Application pratique des réseaux neuro mimétiques aux données spectroscopiques (infrarouge et masse) en vue de l'élucidation structurale

Abstract

In the last few years, intensive research by several groups has shown that neural networks can be used to analyse spectral data for structural elucidation, and that their performance approaches that of an expert in the field. The construction of such networks, their training and evaluation, requires large structural and spectral databases and significant computational resources and time. However, once the network has been completed it can be used very effectively for practical applications on an ordinary desktop computer. In this article we describe the methodology for creating such a network for infrared and mass spectra, and present a program for use on a personal computer, either connected to a spectrometer or independently. The program accepts data in ASCII format, both for the network description and for the spectral information. This approach permits the use of neural networks in an analytical laboratory with limited computational resources. Keywords: neural networks, infrared spectroscopy, mass spectroscopy, structure determination.

Identification of Structural Features from Mass Spectrometry Using a Neural Network Approach: Application to Trimethylsilyl Derivatives Used for Medical Diagnosis

“…As a consequence, careful examination of the hit list produced by the library search algorithm is absolutely essential, and in many cases it remains necessary for the analyst to interpret the mass spectra in order to elucidate an unknown structure. In these circumstances the use of ANN, combined with other taxonomic methods, can provide valuable assistance in the structure determination. − Although the application of ANN to identify specific SFs, fragments, or substructures from spectroscopic information can be routinely carried out on a microcomputer, subject to the availability of specific software, , the prior construction, training, and testing of ANN requires more powerful hardware and software resources. Furthermore presently there is no well established methodology for ANN development in real practical problems, consequently one has to adopt an empirical approach to choose the architecture, learning method, and input and output vectors which best fit the problem at hand.…”

The American Society for Mass Spectrometry

“…(5) Classification by neural networks [7][8][9]14] or feature selection by genetic algorithms [32,33] improved the performance in some cases but did not enable a break-through.…”

The American Society for Mass Spectrometry

“…An example is shown in the next chapter. (5) Classification by neural networks [7][8][9]14] or feature selection by genetic algorithms [32,33] improved the performance in some cases but did not enable a break-through.…”

“…This paper focuses on the application of multivariate data analysis -the typical chemometric approach -to investigate relationships between low resolution electron impact data and chemical structures as well as on the development and use of MS classifiers together with automatic isomer generation [6]. Chemometric methods are successful to some extent in the automatic recognition of substructures or other structural properties from low resolution electron impact mass spectra [6][7][8][9][10][11][12][13][14][15]. In some cases a systematic structure elucidation is possible from the molecular formula of an unknown together with restrictions about the presence or absence of substructures (automatically obtained from spectra).…”