Virtual screening of materials using neuro-genetic approach : Concepts and implementation

We describe the concepts and an implementation of a quantitative structure activity relationship methodology for the discovery of solid materials. The paper focuses on virtual screening methodologies. We have investigated the integration of artificial neural network with genetic algorithm in order to accelerate the search of optima. The learning model monitors the optimization process while it is updated in the course of the screening. The optimization is performed on the basis of catalytic data collected in a large high throughput experimentation campaign. The implementation is carried out in a free software (OptiCat).

[1]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[2]  Estefania Argente,et al.  Can artificial neural networks help the experimentation in catalysis , 2003 .

[3]  Estefania Argente,et al.  Optimisation of olefin epoxidation catalysts with the application of high-throughput and genetic algorithms assisted by artificial neural networks (softcomputing techniques) , 2005 .

[4]  D. Goldberg,et al.  Don't evaluate, inherit , 2001 .

[5]  Tadashi Hattori,et al.  Artificial intelligence approach to catalyst design , 1991 .

[6]  Claude Mirodatos,et al.  Design of Discovery Libraries for Solids Based on QSAR Models , 2005 .

[7]  Yaochu Jin,et al.  A comprehensive survey of fitness approximation in evolutionary computation , 2005, Soft Comput..

[8]  Claude Mirodatos,et al.  The development of descriptors for solids: teaching "catalytic intuition" to a computer. , 2004, Angewandte Chemie.

[9]  Thomas R. Cundari,et al.  Design of a Propane Ammoxidation Catalyst Using Artificial Neural Networks and Genetic Algorithms , 2001 .

[10]  D. Broomhead,et al.  Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks , 1988 .

[11]  LiMin Fu,et al.  Neural networks in computer intelligence , 1994 .

[12]  Frédéric Clerc,et al.  Effect of the Genetic Algorithm Parameters on the Optimisation of Heterogeneous Catalysts , 2005 .

[13]  John Moody,et al.  Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.