Rediscovering Some Problems of Artificial Intelligence in the Context of Organic Chemistry

The set of computer programs known as HEURISTIC DENDRAL is an attempt to develop machine intelligence in a scientific field. In particular its task domain is the analysis of mass spectra, chemical data gathered routinely from a relatively new analytical instrument, the mass spectrometer. HEURISTIC DENDRAL has been developed as a joint project of the Departments of Computer Science, Chemistry, and Genetics at Stanford University. This collaboration of chemists and computer scientists has produced what appears to be an interesting program from the viewpoint of artificial intelligence and a useful tool from the viewpoint of chemistry. For this discussion it is sufficient to say that a mass spectrometer is an instrument into which is put a minute sample of some chemical compound and out of which comes data usually represented as a bar graph. This is what is referred to here as the mass spectrum. The instrument itself bombards molecules of the compound with electrons, thereby producing ions of different masses in varying proportions. The x-points of the bar graph represent the masses of ions produced and the y-points represent the relative abundances of ions of these masses. The HEURISTIC DENDRAL process of analysing a mass spectrum by computer consists of three phases. The first, preliminary inference (or planning), obtains clues from the data as to which classes of chemical compounds are suggested or forbidden by the data. The second phase, structure generation, enumerates all possible explicit structural hypotheses which are compatible with the inferences made in phase one. The third phase, prediction and testing, predicts consequences from each structural