Modelling of the biological activity for a set of ceramic fibre materials: a QSAR study

1H-NMR metabolic profiling of cerebrospinal fluid in patients with complex regional pain syndrome-related dystonia

In complex regional pain syndrome (CRPS)-related dystonia, compelling evidence points to the involvement of the central nervous system, but the underpinning pathobiology is still unclear. Thus, to enable a hypothesis-free, unbiased view of the problem and to obtain new insight into the pathobiology of dystonia in CRPS, we applied an exploratory metabolomics analysis of cerebrospinal fluid (CSF) of patients with CRPS-related dystonia. (1)H-NMR spectroscopy in combination with multivariate modeling were used to investigate metabolic profiles of a total of 105 CSF samples collected from patients with CRPS-related dystonia and controls. We found a significantly different metabolic profile of CSF in CRPS patients compared to controls. The differences were already reflected in the first two principal components of the principal component analysis model, which is an indication that the variance associated with CRPS is stronger than variance caused by such classical confounders as gender, age, or individual differences. A supervised analysis generated a strong model pinpointing the most important metabolites contributed to the metabolic signature of patients with CRPS-related dystonia. From the set of identified discriminators, the most relevant metabolites were 2-keto-isovalerate, glucose, glutamine, and lactate, which all showed increased concentrations, and urea, which showed decreased concentration in CRPS subjects. Our findings point at a catabolic state in chronic CRPS patients with dystonia that is likely associated with inflammation.

Comparison of representational spaces based on structural information in the development of QSAR models for benzylamino enaminone derivatives

In this paper we study different representational spaces of molecule data sets based on 2D representation models for the building of QSAR models for the prediction of the activity of 37 benzylamino enaminone derivatives. Approximations based on classical similarity calculated from fingerprint representation of molecules and isomorphism obtained using sub-graph matching algorithms are compared to fragmentation-based approximations using partial least squares and genetic algorithms. The influence of the anchored position of a non-common moiety and the kind of substituents in the common core structure of the data set are analysed, demonstrating the anomalous behaviour of some molecules and therefore the difficulty in building prediction models. These problems are solved by considering approximate similarity models. These models tune the prediction equations based on the size of the substituent and the anchored position, by adjusting the contribution of each substituent in similarity measurements calculated between the molecule data sets.

A new strategy for using supervised artificial neural networks in QSAR

A new type of environmental QSAR model is presented for the common situation in which the biological activity of molecules mainly depends on their 1-octanol/water partition coefficient (log P). In a first step, a classical regression equation with log P is derived. The residuals obtained with this simple linear equation are then modeled from a supervised artificial neural network including different molecular descriptors as input neurons. Finally, results produced by the linear and nonlinear models are both considered for calculating the activity values, which are compared with the initial actual activity values. A heterogeneous database of 569 organic compounds with 96-h LC50s measured to the fathead minnow (Pimephales promelas), randomly divided into a training set of 484 chemicals and a testing set of 85 chemicals, was used as illustrative example to show the potentialities of this new modeling strategy Finally, practical suggestions are given for designing this type of hybrid QSAR model.