Jacques R. Chrétien's research while affiliated with Université d'Orléans and other places

Modelling of the binding step in dopamine receptor–antagonist interactions was undertaken using sixteen antagonists belonging to the following five chemical series: phenothiazines, thioxanthenes, butyrophenones, benzamides, and benzisoxazoles. The Lower Unoccupied Molecular Orbitals (LUMOs) of the antagonists used for these interactions were compared using a similarity τij index, which enabled us to define the characteristic orbital forms of the active molecules. The result of the intersection of these representative orbital forms was the form common to the antagonists' LUMOs. This form corresponds to the orbital form of the indole's Higher Occupied Molecular Orbital (HOMO), and thus suggests that the aromatic binding site of the dopamine receptor is part of a tryptophan type structure.

Background The new European Regulation on chemical safety, REACH, (Registration, Evaluation, Authorisation and Restriction of CHemical substances), is in the process of being implemented. Many chemicals used in industry require additional testing to comply with the REACH regulations. At the same time EU member states are attempting to reduce the number of animals used in experiments under the 3 Rs policy, (refining, reducing, and replacing the use of animals in laboratory procedures). Computational techniques such as QSAR have the potential to offer an alternative for generating REACH data. The FP6 project CAESAR was aimed at developing QSAR models for 5 key toxicological endpoints of which skin sensitisation was one. Results This paper reports the development of two global QSAR models using two different computational approaches, which contribute to the hybrid model freely available online. Conclusions The QSAR models for assessing skin sensitisation have been developed and tested under stringent quality criteria to fulfil the principles laid down by the OECD. The final models, accessible from CAESAR website, offer a robust and reliable method of assessing skin sensitisation for regulatory use.

Classification models were established on a set of sensory profiles associated with red wine samples bottled from three vintages. These profiles were defined by eight assessors charged, for all wine samples, to assign to each of 17 sensory descriptors a note ranged from 1.0 to 9.0, with two assessments for each judge. A new and innovative method called adaptive fuzzy partition (AFP), derived from fuzzy logic (FL) concepts, was tested on the same data set. FL is particularly suitable to classify sensory analysis data sets, as it can represent the “fuzziness” linked to an expert's subjectivity in the characterization of wine sensory profiles. More precisely, after subdividing the 48 sensory profiles into training and test sets, the AFP method predicted correctly 75% of the test assessments. These very encouraging preliminary results show the proposed methods are worth investigating more thoroughly, testing large and diverse wine data sets. A new and innovative method called adaptive fuzzy partition, derived from fuzzy logic (FL) concepts, is presented. FL is particularly suitable to classify sensory analysis data sets, as it can represent the “fuzziness” linked to an expert's subjectivity in the characterization of wine sensory profiles.

In this paper, a hybrid genetic approach is proposed to solve the problem of designing a subdatabase of the original one with the highest classification performances, the lowest number of features and the highest number of patterns. The method can simultaneously treat the double problem of editing instance patterns and selecting features as a single optimization problem, and therefore aims at providing a better level of information. The search is optimized by dividing the algorithm into self-controlled phases managed by a combination of pure genetic process and dedicated local approaches. Different heuristics such as an adapted chromosome structure and evolutionary memory are introduced to promote diversity and elitism in the genetic population. They particularly facilitate the resolution of real applications in the chemometric field presenting databases with large feature sizes and medium cardinalities. The study focuses on the double objective of enhancing the reliability of results while reducing the time consumed by combining genetic exploration and a local approach in such a way that excessive computational CPU costs are avoided. The usefulness of the method is demonstrated with artificial and real data and its performance is compared to other approaches.

Quantitative structure–activity relationship (QSAR) problems do not have, in general, linear solutions, and the problem is how to model those situations. Another consideration is that the nonlinear model should not be assumed but should emerge from data analysis. This chapter integrates the best models individually developed for each endpoint into a hybrid system for that endpoint. This has to be flexible to accept further inputs or modules, if available. Whereas inputs to the basic models are the chemical descriptors, input to the hybrid model are the n values predicted for each molecule by the n integrated models; the output is always the toxicity for that molecule. The basic theory behind the combinations, as well as the models obtained is illustrated.

The concept of mathematically relating biological activity with physicochemical properties of related chemical compounds emerged in the 1960s. Early quantitative structure–activity relationships (QSARs) were based on simple principles, such as substituent parameters, and linear mathematics. It was gradually realized that QSAR models based on such simplistic properties and statistical algorithms only worked well in certain well-defined situations. QSAR models for relatively simple sets of molecular data are still based on linear algorithms, but this approach has only a limited usefulness in finding multidimensional relational patterns in complex data sets. Linear models are also often hard to generalize across chemical classes and/or test species. This has led to the use of nonlinear algorithms and soft computing techniques, such as fuzzy systems, probabilistic methods, and artificial neural networks to decipher relational patterns in large, imprecise, and complex data sets. This shift in QSAR paradigm has made it possible to predict biological properties of a wide range of chemicals, which otherwise would be difficult, or impossible to determine experimentally.

The overall process in the context of DEMETRA models involves a careful selection of the data, a check of the chemical structures, and the calculation of thousands of descriptors and fragments, and on that basis a development of hundreds of models. Current computer techniques allow the exploration of a huge space of possibilities in a short time, facilitating the task. This chapter explores a full battery of models. Many of the models are not valid, and the performances are poor. However, a certain number of models give interesting results. Good results are obtained with the use of different models and different chemical descriptors. The heterogeneity of the methodologies increases the robustness of the results, once comparable results are obtained. Indeed, one model can support the other, especially when the starting point and methodology are different.

Although many international regulatory bodies recognize the potential benefits of quantitative structure-activity relationship (QSAR) techniques, they are scarcely used in real applications. Some general principles are listed, but the lack of guidelines and standardized protocols accepted and used by all research groups prevents an effective world-wide development of such strategies. The use of appropriate statistical validation tools, such as the training and test set or others, should be adopted for predictive models not only in the case of QSAR based on descriptors but also in the case of models based on rules. In other words, the rules that are defined as appropriate for predictive purposes should also be validated. The statistical tools should prove the capability of the model to be valid in a general way-to be predictive for compounds not used in development of the model.

Despite the reputation of RBFNs (Radial Basis Function Neural Networks), RBFN design is not straightforward since the efficiency of the model depends on many parameters. RBFNs often require many manual parameter adjustments, which is a serious weakness especially when they have to be used automatically. In this paper, a method to design RBFNs for classification problems is proposed, with a view to obtaining classification models rapidly by minimizing manual parameters, with performances very close to the best attainable from numerous trials. The RBFN can be initiated automatically via the use of advanced clustering algorithms adapted to supervised contexts to find preliminary cells. The final architecture is obtained via a growing process controlled by different mechanisms in order to find small and reliable RBF classifiers. A candidate pattern is selected for creating a new unit only if it produces a significant quadratic error while presenting a significant classification potential from its neighborhood properties. The efficiency of the method is demonstrated on artificial and real data sets from the field of chemometrics.

Establishing QSAR in large databases which contain structural and biological information has qualitative differences compared to QSAR studies on compact series of chemical homologues. Indeed, classical QSAR tools often work not so well with databases which count thousands of compounds. The Self-Organising Maps (SOM) suggest a new solution to the problem. A key difference between SOM, also known as Kohonen's neural network, and many other neural networks is that SOM learns without supervision. SOM is a projection technique which reduces the descriptor multidimensional space into a space of any given dimensionality. To adopt the method for QSAR purposes quality estimates for the SOM model evaluation have been developed by the authors. A case study involving SOM is also presented. The processed database contains more titan 2000 organo-phosphorous compounds with various pesticide activities from the STRAC database.