Computer system and methods for constructing biological classifiers and uses thereof

• US 7,991,557 B2
• Filed: 06/20/2005
• Issued: 08/02/2011
• Est. Priority Date: 06/19/2004
• Status: Expired due to Fees

• Current Assignee: Genenews Corporation
• Original Assignee: Genenews Corporation
• Inventors: Liew, Choong-Chin, Dempsey, Adam, Chao, Samuel, Yager, Thomas
• Primary Examiner(s): Lin; Jerry
• Application Number:
  US10/568,264
• Publication Number:
  US 20070269804A1
• Time in Patent Office: 2,234 Days
• Field of Search: 702/19
• US Class Current: 702/19
• CPC Class Codes: G16B 20/00 ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
• CPC Class Codes: G16B 20/20 Allele or variant detection, e.g. single nucleotide polymorphism [SNP] detection
• CPC Class Codes: G16B 20/40 Population genetics; Linkage disequilibrium
• 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: Y02A 90/10 Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Abstract

The present invention provides systems and method for constructing classifiers that distinguish between trait subgroups using molecular marker data from blood samples. The invention further encompasses the use of the classifiers and combinations of molecular markers identified by the classifiers in a wide variety of applications including: diagnosis; prognosis; prediction of disease, stage of disease or disease risk; monitoring disease progression and/or regression; monitoring disease reoccurrence and identifying risk of disease reoccurrence; determining and/or predicting response to treatment and/or treatment outcomes; monitoring and/or predicting treatment compliance or non compliance and the like. The invention further provides a variety of selected molecular markers and a means to identify combinations of the selected molecular markers useful for diagnosing particular traits of interest.

Claims

1. A method for profiling gene expression in a human test subject, the method comprising:

a) measuring a level of expression in a blood sample of said test subject of each gene of a set of genes consisting of heat shock protein 90 kDa alpha (cytosolic), class A member 1 (HSP90AA1);

inhibitor of kappa light polypeptide gene enhancer in B-cells, kinase complex-associated protein (IKBKAP);

interleukin 13 receptor, alpha 1 (IL13RA1);

laminin, gamma 1 (LAMC1);

v-maf musculoaponeurotic fibrosarcoma oncogene homolog B (MAFB); and

platelet factor 4 (PF4), thereby obtaining a sample dataset; and

b) applying a classifier to said sample dataset to thereby classify said test subject into a class representing human subjects having mild osteoarthritis or a class representing human subjects not having osteoarthritis, wherein said classifier is able to discriminate between human subjects having mild osteoarthritis and human subjects not having osteoarthritis, and wherein said classifier is derived from data representing a level of expression of each gene of said set of genes in blood samples of human subjects having mild osteoarthritis and in blood samples of human subjects not having osteoarthritis,

thereby profiling gene expression in a human test subject.

2. The method of claim 1, wherein said classifier is based on a multiple regression equation.

3. The method of claim 1, wherein said classifier has a format:

SCORE=−

1.839+0.8*HSP90AA1−

1.5525*IKBKAP+1.10184*IL13RA1+0.78923*LAMC1−

1.3974*MAFB+1.0602*PF4, where

SCORE, if positive, classifies said test subject into said class representing human subjects having mild osteoarthritis;

SCORE, if negative, classifies said test subject into said class representing human subjects not having osteoarthritis;

HSP90AA1 represents said level of expression of heat shock protein 90 kDa alpha cytosolic), class A member 1 (HSP90AA1) in said sample of said test subject;

IKBKAP represents said level of expression of inhibitor of kappa light polypeptide gene enhancer in B-cells, kinase complex-associated protein (IKBKAP) in said sample of said test subject;

IL13RA1 represents said level of expression of interleukin 13 receptor, alpha 1 (IL13RA1) in said sample of said test subject;

LAMC1 represents said level of expression of laminin, gamma in said sample of said test subject;

MAFB represents said level of expression of v-maf musculoaponeurotic fibrosarcoma oncogene homolog B (MAFB) in said sample of said test subject; and

PF4 represents said level of expression of platelet factor 4 (PF4) in said sample of said test subject.

4. The method of claim 1, wherein said applying said classifier to said sample dataset comprises using a computer programmed to apply said classifier to a dataset representing a level of expression of each gene of said set of genes in a blood sample of a human individual to thereby classify said human individual into said class representing human subjects having mild osteoarthritis or said class representing human subjects not having osteoarthritis.

5. The method of claim 4, wherein said classifier is based on a multiple regression equation.

6. The method of claim 4, wherein said classifier has a format:

SCORE=−

1.839+0.8*HSP90AA1−

1.5525*IKBKAP+1.10184*IL13RA1+0.78923*LAMC1−

1.3974*MAFB+1.0602*PF4, where

SCORE, if positive, classifies said test subject into said class representing human subjects having mild osteoarthritis;

SCORE, if negative, classifies said test subject into said class representing human subjects not having osteoarthritis;

HSP90AA1 represents said level of expression of heat shock protein 90 kDa alpha (cytosolic), class A member 1 (HSP90AA1) in said sample of said test subject;

IKBKAP represents said level of expression of inhibitor of kappa light polypeptide gene enhancer in B-cells, kinase complex-associated protein (IKBKAP) in said sample of said test subject;

IL13RA1 represents said level of expression of interleukin 13 receptor, alpha 1 (IL13RA1) in said sample of said test subject;

LAMC1 represents said level of expression of laminin, gamma 1 (LAMC1) in said sample of said test subject;

MAFB represents said level of expression of v-maf musculoaponeurotic fibrosarcoma oncogene homolog B (MAFB) in said sample of said test subject; and

PF4 represents said level of expression of platelet factor 4 (PF4) in said sample of said test subject.

7. A method for profiling gene expression in a human test subject, the method comprising:

a) obtaining a sample dataset representing a level of expression in a blood sample of said test subject of each gene of a set of genes consisting of heat shock protein 90 kDa alpha (cytosolic), class A member 1 (HSP90AA1);

inhibitor of kappa light polypeptide gene enhancer in B-cells, kinase complex-associated protein (IKBKAP);

interleukin 13 receptor, alpha 1 (IL13RA1);

laminin, gamma 1 (LAMC1);

v-maf musculoaponeurotic fibrosarcoma oncogene homolog B (MAFB); and

platelet factor 4 (PF4); and

b) using a computer, applying a classifier to said sample dataset to thereby classify said test subject into a class representing human subjects having mild osteoarthritis or a class representing human subjects not having osteoarthritis, wherein said classifier is able to discriminate between human subjects having mild osteoarthritis and human subjects not having osteoarthritis, wherein said classifier is derived from data representing a level of expression of each marker of said marker set in blood samples of human subjects having mild osteoarthritis and in blood samples of human subjects not having osteoarthritis, and wherein said computer is programmed to apply said classifier to a dataset representing a level of expression of each gene of said set of genes in a blood sample of a human individual to thereby classify said test individual into said class representing human subjects having mild osteoarthritis or said class representing human subjects not having osteoarthritis,

thereby profiling gene expression in a human test subject.

8. The method of claim 7, wherein said classifier is based on a multiple regression equation.

9. The method of claim 7, wherein said classifier has a format:

SCORE=−

1.839+0.8*HSP90AA1−

1.5525*IKBKAP+1.10184*IL13RA1+0.78923*LAMC1−

1.3974*MAFB+1.0602*PF4, where

SCORE, if positive, classifies said test subject into said class representing human subjects having mild osteoarthritis;

SCORE, if negative, classifies said test subject into said class representing human subjects not having osteoarthritis;

HSP90AA1 represents said level of expression of heat shock protein 90 kDa alpha (cytosolic), class A member 1 (HSP90AA1) in said sample of said test subject;

IKBKAP represents said level of expression of inhibitor of kappa light polypeptide gene enhancer in B-cells, kinase complex-associated protein (IKBKAP) in said sample of said test subject;

IL13RA1 represents said level of expression of interleukin 13 receptor, alpha 1 (IL13RA1) in said sample of said test subject;

LAMC1 represents said level of expression of laminin, gamma 1 (LAMC1) in said sample of said test subject;

MAFB represents said level of expression of v-maf musculoaponeurotic fibrosarcoma oncogene homolog B (MAFB) in said sample of said test subject; and

PF4 represents said level of expression of platelet factor 4 (PF4) in said sample of said test subject.

10. The method of claim 7, wherein said obtaining said sample dataset comprises measuring said level of expression of each gene of said set of genes in said blood sample of said test subject.

11. The method of claim 10, wherein said classifier is based on a multiple regression equation.

12. The method of claim 10, wherein said classifier has a format:

SCORE=−

1.839+0.8*HSP90AA1−

1.5525*IKBKAP+1.10184*IL13RA1+0.78923*LAMC1−

1.3974*MAFB+1.0602*PF4, where

SCORE, if positive, classifies said test subject into said class representing human subjects having mild osteoarthritis;

SCORE, if negative, classifies said test subject into said class representing human subjects not having osteoarthritis;

HSP90AA1 represents said level of expression of heat shock protein 90 kDa alpha (cytosolic), class A member 1 (HSP90AA1) in said sample of said test subject;

IKBKAP represents said level of expression of inhibitor of kappa light polypeptide gene enhancer in B-cells, kinase complex-associated protein (IKBKAP) in said sample of said test subject;

IL13RA1 represents said level of expression of interleukin 13 receptor, alpha 1 (IL13RA1) in said sample of said test subject;

LAMC1 represents said level of expression of laminin, gamma 1 (LAMC1) in said sample of said test subject;

MAFB represents said level of expression of v-maf musculoaponeurotic fibrosarcoma oncogene homolog B (MAFB) in said sample of said test subject; and

PF4 represents said level of expression of platelet factor 4 (PF4) in said sample of said test subject.

13. A method for profiling gene expression in a human test subject, the method comprising:

using a computer, applying a classifier to a sample dataset representing a level of expression in a blood sample of said test subject of each gene of a set of genes consisting of heat shock protein 90 kDa alpha (cytosolic), class A member 1 (HSP90AA1);

inhibitor of kappa light polypeptide gene enhancer in B-cells, kinase complex-associated protein (IKBKAP);

interleukin 13 receptor, alpha 1 (IL13RA1);

laminin, gamma 1 (LAMC1);

v-maf musculoaponeurotic fibrosarcoma oncogene homolog B (MAFB); and

platelet factor 4 (PF4), to thereby classify said test subject into a class representing human subjects having mild osteoarthritis or a class representing human subjects not having osteoarthritis,

wherein said classifier is able to discriminate between human subjects having mild osteoarthritis and human subjects not having osteoarthritis,

wherein said classifier is derived from data representing a level of expression of each marker of said marker set in blood samples of human subjects having mild osteoarthritis and in blood samples of human subjects not having osteoarthritis, and

wherein said computer is programmed to apply said classifier to a dataset representing a level of expression of each gene of said set of genes in a blood sample of a human individual to thereby classify said human individual into said class representing human subjects having osteoarthritis or said class representing human subjects not having osteoarthritis,

thereby profiling gene expression in a human test subject.

14. The method of claim 13, wherein said classifier is based on a multiple regression equation.

15. The method of claim 13, wherein said classifier has a format:

SCORE=−

1.839+0.8*HSP90AA1−

1.5525*IKBKAP+1.10184*IL13RA1+0.78923*LAMC1−

1.3974*MAFB+1.0602*PF4, where

SCORE, if positive, classifies said test subject into said class representing human subjects having mild osteoarthritis;

SCORE, if negative, classifies said test subject into said class representing human subjects not having osteoarthritis;

HSP90AA1 represents said level of expression of heat shock protein 90 kDa alpha (cytosolic), class A member 1 (HSP90AA1) in said sample of said test subject;

IKBKAP represents said level of expression of inhibitor of kappa light polypeptide gene enhancer in B-cells, kinase complex-associated protein (IKBKAP) in said sample of said test subject;

IL13RA1 represents said level of expression of interleukin 13 receptor, alpha 1 (IL13RA1) in said sample of said test subject;

LAMC1 represents said level of expression of laminin, gamma 1 (LAMC1) in said sample of said test subject;

MAFB represents said level of expression of v-maf musculoaponeurotic fibrosarcoma oncogene homolog B (MAFB) in said sample of said test subject; and

PF4 represents said level of expression of platelet factor 4 (PF4) in said sample of said test subject.

16. The method of claim 13, further comprising obtaining said sample dataset by measuring said level of expression of each gene of said set of genes in said blood sample of said test subject, prior to applying said classifier to said sample dataset.

17. The method of claim 16, wherein said classifier is based on a multiple regression equation.

18. The method of claim 16, wherein said classifier has a format:

SCORE=−

1.839+0.8*HSP90AA1−

1.5525*IKBKAP+1.10184*IL13RA1+0.78923*LAMC1−

1.3974*MAFB+1.0602*PF4, where

SCORE, if positive, classifies said test subject into said class representing human subjects having mild osteoarthritis;

SCORE, if negative, classifies said test subject into said class representing human subjects not having osteoarthritis;

HSP90AA1 represents said level of expression of heat shock protein 90 kDa alpha (cytosolic), class A member 1 (HSP90AA1) in said sample of said test subject;

IKBKAP represents said level of expression of inhibitor of kappa light polypeptide gene enhancer in B-cells, kinase complex-associated protein (IKBKAP) in said sample of said test subject;

IL13RA1 represents said level of expression of interleukin 13 receptor, alpha 1 (IL13RA1) in said sample of said test subject;

LAMC1 represents said level of expression of laminin, gamma 1 (LAMC1) in said sample of said test subject;

MAFB represents said level of expression of v-maf musculoaponeurotic fibrosarcoma oncogene homolog B (MAFB) in said sample of said test subject; and

PE4 represents said level of expression of platelet factor 4 (PF4) in said sample of said test subject.