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

Patent metadata

Field	Value
Publication number	US-2022399120-A1
Application number	US-202117304066-A
Country	US
Kind code	A1
Filing date	Jun 14, 2021
Priority date	Jun 14, 2021
Publication date	Dec 15, 2022
Grant date	—

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

1 . An apparatus comprising at least one processor and at least one non-transitory memory comprising a computer program code, the at least one non-transitory memory and the computer program code configured to, with the at least one processor, cause the apparatus to:
select at least one client profile data object from a plurality of client profile data objects based at least in part on at least one whole-genome sequence (WGS) data object related to a disease identifier and associated with the at least one client profile data object; retrieve at least one initial transcriptome data object and at least one subsequent transcriptome data object related to the disease identifier and associated with the at least one client profile data object, wherein the at least one subsequent transcriptome data object is associated with at least one clinical event data object; generate 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 the at least one clinical event data object; train a temporal graph network (TGN) based at least in part on the at least one dynamic multigraph data object to generate a risk window prediction data object associated with the disease identifier; and perform at least one data operation based at least in part on the risk window prediction data object.

2 . The apparatus of claim 1 , wherein the at least one WGS data object comprises 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 apparatus of claim 1 , wherein the at least one initial transcriptome data object comprises at least one initial tissue-relevant transcriptome metadata associated with the disease identifier, wherein the at least one subsequent transcriptome data object comprises at least one subsequent tissue-relevant transcriptome metadata associated with the disease identifier.

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

5 . The apparatus of claim 3 , wherein the at least one non-transitory memory and the computer program code are configured to, with the at least one processor, cause the apparatus to:
calculate at least one differential expression metadata based at least in part on the at least one initial transcriptome data object and the at least one subsequent transcriptome data object, wherein the at least one non-transitory memory and the computer program code are configured to, with the at least one processor, cause the apparatus to generate the at least one dynamic multigraph data object based at least in part on the at least one differential expression metadata.

6 . The apparatus of claim 1 , wherein, for a client profile data object of the at least one client profile data object, a corresponding initial transcriptome data object of the at least one initial transcriptome data object and a corresponding WGS data object of the at least one WGS data object are associated with an initial temporal identifier.

7 . The apparatus of claim 6 , wherein, for the client profile data object of the at least one client profile data object, a corresponding subsequent transcriptome data object of the at least one subsequent transcriptome data object and a corresponding clinical event data object of the at least one clinical event data object are associated with a corresponding subsequent temporal identifier.

8 . The apparatus of claim 7 , wherein the at least one non-transitory memory and the computer program code are configured to, with the at least one processor, cause the apparatus to generate the at least one dynamic multigraph data object based further on the initial temporal identifier and the corresponding subsequent temporal identifier.

9 . The apparatus of claim 1 , wherein the risk window prediction data object comprises an estimated lower bound metadata and an estimated upper bound metadata associated with the disease identifier.

10 . The apparatus of claim 9 , wherein the at least one non-transitory memory and the computer program code are configured to, with the at least one processor, cause the apparatus to:
retrieve at least one validated onset temporal metadata associated with the at least one client profile data object and the disease identifier, wherein the at least one non-transitory memory and the computer program code are configured to, with the at least one processor, cause the apparatus to train the TGN based at least in part on the at least one validated onset temporal metadata.

11 . The apparatus of claim 1 , wherein, when performing the at least one data operation based at least in part on the risk window prediction data object, the at least one non-transitory memory and the computer program code are configured to, with the at least one processor, cause the apparatus to:
transmit the risk window prediction data object to a client computing entity.

12 . The apparatus of claim 1 , wherein the at least one non-transitory memory and the computer program code are configured to, with the at least one processor, cause the apparatus to:
retrieve a second initial transcriptome data object and a second subsequent transcriptome data object related to the disease identifier and associated with a second client profile data object of the at least one client profile data object, wherein the second subsequent transcriptome data object is associated with a second clinical event data object; generate a second dynamic multigraph data object based at least in part on the second initial transcriptome data object, the second subsequent transcriptome data object, and the second clinical event data object; and generate a second risk window prediction data object based at least in part on providing the second dynamic multigraph data object to the TGN.

13 . A computer-implemented method comprising:
selecting at least one client profile data object from a plurality of client profile data objects based at least in part on at least one whole-genome sequence (WGS) data object related to a disease identifier and associated with the at least one client profile data object; retrieving at least one initial transcriptome data object and at least one subsequent transcriptome data object related to the disease identifier and associated with the at least one client profile data object, wherein the at least one subsequent transcriptome data object is associated with at least one clinical event 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 the at least one clinical event data object; training a temporal graph network (TGN) based at least in part on the at least one dynamic multigraph data object to generate a risk window prediction data object associated with the disease identifier; and performing at least one data operation based at least in part on the risk window prediction data object.

14 . The computer-implemented method of claim 13 , wherein the at least one WGS data object comprises at least one of at least one polygenic risk score (PRS) metadata related to the

Assignees

• Optum Services Ireland Ltd

Inventors

• Godden Paul J

Classifications

• G16B50/30

  Data warehousing; Computing architectures · CPC title

• G16H50/30 Primary

  for calculating health indices; for individual health risk assessment · CPC title

• G16B25/10

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

• G16B40/20

  Supervised data analysis · CPC title

• G16H10/40

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