Computer-assisted methods can be used to investigate the relationships between the molecular structures of compounds and their biological activity. A number of approaches have been reported in the literature, including correlations of activity with substituent constants, conformational analysis and display, quantum mechanical methods, and methods relying on discriminant development and pattern-recognition techniques. Application areas for the technology include drug design, agricultural chemical design, and studies of chemical toxicity and genetic toxicity (mutagenic or carcinogenic potential). These structure-activity methods are introduced, and citations are given. Several current structure-activity relationship (SAR) studies using pattern recognition are presented as examples of typical projects that are feasible with the approach. They include the investigation of a set of 122 antiinflammatory steroids, a study of 153 retinoids for cancer prevention, and a study of chemicals that have been tested in a sister chromatid exchange mutagen screen.