An Expert System for the Pattern Recognition of Biological Effects

The objective of this project is to develop an expert system capable of measuring and interpreting complex, time-related, global changes in gene, protein expression, and metabolite pattern profiles. The expert system will identify toxic substancesexposure at very low, sub-symptomatic concentrations to military personnel. The project will meet three challenges to the development of the system: (a) identify the toxic substances and quantify the low exposure level with estimated probabilisticconfidence; (b) predict the future evolution of the biological effects utilizing available time-dependent measurement records of pattern profiles; and (c) integrate the usage of all available pattern profiles and optimize the synergized capability ofinterpreting and predicting the biological effects. In Phase I, we will develop a system concept by applying proven multivariate statistical methods for signal processing widely used in electrical engineering and geophysical sciences. The feasibility andextendibility of the concept in terms of accuracy, efficiency, and applicability will be demonstrated with a few practical examples.