# US 2025/0165502 A1 · Database and Data Processing System for Use with a Network-Based Personal Genetics Services Platform

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0165502 A1
- Document ID: US20250165502A1
- Status: Published application
- Kind: A1
- Application number: 19/025,524
- Filed: 2025-01-16
- Published: 2025-05-22
- Earliest claimed: 2011-11-23
- Assignees: 23andMe, Inc.
- Applicants: 23andMe, Inc.
- Inventors: Brian Thomas Naughton; Chuong Do; John Michael Macpherson
- Web page: https://patentgrep.com/patent/US20250165502A1

## CPC

- G06F 16/284: {Relational databases}
- G16B 20/00: ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
- G16B 20/10: Ploidy or copy number detection
- G16B 20/20: Allele or variant detection, e.g. single nucleotide polymorphism [SNP] detection
- G16B 50/00: ICT programming tools or database systems specially adapted for bioinformatics
- G16B 50/10: Ontologies; Annotations
- G16B 50/30: Data warehousing; Computing architectures
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G16H 50/30: for calculating health indices; for individual health risk assessment
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G16B: BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

Databases and data processing systems for use with a network-based personal genetics services platform may include member information pertaining to a plurality of members of the network-based personal genetics services platform. The member information may include genetic information, family history information, environmental information, and phenotype information of the plurality of members. A data processing system may determine, based at least in part on the member information, a model for predicting a phenotype from genetic information, family history information, and environmental information, wherein determining the model includes training the model using the member information pertaining to a set of the plurality of members. The data processing system may also receive a request from a questing member to predict a phenotype of interest, and apply an individual's genetic information, family history information, and environmental information to the model to obtain a prediction associated with the phenotype of interest for the requesting member.

## Claims

### Claim 1

A computer-implemented method comprising:
obtaining member information pertaining to a plurality of members of a networked platform, the member information comprising genetic information and family history information;
selecting a simplified model that predicts likelihoods of cancer in individuals from the plurality of members, wherein the simplified model was trained based at least in part on the member information but with the family history information omitted, wherein the simplified model is selected instead of a complex model that was trained based at least in part on the member information and the family history information, and wherein the simplified model is selected when any one following condition is true:
(i) the genetic information of an individual from the plurality of members indicates that the individual exhibits a deleterious gene mutation correlated with cancer,
(ii) the genetic information of the individual indicates that the individual does not exhibit the deleterious gene mutation and the genetic information of a father of the individual indicates that the father exhibits the deleterious gene mutation, or
(iii) the genetic information of the individual indicates that the individual does not exhibit the deleterious gene mutation, it is unknown whether the genetic information of the father indicates that the father exhibits the deleterious gene mutation, and the family history information of the individual indicates a threshold likelihood that the father exhibits the deleterious gene mutation; and
applying the genetic information of the individual to the simplified model to obtain a prediction of a likelihood that the individual will develop cancer.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the cancer is prostate cancer.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein the family history information of the individual includes phenotype information that characterizes other diseases and conditions of family members of the individual.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein at least some of the member information is collected through the networked platform.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, wherein the simplified model was trained based on performing machine learning on the genetic information of at least a portion of the plurality of members.

### Claim 6 (depends on 5)

The computer-implemented method of claim 5, wherein the simplified model was validated using the genetic information pertaining to a different portion of the plurality of members.

### Claim 7 (depends on 5)

The computer-implemented method of claim 5, wherein training the simplified model includes performing logistic regression on the member information of at least the portion of the plurality of members.

### Claim 8 (depends on 5)

The computer-implemented method of claim 5, wherein training the simplified model includes building a decision tree based on the member information of at least the portion of the plurality of members.

### Claim 9 (depends on 1)

The computer-implemented method of claim 1, wherein the simplified model accounts for genetic inheritance.

### Claim 10 (depends on 1)

The computer-implemented method of claim 1, wherein the simplified model accounts for a known relationship between the genetic information and likelihoods of cancer.

### Claim 11

A computing system comprising:
one or more processors;
memory; and
program instructions, stored in the memory, that upon execution by the one or more processors cause the computing system to perform operations comprising:
obtaining member information pertaining to a plurality of members of a networked platform, the member information comprising genetic information and family history information;
selecting a simplified model that predicts likelihoods of cancer in individuals from the plurality of members, wherein the simplified model was trained based at least in part on the member information but with the family history information omitted, wherein the simplified model is selected instead of a complex model that was trained based at least in part on the member information and the family history information, and wherein the simplified model is selected when any one following condition is true:
(i) the genetic information of an individual from the plurality of members indicates that the individual exhibits a deleterious gene mutation correlated with cancer,
(ii) the genetic information of the individual indicates that the individual does not exhibit the deleterious gene mutation and the genetic information of a father of the individual indicates that the father exhibits the deleterious gene mutation, or
(iii) the genetic information of the individual indicates that the individual does not exhibit the deleterious gene mutation, it is unknown whether the genetic information of the father indicates that the father exhibits the deleterious gene mutation, and the family history information of the individual indicates a threshold likelihood that the father exhibits the deleterious gene mutation; and
applying the genetic information of the individual to the simplified model to obtain a prediction of a likelihood that the individual will develop cancer.

### Claim 12 (depends on 11)

The computing system of claim 11, wherein the cancer is prostate cancer.

### Claim 13 (depends on 12)

The computing system of claim 12, wherein the family history information of the individual includes phenotype information that characterizes other diseases and conditions of family members of the individual.

### Claim 14

A non-transitory computer-readable medium, storing program instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations comprising:
obtaining member information pertaining to a plurality of members of a networked platform, the member information comprising genetic information and family history information;
selecting a simplified model that predicts likelihoods of cancer in individuals from the plurality of members, wherein the simplified model was trained based at least in part on the member information but with the family history information omitted, wherein the simplified model is selected instead of a complex model that was trained based at least in part on the member information and the family history information, and wherein the simplified model is selected when any one following condition is true:
(i) the genetic information of an individual from the plurality of members indicates that the individual exhibits a deleterious gene mutation correlated with cancer,
(ii) the genetic information of the individual indicates that the individual does not exhibit the deleterious gene mutation and the genetic information of a father of the individual indicates that the father exhibits the deleterious gene mutation, or
(iii) the genetic information of the individual indicates that the individual does not exhibit the deleterious gene mutation, it is unknown whether the genetic information of the father indicates that the father exhibits the deleterious gene mutation, and the family history information of the individual indicates a threshold likelihood that the father exhibits the deleterious gene mutation; and
applying the genetic information of the individual to the simplified model to obtain a prediction of a likelihood that the individual will develop cancer.

### Claim 15 (depends on 14)

The non-transitory computer-readable medium of claim 14, wherein the cancer is prostate cancer.

### Claim 16 (depends on 14)

The non-transitory computer-readable medium of claim 14, wherein the family history information of the individual includes phenotype information that characterizes other diseases and conditions of family members of the individual.

### Claim 17 (depends on 14)

The non-transitory computer-readable medium of claim 14, wherein the simplified model was trained based on performing machine learning on the genetic information of at least a portion of the plurality of members.

### Claim 18 (depends on 17)

The non-transitory computer-readable medium of claim 17, wherein training the simplified model includes performing logistic regression on the member information of at least the portion of the plurality of members.

### Claim 19 (depends on 17)

The non-transitory computer-readable medium of claim 17, wherein training the simplified model includes building a decision tree based on member information of at least the portion of the plurality of members.

### Claim 20 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the simplified model accounts for a known relationship between the genetic information and likelihoods of cancer.
