# US 2021/0343362 A1 · Cross-variant polygenic predictive data analysis

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

- Number: US 2021/0343362 A1
- Document ID: US20210343362A1
- Status: Published application
- Kind: A1
- Application number: 16/863,403
- Filed: 2020-04-30
- Published: 2021-11-04
- Earliest claimed: 2020-04-30
- Assignees: Optum Services (Ireland) Limited
- Applicants: Optum Services ( Ireland) Limited
- Inventors: Kenneth Bryan; Megan O'Brien; David S. Monaghan; Chirag Chadha
- Web page: https://patentgrep.com/patent/US20210343362A1

## CPC

- G16H 50/30: for calculating health indices; for individual health risk assessment
- G06F 17/18: for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)}
- G06F 18/211: Selection of the most significant subset of features
- G06F 18/22: Matching criteria, e.g. proximity measures
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06N 20/00: Machine learning
- G16B 40/00: ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
- G16B 20/20: Allele or variant detection, e.g. single nucleotide polymorphism [SNP] detection
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G16B: BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY

## Abstract

There is a need for more effective and efficient predictive data analysis solutions for processing genetic sequencing data. This need can be addressed by, for example, techniques for performing predictive data analysis based on genetic sequences that utilize at least one of cross-variant polygenic risk modeling using genetic risk profiles, cross-variant polygenic risk modeling using functional genetic risk profiles, per-condition polygenic clustering operations, cross-condition polygenic predictive inferences, and cross-condition polygenic diagnoses.

## Claims

### Claim 1

A computer-implemented for cross-condition polygenic predictive inference for a primary medical condition and a secondary medical condition, the computer-implemented method comprising:
identifying one or more primary cross-variant polygenic risk data objects for the primary medical condition;
identifying one or more secondary cross-variant polygenic risk data objects for the secondary medical condition;
generating a cross-condition polygenic similarity measure between the primary medical condition and the secondary medical condition based on comparing the one or more primary cross-variant polygenic risk data objects and the one or more secondary cross-variant polygenic risk data objects; and
performing a prediction-based action based on the cross-condition polygenic similarity measure.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein:
the one or more primary cross-variant polygenic risk data objects comprise a primary genetic risk profile associated with a primary individual; and
the one or more secondary cross-variant polygenic risk data objects comprise a secondary genetic risk profile associated with a secondary individual.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, wherein:
the primary genetic risk profile describes one or more primary per-variant genetic risk scores for a primary set of correlated genetic variants for the primary individual with respect to the target medical condition in accordance with a primary chromosome-based grouping of the primary set of correlated genetic variants; and
the secondary genetic risk profile describes one or more secondary per-variant genetic risk scores for a secondary set of correlated genetic variants for the secondary individual with respect to the target medical condition in accordance with a secondary chromosome-based grouping of the secondary set of correlated genetic variants.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein:
the one or more primary cross-variant polygenic risk data objects comprise a primary functional genetic risk profile associated with a primary individual; and
the one or more secondary cross-variant polygenic risk data objects comprise a secondary functional genetic risk profile associated with a secondary individual.

### Claim 5 (depends on 4)

The computer-implemented method of claim 4, wherein:
the primary functional genetic risk profile describes one or more primary per-variant genetic risk scores for a primary set of correlated genetic variants for the primary individual with respect to the target medical condition in accordance with a primary functional-grouping-based grouping of the primary set of correlated genetic variants; and
the secondary functional genetic risk profile describes one or more secondary per-variant genetic risk scores for a secondary set of correlated genetic variants for the secondary individual with respect to the target medical condition in accordance with a secondary functional-grouping-based grouping of the secondary set of correlated genetic variants.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein generating cross-condition polygenic similarity measure comprises:
for each object pair of a plurality of object pairs that comprises a primary cross-variant polygenic risk data object of the one or more primary cross-variant polygenic risk data objects and a secondary cross-variant polygenic risk data object of the one or more secondary cross-variant polygenic risk data objects, determining a pairwise polygenic similarity measure of a plurality of pairwise polygenic similarity measures; and
generating the cross-condition polygenic similarity measure based on each pairwise polygenic similarity measure of the plurality of pairwise polygenic similarity measures.

### Claim 7 (depends on 6)

The computer-implemented method of claim 6, wherein determining the pairwise polygenic similarity measure for a particular object pair comprises:
determining an intersectional variant count of the primary cross-variant polygenic risk data object in the object pair and the secondary cross-variant polygenic risk data object in the object pair;
determining a maximal variant count of the primary cross-variant polygenic risk data object in the object pair and the secondary cross-variant polygenic risk data object in the object pair; and
determining the pairwise polygenic similarity measure based on the intersectional variant count and the maximal variant count.

### Claim 8 (depends on 6)

The computer-implemented method of claim 6, wherein determining the pairwise polygenic similarity measure for a particular object pair comprises:
determining an intersectional variant count of the primary cross-variant polygenic risk data object in the object pair and the secondary cross-variant polygenic risk data object in the object pair;
determining a minimal variant count of the primary cross-variant polygenic risk data object in the object pair and the secondary cross-variant polygenic risk data object in the object pair; and
determining the pairwise polygenic similarity measure based on the intersectional variant count and the minimal variant count.

### Claim 9 (depends on 6)

The computer-implemented method of claim 6, wherein determining the pairwise polygenic similarity measure for a particular object pair comprises:
determining an intersectional variant count of the primary cross-variant polygenic risk data object in the object pair and the secondary cross-variant polygenic risk data object in the object pair;
determining a union variant count of the primary cross-variant polygenic risk data object in the object pair and the secondary cross-variant polygenic risk data object in the object pair; and
determining the pairwise polygenic similarity measure based on the intersectional variant count and the union variant count.

### Claim 10 (depends on 6)

The computer-implemented method of claim 6, wherein determining the pairwise polygenic similarity measure for a particular object pair comprises:
identifying a plurality of genetic variants each associated with at least one of the primary cross-variant polygenic risk data object in the object pair and the secondary cross-variant polygenic risk data object in the object pair;
selecting a comparative variant subset of the plurality of genetic variants;
for each genetic variant in the comparative variant subset, determining a per-variant pairwise polygenic similarity measure based on comparing a primary per-variant genetic risk score for the genetic variant inferred from the primary cross-variant polygenic risk data object and a secondary per-variant genetic risk score for the genetic variant inferred from the secondary cross-variant polygenic risk data object; and
determining the pairwise polygenic similarity measure based on each per-variant pairwise polygenic similarity measure for a genetic variant in the comparative variant subset.

### Claim 11 (depends on 10)

The computer-implemented method of claim 10, wherein selecting the comparative variant subset comprises adopting the plurality of genetic variants as the comparative variant sub set.

### Claim 12 (depends on 10)

The computer-implemented method of claim 10, wherein selecting the comparative variant subset comprises adopting an intersectional variant set of the primary cross-variant polygenic risk data object in the object pair and the secondary cross-variant polygenic risk data object in the object pair as the comparative variant subset.

### Claim 13 (depends on 10)

The computer-implemented method of claim 10, wherein selecting the comparative variant subset comprises adopting a symmetric difference variant set of the primary cross-variant polygenic risk data object in the object pair and the secondary cross-variant polygenic risk data object in the object pair as the comparative variant subset.

### Claim 14 (depends on 1)

The computer-implemented method of claim 1, wherein performing the one or more prediction-based actions comprises:
determining whether the cross-condition polygenic similarity measure exceeds a cross-condition polygenic similarity threshold, and
in response to determining that the cross-condition polygenic similarity measure exceeds the cross-condition polygenic similarity threshold, generating an inferred drug prescription profile of the secondary medical condition based on an existing drug prescription profile of the primary medical condition.

### Claim 15

An apparatus for cross-condition polygenic predictive inference for a primary medical condition and a secondary medical condition, the apparatus comprising at least one processor and at least one memory including program code, the at least one memory and the program code configured to, with the processor, cause the apparatus to at least:
identify one or more primary cross-variant polygenic risk data objects for the primary medical condition;
identify one or more secondary cross-variant polygenic risk data objects for the secondary medical condition;
generate a cross-condition polygenic similarity measure between the primary medical condition and the secondary medical condition based on comparing the one or more primary cross-variant polygenic risk data objects and the one or more secondary cross-variant polygenic risk data objects; and
perform a prediction-based action based on the cross-condition polygenic similarity measure.

### Claim 16 (depends on 15)

The apparatus of claim 15, wherein:
the one or more primary cross-variant polygenic risk data objects comprise a primary genetic risk profile associated with a primary individual; and
the one or more secondary cross-variant polygenic risk data objects comprise a secondary genetic risk profile associated with a secondary individual.

### Claim 17 (depends on 16)

The apparatus of claim 16, wherein:
the primary genetic risk profile describes one or more primary per-variant genetic risk scores for a primary set of correlated genetic variants for the primary individual with respect to the target medical condition in accordance with a primary chromosome-based grouping of the primary set of correlated genetic variants; and
the secondary genetic risk profile describes one or more secondary per-variant genetic risk scores for a secondary set of correlated genetic variants for the secondary individual with respect to the target medical condition in accordance with a secondary chromosome-based grouping of the secondary set of correlated genetic variants.

### Claim 18 (depends on 15)

The apparatus of claim 15, wherein:
the one or more primary cross-variant polygenic risk data objects comprise a primary functional genetic risk profile associated with a primary individual; and
the one or more secondary cross-variant polygenic risk data objects comprise a secondary functional genetic risk profile associated with a secondary individual.

### Claim 19 (depends on 18)

The apparatus of claim 18, wherein:
the primary functional genetic risk profile describes one or more primary per-variant genetic risk scores for a primary set of correlated genetic variants for the primary individual with respect to the target medical condition in accordance with a primary functional-grouping-based grouping of the primary set of correlated genetic variants; and
the secondary functional genetic risk profile describes one or more secondary per-variant genetic risk scores for a secondary set of correlated genetic variants for the secondary individual with respect to the target medical condition in accordance with a secondary functional-grouping-based grouping of the secondary set of correlated genetic variants.

### Claim 20

A computer program product for cross-condition polygenic predictive inference for a primary medical condition and a secondary medical condition, the computer program product comprising at least one non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions configured to:
identify one or more primary cross-variant polygenic risk data objects for the primary medical condition;
identify one or more secondary cross-variant polygenic risk data objects for the secondary medical condition;
generate a cross-condition polygenic similarity measure between the primary medical condition and the secondary medical condition based on comparing the one or more primary cross-variant polygenic risk data objects and the one or more secondary cross-variant polygenic risk data objects;
perform the cross-condition polygenic predictive inference based on the cross-condition polygenic similarity measure to generate a cross-condition polygenic prediction; and
perform a prediction-based action based on the cross-condition polygenic similarity measure.
