Method, apparatus and computer program product for providing a multi-omics framework for estimating temporal disease trajectories

Patent metadata

Field	Value
Publication number	US-12362069-B2
Application number	US-202117304066-A
Country	US
Kind code	B2
Filing date	Jun 14, 2021
Priority date	Jun 14, 2021
Publication date	Jul 15, 2025
Grant date	Jul 15, 2025

Abstract

Methods, apparatuses, systems, computing devices, computing entities, and/or the like are provided. An example method may include selecting at least one client profile data object from a plurality of client profile data objects; retrieving at least one initial transcriptome data object and at least one subsequent transcriptome data object associated with the at least one client profile data object; generating at least one dynamic multigraph data object based at least in part on the at least one initial transcriptome data object, the at least one subsequent transcriptome data object, and at least one clinical event data object; training a temporal graph network based at least in part on the at least one dynamic multigraph data object to generate a risk window prediction data object; and performing at least one data operation based at least in part on the risk window prediction data object.

First claim

The invention claimed is:

1. A system comprising memory and one or more processors communicatively coupled to the memory, the one or more processors configured to:
receive a first initial transcriptome data object, validated onset temporal metadata, and a first subsequent transcriptome data object related to a disease identifier and associated with a first client profile data object, wherein the first subsequent transcriptome data object is associated with a clinical event data object and the validated onset temporal metadata comprises a timestamp that indicates a clinically validated time that a disease corresponding to the disease identifier was determined to be onset for the first client profile data object;
receive a dynamic multigraph data object that corresponds to the disease identifier, wherein the dynamic multigraph data object comprises a plurality of nodes and a plurality of edges that correspond to a plurality of client profile data objects associated with the disease identifier;
store the first initial transcriptome data object, the validated onset temporal metadata, the first subsequent transcriptome data object, and the clinical even data object as one or more nodes of the plurality of nodes within the dynamic multigraph data object, wherein the dynamic multigraph data object comprises one or more time axes that are associated with a temporal progression of the disease and the one or more nodes are linked to one or more temporal identifiers positioned on the one or more time axes;
generate, using a temporal graph network (TGN) and based at least in part on the dynamic multigraph data object, a first risk window prediction data object that comprises an estimated lower bound metadata and an estimated upper bound metadata associated with the disease identifier;
train the TGN until a time associated with the validated onset temporal metadata falls between the estimated lower bound metadata and the estimate upper bound metadata of the first risk window prediction data object, wherein the TGN is trained by:
comparing the first risk window prediction data object with the time associated with the validated onset temporal metadata, and
responsive to the time failing to fall between the estimated lower bound metadata and the estimated upper bound metadata of the first risk window prediction data object, adjusting one or more parameters of the TGN and regenerating the first risk window prediction data object;

receive, via a user interface, an input that identifies a second client profile data object;
store a second initial transcriptome data object and a second subsequent transcriptome data object that correspond to the second client profile data object within the dynamic multigraph data object;
generate, using the TGN and based at least in part on the dynamic multigraph data object, a second risk window prediction data object; and
render, using the user interface, the second risk window prediction data object.

2. The system of claim 1 , wherein the first client profile data object is associated with a whole-genome sequence (WGS) data object comprising at least one of at least one polygenic risk score (PRS) metadata related to the disease identifier or at least one combined PRS and phenome-wide association study (PRS-PheWAS) metadata related to the disease identifier.

3. The system of claim 1 , wherein the first initial transcriptome data object comprises initial transcriptome metadata related to one or more particular tissues or cells associated with the disease identifier, and wherein the first subsequent transcriptome data object comprises subsequent transcriptome metadata related to the one or more particular tissues or cells associated with the disease identifier.

4. The system of claim 3 , wherein the first initial transcriptome data object comprises an initial single-cell ribonucleic acid (RNA) sequencing assay (scRNA-seq) metadata associated with the disease identifier, and wherein the first subsequent transcriptome data object comprises subsequent scRNA-seq assay metadata associated with the disease identifier.

5. The system of claim 3 , wherein the one or more processors are further configured to:
calculate differential expression metadata based at least in part on the first initial transcriptome data object and the first subsequent transcriptome data object; and
generate the dynamic multigraph data object based at least in part on the differential expression metadata.

6. The system of claim 1 , wherein the first client profile data object is associated with a whole-genome sequence (WGS) data object and the first initial transcriptome data object and the WGS data object are associated with an initial temporal identifier.

7. The system of claim 6 , wherein the first subsequent transcriptome data object and the clinical event data object are associated with a subsequent temporal identifier.

8. The system of claim 7 , wherein the one or more processors are further configured to:
generate the dynamic multigraph data object based further on the initial temporal identifier and the subsequent temporal identifier.

9. The system of claim 1 , wherein the one or more processors are further configured to:
transmit the first risk window prediction data object to a client computing entity.

10. A computer-implemented method comprising:
receiving, by one or more processors, a first initial transcriptome data object, validated onset temporal metadata, and a first subsequent transcriptome data object related to a disease identifier and associated with a first client profile data object, wherein the first subsequent transcriptome data object is associated with a clinical event data object and the validated onset temporal metadata comprises a timestamp that indicates a clinically validated time that a disease corresponding to the disease identifier was determined to be onset for the first client profile data object;
receiving, by the one or more processors, a dynamic multigraph data object that corresponds to the disease identifier, wherein the dynamic multigraph data object comprises a plurality of nodes and a plurality of edges that correspond to a plurality of client profile data objects associated with the disease identifier;
storing, by the one or more processors, the first initial transcriptome data object, the validated onset temporal metadata, the first subsequent transcriptome data object, and the clinical event data object as one or more nodes of the plurality of nodes within the dynamic multigraph data object, wherein the dynamic multigraph data object comprises one or more time axes that are associated with a temporal progression of the disease and the one or more nodes are linked to one or more temporal identifiers positioned on the one or more time axes;
generating, by the one or more processor, using a temporal graph network (TGN), and based at least in part on the dynamic multigraph data object, a first risk window prediction data object that comprises an estimate lower bound metadata and an estimate upper bound metadata associated with the disease identifier;
training, by the one or more processor, the TGN until a time associated with the validated onset temporal metadata falls between the estimated lower bound metadata and the estimate upper bound metadata of the first risk window prediction data object, wherein the TGN is trained by:
comparing the first risk window prediction data object with the time associated with the validated onset temporal metadata, and
responsive to the time failing to fall between the estimated lower bound metadata and the estimated upper bound metadata of the first risk window prediction data object, adjusting one or more parameters of the TGN and regenerating the f

Assignees

• Optum Services Ireland Ltd

Inventors

• Godden Paul J

Classifications

• G16H10/60

  for patient-specific data, e.g. for electronic patient records · CPC title

• G16B25/10

  Gene or protein expression profiling; Expression-ratio estimation or normalisation · CPC title

• G16B50/30

  Data warehousing; Computing architectures · CPC title

• G16H10/40

  for data related to laboratory analysis, e.g. patient specimen analysis · CPC title

• G16B40/20

  Supervised data analysis · CPC title