Patient-specific cellular pathway activity inference computer system

Patent metadata

Field	Value
Publication number	US-11355218-B2
Application number	US-201715667544-A
Country	US
Kind code	B2
Filing date	Aug 2, 2017
Priority date	Apr 29, 2010
Publication date	Jun 7, 2022
Grant date	Jun 7, 2022

Abstract

The present invention relates to methods for evaluating the probability that a patient's diagnosis may be treated with a particular clinical regimen or therapy.

First claim

What is claimed is:

1. A patient-specific cellular pathway activity inference computer system comprising:
a non-transitory computer readable medium storing measured attributes of tissue samples, the measured attributes including at least one of a copy number attribute, a gene expression attribute, or a protein attribute, and storing software instructions;
at least one processor coupled with the non-transitory computer readable medium and configured to execute the software instructions to:
(a) obtain a probabilistic pathway model representing a pathway network of a cellular process of cells, the probabilistic pathway model comprising a data structure of nodes connected by edges in a directed graph, wherein the directed graph includes influence levels representing biological pathway interactions as edges between nodes of biological elements of the directed graph, where the influence levels modify activity values of biological elements in the directed graph to provide activity values of subsequent nodes of biological elements in the directed graph;
(b) obtain data structures of directed graphs determined using the measured attributes of the tissue samples, wherein the directed graphs include the influence levels representing the biological pathway interactions as the edges between the nodes of the biological elements of the directed graphs, where the influence levels are shared across the directed graphs and modify activity values of the biological elements in the directed graphs to provide the activity values of the subsequent nodes of biological elements in the directed graphs;
(c) train the probabilistic pathway model representing the pathway network of the cellular process, the training comprising:
(i) incorporating the measured attributes for biological elements into the data structures as nodes in the directed graphs for the tissue samples, and
(ii) determining the influence levels of the probabilistic pathway model by iteratively changing the influence levels in the directed graphs for the tissue samples and obtaining the activity values in the directed graphs for the tissue samples until convergence of the activity values;

(d) estimate at least one assumed attribute in the probabilistic pathway model using measured attributes of a patient sample and the influence levels that are connected via edges in the probabilistic pathway model to the at least one assumed attribute, wherein a first biological element corresponds to a first protein;
(e) infer an integrated pathway activity for the first biological element for the patient sample based on at least one of the measured attributes other than for the first protein, a first influence level of a first biological pathway interaction of the first biological element of the probabilistic pathway model, and the estimated at least one assumed attribute that are connected via the edges in the probabilistic pathway model to the first biological element; and
(f) present, via a display, a numerical difference between the integrated pathway activity for the first protein for the patient sample and a second integrated pathway activity associated with one or more other patients.

2. The system of claim 1 , wherein the probabilistic pathway model incorporates the gene expression attribute as one of the measured attributes.

3. The system of claim 1 , wherein the other patients have known clinical outcomes, wherein the at least one processor is further configured to:
classify the patient as belonging to a cluster of the other patients based on the numerical difference, wherein the numerical difference between the integrated pathway activity for the patient sample and the second integrated pathway activity is presented with a predicted clinical outcome for the patient corresponding to the known clinical outcome of the cluster of the other patients.

4. The system of claim 1 , wherein the at least one processor is further configured to obtain the pathway network from a pathway interaction database.

5. The system of claim 1 , wherein the pathway network represents an endogenous entity.

6. The system of claim 5 , wherein the at least one processor is further configured to assign the endogenous entity a numeric state representing an activity level.

7. The system of claim 6 , wherein the activity level represents one of the following states: an activated state, a nominal activity state, and an inactive state.

8. The system of claim 1 , wherein the measured attributes incorporated into the probabilistic pathway model include at least one of the following: a mutation, a differential genetic sequence object, a gene copy number, a transcription level, a translation level, a protein activity, and protein interaction.

9. The system of claim 1 , wherein the at least one assumed attribute incorporated into the probabilistic pathway model include at least one of the following: a compound attribute, a class attribute, a gene copy number, a translation level, and a protein activity.

10. The system of claim 1 , wherein the probabilistic pathway model represents a transcription pathway network as the pathway network.

11. The system of claim 10 , wherein the transcription pathway network includes at least one of the following: FOXM1 transcription network, HIF-1 alpha transcription factor network, HIF-2 alpha transcription factor network, FOXA2 transcription factor network, and FOXA3 transcription factor network.

12. The system of claim 1 , wherein the numerical difference indicates an upregulated gene activity.

13. The system of claim 1 , wherein the numerical difference indicates a downregulated gene activity.

14. The system of claim 1 , wherein the numerical difference is with respect to tumor tissue and healthy tissue.

15. The system of claim 1 , wherein the estimated at least one assumed attribute is provided as an input to the first biological pathway interaction.

16. A computer-implemented method of using measurements of a patient sample if a patient for determining a patient-specific cellular pathway activity, the method comprising:
storing measured attributes of tissue samples, the measured attributes including at least one of a copy number attribute, a gene expression attribute, or a protein attribute;
obtaining a probabilistic pathway model representing a pathway network of a cellular process of cells, the probabilistic pathway model comprising a data structure of nodes connected by edges in a directed graph, wherein the directed graph includes influence levels representing biological pathway interactions as edges between nodes of biological elements of the directed graph, where the influence levels modify activity values of biological elements in the directed graph to provide activity values of subsequent nodes of biological elements in the directed graph;
obtain data structures of directed graphs determined using the measured attributes of the tissue samples, wherein the directed graphs include the influence levels representing the biological pathway interactions as the edges between the nodes of the biological elements of the directed graphs, where the influence levels are shared across the directed graphs and modify activity values of the biological elements in the directed graphs to obtain the activity values of the subsequent nodes of biological elements in the directed graphs;
training the probabilistic pathway model representing the pathway network of the cellular process, the training comprising:
(i) incorporating the measured attributes for biological elements into the data structures as nodes in the directed graphs for the tissue samples, and
(ii) determini

Assignees

• Univ California
• Thf Regents Of The Univ Of California

Inventors

• Vaske Charles J
• Benz Stephen C
• Stuart Joshua M
• Haussler David

Classifications

• G16B40/30

  Unsupervised data analysis · CPC title

• G16B5/00 Primary

  ICT specially adapted for modelling or simulations in systems biology, e.g. gene-regulatory networks, protein interaction networks or metabolic networks · CPC title

• G16B25/10

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

• G16B45/00

  ICT specially adapted for bioinformatics-related data visualisation, e.g. displaying of maps or networks · CPC title

• 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