IP Library Granted Patent US 11,581,096
Granted Patent B2
US 11,581,096 · App. 16/151,721 · Granted Feb 14, 2023

Attribute identification based on seeded learning

Inventors: Andrew Alexander Kenedy (Sugar Land, TX); Charles Anthony Eldering (Glenside, PA)
Assignee: 23andMe, Inc.
G16H70/20G06F16/00G06F16/2282G06F16/24575G06F16/24578G06F16/285G06F16/951G06F16/955G06F16/9535G06N3/08G06N5/04G06N7/005G06Q40/08G16B20/00G16B20/20G16B20/40G16H20/30G16H40/63G16H50/30G16H50/70
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,581,096
App. No.
16/151,721
Granted
Feb 14, 2023
Kind
B2
Abstract

A system and method are presented in which known genetic attributes associated with a condition are used to seed the determination of additional attributes which are associated with the condition. Based on the learning, the additional attributes (genetic, behavioral, or both) provide for an increased correlation between the combined attributes and the condition. For behavioral attributes, a measure of the impact of the behavioral attribute on the risk of the condition can be transmitted to another device or system.

Claims (45)

1. A computing system comprising:

a first database containing genetic attributes, behavioral attributes, and health condition attributes for a population of individuals, wherein the genetic attributes are based on specific nucleotide sequences found in the population of individuals, and wherein the behavioral attributes are based on actions performed by the population of individuals;

a second database containing sets of the genetic attributes respectively associated with health-related conditions;

a memory storing program instructions; and

a processor configured to execute the program instructions to carry out operations including:

obtaining, from the first database, the genetic attributes and the behavioral attributes for a subgroup of individuals from the population of individuals, wherein the health condition attributes for the subgroup of individuals indicate that the subgroup of individuals have in common a health condition that is found in the health-related conditions;

obtaining, from the second database, a set of the genetic attributes associated with the health condition, wherein a first correlation, calculated between (i) the set of the genetic attributes associated with the health condition and (ii) the health condition, has a first correlation value;

creating a set of core genetic attributes based on a subset of the set of genetic attributes associated with the health condition above a predetermined threshold;

clustering attribute sub-combinations of the genetic and behavioral attributes for the subgroup of individuals, to form a particular attribute sub-combination of the genetic and behavioral attributes for the subgroup of individuals, wherein the particular attribute sub-combination has a second correlation value with the health condition that is higher than the first correlation value; and

generating a combined set of attributes including the set of core genetic attributes and the particular attribute sub-combination.

2. The computing system of claim 1 , wherein the particular attribute sub-combination contains a behavioral attribute.

3. The computing system of claim 2 , wherein the operations further include:

transmitting a representation of the combined set of attributes to indicate that the behavioral attribute is associated with the health condition.

4. The computing system of claim 2 , wherein removal of the behavioral attribute from the combined set of attributes results in a lower risk of the health condition than with the behavioral attribute present in the combined set of attributes.

5. The computing system of claim 1 , wherein the particular attribute sub-combination contains a genetic attribute.

6. The computing system of claim 1 , wherein the operations further include:

transmitting a representation of the combined set of attributes to indicate that the particular attribute sub-combination is associated with the health condition.

7. A computer-implemented method comprising:

obtaining, by a computing device and from a first database containing genetic attributes, behavioral attributes, and health condition attributes for a population of individuals, the genetic attributes and the behavioral attributes for a subgroup of individuals from the population of individuals, wherein the health condition attributes indicate that the subgroup of individuals from the population of individuals have in common a health condition that is found in a set of health-related conditions, wherein the genetic attributes are based on specific nucleotide sequences found in the population of individuals, and wherein the behavioral attributes are based on actions performed by the population of individuals;

obtaining, by the computing device and from a second database containing sets of the genetic attributes respectively associated with the health-related conditions, a set of the genetic attributes associated with the health condition, wherein a first correlation, calculated between (i) the set of the genetic attributes associated with the health condition and (ii) the health condition, has a first correlation value;

creating, by the computing device, a set of core genetic attributes based on a subset of the set of the genetic attributes associated with the health condition above a predetermined threshold;

clustering, by the computing device, attribute sub-combinations of the genetic and behavioral attributes for the subgroup of individuals, to form a particular attribute sub-combination of the genetic and behavioral attributes for the subgroup of individuals, wherein the particular attribute sub-combination has a second correlation value with the health condition that is higher than the first correlation value; and

generating, by the computing device, a combined set of attributes including the set of core genetic attributes and the particular attribute sub-combination.

8. The computer-implemented method of claim 7 , wherein the particular attribute sub-combination contains a behavioral attribute.

9. The computer-implemented method of claim 8 , further comprising:

transmitting a representation of the combined set of attributes to indicate that the behavioral attribute is associated with the health condition.

10. The computer-implemented method of claim 8 , wherein removal of the behavioral attribute from the combined set of attributes results in a lower risk of the health condition than with the behavioral attribute present in the combined set of attributes.

11. The computer-implemented method of claim 7 , wherein the particular attribute sub-combination contains a genetic attribute.

12. The computer-implemented method of claim 7 , further comprising:

transmitting a representation of the combined set of attributes to indicate that the particular attribute sub-combination is associated with the health condition.

13. A computer-implemented method comprising:

obtaining, by a computing device and from a first database containing genetic attributes, behavioral attributes, and health condition attributes for a population of individuals, the genetic attributes and the behavioral attributes for a subgroup of individuals from the population, wherein the health condition attributes indicate that the subgroup of individuals from the population have in common a health condition that is found in a set of health-related conditions, wherein the genetic attributes are based on specific nucleotide sequences found in the population of individuals, and wherein the behavioral attributes are based on actions performed by the population of individuals;

obtaining, by the computing device and from a second database containing sets of the genetic attributes respectively associated with the health-related conditions, a set of the genetic attributes associated with the health condition, wherein a first correlation, calculated between (i) the set of the genetic attributes associated with the health condition and (ii) the health condition, has a first correlation value;

creating, by the computing device, a set of core genetic attributes based on a subset of the set of the genetic attributes associated with the health condition above a predetermined threshold;

clustering, by the computing device, attribute sub-combinations of the behavioral attributes for the subgroup of individuals, to form a particular attribute sub-combination of the behavioral attributes for the subgroup of individuals, wherein the particular attribute sub-combination has a second correlation value with the health condition that is higher than the first correlation value; and

generating, by the computing device, a combined set of attributes including the set of core genetic attributes and the particular attribute sub-combination.

14. The computer-implemented method of claim 13 , wherein removal of a behavior attribute from the combined set of attributes results in a lower risk of the health condition than with the behavioral attribute present in the combined set of attributes.

15. The computer-implemented method of claim 14 , further comprising:

transmitting a representation of the behavioral attribute and an indication of the lower risk of the health condition based on the removal of the behavioral attribute from the combined set of attributes.

16. The computer-implemented method of claim 13 , further comprising:

transmitting a representation of the combined set of attributes to indicate that the particular attribute sub-combination is associated with the health condition.

17. The computer-implemented method of claim 13 , further comprising:

determining an increased risk for the health condition based on presence of the particular attribute sub-combination.

18. The computer-implemented method of claim 17 , further comprising:

transmitting a representation of the increased risk for the health condition based on the presence of the particular attribute sub-combination.

Assignments (8)
CORRECTIVE ASSIGNMENT TO CORRECT THE APP. NO. 63806415 TO 63806145 AND APPL NO. 17721779 TO 17731779 PREVIOUSLY RECORDED ON REEL 73168 FRAME 531. ASSIGNOR(S) HEREBY CONFIRMS THE CHANGE OF NAME. Recorded Jan 6, 2026
From: 23ANDME PGS LLC
To: 23ANDME GENOMICS LLC
Reel/Frame 074434/0334 →
CHANGE OF NAME Recorded Oct 22, 2025
From: 23ANDME PGS LLC
To: 23ANDME GENOMICS LLC
Reel/Frame 073168/0531 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 26, 2025
From: 23ANDME, INC.
To: 23ANDME PGS LLC
Reel/Frame 072562/0795 →
CORRECTIVE ASSIGNMENT TO CORRECT THE ASSIGNEE ADDRESS PREVIOUSLY RECORDED AT REEL: 058554 FRAME: 0021. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT . Recorded Jan 7, 2022
From: EXPANSE BIOINFORMATICS, INC.
To: 23ANDME, INC.
Reel/Frame 058982/0739 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 5, 2022
From: EXPANSE BIOINFORMATICS, INC.
To: 23ANDME, INC.
Reel/Frame 058554/0021 →
CHANGE OF ADDRESS BY ASSIGNEE Recorded Apr 5, 2021
From: EXPANSE BIOINFORMATICS, INC.
To: EXPANSE BIOINFORMATICS, INC.
Reel/Frame 055823/0714 →
CHANGE OF NAME Recorded Oct 5, 2018
From: EXPANSE NETWORKS, INC.
To: EXPANSE BIOINFORMATICS, INC.
Reel/Frame 047761/0662 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 5, 2018
From: KENEDY, ANDREW A.; ELDERING, CHARLES A.
To: EXPANSE NETWORKS, INC.
Reel/Frame 047080/0673 →
Continuity (5)
Continuation 15297208 · Oct 19, 2016
Continuation 13534952 · Jun 27, 2012
Continuation 12049332 · Mar 15, 2008
Provisional Application 60895236 · Mar 16, 2007
Related Publication 20190034163A1 · Jan 31, 2019