Application US20190018929

Predictive Test for Melanoma Patient Benefit from Interleukin-2 (IL2) Therapy
[+] Show Details

US20190018929

1. A method for detecting class labels in a melanoma patient, comprising the steps of: (3) (5)

a) performing mass spectrometry on a blood-based sample of the patient and obtaining mass spectrometry data of the sample;

b) performing a classification of the mass spectrometry data with the aid of a computer implementing a classifier, wherein the classifier is developed from a development set of samples from melanoma patients treated with the high dose IL2 therapy and consists of a hierarchical combination of classifiers 1 and 2,

wherein classifier 1 is developed from the development set of samples and a set of mass spectral features identified as being associated with an acute response biological function and generates either an Early class label and a Late class label, or the equivalent,

and wherein classifier 2 is developed from a subset of samples in the development set classified as Late by classifier 1 and also generates an Early class label and a Late class label or the equivalent,

wherein class labels are detected for the patient.

2. The method of claim 1, wherein Classifier 1 and Classifier 2 use the features for performing classification of the sample recited in Appendix B or a subset thereof. (0)

7. The method of claim 1, wherein classifier 1 and classifier 2 are developed using the procedure of FIG. 7A-7B. (0)

12. A method of detecting class labels for a melanoma patient comprising performing the method of claim 1, as well as classifying the sample of the patient with a classifier developed from mass spectral data of a set of blood based samples obtained from melanoma patients treated with an anti-PD-1 drug to generate a class label, wherein class labels are detected. (0)

3. A method for detecting a class label in a melanoma, comprising the steps of: (1) (3)

a) performing mass spectrometry on a blood-based sample of the patient and obtaining mass spectrometry data of the sample;

b) performing a classification of the mass spectrometry data with the aid of a computer implementing a classifier 2, wherein the classifier 2 is developed from a subset of a development set of samples from melanoma patients treated with the high dose IL2 therapy which have been classified as Late or the equivalent by a classifier 1 using a set of mass spectral features identified as being associated with an acute response biological function;

wherein class labels are detected for the patient.

4. The method of claim 3, wherein Classifier 2 uses the features for performing classification of the sample recited in Appendix B or a subset thereof. (0)

5. A classifier development method comprising the steps of: (2) (7)

a) obtaining a development set of blood-based samples from a population of melanoma patients in advance of treatment with high dose IL2 therapy;

b) performing mass spectrometry on the development set of samples;

c) with the aid of a computer developing a first classifier using a set of mass spectral features which are associated with an acute response biological function, the first classifier generating a class label of either early or late or the equivalent;

d) classifying the development set of samples with the first classifier;

e) selecting a subset of the samples which are classified as Late by the first classifier;

f) with the aid of the computer, developing a second classifier using the subset selected in step e) as the development set of the second classifier, the second classifier generating a class label of early or late or the equivalent; and

g) defining a final classification schema which combines the first classifier and the second classifier.

6. The method of claim 5, wherein the first and second classifiers use features for classification recited in Appendix B or a subset thereof. (0)

8. The method of claim 5 wherein the first and second classifiers are developed using the procedure of FIGS. 7A-7B. (0)

9. (canceled) (0)

10. (canceled) (0)

11. (canceled) (0)

13. A method of detecting a class label for a melanoma patient on high dose IL2 therapy by performing a classification of the sample with a classifier developed from mass spectral data of a set of blood based samples obtained from melanoma patients treated with an anti-PD-1 drug, the classifier generating a class label of Late or the equivalent and Early or the equivalent, wherein a class label is detected. (0)

14. A method of detecting a class label for a melanoma patient on high dose IL2 therapy by performing a classification of the sample with a hierarchical combination of tumor size classifiers developed from mass spectral data of a set of blood based samples obtained from melanoma patients treated with an anti-PD-1 drug, the hierarchical combination of tumor size classifiers generating a class label of either Good or the Equivalent or Bad or the equivalent, wherein a class label is detected. (0)

View Abstract and Specification Size

PDF with Images and Document Face >

Full Text Publication >

Application US20190018929

Predictive Test for Melanoma Patient Benefit from Interleukin-2 (IL2) Therapy

Patent Matrix® Search