An increasingly common problem faced by molecular biologists is the need to determine the probable function of a protein from its amino and sequence. Since DNA sequencing is so easily carried out nowadays many investigators have knowledge of the amino acid sequence of proteins with no known function. The human genome effort will no doubt exacerbate this situation. Since X-ray crystallography and other physical and biochemical methods for characterizing proteins are laborous and slow, there is great interest in the use of computers to help determine the structure and function of unknown proteins. Recent progress has been made by application of artificial intelligence techniques to examine structural correlates of function and to ascertain relationships between known proteins and unknown ones. The protein analysis system, ARIADNE, developed by T. Smith, R. Lathrop and T. Webster is a highly advanced effort in that direction. We propose here to develop a product consisting of an implementation of ARIADNE in a form that can be used by individual laboratories and scientists on personal computers or workstations. We plan to implement ARIADNE for personal computers, provide a user friendly interface an seamless access to molecular databases and to provide an ARIADNE pattern database for unknowns to be compared with. As a commercial product such software could be used in many in research labs. The program could also be a very important tool for data resulting from large scale sequencing efforts such as the Human Genome Project.