Rationalizing network predictions using similarity to known connections

Patent metadata

Field	Value
Publication number	US-10607074-B2
Application number	US-201715821063-A
Country	US
Kind code	B2
Filing date	Nov 22, 2017
Priority date	Nov 22, 2017
Publication date	Mar 31, 2020
Grant date	Mar 31, 2020

Abstract

Rationalization of network predictions using similarity to known connections is provided. In various embodiments, a graph is read. The graph comprises a plurality of nodes. Each of the plurality of nodes corresponds to an entity or property. The plurality of nodes is interconnected by a plurality of edges. Each edge corresponds to a relationship between connected nodes. A new edge in the graph is predicted. The new edge corresponds to a relationship between a first node and a second node. The first node corresponds to an entity and the second node corresponds to an entity or property. One or more additional nodes connected to the second node is located. The one or more additional nodes is scored according to its connections in common with the first node. One or more sources is provided to a user describing the connection between the one or more additional node and the second node.

First claim

What is claimed is:

1. A method comprising:
reading a graph comprising a plurality of nodes, each of the plurality of nodes corresponding to an entity or property, the plurality of nodes being interconnected by a plurality of edges, each edge corresponding to a relationship between connected nodes;
predicting a new edge in the graph, the new edge corresponding to a relationship between a first node and a second node, the first node corresponding to an entity and the second node corresponding to an entity or property;
locating one or more additional nodes connected to the second node;
scoring the one or more additional nodes according to its connections in common with the first node;
providing to a user one or more sources describing the connection between the one or more additional node and the second node.

2. The method of claim 1 , wherein the entities comprise a gene, a target, a disease condition, or a phenotype.

3. The method of claim 1 , wherein the relationships comprise acts-on or has-property.

4. The method of claim 1 , wherein the graph is represented as a matrix.

5. The method of claim 2 , wherein the matrix is a binary matrix.

6. The method of claim 1 , further comprising:
providing to the user one or more extracts of the one or more sources, the extracts describing the connection between the one or more additional node and the second node.

7. The method of claim 1 , further comprising: constructing the graph by textual analysis of existing literature.

8. The method of claim 1 , wherein scoring the one or more additional nodes comprises:
computing a probability of its connections in common with the first node.

9. The method of claim 8 , wherein computing the probability comprises computing a chi squared probability.

10. The method of claim 8 , wherein computing the probability comprises applying Fisher's exact test.

11. The method of claim 4 , wherein predicting the new edge in the graph comprises:
factorizing the matrix and computing a product matrix therefrom.

12. The method of claim 11 , wherein scoring the one or more additional nodes comprises:
locating non-zero values in the product matrix.

13. The method of claim 10 , wherein factorizing the matrix comprises applying alternating least squares matrix factorization.

14. A system comprising:
a computing node comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor of the computing node to cause the processor to perform a method comprising:
reading a graph comprising a plurality of nodes, each of the plurality of nodes corresponding to an entity or property, the plurality of nodes being interconnected by a plurality of edges, each edge corresponding to a relationship between connected nodes;
predicting a new edge in the graph, the new edge corresponding to a relationship between a first node and a second node, the first node corresponding to an entity and the second node corresponding to an entity or property;
locating one or more additional nodes connected to the second node;
scoring the one or more additional nodes according to its connections in common with the first node;
providing to a user one or more sources describing the connection between the one or more additional node and the second node.

15. A computer program product for providing context for predicted biologic connections, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform a method comprising:
reading a graph comprising a plurality of nodes, each of the plurality of nodes corresponding to an entity or property, the plurality of nodes being interconnected by a plurality of edges, each edge corresponding to a relationship between connected nodes;
predicting a new edge in the graph, the new edge corresponding to a relationship between a first node and a second node, the first node corresponding to an entity and the second node corresponding to an entity or property;
locating one or more additional nodes connected to the second node;
scoring the one or more additional nodes according to its connections in common with the first node;
providing to a user one or more sources describing the connection between the one or more additional node and the second node.

16. The computer program product of claim 15 , wherein the graph is represented as a matrix.

17. The computer program product of claim 15 , wherein computing the probability comprises computing a chi squared probability.

18. The computer program product of claim 16 , wherein predicting the new edge in the graph comprises:
factorizing the matrix and computing a product matrix therefrom.

19. The computer program product of claim 16 , wherein scoring the one or more additional nodes comprises:
locating non-zero values in the product matrix.

20. The computer program product of claim 18 , wherein factorizing the matrix comprises applying alternating least squares matrix factorization.

Assignees

• IBM

Inventors

• Lacoste Alix
• Spangler William S
• Wang Feng

Classifications

• G16B40/00

  ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding · CPC title

• G06F17/17

  Function evaluation by approximation methods, e.g. inter- or extrapolation, smoothing, least mean square method ({G06F17/18 takes precedence } ; interpolation for numerical control G05B19/18) · CPC title

• G06K9/6224

  Physics · mapped topic

• G06K9/6269

  Physics · mapped topic

• G06N7/005

  Physics · mapped topic