DENDRAL project

The DENDRAL project initiated in 1964 at Stanford was the prototypical application of artificial intelligence techniques - or what was understood at that time under this name - to chemical problems. Chemical structure generators were developed and information from mass spectra was used to prune the chemical graphs in order to derive the chemical structure associated with a certain mass spectrum. 

R. K. Lindsay, B. G. Buchanan, E. A. Feigenbaum, J. Lederberg, Applications of Artificial Intelligence for Organic Chemistry - The DENDRAL Project, McGraw-Hill, New York, 1980. 

Chemistry — The DENDRAL Project, McGraw-Hill, New York, 1980. 

The DENDRAL project has been reviewed by Gray " and responded to by Feigenbaum and co-workers. 

Searches through more than one data base in combination would be very desirable. For example, one often possesses mass spectral and nmr data for an unknown and it would be very useful to be able to identify any compounds that match these data in a single search. Work is going on in this area do interface programs so that this approach can be tested. In another development, it is expiected that the CONGEN programs developed for the DENDRAL project [30] will be merged into CIS within the... 

A very important role in the proliferation and practical use of mathematical chemistry has been played by computers, especially in the last two decades, when the use of computers was extended from numerical computations and data handling to decision-making and logical problem-solving processes. The DENDRAL project, started at Stanford in the 1960s, may serve as an illustrative example [3], It was fairly successful, and strongly influenced the collaboration between chemists, computer scientists, and mathematicians. Many applications of artificial intelligence in chemistry, and especially the construction of expert systems, are natural consequences of this collaboration [4],... 

At almost the same time as the DENDRAL project began, Vleduts was the first to put forward the idea of obtaining suggestions for organic synthesis from computers [5], and the famous article of Corey and Wipke [6] started the great... 

Computer-aided structure elucidation (CASE) has been developed over a period of 30 years. Several major projects that were initiated and carried out during this time consist, in the main, of interdisciplinary efforts toward the automatic solution of problems arising from the everyday practice of chemists. The DARC system of Dubois et the Heuristic DENDRAL project developed at Stanford University, and the CHEMICS system of Sasaki et as well as the developments of... 

This was the starting point for the DENDRAL project, initiated in 1965 by Edward Feigenbaum, Nobel Prize winner Joshua Lederberg, and Bruce Buchanan, in cooperation with chemist Carl Djerassi. The basic approach was to design software that mimics the concept of human reasoning and allows the formalization of scientific knowledge. 

CONstrained GENeration (CONGEN) is software for generating all isomers for a given structure and is part of the DENDRAL project. 

MOLION is software designed to detect the parent ion in a mass spectrum and to derive the sum formula. It is part of the DENDRAL project. 

PLANNER is a construction module in the DENDRAL project for automatic constraint generation. 

REACT is a program from the DENDRAL projects that predicts potential reactions of a candidate strnctnre with another structure. 

Djerassi, C., Smith, D., Crandell, C., Gray, N., Nourse, J., and Bindley, M. (1982) Applications of artificial intelligence for chemical inference. XLII. The DENDRAL project computational aids to natural products structure elucidation. Pure Appl. Chem 54,2425-2442. 

Techniques to enumerate molecules (including cyclic ones) from a molecular formula appeared in the 1970s. The first algorithm to do so, CONGEN, was a product of the DENDRAL project. The solution consisted of decomposing the molecular formula into cyclic substructmes, which were combined by bridges to get molecules. The cyclic substructmes were built from a database of 3000 elementary cycles. A second approach, simpler in principle, has been the technique chosen by the researchers involved in the CHEMICS project.In this approach, only canonical structmes are... 

---