Treatment determination and impact analysis

• US 10,379,812 B2
• Filed: 10/20/2015
• Issued: 08/13/2019
• 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): Trujillo, James
• Assistant Examiner(s): Shechtman, Cheryl M
• Application Number:
  US14/887,688
• Publication Number:
  US 20160042143A1
• Time in Patent Office: 1,393 Days
• Field of Search: None
• 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, software, database and system for determining an optimal treatment for an illness in an individual and for determining the impact (e.g., side effects and intended benefits) of the treatment in the individual are presented in which an attribute profile of the individual containing genetic and non-genetic attributes is compared against a database containing combinations genetic and non-genetic attributes that are statistically associated with successful treatment of the illness in other individuals.

Claims

1. A computer implemented method comprising steps executing on a processor operating as part of a computing system including:

receiving a query in a form of a signal that is representative of a non-monogenic health condition as related to a first individual;

in response to receiving the query, accessing a first memory sector, contained within the computing system, the first memory sector including a first attribute profile database associated with the first individual, the first attribute profile database comprising single nucleotide polymorphism (SNP) pangenetic attributes and non-pangenetic attributes associated with the first individual, and wherein at least one of the non-pangenetic attributes is both modifiable and potentially related to the non-monogenic health condition;

also in response to receiving the query, accessing a second memory sector contained within the computing system, the second memory sector including a second attribute profile database associated with a set of other individuals, the second attribute profile database comprising SNP pangenetic attributes and non-pangenetic attributes of the set of other individuals;

scanning via the processor, a subset of attribute profiles of the set of other individuals having the non-monogenic health condition to establish at least one combination of at least two SNP pangenetic attributes and at least one modifiable non-pangenetic attribute;

discovering, via processor based statistical testing and from the at least one combination of at least two SNP pangenetic attributes and at least one modifiable non-pangenetic attribute, a correlated combination of at least SNP two pangenetic attributes and at least one modifiable non-pangenetic attribute, wherein the correlated combination of the at least two SNP pangenetic attributes and the at least one modifiable non-pangenetic attribute is statistically associated above a first threshold with presence of the non-monogenic health condition in the set of other individuals and is also found in the first attribute profile database associated with the first individual;

confirming, via processor based statistical testing, that alteration of the at least one modifiable non-pangenetic attribute from the correlated combination results in a statistically significant altered probability above a second threshold of having the non-monogenic health condition; and

in response to learning the correlated combination of the at least two pangenetic attributes and the at least one modifiable non-pangenetic attribute and confirming the alteration of the at least one modifiable non-pangenetic attribute resulting in a statistically significant altered probability above the second threshold of having the non-monogenic health condition, transmitting, as output from the computing system, an output signal representing the at least one modifiable non-pangenetic attribute as a set of lifestyle modifications for the first individual.

2. The computer implemented method of claim 1, wherein the set of lifestyle modifications are ranked according to a greatest statistically significant altered probability of avoiding the non-monogenic health condition.

3. The computer implemented method of claim 1, wherein the second attribute profile database contains at least one time indicator, wherein the at least one time indicator is associated with a duration of the at least one modifiable non-pangenetic attribute.

4. The computer implemented method of claim 1, wherein the output signal representing the at least one modifiable non-pangenetic attribute as a set of lifestyle modifications for said first individual contains a timeframe implementation indicator, and wherein the timeframe implementation indicator is representative of the timeframe over which alteration of the at least one modifiable non-pangenetic attribute results in a statistically significant altered probability above the second threshold of having the non-monogenic health condition.

5. The computer implemented method of claim 1, wherein the correlated combination forms a predictive model indicating a predisposition to presence of the non-monogenic health condition in the set of other individuals.

6. A computer implemented method comprising steps executing on a processor operating as part of a computing system including:

receiving a query in a form of a signal that is representative of a non-monogenic health condition as related to a first individual;

in response to receiving the query, accessing a first memory sector, contained within the computing system, the first memory sector including a first attribute profile database associated with the first individual, the first attribute profile database comprising single nucleotide polymorphism (SNP) pangenetic attributes and non-pangenetic attributes associated with the first individual;

also in response to receiving the query, accessing a second memory sector contained within the computing system, the second memory sector including a second attribute profile database associated with a set of other individuals, the second attribute profile database comprising SNP pangenetic attributes and non-pangenetic attributes of the set of other individuals;

identifying, using the processor, at least one combination of at least two SNP pangenetic attributes and at least one modifiable non-pangenetic attribute, wherein the combination is found within the first attribute profile database and the second attribute profile database;

discovering, using the processor, a statistical association of the at least one combination of at least two SNP pangenetic attributes and at least one modifiable non-pangenetic attribute with the non-monogenic health condition, wherein the at least two SNP pangenetic attributes and the at least one modifiable non-pangenetic attribute are statistically associated above a first threshold with the non-monogenic health condition;

confirming, using the processor for statistical testing, that alteration of the at least one modifiable non-pangenetic attribute results in a statistically significant altered probability above a second threshold of having the non-monogenic health condition; and

transmitting as output from the computer implemented method, an output signal representing the at least one learned modifiable non-pangenetic attribute as a set of lifestyle modifications for said first individual.

7. The computer implemented method of claim 6, wherein the set of lifestyle modifications are ranked according to a greatest statistically significant altered probability of avoiding the non-monogenic health condition.

8. The computer implemented method of claim 6, wherein the second attribute profile database contains at least one time indicator, wherein the at least one time indicator is associated with a duration of the at least one modifiable non-pangenetic attribute.

9. The computer implemented method of claim 6, wherein the output signal representing the at least one modifiable non-pangenetic attribute as the set of lifestyle modifications for the first individual contains a timeframe implementation indicator, and wherein the timeframe implementation indicator is representative of the timeframe over which alteration of the at least one modifiable non-pangenetic attribute results in a statistically significant altered probability of having the non-monogenic health condition.

10. A computer implemented method comprising steps executing on a processor operating as part of a computing system including:

accessing a first memory sector contained within the computing system including a first attribute profile database associated with a set of individuals, the first attribute profile database comprising single nucleotide polymorphism (SNP) pangenetic attributes and non-pangenetic attributes of the set of individuals;

discovering, via the processor as applied to the first attribute profile database, at least one combination of at least two SNP pangenetic attributes and at least one modifiable non-pangenetic attribute, wherein the at least one combination of at least two SNP pangenetic attributes and at least one modifiable non-pangenetic attribute is statistically associated above a first threshold with a non-monogenic health condition;

and wherein removal of the at least one modifiable non-pangenetic attribute from the at least one combination results in a statistically significant altered probability of having the non-monogenic health condition;

confirming, via processor based statistical testing, that alteration of the at least one modifiable non-pangenetic attribute results in a statistically significant altered probability above a second threshold of having the non-monogenic health condition;

receiving a query signal that is representative of the non-monogenic health condition as related to a user;

accessing a second memory sector contained within the computing system, the second memory sector including a second attribute profile database associated with the user, the second attribute profile database comprising SNP pangenetic attributes and non-pangenetic attributes associated with the user;

scanning the second memory sector for the at least one combination of at least two SNP pangenetic attributes and at least one modifiable non-pangenetic attribute including the at least one modifiable non-pangenetic attribute; and

if the at least one combination of at least two SNP pangenetic attributes and at least one modifiable non-pangenetic attribute including the at least one modifiable non-pangenetic attribute is present in the second memory sector, transmitting as output from said computer implemented method, an output signal representing the at least one modifiable non-pangenetic attribute as a set of lifestyle modifications for the user.

11. The computer implemented method of claim 10, wherein the set of lifestyle modifications are ranked according to a greatest statistically significant altered probability of avoiding the non-monogenic health condition.

12. The computer implemented method of claim 10, wherein the second attribute profile database contains at least one time indicator, wherein the at least one time indicator is associated with a duration of the at least one modifiable non-pangenetic attribute.

13. The computer implemented method of claim 10, wherein the output signal representing the at least one modifiable non-pangenetic attribute as the set of lifestyle modifications for the user contains a timeframe implementation indicator, and wherein said timeframe implementation indicator is representative of the timeframe over which alteration of the at least one correlated modifiable non-pangenetic attribute results in a statistically significant altered probability of having the non-monogenic health condition.