Application of artificial intelligence in organic chemistry. Part XIX^*. Pattern recognition and structural determination of flavonoids using ¹³C‒NMR spectra

Abstract

This essay describes another improvement to the expert system named SISTEMAT. The purpose of such improvement is to help chemists who work with natural products to figure out chemical structures. SISTEMAT uses Nuclear Magnetic Resonance (NMR)13C data to ensemble compatible substructures according to related spectra. The system also is able to suggest a list of probable carbon skeletons. Those will work as models to structure generating programs, reducing the combinatorial explosion problem. This is the first essay from our research group which shows our system applications to aromatic compounds. A database with 700 NMR13C spectra of flavonoids obtained from the literature was used. We applied heuristic SISTEMAT in order to discover ranges of chemical shifts that characterise several skeleton types. The diversity of flavonoid structures is due to several oxidation patterns at rings A and B. This phenomenon causes a great complexity in the absorptions at the aromatic region. Heuristic SISTEMAT was able to discover more accurate rules that differentiate specific patterns of oxidation for some skeleton types. The performance of the software was checked against a higher complex structure of a dimeric flavonoid recently isolated. The system gives only two possibilities of skeleton types (among 70 others). Both substructures found by the program showed correct linkages between carbons 2 and 7″and 4 and 8″of the monomers.

SISTAX: an intelligent tool for recovering information on natural products chemistry

“…The former task has been thoroughly explored by our research group. [4][5][6][7][8][9][10][11][12][13][14][15][16] The latter is only beginning. 17 The system allows the analysis of the The database of SISTEMAT shows all the facilities of an associated database allied to the storage of compound structures in compacted vector forms, which are transformed into connectivity matrices during the search process.…”

“…[1][2][3][4][5][6][7][8][9][10][11] Substructures, allied to other biochemical inferences, are the main tools for chemotaxonomy methodology, and may be useful to discrimimate genera, species etc. 12,13 The aim of this work is to demonstrate how a specialist system developed to assist the chemist in both fields described above can be used for chemotaxonomic purposes.…”

Application of a New Program, H1MACH, for Prediction of Iridoid Skeletons

“…The principal one among them was the combinatorial explosion in the structure generator. [22] Other classes such as steroids, lignoids, alkaloids, etc. From this system, various others have been developed such as the ACCESS, DARC/EPIOS, SpecInfo, and, more recently, the Assemble 2.0 systems.…”

Applications of artificial intelligence to structure determination of organic compounds. XX*. Determination of groups attached to the skeleton of natural products using 13C nuclear magnetic resonance spectroscopy

“…The presence of SCCs in an NP often causes difficulties for some of the previously described modules of the expert system SISTEMAT [1][2][3][4] (those relating to 13 C NMR analysis), because the presence of signals due to non-skeletal carbon atoms may confuse the identification algorithms, leading to false results. Thus, we realized that it was of paramount importance for the correct operation of our expert system to have a module capable of pre-processing the raw data, in order to avoid this problem.…”