Method for predicting breast cancer patient response to combination therapy
A mass-spectral method is disclosed for determining whether breast cancer patient is likely to benefit from a combination treatment in the form of administration of a targeted anti-cancer drug in addition to an endocrine therapy drug. The method obtains a mass spectrum from a blood-based sample from the patient. The spectrum is subject to one or more predefined pre-processing steps. Values of selected features in the spectrum at one or more predefined m/z ranges are obtained. The values are used in a classification algorithm using a training set comprising class-labeled spectra and a class label for the sample is obtained. If the class label is “Poor”, the patient is identified as being likely to benefit from the combination treatment. In a variation, the “Poor” class label predicts whether the patient is unlikely to benefit from endocrine therapy drugs alone, regardless of the patient's HER2 status.
1. A method of determining whether a post-menopausal hormone receptor positive breast cancer patient with HER2-negative status is likely to benefit from administration of a combination treatment comprising administration of a targeted anti-cancer drug in addition to an endocrine therapy drug, comprising the steps of:
a) conducting mass spectrometry on a blood-based sample from the patient with a mass-spectrometer and thereby obtaining a mass spectrum of the blood-based sample;
b) performing one or more predefined pre-processing steps on the mass spectrum obtained in step a);
c) obtaining, using a programmed computer, integrated intensity values of selected features in said mass spectrum at one or more predefined m/z ranges after the pre-processing steps on the mass spectrum in step b) have been performed, wherein the one or more predefined m/z ranges is selected from the group of m/z ranges consisting of:
5732 to 5795
5811 to 5875
6398 to 6469
11376 to 11515
11459 to 11599
11614 to 11756
11687 to 11831
11830 to 11976
12375 to 12529
23183 to 23525
23279 to 23622 and
65902 to 67502;
d) executing, in said programmed computer, a classification algorithm comparing the integrated intensity values obtained in step c) to features in the stored set of mass spectral data and obtaining a class label for the sample, wherein the programmed computer comprises a stored set of class-labeled mass spectral data from blood-based samples from other treated solid epithelial tumor cancer patients; and
e) identifying the patient as being likely to benefit from the combination treatment if the class label for the sample obtained by the classification algorithm in step d) is “Poor” or the equivalent.
2. The method of claim 1 , wherein the targeted anti-cancer drug comprises lapatinib.
3. The method of claim 1 , wherein the endocrine therapy drug comprises an aromatase inhibitor.
4. The method of claim 3 , wherein the aromatase inhibitor comprises letrozole.
5. The method of claim 1 , wherein the endocrine therapy drug comprises a selective estrogen receptor modulator (SERM).
6. The method of claim 5 , wherein the endocrine therapy drug comprises selective estrogen receptor downregulator (SERD).
7. The method of claim 5 , wherein the endocrine therapy drug comprises tamoxifen or the equivalent.
8. The method of claim 1 , wherein the stored set of class-labeled mass spectral data from blood-based samples from other treated solid epithelial tumor cancer patients used in the classification step d) comprise class-labeled spectra of samples obtained from non-small cell lung cancer patients and the class labels indicate whether such patients benefitted from treatment with an epidermal growth factor receptor inhibitor (“Good”) or did not benefit (“Poor”).