Quantum computing techniques for determining gene predictors in gene regulatory networks

Patent metadata

Field	Value
Publication number	US-2023197193-A1
Application number	US-202117645130-A
Country	US
Kind code	A1
Filing date	Dec 20, 2021
Priority date	Dec 20, 2021
Publication date	Jun 22, 2023
Grant date	—

Abstract

Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing health-related predictive data analysis. Certain embodiments of the present invention utilize systems, methods, and computer program products that perform health-related predictive data analysis by generating an optimal predictor set for a gene regulatory network using a quantum logic circuit that comprises one or more quantum logic subcircuits for each quantum processing unit that is associated with a quantum subcircuit and is configured to perform a conjunctive phase logic operation performed on each ancilla bit of a quantum subcircuit.

First claim

1 . A computer-implemented method for determining an optimal predictor set based at least in part on gene expression data for a plurality of genes, the computer-implemented method comprising:
identifying, using one or more processors and based at least in part on the gene expression data for the plurality of genes, a plurality of potential predictor sets for the target gene designation, wherein each potential predictor set is associated with one or more cross-temporal gene state transformation relationships; for each potential predictor set, using the one or more processors:
generating a conjunctive predictor set representation that describes a conjunction of one or more transformation relationship models associated with the one or more cross-temporal gene state transformation relationships;
for each transformation relationship model, generating a quantum processing unit that comprises: (i) a plurality of gene designation superposition qubits for a plurality of affected qubits of the cross-temporal gene transformation relationship that is associated with the transformation relationship model, and (ii) an ancilla qubit whose value is determined based at least in part on the plurality of gene designation superposition qubits;
generating a quantum logic circuit that: (i) comprises one or more quantum logic subcircuits for each quantum processing unit, and (ii) is configured to perform a conjunctive phase logic operation on each ancilla bit; and
generating an eligibility indicator for the potential predictor set based at least in part on an output of the conjunctive phase logic operation;
determining, using the one or more processors, the optimal predictor set based at least in part on each potential predictor set having an affirmative eligibility indicator; and performing, using the one or more processors, one or more prediction-based actions based at least in part on the optimal predictor set.

2 . The computer-implemented method of claim 1 , wherein generating the eligibility indicator for a particular potential predictor set comprises:
performing a Grover mirror operation based at least in part on the quantum logic subcircuit for the potential predictor set to generate hidden phase data for the particular potential predictor set; and generating the eligibility indicator for the particular potential predictor set based at least in part on the hidden phase data for the particular potential predictor set.

3 . The computer-implemented method of claim 2 , wherein:
the Grover mirror operations comprises one or more Grover mirror iterations each associated with an amplitude amplification iteration count, and each amplitude amplification iteration count for a particular Grover mirror iteration is determined based at least in part on historical execution data for the particular Grover mirror iteration.

4 . The computer-implemented method of claim 1 , wherein the quantum logic subcircuit further comprises, for each potential predictor set, an equivalent decoder subcircuit.

5 . The computer-implemented method of claim 1 , wherein each transformation relationship model is a disjunctive representation of a cross-temporal gene state transformation relationship that is associated with the transformation relationship model.

6 . The computer-implemented method of claim 1 , wherein determining the plurality of potential predictor sets comprises:
identifying a plurality of gene designations, wherein each gene designation is associated with a designated subset of the plurality of genes; for each gene designation, determining a gene designation predictor set, wherein: (i) each gene designation predictor set for a particular gene designation describes one or more gene designation predictors for the particular gene designation, and (ii) each gene designation predictor for the particular gene designation describes that a temporally precedent value of one or more temporally precedent gene designations affects a temporally subsequent value of the particular gene designation; and determining the plurality of potential predictor sets based at least in part on each gene designation predictor set.

7 . The computer-implemented method of claim 6 , wherein determining the plurality of potential predictor sets based at least in part on each gene designation predictor set comprises:
determining a plurality of gene designation predictor combinations, wherein each gene designation predictor combinations comprises one gene designation predictor from each gene designation predictor set; and determining each potential predictor set based at least in part on each gene designation predictor combination.

8 . The computer-implemented method of claim 6 , wherein determining the plurality of gene designations comprises:
for each gene, determining: (i) a cross-temporal gene state change frequency indicator across the gene expression data, and (ii) a co-state gene cluster of a qualified subset of the plurality of genes having an affirmative cross-temporal gene state change frequency indicator; and determining the plurality of gene designations based at least in part on each co-state gene cluster.

9 . An apparatus for determining an optimal predictor set based at least in part on gene expression data for a plurality of genes, 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, based at least in part on the gene expression data for the plurality of genes, a plurality of potential predictor sets for the target gene designation, wherein each potential predictor set is associated with one or more cross-temporal gene state transformation relationships; for each potential predictor set:
generate a conjunctive predictor set representation that describes a conjunction of one or more transformation relationship models associated with the one or more cross-temporal gene state transformation relationships;
for each transformation relationship model, generate a quantum processing unit that comprises: (i) a plurality of gene designation superposition qubits for a plurality of affected qubits of the cross-temporal gene transformation relationship that is associated with the transformation relationship model, and (ii) an ancilla qubit whose value is determined based at least in part on the plurality of gene designation superposition qubits;
generate a quantum logic circuit that: (i) comprises one or more quantum logic subcircuits for each quantum processing unit, and (ii) is configured to perform a conjunctive phase logic operation on each ancilla bit; and
generate an eligibility indicator for the potential predictor set based at least in part on an output of the conjunctive phase logic operation;
determine the optimal predictor set based at least in part on each potential predictor set having an affirmative eligibility indicator; and perform one or more prediction-based actions based at least in part on the optimal predictor set.

10 . The apparatus of claim 9 , wherein generating the eligibility indicator for a particular potential predictor set comprises:
performing a Grover mirror operation based at least in part on the quantum logic subcircuit for the potential predictor set to generate hidden phase data for the particular potential predictor set; and generating the eligibility indicator for the particular potential predictor set based at least in part on the hidden phase data for the particular potential predictor set.

11 . The apparatus of claim 10 , wherein:
the Grover mirror operations comprises one or more Grover mirror iterations each associated

Assignees

• Optum Services Ireland Ltd

Inventors

• Sathaye Ninad D
• Godden Paul J
• Del Pino Ruiz Vicente Ruben
• Versaggi Matthew R

Classifications

• G16H50/20

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title

• G06N10/60

  Quantum algorithms, e.g. based on quantum optimisation, quantum Fourier or Hadamard transforms · CPC title

• G06N10/20

  Models of quantum computing, e.g. quantum circuits or universal quantum computers · CPC title

• G16B25/10 Primary

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

• G16H50/30

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