Using Artificial Neural Networks to boost high-throughput discovery in heterogeneous catalysis

被引:69
作者
Baumes, L [1 ]
Farrusseng, D [1 ]
Lengliz, M [1 ]
Mirodatos, C [1 ]
机构
[1] Inst Rech Catalyse, CNRS, F-69626 Villeurbanne, France
来源
QSAR & COMBINATORIAL SCIENCE | 2004年 / 23卷 / 09期
关键词
Artificial Neural Networks; high throughput screening; material discovery; heterogeneous catalysis; genetic algorithm;
D O I
10.1002/qsar.200430900
中图分类号
R914 [药物化学];
学科分类号
100701 ;
摘要
The work presents for the first time a detailed methodology which enable to scrutinize and identify solids that are relevant to be tested in a high throughput program. In the present case study, Artificial Neural Networks (ANN) are used to predict performances of catalysts for the Water Gas Shift reaction. In contrast to previous studies, it is shown that the quantitative prediction by ANN of performances is not adapted to a primary screening stage. On the contrary, ANN used as classifier tool within the course of an Evolutionary Strategy are well performing and well suited for high throughput heterogeneous catalysis. The virtual screening enables to pre-select candidates to be screened experimentally with a very high rate of relevance at an early stage of a high throughput experimentation program, thus reducing significantly the number of trials.
引用
收藏
页码:767 / 778
页数:12
相关论文
共 27 条
[1]   Combinatorial chemistry - The emperor's new clothes? [J].
Akporiaye, D ;
Dahl, I ;
Karlsson, A ;
Plassen, M ;
Wendelbo, R ;
Bem, DS ;
Broach, RW ;
Lewis, GJ ;
Miller, M ;
Moscoso, J .
MICROPOROUS AND MESOPOROUS MATERIALS, 2001, 48 (1-3) :367-373
[2]  
Baerns M, 2002, NATO SCI SER II MATH, V69, P469
[3]  
Baumes L, 2003, LECT NOTES ARTIF INT, V2773, P265
[4]   Fundamental and combinatorial approaches in the search for and optimisation of catalytic materials for the oxidative dehydrogenation of propane to propene [J].
Buyevskaya, OV ;
Brückner, A ;
Kondratenko, EV ;
Wolf, D ;
Baerns, M .
CATALYSIS TODAY, 2001, 67 (04) :369-378
[5]   Ethylene and propene by oxidative dehydrogenation of ethane and propane - 'Performance of rare-earth oxide-based catalysts and development of redox-type catalytic materials by combinatorial methods' [J].
Buyevskaya, OV ;
Wolf, D ;
Baerns, M .
CATALYSIS TODAY, 2000, 62 (01) :91-99
[6]  
Corma A, 2002, NATO SCI SER II-MATH, V69, P153
[7]  
Corma A, 2002, CHEMPHYSCHEM, V3, P939, DOI 10.1002/1439-7641(20021115)3:11<939::AID-CPHC939>3.0.CO
[8]  
2-E
[9]   Design of a propane ammoxidation catalyst using artificial neural networks and genetic algorithms [J].
Cundari, TR ;
Deng, J ;
Zhao, Y .
INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2001, 40 (23) :5475-5480
[10]  
Farrusseng D, 2003, HIGH-THROUGHPUT ANALYSIS: A TOOL OF COMBINATORIAL MATERIALS SCIENCE, P551