NOVEL GROUPS OF BIOMARKERS FOR DIAGNOSING ALZHEIMER'S DISEASE

• US 20110202284A1
• Filed: 02/10/2011
• Published: 08/18/2011
• Est. Priority Date: 02/10/2010
• Status: Abandoned Application

• Current Assignee: Rules-Based Medicine, Inc.
• Original Assignee: Rules-Based Medicine, Inc.
• Inventors: Kozma, Lynn, McReynolds, Cristopher, Rocke, David M., Wyss-Coray, Anton
• Application Number:
  US13/025,061
• Publication Number:
  US 20110202284A1
• Time in Patent Office: Days
• US Class Current: 702/19
• CPC Class Codes: G01N 2333/4737 C-reactive protein
• CPC Class Codes: G01N 2333/50 Fibroblast growth factors [FGF]
• CPC Class Codes: G01N 2333/523 Beta-chemokines, e.g. RANTES, I-309/TCA-3, MIP-1alpha, MIP-1beta/ACT-2/LD78/SCIF, MCP-1/MCAF, MCP-2, MCP-3, LDCF-1or LDCF-2
• CPC Class Codes: G01N 2333/7151 for tumor necrosis factor [TNF]; for lymphotoxin [LT]
• CPC Class Codes: G01N 2333/775 Apolipopeptides
• CPC Class Codes: G01N 2333/96494 Matrix metalloproteases, e. g. 3.4.24.7
• CPC Class Codes: G01N 2800/2821 Alzheimer
• CPC Class Codes: G01N 2800/60 Complex ways of combining multiple protein biomarkers for diagnosis
• CPC Class Codes: G01N 33/6896 Neurological disorders, e.g. Alzheimer's disease
• 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

Abstract

The inventors have discovered sets of proteinaceous biomarkers which can be measured in biological fluid samples to diagnosis or aid in the diagnosis of Alzheimer'"'"'s disease and distinguish AD samples from non-demented samples.

Claims

1. A method of aiding diagnosis of Alzheimer'"'"'s disease (“

AD”

), comprising;

a) measuring a level of each of at least three AD diagnosis biomarkers in a biological fluid sample in an individual, wherein the at least three AD diagnosis biomarkers are selected from the group consisting of;

ACE (angiotensin converting enzyme or CD143), alpha-1-antitrypsin, Apo AI (apolipoprotein AI), Apo CIII (apolipoprotein CIII), Apo E (apolipoprotein E), CRP (C-reactive protein), cortisol, FGF-4 (fibroblast growth factor-4), MCP-3 (monocyte chemotactic protein-3), MMP-9 (matrix metalloproteinase-9), and TRAIL R3 (Receptor-3 for Tumor necrosis factor-related apoptosis-inducing ligand)

b) implementing a scoring algorithm;

c) generating a score based on the measured levels of the AD diagnosis biomarkers; and

d) comparing the score with a cutoff score, wherein the diagnosis of AD is aided by determining whether the score is above, equal to, or below the cutoff score;

wherein the method has an accuracy of at least about 65% in classifying the individual as either having Alzheimer'"'"'s disease or nondemented.

3. The method of claim 1, wherein the set of AD diagnosis biomarkers comprises at least four AD diagnosis biomarkers, wherein the at least four AD diagnosis biomarkers are selected from the group consisting of:

ACE, alpha-1-antitrypsin, Apo AI, Apo CIII, Apo E, CRP, cortisol, FGF-4, MCP-3, MMP-9, and TRAIL R3.

4. The method of claim 1, wherein the set of AD diagnosis biomarkers comprises at least five AD diagnosis biomarkers, wherein the at least four AD diagnosis biomarkers are selected from the group consisting of:

ACE, alpha-1-antitrypsin, Apo AI, Apo CIII, Apo E, CRP, cortisol, FGF-4, MCP-3, MMP-9, and TRAIL R3.

5. The method of claim 1, wherein the set of AD diagnosis biomarkers comprises at least six AD diagnosis biomarkers, wherein the at least four AD diagnosis biomarkers are selected from the group consisting of:

ACE, alpha-1-antitrypsin, Apo AI, Apo CIII, Apo E, CRP, cortisol, FGF-4, MCP-3, MMP-9, and TRAIL R3.

6. The method of claim 1, wherein the set of AD diagosis biomakers comprises at least one of the following AD diagnosis biomarkers:

ACE, cortisol, Apo E, MCP-3, and MMP-9.

7. The method of claim 1, wherein the set of AD diagosis biomakers comprises at least two of the following AD diagnosis biomarkers:

ACE, cortisol, Apo E, MCP-3, and MMP-9.

8. The method of claim 1, wherein the set of AD diagosis biomakers comprises at least three of the following AD diagnosis biomarkers:

ACE, cortisol, Apo E, MCP-3, and MMP-9.

9. The method of claim 1, wherein the set of AD diagnosis biomarkers comprises a set shown in Table 3.

10. The method of claim 1, wherein the method has an accuracy of at least about 67% in classifying the individual as either having Alzheimer'"'"'s disease or nondemented.

11. The method of claim 1, wherein the method has an accuracy of at least about 69% in classifying the individual as either having Alzheimer'"'"'s disease or nondemented.

12. The method of claim 1, wherein the method has an accuracy of at least about 71% in classifying the individual as either having Alzheimer'"'"'s disease or nondemented.

13. The method of claim 1, wherein the cutoff score is generated by a scoring algorithm.

14. The method of claim 1, wherein the cutoff score is based on measured levels of the AD diagnosis biomarkers in a control population and a population having AD.

15. The method of claim 14, wherein the control population is a non-demented control (NDC) population.

16. The method of claim 14, wherein the control population is a healthy age-matched non-demented control (NDC) population.

17. The method of claim 1, wherein the biological fluid sample is a peripheral biological fluid sample.

18. The method of claim 17, wherein the peripheral biological fluid sample is blood, serum, or plasma.

19. The method of claim 1, wherein the individual is a human.

20. The method of claim 1, wherein the scoring algorithm comprises a method selected from the group consisting of:

Significance Analysis of Microarrays, Tree Harvesting, CART, MARS, Self Organizing Maps, Frequent Item Set, Bayesian networks, Prediction Analysis of Microarray (PAM), SMO, Simple Logistic Regression, Logistic Regression, Multilayer Perceptron, Bayes Net, Naï

ve Bayes, Naï

ve Bayes Simple, Naï

ve Bayes Up, IB1, Ibk, Kstar, LWL, AdaBoost, ClassViaRegression, Decorate, Multiclass Classifier, Random Committee, j48, LMT, NBTree, Part, Random Forest, Ordinal Classifier, Sparse Linear Programming (SPLP), Sparse Logistic Regression (SPLR), Elastic NET, Support Vector Machine, Prediction of Residual Error Sum of Squares (PRESS), and combinations thereof.

21. The method of claim 20, wherein the method comprises Logistic Regression.

22. The method of claim 1, wherein the scoring algorithm is implemented by a computer.

23. The method of claim 1, wherein the score is determined by the formula:

(e^sum)/(1+e^sum), wherein the sum is determined by the formula;

Intercept+Σ

Coefficient(AD diagnosis biomarker_i)*ln [AD diagnosis biomarker_i+0.005], wherein i is 1 to N, N is the number of AD diagnosis biomarkers used, and [AD diagnosis biomarker] is the actual measured level of an AD diagnosis biomarker.

24. The method of claim 1, wherein the measuring is performed by a sandwich antibody array assay.

25. The method of claim 1, wherein the score is combined with one or more cognitive assessment tools and/or clinical observations in making the diagnosis or in aiding the diagnosis of AD.

26. The method of claim 1, wherein the measured levels are obtained by measuring the levels of the AD diagnosis biomarkers in the sample.

27. The method of claim 1, wherein the measured levels are obtained from a third party.

2. A computer implemented method of diagnosing or aiding diagnosis of Alzheimer'"'"'s disease (“

AD”

) comprising;

a) implementing a scoring algorithm;

b) generating a score based on measured levels of a set of AD diagnosis biomarkers in a biological fluid sample in an individual; and

c) comparing the score with a cutoff score, wherein the diagnosis of AD is made or aided by determining whether the score is above, equal to, or below the cutoff score, wherein the set of AD diagnosis biomarkers comprises at least three AD diagnosis biomarkers, wherein the at least three AD diagnosis biomarkers are selected from the group consisting of;

ACE (angiotensin converting enzyme or CD

     143), alpha-1-antitrypsin, Apo AI (apolipoprotein AI), Apo CIII (apolipoprotein CIII), Apo E (apolipoprotein E), CRP (C-reactive protein), cortisol, FGF-4 (fibroblast growth factor-4), MCP-3 (monocyte chemotactic protein-3), MMP-9 (matrix metalloproteinase-9), and TRAIL R3 (Receptor-3 for Tumor necrosis factor-related apoptosis-inducing ligand), and wherein the method has an accuracy of at least about 65% in classifying the individual as either having Alzheimer'"'"'s disease or nondemented.