Computed assisted spectral interpretation

N.A.B. Gray, A. Buchs, D.H. Smith and C. Djerassi, Application of artificial intelligence for chemical inference. Part XXXVI. Computer assisted structural interpretation of mass spectral data, Helv. Chim. Acta, 64 (1981) 458-470. 

Intelligent computer assisted interpretation of spectroscopic data should be based on the knowledge from large structure oriented data collections. Both the inspection of spectral features and the statistical evaluation of similar structures (from library searches) can provide a set of probability ranked substructures which are readily assembled to target structures. The idea of substructure analysis allows the chemist to combine the results of different interpretation strategies, different databases and different spectroscopic methods to yield the structural information desired. Thus in a multidimensional data system hke SPECINFO structural noise can be effectively suppressed, if all information available in the spectroscopic laboratory is combined in a central intelligent computer system. 

Three different approaches have been used for computer-assisted interpretations of chemical data. 1. Heuristic methods try to formulate computer programs working in a similar way as a chemist would solve the problem. 2. Retrieval methods have been successfully used for library search (an unknown spectrum is compared with a spectral library). 3. Pattern recognition methods are especially useful for the classification of objects (substances, materials) into discrete classes on the basis of measured features. A set of characteristic features (e.g. a spectrum) of an object is considered as an abstract pattern that contains information about a not directly measurable property (e.g. molecular structure or biological activity) of the object. Pure pattern recognition methods try to find relationships between the pattern and the "obscure property" without using chemical knowledge or chemical prejudices. 

Since the early days of computer-assisted structure elucidation, the following three processes, in general, have been adopted (1) derivation of substructures from measured spectral data of an unknown (2) generation of all possible total structures based on the derived substructures (3) examination of candidate structures thus obtained (see Structure Determination by Computer-based Spectrum Interpretation). Any automated structure elucidation system for organic compounds... 

Three main spectra collections now exist. The first is the NIST/EPA/NIH mass spectral database, which contains 190 000 spectra of 163 000 compounds [1]. This original collection of spectra and related information is produced by the National Institute of Standards and Technology (NIST) with the assistance of expert advisors from the Environmental Protection Agency (EPA) and National Institutes of Health (NIH). This library is available on CD-ROM for personal computers with integrated tools for GC/MS deconvolution, mass spectra interpretation and chemical substructure identification. This US government publication is very cheap and of very high quality. This library is widely spread in many commercial mass spectrometers. Mass spectra for over 15 000 compounds are accessible on-line [2],... 

Spectral databases for FT-IR, NMR, and MS have been reviewed by Warr. There are several reviews of computer methods used in the identification of unknowns and a review of the use of computers in quantitative analysis." In order to assist interpretation, there are computer programs which will, when a peak of interest has been highlighted, automatically locate and display... 

---