Attribute combination discovery for predisposition determination

• US 9,582,647 B2
• Filed: 11/21/2011
• Issued: 02/28/2017
• Est. Priority Date: 03/16/2007
• Status: Active Grant

• Current Assignee: 23andme Incorporated (23andMe Holding Co.)
• Original Assignee: Expanse Bioinformatics, Inc.
• Inventors: Kenedy, Andrew Alexander, Eldering, Charles Anthony
• Primary Examiner(s): Reyes, Mariela
• Assistant Examiner(s): MINCEY, JERMAINE A
• Application Number:
  US13/301,209
• Publication Number:
  US 20120066255A1
• Time in Patent Office: 1,926 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/00 Information retrieval; Database structures therefor; File system structures therefor
• CPC Class Codes: G06F 16/2282 Tablespace storage structures; Management thereof
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: G06F 16/955 using information identifiers, e.g. uniform resource locators [URL]
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G09B 19/00 Teaching not covered by other main groups of this subclass teaching or practice apparatus for gun-aiming or gun-laying F41G3/26
• CPC Class Codes: G16B 20/00 ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
• CPC Class Codes: G16B 20/20 Allele or variant detection, e.g. single nucleotide polymorphism [SNP] detection
• CPC Class Codes: G16B 20/40 Population genetics; Linkage disequilibrium
• CPC Class Codes: G16H 20/30 relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
• CPC Class Codes: G16H 40/63 for local operation
• CPC Class Codes: G16H 50/30 : for calculating health indices; for individual health risk assessment
• CPC Class Codes: G16H 50/70 : for mining of medical data, e.g. analysing previous cases of other patients
• CPC Class Codes: G16H 70/20 : relating to practices or guidelines
• CPC Class Codes: H04L 67/306 : User profiles

Abstract

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.

Claims

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;

with

ii. 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.

2. The computer-based method of claim 1, wherein the prediction includes at least one statistical measure of the predisposition of the individual to acquire the at least one medical disease.

3. The computer-based method of claim 2, wherein the at least one statistical measure includes a probability.

4. The computer-based method of claim 1, wherein d)-e) are applied to a plurality of medical diseases and wherein the output of f) displays the prediction of the predisposition of the individual to the plurality of medical diseases.

5. The computer-based method of claim 4, wherein the prediction includes at least one statistical measure of the predisposition of the individual to acquire the plurality of medical diseases.

6. The computer-based method of claim 1, wherein d)-e) are applied to a plurality of medical diseases and wherein the output of f) displays the dataset ranked prediction of the individual to the plurality of medical diseases.

7. The computer-based method of claim 5, wherein the dataset ranked prediction includes at least one statistical measure of the predisposition of the individual to acquire the plurality of medical diseases.

8. The computer-based method of claim 7, wherein the at least one statistical measure includes a probability.

9. A computer readable storage medium containing instructions which when executed by a computer result in the execution of a 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 method comprising:

a) receiving at the processor, via a 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;

with

ii. 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 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.

10. The computer readable storage medium of claim 9, wherein the prediction includes at least one statistical measure of the predisposition of the individual to acquire the at least one medical disease.

11. The computer readable storage medium of claim 10, wherein the at least one statistical measure includes a probability.

12. The computer readable storage medium of claim 9, wherein d)-e) are applied to a plurality of medical diseases and wherein the output of f) displays the prediction of the predisposition of the individual to the plurality of medical diseases.

13. The computer readable storage medium of claim 11, wherein the prediction includes at least one statistical measure of the predisposition of the individual to acquire the plurality of medical diseases.

14. The computer readable storage medium of claim 9, wherein d)-e) are applied to a plurality of medical diseases and wherein the output of f) displays the dataset ranked prediction of the individual to the plurality of medical diseases.

15. The computer readable storage medium of claim 13, wherein the dataset ranked prediction includes at least one statistical measure of the predisposition of the individual to acquire the plurality of medical diseases.

16. The computer readable storage medium of claim 15, wherein the at least one statistical measure includes a probability.

17. A system 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 system comprising:

a) a user interface for receiving a query to report on the at least one medical disease with respect to the individual;

b) a data interface for accessing 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) a first memory containing pangenetic and non-pangenetic attributes for a reference set of individuals, the pangenetic attributes comprising genetic or epigenetic attributes;

d) a processor for accessing data and performing calculations;

e) a second memory containing computer-readable instructions, which upon execution by the processor, result in the method of;

i. accessing the attribute profile associated with the individual through the data interface;

ii. accessing 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;

iii. accessing 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,

iv. calculating 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;

v. calculating from the attribute combinations 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 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;

vi. generating output for display indicating the prediction of the predisposition of the individual to acquire the medical disease based on the identified attribute combinations.

18. The system of claim 17, further comprising:

f) a display interface for transmitting the output of vi. for display.

19. The system of claim 17, wherein the prediction includes at least one statistical measure of the predisposition of the individual to acquire the at least one medical disease.

20. The system of claim 19, wherein the at least one statistical measure includes a probability.