Expert systems are now commonly developed to solve practical problems. Nevertheless, genetics has just begun to benefit from this new technology, since genetic expert systems are extremely rare and often purely experimental. A prototype for risk calculation in pedigrees was developed at the University of Utah, using a commercial frames/rules developmental shell (Intelligence Compiler), which runs on an IBM PC (I). When small data sets were used, the implementation functioned well, but it could not handle larger data sets. Performance became a major issue, with two possible solutions. The first possibility would have been to port the system to a more powerful machine, and the second would have been to use several different shells or languages, each efficiently representing a specific type of knowledge. Neither of these solutions was applicable in this case. From this experience, we learned that performance, portability, and modifiability were three major requirements for genetic expert systems. To achieve these goals, we implemented the gene mapping expert system GMES; (GMES is unrelated to the gene mapping system, GMS (2)) in Lisp (3) combined with a frame/object shell (FROBS) (4, 5). We were able to efficiently represent, control, and optimize a gene mapping experiment, achieving portability by building GMES on top of a C-based version of Common Lisp (6). Lisp combined with the FROBS expert system shell permitted a declarative representation of each of the components of the experiment, resulting in a transparent specification of the problem within a maintainable system. 0 I!390 Academic Press, Inc.
THE GENE MAPPING EXPERIMENT
At meiosis, homologous chromosomes break and exchange segments (recombine) in a process called crossing-over. At the end of meiosis, each n-chromosome daughter cell of an original 2n-chromosome cell contains a patchwork of the original chromosome pairs (7, 8).