Attribute combination discovery for predisposition determination

摘要

A method and system are presented in which a query attribute is used as the basis for accessing stored attribute combinations and their frequencies of occurrence for query-attribute-positive individuals and query-attribute-negative individuals and tabulating, based on frequencies of occurrence, those attribute combinations that are most likely to co-occur with the query attribute.

主权项

1. A computer-based method for generating a prediction indicating a predisposition of an individual to acquire at least one medical disease which the individual may be subject to, the computer including a user interface, a processor, a memory, and a display, the computer-based method comprising:
a) receiving at the processor, via the user interface, a query to report on the at least one medical disease with respect to the individual; b) accessing via the processor an attribute profile associated with the individual, wherein the attribute profile contains pangenetic and non-pangenetic attributes, the pangenetic attributes comprising genetic or epigenetic attributes; c) accessing via the processor a dataset, stored in the memory, which contains pangenetic and non-pangenetic attributes for a reference set of individuals, the pangenetic attributes comprising genetic or epigenetic attributes; d) calculating with the processor attribute combinations and a strength of association of the attribute combinations based on a comparison of:
i. attribute profiles of a first subset of individuals selected from the set of reference individuals, the first subset of reference individuals having the at least one medical disease; withii. attribute profiles of a second subset of individuals selected from the set of reference individuals, the second subset of reference individuals not having the at least one medical disease,wherein the calculation determines a common set of pangenetic attributes between the individual, the first subset of individuals selected from the set of reference individuals, and the second subset of individuals selected from the set of reference individuals; e) identifying from the attribute combinations of d) and the non-pangenetic attributes of the individual and the reference individuals a set of identified attribute combinations including at least one pangenetic attribute and at least one non-pangenetic attribute associated with the at least one medical disease that corresponds in part to the common set of pangenetic attributes between the individual, the first subset of individuals selected from the set of reference individuals, and the second subset of individuals selected from the set of reference individuals; and f) generating output for display indicating the prediction of the predisposition of the individual to acquire the at least one medical disease based on the identified attribute combinations.