METHOD AND APPARATUS FOR MULTI-PARAMETER DATA ANALYSIS

• US 20120035859A1
• Filed: 04/23/2010
• Published: 02/09/2012
• Est. Priority Date: 04/24/2009
• Status: Active Grant

• Current Assignee: Global Life Sciences Solutions Operations UK Ltd. (Danaher Corporation)
• Original Assignee: GE Healthcare UK Limited (Danaher Corporation)
• Inventors: Thomas, Nicholas
• Granted Patent: US 10,451,536 B2
• Time in Patent Office: Days
• US Class Current: 702/19
• CPC Class Codes: G01N 15/1429 Signal processing
• CPC Class Codes: G01N 15/1433 using image recognition
• CPC Class Codes: G01N 2015/1477 Multiparameters
• CPC Class Codes: G01N 2015/1497 Particle shape

Abstract

In one aspect, the present invention relates to a method 200 for identifying one or more phenotypes from a multi-parameter data set. The method 200 comprises measuring 202 correlation between pairs of parameters within the multi-parameter data set, modifying 204 correlated parameter values within a predetermined multi-parameter data analysis set to form an analysis parameter set, and analysing 206 the multi-parameter data set using the analysis parameter set to identify one or more phenotypes from the multi-parameter data set. Various embodiments of the present invention may, for example, be used in an automated high-content screening (HCS) apparatus 100 for biological cellular analysis.

Claims

1. A method (200) for identifying one or more phenotypes from a multi-parameter data set, the method comprising:

measuring (202) correlation between pairs of parameters within the multi-parameter data set;

modifying (204) correlated parameter values within a predetermined multi-parameter data analysis set to form an analysis parameter set; and

analysing (206) the multi-parameter data set using the analysis parameter set to identify one or more phenotypes from the multi-parameter data set.

2. The method (200) of claim 1, further comprising identifying one or more phenotypes from a plurality of multi-parameter data sets and comparing respective phenotypes from the multi-parameter data sets to identify variations therebetween.

3. The method (200) of claim 1, further comprising forming one or more respective analysis parameter sets for a plurality of multi-parameter data sets, and comparing the analysis parameter sets to determine whether or not a correlation relationship is maintained between the multi-parameter data sets.

4. The method (200) of claim 1, wherein correlation is determined by a non-parametric statistical pair-wise measurement made between the phenotypes in the predetermined multi-parameter data analysis set.

5. The method (200) of claim 4, wherein the non-parametric statistical pair-wise measurement comprises a Kolmogorov-Smimov (KS) distance measurement analysis.

6. The method (200) of claim 1, wherein modifying (204) correlated parameter values within the predetermined multi-parameter data analysis set comprises removing one of a pair of parameters whose correlation exceeds a predetermined threshold value from the analysis parameter set.

7. A computer program product comprising machine instructions operable to configure a data processing apparatus to implement the method (200) of claim 1.

8. An apparatus (100) for automated high-content screening (HCS) of one or more multi-parameter data sets, the apparatus (100) comprising a processor (114) that is operable to:

measure correlation between pairs of parameters within a multi-parameter data set;

modify correlated parameter values within a predetermined multi-parameter data analysis set for the multi-parameter data set to form an analysis parameter set; and

analyse the multi-parameter data set using the analysis parameter set to identify one or more phenotypes from the multi-parameter data set.

9. The apparatus (100) of claim 8, wherein the processor (114) is further operable to identify one or more phenotypes from a plurality of multi-parameter data sets and compare respective phenotypes from the multi-parameter data sets to identify variations therebetween.

10. The apparatus (100) of claim 8, wherein the processor (114) is further operable to form one or more respective analysis parameter sets for a plurality of multi-parameter data sets, and compare the analysis parameter sets to determine whether or not a correlation relationship is maintained between the multi-parameter data sets.

11. The apparatus (100) of claim 8, wherein the processor (114) is further operable to determine correlation by using a non-parametric statistical pair-wise measurement made between the phenotypes in the predetermined multi-parameter data analysis set.

12. The apparatus (100) of claim 11, wherein the non-parametric statistical pair-wise measurement comprises use of a Kolmogorov-Smirnov (KS) distance measurement analysis.

13. The apparatus (100) of claim 8, wherein the processor (114) is further operable to modify correlated parameter values by removing one of a pair of parameters whose correlation exceeds a predetermined threshold value from the analysis parameter set.