System, method and software arrangement utilizing a multi-strip procedure that can be applied to gene characterization using dna-array data

• US 20070100556A1
• Filed: 11/16/2004
• Published: 05/03/2007
• Est. Priority Date: 11/17/2003
• Status: Active Grant

• Current Assignee: New York University
• Original Assignee: Bud Mishra, Gilad Lerman, Joseph Mcquown
• Inventors: Mishra, Bud, Lerman, Gilad, McQuown, Joseph
• Granted Patent: US 7,957,908 B2
• Time in Patent Office: Days
• US Class Current: 702/19
• CPC Class Codes: G16B 25/00 ICT specially adapted for hybridisation; ICT specially adapted for gene or protein expression
• CPC Class Codes: G16B 25/10 Gene or protein expression profiling; Expression-ratio estimation or normalisation
• 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 40/10 Signal processing, e.g. from mass spectrometry [MS] or from PCR

Abstract

A system, method and software arrangement are provided that use a fast adaptive multiscale procedure to characterize a random set of points spanning a high dimensional Euclidean space, and concentrated around special lower dimensional subsets. The procedure can be adapted to analyze gene expression data from microarray experiments, and may be applied generally to existing datasets without regard to whether a particular model exists to otherwise describe the dataset. The procedure accordingly can be used for identifying and mathematically isolating stable sets of data points in a given dataset from those in the same dataset that deviate from a stable model under various conditions.

Claims

1. A process for identifying statistically-outlying data points in at least one dataset, comprising:

a) receiving the at least one dataset; and

b) identifying the statistically-outlying data points present in the at least one dataset based on the information contained in the at least one dataset.

2. The process of claim 1, wherein the at least one dataset comprises data associated with levels of gene expression obtained under two different conditions.

3. The process of claim 2, wherein the two different conditions reflect an occurrence of at least one of a physiological process, a pathophysiological process, an oncogenic process, a mutational process, a pharmacologically-induced process, an immuno-precipitation-induced process, and a developmental process.

4. The process of claim 1, further comprising one or more of the following steps:

c) storing the at least one dataset in a matrix;

d) shifting each row of the matrix by a center of mass of the at least one dataset;

e) computing a principal axis of the at least one dataset;

f) rotating the at least one dataset so that the principal axis coincides with x-axis; and

g) generating strip functions that define boundaries outside which the statistically-outlying data points in the at least one dataset are located.

5. The process of claim 4, wherein the at least one dataset comprises the set E={χ

_i}_i=1^N of N points in R^D.

6. The process of claim 4, wherein the strip functions that define boundaries that identify the statistically-outlying data points present in the at least one dataset are generated by computing a stopping point F_Q using a top-down procedure.

7. The process of claim 6, wherein the strip functions are smoothed by averaging of the strips generated from more than one determination.

8. The process of claim 6, wherein a stopping point in the computation of F_Q is set at Q′

∈

D(Q₀)) if F_Q′

>

α

₀.

9. The process of claim 6, wherein a stopping point in the computation of F_Q is set at Q′

∈

D(Q₀)) if |{tilde over (Q)}|<

n₀.

10. The process of claim 6, wherein a stopping point in the computation of F_Q is set at Q′

∈

D(Q₀)) if β

_{{tilde over (Q)}}>

δ

₀.

11. The process of claim 6, wherein a stopping point in the computation of F_Q is set at Q′

∈

D(Q₀)) if |{circumflex over (Q)}′

\{tilde over (Q)}|>

α

₁.|{tilde over (Q)}′

|.

12. The process of claim 6, wherein the stopping point in the computation of F_Q is applied twice.

40. The method of claim 1, wherein the at least one data set comprises data associated with financial trends.

13. A software arrangement operable by a processing arrangement for identifying the statistically-outlying data points present in at least one dataset based on the information contained in the at least one dataset, the software arrangement comprising:

a) a first set of instructions operable to configure the processing arrangement to receive the at least one dataset; and

b) a second set of instructions operable to configure the processing arrangement to identify the statistically-outlying data points present in the at least one dataset based on the information contained in the at least one dataset.

14. The software arrangement of claim 13, wherein the at least one dataset comprises data associated with levels of gene expression obtained under two different conditions.

15. The software arrangement of claim 14, wherein the two different conditions reflect an occurrence of at least one of a physiological process, a pathophysiological process, an oncogenic process, a mutational process, a pharmacologically-induced process, an immuno-precipitation-induced process, and a developmental process.

16. The software arrangement of claim 13, further comprising at least one of the instructions:

c) a third set of instructions operable to configure the processing arrangement to store the at least one dataset in a matrix;

d) a fourth set of instructions operable to configure the processing arrangement to shift each row of the matrix by a center of mass of the at least one dataset;

e) a fifth set of instructions operable to configure the processing arrangement to compute a principal axis of the at least one dataset;

f) a sixth set of instructions operable to configure the processing arrangement to rotate the at least one dataset so that the principal axis coincides with x-axis; and

g) a seventh set of instructions operable to configure the processing arrangement to generate strip functions that define boundaries outside which the statistically-outlying data points in the at least one dataset are located.

17. The software arrangement of claim 16, wherein the at least one dataset comprises a set E={χ

_i}_i=1^N of N points in R^D.

18. The software arrangement of claim 16, wherein the strip functions that define boundaries that identify the statistically-outlying data points present in the at least one dataset are generated by computing a stopping point F_Q using a top-down procedure.

19. The software arrangement of claim 18, wherein the strip functions are smoothed by averaging of the strips generated from more than one determination.

20. The software arrangement of claim 18, wherein the stopping point in the computation of F_Q is set at Q′

∈

D(Q₀)) if F_Q′

>

α

₀.

21. The software arrangement of claim 18, wherein the stopping point in the computation of F_Q is set at Q′

∈

D(Q₀)) if |{tilde over (Q)}|<

n₀.

22. The software arrangement of claim 18, wherein the stopping point in the computation of F_Q is set at Q′

∈

D(Q₀)) if β

_{{tilde over (Q)}}>

δ

₀.

23. The software arrangement of claim 18, wherein the stopping point in the computation of F_Q is set at Q′

∈

D(Q₀)) if |{circumflex over (Q)}′

\{tilde over (Q)}|>

α

₁.|{tilde over (Q)}′

|.

24. The software arrangement of claim 18, wherein the stopping point in the computation of F_Q is applied twice.

41. The software arrangement of claim 13, wherein the at least one data set comprises data associated with financial trends.

25. A storage medium which includes thereon a software arrangement to be executed by a:

processing arrangement for identifying the statistically-outlying data points present in the at least one dataset based on the information contained in the at least one dataset, the software arrangement comprising;

a) a first set of instructions operable to configure the processing arrangement to receive the at least one dataset; and

b) a second set of instructions operable to configure the processing arrangement to identify the statistically-outlying data points present in the at least one dataset based on the information contained in the at least one dataset.

26. The storage medium of claim 25, wherein the at least one dataset comprises data associated with levels of gene expression obtained under two different conditions.

27. The storage medium of claim 26, wherein the two different conditions reflect the occurrence of at least one of a physiological process, a pathophysiological process, an oncogenic process, a mutational process, a pharmacologically-induced process, an immuno-precipitation-induced process, and a developmental process.

28. The storage medium of claim 25, wherein the software arrangement further comprises at least one of the following instructions:

c) a third set of instructions operable to configure the processing arrangement to store the at least one dataset in a matrix;

d) a fourth set of instructions operable to configure the processing arrangement to shift each row of the matrix by a center of mass of the at least one dataset;

e) a fifth set of instructions operable to configure the processing arrangement to compute a principal axis of the at least one dataset;

f) a sixth set of instructions operable to configure the processing arrangement to rotate the at least one dataset so that the principal axis coincides with x-axis; and

g) a seventh set of instructions operable to configure the processing arrangement to generate strip functions that define boundaries outside which the statistically-outlying data points in the at least one dataset are located.

29. The storage medium of claim 28, wherein the at least one dataset comprises a set E={χ

_i}_i=1^N of N points in R^D.

30. The storage medium of claim 28, wherein the strip functions that define boundaries that identify the statistically-outlying data points present in the at least one dataset are generated by computing at stopping point F_Q using a top-down procedure.

31. The storage medium of claim 30, wherein the strip functions are smoothed by the averaging of the strips generated from more than one determination.

32. The storage medium of claim 30, wherein the stopping point in the computation of F_Q is set at Q′

∈

D(Q₀)) if F_Q′

>

α

₀.

33. The storage medium of claim 30, wherein the stopping point in the computation of F_Q is set at Q′

∈

D(Q₀)) if |{tilde over (Q)}|<

n₀.

34. The storage medium of claim 30, wherein the stopping point in the computation of F_Q is set at Q′

∈

D(Q₀)) if β

_{{tilde over (Q)}}>

δ

₀.

35. The storage medium of claim 30, wherein the stopping point in the computation of F_Q is set at Q′

∈

D(Q₀)) if |{circumflex over (Q)}′

\{tilde over (Q)}|>

α

₁.|{tilde over (Q)}′

|.

36. The storage medium of claim 30, wherein the stopping point in the computation of F_Q is applied twice.

42. The storage medium of claim 25, wherein the at least one data set comprises data associated with financial trends.

37. A system comprising:

a processing arrangement operably configured to;

a) receiving the at least one dataset; and

b) identifying the statistically-outlying data points present in the at least one dataset based on the information contained in the at least one dataset.

38. The system of claim 37, further comprising further processing arrangement configured to generate the at least one dataset.

39. The system of claim 38, further comprising a detector configured to detect a plurality of signals indicative of gene expression and convert the detected signals into the at least one dataset.