Intelligent DNA-Based Molecular Diagnostics Using Linked Genetic Markers

This paper describes a knowledge-based system for molecular diagnostics, and its application to fully automated diagnosis of X-hnked genetic disorders. Molecular diagnostic information is used in chnical practice for determining genetic risks, such as carrier determination and prenatal diagnosis. Initially, blood samples are obtained from related individuals, and PCR amphfication is performed. Linkage-based molecular diagnosis then entails three data analysis steps. First, for every individual, the alleles (i.e., DNA composition) are determined at specified chromosomal locations. Second, the flow of genetic material among the individuals is established. Third, the probability that a given individual is either a carrier of the disease or affected by the disease is determined. The current practice is to perform each of these three steps manually, which is costly, time consuming, labor-intensive, and error-prone. As such, the knowledge-intensive data analysis and interpretation supersede the actual experimentation effort as the major bottleneck in molecular diagnostics. By examining the human problem solving for the task, we have designed and implemented a prototype knowledge-based system capable of fully automating hnkage-based molecular diagnostics in X-hnked genetic disorders, including Duchenne Muscular Dystrophy (DMD). Our system uses knowledge-based interpretation of gel electrophoresis images to deternline individuai DNA marker labels, a constraint satisfaction search for consistent genetic flow among individuals, and a blackboard-style problem solver for risk assessment. We describe the system's successful diagnosis of DMD carrier and affected individuals from raw chnical data.