Neural Networks as a Tool To Classify Compounds According to Aromaticity Criteria
- 26 April 2007
- journal article
- research article
- Published by Wiley in Chemistry – A European Journal
- Vol. 13 (14), 3913-3923
- https://doi.org/10.1002/chem.200601101
Abstract
Aromaticity is a fundamental concept in chemistry, with many theoretical and practical implications. Although most organic compounds can be categorized as aromatic, non-aromatic, or antiaromatic, it is often difficult to classify borderline compounds as well as to quantify this property. Many aromaticity criteria have been proposed, although none of them gives an entirely satisfactory solution. The inability to fully arrange organic compounds according to a single criterion arises from the fact that aromaticity is a multidimensional phenomenon. Neural networks are computational techniques that allow one to treat a large amount of data, thereby reducing the dimensionality of the input set to a bidimensional output. We present the successful applications of Kohonen's self-organizing maps to classify organic compounds according to aromaticity criteria, showing a good correlation between the aromaticity of a compound and its placement in a particular neuron. Although the input data for the training of the network were different aromaticity criteria (stabilization energy, diamagnetic susceptibility, NICS, NICS(1), and HOMA) for five-membered heterocycles, the method can be extended to other organic compounds. Some useful features of this method are: 1) it is very fast, requiring less than one minute of computational time to place a new compound in the map; 2) the placement of the different compounds in the map is conveniently visualized; 3) the position of a compound in the map depends on its aromatic character, thus allowing us to establish a quantitative scale of aromaticity, based on Euclidean distances between neurons, 4) it has predictive power. Overall, the results reported herein constitute a significant contribution to the longstanding debate on the quantitative treatment of aromaticity.Keywords
This publication has 96 references indexed in Scilit:
- Learning protein secondary structure from sequential and relational dataNeural Networks, 2005
- Description of Electron Delocalization via the Analysis of Molecular FieldsChemical Reviews, 2005
- Energetic Aspects of Cyclic Pi-Electron Delocalization: Evaluation of the Methods of Estimating Aromatic Stabilization EnergiesChemical Reviews, 2005
- Neural networks as data mining tools in drug designJournal of Physical Organic Chemistry, 2003
- An Insight into the Local Aromaticities of Polycyclic Aromatic Hydrocarbons and FullerenesChemistry – A European Journal, 2003
- To What Extent Can Aromaticity Be Defined Uniquely?The Journal of Organic Chemistry, 2002
- Nucleus-Independent Chemical Shifts: A Simple and Efficient Aromaticity ProbeJournal of the American Chemical Society, 1996
- Aromaticity and Antiaromaticity in Five‐Membered C4H4X Ring Systems: “Classical” and “Magnetic” Concepts May Not Be “Orthogonal”Angewandte Chemie-International Edition, 1995
- Crystallographic studies of inter- and intramolecular interactions reflected in aromatic character of .pi.-electron systemsJournal of Chemical Information and Computer Sciences, 1993
- Efficient implementation of the gauge-independent atomic orbital method for NMR chemical shift calculationsJournal of the American Chemical Society, 1990