Method and system for determining whether a drug will be effective on a patient with a disease

• US 7,879,620 B2
• Filed: 03/10/2010
• Issued: 02/01/2011
• Est. Priority Date: 03/31/2006
• Status: Active Grant

• Current Assignee: Biodesix, Inc.
• Original Assignee: Biodesix, Inc.
• Inventors: Tsypin, Maxim, Röder, Heinrich, Grigorieva, Julia
• Primary Examiner(s): Gakh; Yelena G
• Assistant Examiner(s): XU, XIAOYUN
• Application Number:
  US12/661,129
• Publication Number:
  US 20100204061A1
• Time in Patent Office: 328 Days
• Field of Search: None
• US Class Current: 436/173
• CPC Class Codes: A61P 35/00 Antineoplastic agents
• CPC Class Codes: G06F 18/2115 by evaluating different subsets according to an optimisation criterion, e.g. class separability, forward selection or backward elimination
• CPC Class Codes: G06F 18/24147 Distances to closest patterns, e.g. nearest neighbour classification
• CPC Class Codes: G06V 20/69 Microscopic objects, e.g. biological cells or cellular parts
• CPC Class Codes: G06V 2201/03 Recognition of patterns in medical or anatomical images
• CPC Class Codes: G16B 20/00 ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
• 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
• CPC Class Codes: Y02A 90/10 Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
• CPC Class Codes: Y10T 436/24 Nuclear magnetic resonance, electron spin resonance or other spin effects or mass spectrometry

Abstract

A process of determining whether a patient with a disease or disorder will be responsive to a drug, used to treat the disease or disorder, including obtaining a test spectrum produced by a mass spectrometer from a serum produced from the patient. The test spectrum may be processed to determine a relation to a group of class labeled spectra produced from respective serum from other patients having the or similar clinical stage same disease or disorder and known to have responded or not responded to the drug. Based on the relation of the test spectrum to the group of class labeled spectra, a determination may be made as to whether the patient will be responsive to the drug.

Claims

1. A laboratory test processing center, comprising:

one or more data storage devices storing (a) class-labeled mass spectral data obtained from blood-based samples of a multitude of cancer patients, the class labels for the mass spectral data indicating whether or not a patient associated with the mass spectral data responded to treatment of cancer from administration of an epidermal growth factor receptor pathway targeting drug; and

(b) a mass spectrum of a blood-based sample of a cancer patient to be tested;

a processing unit operating in accordance with a set of instructions to perform the following operations on the mass spectrum of the blood-based sample of a patient to be tested and the class-labeled mass spectral data;

(a) perform one or more predefined pre-processing steps on the mass spectrum of the blood-based sample of a patient to be tested;

(b) obtain integrated intensity values of features in the mass spectrum of the blood-based sample of a patient to be tested at one or more predetermined m/z ranges in said mass spectrum after the performance of said predefined pre-processing steps;

(c) implement a classification algorithm on the integrated intensity values and the class-labeled mass spectral data, the classification algorithm assigning a class label for the blood-based sample of a patient to be tested indicating whether or not the said patient is likely to benefit from administration of an epidermal growth factor receptor pathway targeting drug; and

(d) output the class label assigned by the classification algorithm to the blood-based sample of a cancer patient to be tested;

wherein the cancer patient is a non-small cell lung cancer patient, and

wherein the class label assigned to the blood-based sample of cancer patient to be tested indicates wherein the patient is likely to benefit from administration of at least one of (a) gefitinib and (b) erlotinib.

2. The laboratory test processing center of claim 1, further comprising a mass spectrometer, wherein the mass spectrometer produces a mass spectrum from a raw blood-based sample of the cancer patient and wherein the mass spectrum is stored in the one or more data storage devices.

3. The laboratory test processing center of claim 1, wherein the class-labeled spectra comprise class-labeled spectra from a multitude of non-small cell lung cancer patients.

4. The laboratory test processing center of claim 1, wherein the one or more predetermined m/z ranges are 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

65902 to 67502.

5. The laboratory test processing center of claim 1, wherein the classification algorithm comprises a k-nearest neighbor classification algorithm.

6. The laboratory test processing center of claim 5, wherein the classification algorithm comprises a probabilistic k-nearest neighbor classification algorithm.

7. The laboratory test processing center of claim 1, wherein the predefined pre-processing steps comprise:

a) subtracting background contained in the mass spectrum of the blood-based sample of the patient to be tested to produce a background subtracted spectrum, wherein the subtracting step comprises estimating non-constant levels of background and subtracting the estimated background from the mass spectral data;

b) normalizing the background subtracted spectrum; and

c) aligning the normalized, background subtracted spectrum to a predefined mass scale.

8. The laboratory test processing center of claim 7, wherein the subtracting background step estimates non-constant levels of background in a moving window comprising a range of m/z values in said mass spectral data using robust asymmetric estimates of background.