Systems and methods for identifying cancer treatments from normalized biomarker scores

• US 10,340,031 B2
• Filed: 06/12/2018
• Issued: 07/02/2019
• Est. Priority Date: 06/13/2017
• Status: Active Grant

• Current Assignee: Bostongene Corporation
• Original Assignee: Bostongene Corporation
• Inventors: Bagaev, Alexander, Frenkel, Feliks, Ataullakhanov, Ravshan
• Primary Examiner(s): Vanni, G Steven
• Application Number:
  US16/006,340
• Publication Number:
  US 20180358118A1
• Time in Patent Office: 385 Days
• Field of Search: None
• CPC Class Codes: C12Q 1/6886 for cancer immunoassay for cancer G01N33/574
• CPC Class Codes: C12Q 2600/156 Polymorphic or mutational markers
• CPC Class Codes: C12Q 2600/158 Expression markers
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 17/18 for evaluating statistical data , e.g. average values, frequency distributions, probability functions, regression analysis forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04
• CPC Class Codes: G16B 20/00 ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
• CPC Class Codes: G16B 25/10 Gene or protein expression profiling; Expression-ratio estimation or normalisation
• CPC Class Codes: G16B 30/00 ICT specially adapted for sequence analysis involving nucleotides or amino acids
• CPC Class Codes: G16B 40/00 ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
• CPC Class Codes: G16B 40/20 Supervised data analysis
• CPC Class Codes: G16B 40/30 Unsupervised data analysis
• CPC Class Codes: G16B 45/00 ICT specially adapted for bioinformatics-related data visualisation, e.g. displaying of maps or networks
• CPC Class Codes: G16B 5/00 ICT specially adapted for modelling or simulations in systems biology, e.g. gene-regulatory networks, protein interaction networks or metabolic networks
• CPC Class Codes: G16B 5/20 Probabilistic models
• CPC Class Codes: G16B 50/00 ICT programming tools or database systems specially adapted for bioinformatics
• CPC Class Codes: G16B 50/30 Data warehousing; Computing architectures
• CPC Class Codes: G16H 10/20 for electronic clinical trials or questionnaires
• CPC Class Codes: G16H 20/00 ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
• CPC Class Codes: G16H 20/10 relating to drugs or medications, e.g. for ensuring correct administration to patients
• CPC Class Codes: G16H 20/40 relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
• CPC Class Codes: G16H 50/20 : for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/30 : for calculating health indices; for individual health risk assessment
• CPC Class Codes: G16H 50/50 : for simulation or modelling of medical disorders
• CPC Class Codes: G16H 50/70 : for mining of medical data, e.g. analysing previous cases of other patients
• CPC Class Codes: G16H 70/20 : relating to practices or guidelines

Abstract

Techniques for determining therapy scores for at least two of an anti-PD1 therapy, an anti-CTLA4 therapy, an IL-2 therapy, an IFN alpha therapy, an anti-cancer vaccine therapy, an anti-angiogenic therapy, and an anti-CD20 therapy. The techniques include determining, using sequencing data for the subject and information indicating distribution of biomarker values across one or more reference populations, a first set of normalized biomarker scores for a first set of biomarkers associated with a first therapy; and a second set of normalized biomarker scores for a second set of biomarkers associated with a second therapy; providing the first set of normalized biomarker scores as input to a statistical model to obtain a first therapy score for the first therapy; and providing the second set of normalized biomarker scores as input to the statistical model to obtain a second therapy score for the second therapy.

Claims

1. A system, comprising:

at least one computer hardware processor;

at least one database that stores biomarker information; and

at least one non-transitory computer-readable storage medium storing processor-executable instructions that, when executed by the at least one computer hardware processor, cause the at least one computer hardware processor to perform;

obtaining sequencing data about at least one biological sample of a subject known to have or suspected of having cancerous cells or pre-cancerous cells;

accessing, in the at least one database, biomarker information indicating a distribution of values for each biomarker, across a respective group of people, in at least a reference subset of the plurality of biomarkers, each of the plurality of biomarkers being associated with at least one therapy in a plurality of therapies, the plurality of biomarkers including a first biomarker and the biomarker information including a distribution of values for the first biomarker;

determining, using both the sequencing data and the biomarker information;

a first set of normalized biomarker scores for a first set of biomarkers associated with a first therapy in the plurality of therapies,

a second set of normalized biomarker scores for a second set of biomarkers associated with a second therapy in the plurality of therapies, and

a third set of normalized biomarker scores for a third set of biomarkers associated with a third therapy in the plurality of therapies,

wherein the first set of biomarkers is different from the second set of biomarkers, and wherein determining the first set of normalized biomarker scores comprises determining a first normalized biomarker score for the first biomarker using the distribution of values for the first biomarker at least in part by;

determining an un-normalized score for the first biomarker using the sequencing data,

determining a Z-score based on the first distribution of values for the first biomarker, and

determining a normalized score for the first biomarker based on the un-normalized score and the Z-score; and

determining, using the first, second, and third sets of normalized biomarker scores and a statistical model, respective first, second, and third therapy scores for the first, second and third therapies;

wherein the plurality of therapies comprise at least three therapies selected from the group consisting of;

an anti-PD1 therapy, an anti-CTLA4 therapy, an IL-2 therapy, an IFN alpha therapy, an anti-cancer vaccine therapy, an anti-angiogenic therapy, and an anti-CD20 therapy, and

wherein the first, second, and third sets of biomarkers associated with the first, second and third each comprises at least three biomarkers selected from the group of biomarkers associated with the respective therapy in Table 2.

2. The system of claim 1, wherein determining the first therapy score for the first therapy comprises:

determining weights for two or more scores in the first set of normalized biomarker scores for the subject; and

determining the first therapy score as a sum of the two or more scores, with summands of the sum being weighted by the determined weights.

3. The system of claim 2, wherein determining the weights comprises determining the weights using a generalized linear model.

4. The system of claim 3, wherein determining the weights comprises determining the weights using a logistic regression model.

5. The system of claim 1, wherein the processor-executable instructions further cause the at least one processor to perform:

recommending at least one of the plurality of therapies for the subject based on the determined therapy scores.

6. The system of claim 5, wherein recommending the at least one of the plurality of therapies comprises:

ranking the plurality of therapies based on the determined therapy scores; and

recommending at least a threshold number of top-ranked therapies for the subject.

7. The system of claim 1, wherein the processor-executable instructions further cause the at least one processor to perform:

generating a graphical user interface (GUI) comprising;

a first portion associated with the first therapy in the plurality of therapies, the first portion including a first plurality of GUI elements, each of the first plurality of GUI elements being associated with a respective biomarker in the first set of biomarkers associated with the first therapy and having at least one visual characteristic determined based on a normalized score of the respective biomarker in the first set of normalized scores; and

a second portion associated with the second therapy in the plurality of therapies, the second portion including a second plurality of GUI elements different from the first plurality of GUI elements, each of the second plurality of GUI elements being associated with a respective biomarker in the second set of biomarkers associated with the second therapy and having at least one visual characteristic determined based on a normalized score of the respective biomarker in the second set of normalized scores; and

displaying the generated GUI.

8. The system of claim 7, wherein the at least one visual characteristic comprises color of a GUI element and/or size of the GUI element.

9. The system of claim 7, wherein the processor-executable instructions further cause the at least one processor to perform:

in response to receiving, via the GUI, a user selection of the first therapy, presenting, via the GUI, information about at least one biomarker with which at least one of the first plurality of GUI elements is associated.

10. The system of claim 7, wherein the first portion and the second portion are positioned, relative to one another in the GUI, based on relative magnitude of the first therapy score and the second therapy score.

11. The system of claim 1, wherein each of the plurality of biomarkers is selected from the group consisting of:

a genetic biomarker, a cellular biomarker, a saccharide biomarker, a lipid biomarker, a heterocyclic biomarker, an elementary compound biomarker, an imaging biomarker, an anthropological biomarker, a personal habit biomarker, a disease-state biomarker, and an expression biomarker.

12. The system of claim 1, wherein the first therapy score is indicative of response of the subject to administration of the first therapy.

13. The system of claim 1, wherein the statistical model comprises a linear model.

14. The system of claim 1, wherein the statistical model comprises a generalized linear model.

15. The system of claim 1, wherein the statistical model comprises a neural network model, a Bayesian regression model, an adaptive non-linear regression model, a mixture model, and/or a random forest regression model.

16. The system of claim 1, wherein the first, second, and third sets of biomarkers associated with the first, second and third each of the plurality of therapies each comprises at least five biomarkers selected from the group of biomarkers associated with the respective therapy in Table 2.

17. The system of claim 1, wherein the first, second, and third sets of biomarkers associated with the first, second and third each of the plurality of therapies each comprises at least ten biomarkers selected from the group of biomarkers associated with the respective therapy in Table 2.

18. At least one non-transitory computer-readable storage medium storing processor-executable instructions that, when executed by at least one computer hardware processor, cause the at least one computer hardware processor to perform:

obtaining sequencing data about at least one biological sample of a subject known to have or suspected of having cancerous cells or pre-cancerous cells;

accessing, in at least one database, biomarker information indicating a distribution of values for each biomarker, across a respective group of people, in at least a reference subset of the plurality of biomarkers, each of the plurality of biomarkers being associated with at least one therapy in a plurality of therapies, the plurality of biomarkers including a first biomarker and the biomarker information including a distribution of values for the first biomarker;

determining, using both the sequencing data and the biomarker information;

a first set of normalized biomarker scores for a first set of biomarkers associated with a first therapy in the plurality of therapies,

a second set of normalized biomarker scores for a second set of biomarkers associated with a second therapy in the plurality of therapies, and

a third set of normalized biomarker scores for a third set of biomarkers associated with a third therapy in the plurality of therapies,

wherein the first set of biomarkers is different from the second set of biomarkers, and

wherein determining the first set of normalized biomarker scores comprises determining a first normalized biomarker score for the first biomarker using the distribution of values for the first biomarker at least in part by;

determining an un-normalized score for the first biomarker using the sequencing data,

determining a Z-score based on the first distribution of values for the first biomarker, and

determining a normalized score for the first biomarker based on the un-normalized score and the Z-score; and

determining, using the first, second, and third sets of normalized biomarker scores and a statistical model, respective first, second, and third therapy scores for the first, second and third therapies;

wherein the plurality of therapies comprise at least three therapies selected from the group consisting of;

an anti-PD1 therapy, an anti-CTLA4 therapy, an IL-2 therapy, an IFN alpha therapy, an anti-cancer vaccine therapy, an anti-angiogenic therapy, and an anti-CD20 therapy, and

wherein the first, second, and third sets of biomarkers associated with the first, second and third each comprises at least three biomarkers selected from the group of biomarkers associated with the respective therapy in Table 2.

19. A method, comprising:

using at least one computer hardware processor to perform;

obtaining sequencing data about at least one biological sample of a subject known to have or suspected of having cancerous cells or pre-cancerous cells;

accessing, in at least one database, biomarker information indicating a distribution of values for each biomarker, across a respective group of people, in at least a reference subset of the plurality of biomarkers, each of the plurality of biomarkers being associated with at least one therapy in a plurality of therapies, the plurality of biomarkers including a first biomarker and the biomarker information including a distribution of values for the first biomarker;

determining, using both the sequencing data and the biomarker information;

a first set of normalized biomarker scores for a first set of biomarkers associated with a first therapy in the plurality of therapies,

a second set of normalized biomarker scores for a second set of biomarkers associated with a second therapy in the plurality of therapies, and

a third set of normalized biomarker scores for a third set of biomarkers associated with a third therapy in the plurality of therapies,

wherein the first set of biomarkers is different from the second set of biomarkers, and wherein determining the first set of normalized biomarker scores comprises determining a first normalized biomarker score for the first biomarker using the distribution of values for the first biomarker at least in part by;

determining an un-normalized score for the first biomarker using the sequencing data,

determining a Z-score based on the first distribution of values for the first biomarker, and

determining a normalized score for the first biomarker based on the un-normalized score and the Z-score; and

determining, using the first, second, and third sets of normalized biomarker scores and a statistical model, respective first, second, and third therapy scores for the first, second and third therapies;

wherein the plurality of therapies comprise at least three therapies selected from the group consisting of;

an anti-PD1 therapy, an anti-CTLA4 therapy, an IL-2 therapy, an IFN alpha therapy, an anti-cancer vaccine therapy, an anti-angiogenic therapy, and an anti-CD20 therapy, and

wherein the first, second, and third sets of biomarkers associated with the first, second and third each comprises at least three biomarkers selected from the group of biomarkers associated with the respective therapy in Table 2.

20. The method of claim 19, wherein the statistical model comprises a linear model.

21. The method of claim 19, wherein the statistical model comprises a generalized linear model.

22. The method of claim 19, wherein the statistical model comprises a neural network model, a Bayesian regression model, an adaptive non-linear regression model, a mixture model, and/or a random forest regression model.

23. The method of claim 19, wherein the first, second, and third sets of biomarkers associated with the first, second and third each of the plurality of therapies each comprises at least five biomarkers selected from the group of biomarkers associated with the respective therapy in Table 2.

24. The method of claim 19, wherein the first, second, and third sets of biomarkers associated with the first, second and third each of the plurality of therapies each comprises at least ten biomarkers selected from the group of biomarkers associated with the respective therapy in Table 2.