The rational synthetic parameter analysis for subclasses of microporous aluminophosphates based on hierarchical feature selection model

Abstract Open-framework aluminophosphates (AlPOs) is an important family of porous crystal materials. But the synthetic chemistry of this kind of materials is very complicated, and the synthesis mechanism has not been clearly understood yet. In this paper, we propose a Hierarchical Feature Selection Model (HFSM) composed of two layers to analyze the rational synthetic parameters for the subclass of microporous aluminophosphates (AlPOs) containing (6,8)-rings. In the first layer, we select a feature subset that could separate the (6,8)-ring-containing microporous AlPOs from other AlPOs. In the second layer, we further analyze which of these selected features are critical for the formation of each special subclass in (6,8)-ring-containing microporous AlPOs. With the optimal feature subset selected by the proposed model, we can obtain the highest accuracy rates as 94.28%, 94.03%, 91.27% and 92.20% for the classification of AEN, AWO, CHA and ERI, respectively. Extensive analysis is presented for the synthetic parameters selected by the hierarchical model, which could provide a useful guidance to the rational synthesis of such materials.

[1]  Jihong Yu,et al.  Insight into the construction of open-framework aluminophosphates. , 2006, Chemical Society reviews.

[2]  Jiyang Li,et al.  Prediction of the formation of microporous aluminophosphates containing (6, 8)-rings using support vector machines , 2014 .

[3]  Susumu Goto,et al.  LIGAND: chemical database for enzyme reactions , 1998, Bioinform..

[4]  Yi Li,et al.  Prediction of Open-Framework Aluminophosphate Structures Using the Automated Assembly of Secondary Building Units Method with Lowenstein's Constraints , 2005 .

[5]  R. Fisher.  THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

[6]  N. L. Franklin,et al.  Statistical Analysis in Chemistry and the Chemical Industry , 1955 .

[7]  F. Allen.  The Cambridge Structural Database: a quarter of a million crystal structures and rising. , 2002, Acta crystallographica. Section B, Structural science.

[8]  S. Wold,et al.  New chemical descriptors relevant for the design of biologically active peptides. A multivariate characterization of 87 amino acids. , 1998, Journal of medicinal chemistry.

[9]  Jianzhong Wang,et al.  Maximum weight and minimum redundancy: A novel framework for feature subset selection , 2013, Pattern Recognit..

[10]  Paolo Soda,et al.  A multi-objective optimisation approach for class imbalance learning , 2011, Pattern Recognit..

[11]  W. Kraeft.  Quantum Statistics of Charged Particle Systems , 2011 .

[12]  Jihong Yu,et al.  Solid-state NMR spectroscopy of anionic framework aluminophosphates: a new method to determine the al/p ratio. , 2006, The journal of physical chemistry. B.

[13]  David A. Fletcher,et al.  The United Kingdom Chemical Database Service , 1996, J. Chem. Inf. Comput. Sci..

[14]  Jun Kong,et al.  A Novel Integrated Feature Selection Method for the Rational Synthesis of Microporous Aluminophosphate , 2012 .

[15]  M. Karelson.  Molecular descriptors in QSAR/QSPR , 2000 .

[16]  Miao Qi,et al.  A novel classification method based on the ensemble learning and feature selection for aluminophosphate structural prediction , 2014 .

[17]  Jihong Yu,et al.  Cotemplating ionothermal synthesis of a new open-framework aluminophosphate with unique Al/P ratio of 6/7 , 2008 .

[18]  Matthieu Cord,et al.  Machine Learning Techniques for Multimedia - Case Studies on Organization and Retrieval , 2008, Machine Learning Techniques for Multimedia.

[19]  M. Karelson,et al.  Quantum-Chemical Descriptors in QSAR/QSPR Studies. , 1996, Chemical reviews.

[20]  Miao Qi,et al.  AlPOs Synthetic Factor Analysis Based on Maximum Weight and Minimum Redundancy Feature Selection , 2013, International journal of molecular sciences.

[21]  Ronghui Wang,et al.  CHARACTERISTICS AND PERFORMANCE OF SAPO-34 CATALYST FOR METHANOL-TO-OLEFIN CONVERSION , 1990 .

[22]  William H. Press,et al.  Numerical recipes in C (2nd ed.): the art of scientific computing , 1992 .

[23]  Pedro Larrañaga,et al.  A review of feature selection techniques in bioinformatics , 2007, Bioinform..

[24]  Aleix M. Martínez,et al.  Subclass discriminant analysis , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  Jihong Yu,et al.  Rational Synthesis of Microporous Aluminophosphates with an Inorganic Open Framework Analogous to Al4P5O20H·C6H18N2 , 2000 .

[26]  J. M. Thomas,et al.  Synthese eines kleinporigen mikroporösen Materials unter Verwendung eines computer‐gestützt entworfenen Templats , 1997 .

[27]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[28]  Stacey I. Zones,et al.  A combustion-free methodology for synthesizing zeolites and zeolite-like materials , 2003, Nature.

[29]  Yudong D. He,et al.  Gene expression profiling predicts clinical outcome of breast cancer , 2002, Nature.

[30]  Jun Kong,et al.  Computational prediction of the formation of microporous aluminophosphates with desired structural features , 2010 .

[31]  Carsten O. Daub,et al.  The mutual information: Detecting and evaluating dependencies between variables , 2002, ECCB.

[32]  S H Kaufmann,et al.  Successful virtual screening of a chemical database for farnesyltransferase inhibitor leads. , 2000, Journal of medicinal chemistry.

[33]  Wenguo Xu,et al.  Structures and Templating Effect in the Formation of 2D Layered Aluminophosphates with Al3P4O163- Stoichiometry , 1999 .

[34]  Daoqiang Zhang,et al.  Constraint Score: A new filter method for feature selection with pairwise constraints , 2008, Pattern Recognit..