not previously been investigated. In this study, the influence of leaf wax cover on the residual toxicity of deltamethrin and dimethoate was investigated using the standard test arthropod Folsomia candida Willem (Collembola: Isotomidae) as a surrogate for soft-bodied leaf-dwelling insects. Sixteen leaf types were studied, representing a wide range of crop species. Deltamethrin efficacy increased with increasing leaf surface wax cover. No such relationship was observed, however, for the more polar insecticide dimethoate. Leaf surface roughness was examined using atomic force microscopy and was also observed to influence the efficacy of deltamethrin. The increased efficacy of deltamethrin may be attributed in part to the acquisition of insecticide-contaminated wax particles by F. candida walking over treated leaf surfaces. We provide a regression equation to describe the relationship between wax content, surface roughness and the response of F. candida to deltamethrin-treated leaf surfaces. We discuss the implications of our findings for the risk assessment of pesticides in IPM, in particular concerning the choice of leaf substrates for use in toxicity screening tests with natural enemies.

Variable selection and specification of robust QSAR models from multicollinear data: arylpiperazinyl derivatives with affinity and selectivity for α2-adrenoceptors

Two QSAR models have been identified that predict the affinity and selectivity of arylpiperazinyl derivatives for α1 and α2 adrenoceptors (ARs). The models have been specified and validated using 108 compounds whose structures and inhibition constants (Ki) are available in the literature [Barbaro et al., J. Med. Chem., 44 (2001) 2118; Betti et al., J. Med. Chem., 45 (2002) 3603; Barbaro et al., Bioorg. Med. Chem., 10 (2002) 361; Betti et al., J. Med. Chem., 46 (2003) 3555]. One hundred and forty-seven predictors have been calculated using the Cerius 2 software available from Accelrys. This set of variables exhibited redundancy and severe multicollinearity, which had to be identified and removed as appropriate in order to obtain robust regression models free of inflated errors for the β estimates – so-called bouncing βs. Those predictors that contained information relevant to the α2 response were identified on the basis of their pairwise linear correlations with affinity (−log Ki) for α2 adrenoceptors; the remaining variables were discarded. Subsequent variable selection made use of Factor Analysis (FA) and Unsupervised Variable Selection (UzFS). The data was divided into test and training sets using cluster analysis. These two sets were characterised by similar and consistent distributions of compounds in a high dimensional, but relevant predictor space. Multiple regression was then used to determine a subset of predictors from which to determine QSAR models for affinity to α2-ARs. Two multivariate procedures, Continuum Regression (the Portsmouth formulation) and Canonical Correlation Analysis (CCA), have been used to specify models for affinity and selectivity, respectively. Reasonable predictions were obtained using these in silico screening tools.