USING GAME THEORY IN IDENTIFYING COMPOUNDS THAT BIND TO TARGETS

• US 20140114581A1
• Filed: 02/28/2012
• Published: 04/24/2014
• Est. Priority Date: 02/28/2011
• Status: Abandoned Application

• Current Assignee: Carnegie Mellon University
• Original Assignee: Carnegie Mellon University
• Inventors: Langmead, Christopher J., Kamisetty, Hetunandan
• Application Number:
  US14/001,932
• Publication Number:
  US 20140114581A1
• Time in Patent Office: Days
• US Class Current: 702/19
• CPC Class Codes: G01N 33/566 using specific carrier or receptor proteins as ligand binding reagents where possible specific carrier or receptor proteins are classified with their target compounds
• CPC Class Codes: G16C 20/50 Molecular design, e.g. of drugs

Abstract

A method performed by one or more processing devices includes retrieving information indicative of compounds and mutations of a target; generating one or more predictions of binding affinities of the compounds to the mutations; generating a simulation for introducing at least one of the compounds in response to at least one of the mutations; identifying, based on an application of a game theory algorithm to the simulation and to the one or more predictions, an equilibrium of the simulation; and identifying, from the equilibrium, a subset of the compounds with an increased binding affinity to the mutations relative to other binding affinities of other of the compounds.

Claims

1. A method performed by one or more processing devices, comprising:

retrieving information indicative of compounds and mutations of a target;

generating one or more predictions of binding affinities of the compounds to the mutations;

generating a simulation for introducing at least one of the compounds in response to at least one of the mutations;

identifying, based on an application of a game theory algorithm to the simulation and to the one or more predictions, an equilibrium of the simulation; and

identifying, from the equilibrium, a subset of the compounds with an increased binding affinity to the mutations relative to other binding affinities of other of the compounds.

2. The method of claim 1, further comprising:

identifying, from the equilibrium, a distribution of probabilities that the mutations arise in response to the compounds.

3. The method of claim 1,

wherein the simulation comprises a game;

wherein the game comprises a target player and a compound player;

wherein the target player corresponds to a target;

wherein the compound player corresponds to an entity that generates compounds;

wherein the target player is associated with a first plurality of actions to be performed during execution of the game;

wherein at least one of the first plurality of actions comprises introducing a mutation into the game;

wherein the compound player is associated with a second plurality of actions to be formed during execution of the game;

wherein at least one of the second plurality of actions comprises introducing a compound into the game;

wherein execution of the game generates a utility for a compound-target pair resulting from at least one of the first plurality of actions and at least one of the second plurality of actions; and

wherein a utility is indicative of a binding affinity.

4. The method of claim 1,

wherein a compound comprises one or more of a drug, a combination of drugs, a nucleic acid, and a polymer;

and

wherein a target comprises one or more of a protein, an enzyme, and a nucleic acid.

5. The method of claim 1, wherein the equilibrium comprises a Correlated Equilibrium.

6. The method of claim 1, wherein the subset comprises a cocktail, and wherein the method further comprises:

identifying information indicative of a percentage of each compound in the subset to be included in the cocktail.

7. The method of claim 1, wherein generating the one or more predictions comprises:

applying a regression model to (i) properties of the compounds retrieved, and (ii) properties of the mutations retrieved;

wherein the regression model is associated with relationships among properties of known compounds, properties of known mutations, and binding affinities among the known compound and the known mutations.

8. One or more machine-readable media configured to store instructions that are executable by one or more processing devices to perform operations comprising:

retrieving information indicative of compounds and mutations of a target;

generating one or more predictions of binding affinities of the compounds to the mutations;

generating a simulation for introducing at least one of the compounds in response to at least one of the mutations;

identifying, based on an application of a game theory algorithm to the simulation and to the one or more predictions, an equilibrium of the simulation; and

identifying, from the equilibrium, a subset of the compounds with an increased binding affinity to the mutations relative to other binding affinities of other of the compounds.

9. The one or more machine-readable media of claim 8, wherein the operations further comprise:

identifying, from the equilibrium, a distribution of probabilities that the mutations arise in response to the compounds.

10. The one or more machine-readable media of claim 8,

wherein the simulation comprises a game;

wherein the game comprises a target player and a compound player;

wherein the target player corresponds to a target;

wherein the compound player corresponds to an entity that generates compounds;

wherein the target player is associated with a first plurality of actions to be performed during execution of the game;

wherein at least one of the first plurality of actions comprises introducing a mutation into the game;

wherein the compound player is associated with a second plurality of actions to be formed during execution of the game;

wherein at least one of the second plurality of actions comprises introducing a compound into the game;

wherein execution of the game generates a utility for a compound-target pair resulting from at least one of the first plurality of actions and at least one of the second plurality of actions; and

wherein a utility is indicative of a binding affinity.

11. The one or more machine-readable media of claim 8,

wherein a compound comprises one or more of a drug, a combination of drugs, a nucleic acid, and a polymer;

and

wherein a target comprises one or more of a protein, an enzyme, and a nucleic acid.

12. The one or more machine-readable media of claim 8, wherein the equilibrium comprises a Correlated Equilibrium.

13. The one or more machine-readable media of claim 8, wherein the subset comprises a cocktail, and wherein the operations further comprise:

identifying information indicative of a percentage of each compound in the subset to be included in the cocktail.

14. The one or more machine-readable media of claim 8, wherein generating the one or more predictions comprises:

applying a regression model to (i) properties of the compounds retrieved, and (ii) properties of the mutations retrieved;

wherein the regression model is associated with relationships among properties of known compounds, properties of known mutations, and binding affinities among the known compound and the known mutations.

15. An electronic system comprising:

one or more processing devices; and

one or more machine-readable media configured to store instructions that are executable by the one or more processing devices to perform operations comprising;

retrieving information indicative of compounds and mutations of a target;

generating one or more predictions of binding affinities of the compounds to the mutations;

generating a simulation for introducing at least one of the compounds in response to at least one of the mutations;

identifying, based on an application of a game theory algorithm to the simulation and to the one or more predictions, an equilibrium of the simulation; and

identifying, from the equilibrium, a subset of the compounds with an increased binding affinity to the mutations relative to other binding affinities of other of the compounds.

16. The electronic system of claim 15, wherein the operations further comprise:

identifying, from the equilibrium, a distribution of probabilities that the mutations arise in response to the compounds.

17. The electronic system of claim 15,

wherein the simulation comprises a game;

wherein the game comprises a target player and a compound player;

wherein the target player corresponds to a target;

wherein the compound player corresponds to an entity that generates compounds;

wherein the target player is associated with a first plurality of actions to be performed during execution of the game;

wherein at least one of the first plurality of actions comprises introducing a mutation into the game;

wherein the compound player is associated with a second plurality of actions to be formed during execution of the game;

wherein at least one of the second plurality of actions comprises introducing a compound into the game;

wherein execution of the game generates a utility for a compound-target pair resulting from at least one of the first plurality of actions and at least one of the second plurality of actions; and

wherein a utility is indicative of a binding affinity.

18. The electronic system of claim 15,

wherein a compound comprises one or more of a drug, a combination of drugs, a nucleic acid, and a polymer;

and

wherein a target comprises one or more of a protein, an enzyme, and a nucleic acid.

19. The electronic system of claim 15, wherein the equilibrium comprises a Correlated Equilibrium.

20. The electronic system of claim 15, wherein the subset comprises a cocktail, and wherein the operations further comprise:

identifying information indicative of a percentage of each compound in the subset to be included in the cocktail.

21. The electronic system of claim 15, wherein generating the one or more predictions comprises:

applying a regression model to (i) properties of the compounds retrieved, and (ii) properties of the mutations retrieved;

wherein the regression model is associated with relationships among properties of known compounds, properties of known mutations, and binding affinities among the known compound and the known mutations.