# US 2022/0026416 A1 · Method for identification of cancer patients with durable benefit from immunotehrapy in overall poor prognosis subgroups

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0026416 A1
- Document ID: US20220026416A1
- Status: Published application
- Kind: A1
- Application number: 17/495,213
- Filed: 2021-10-06
- Published: 2022-01-27
- Earliest claimed: 2017-01-05
- Assignees: Biodesix, Inc.
- Applicants: Biodesix, Inc.
- Inventors: Carlos OLIVEIRA; Heinrich RODER; Julia GRIGORIEVA; Joanna RODER
- Web page: https://patentgrep.com/patent/US20220026416A1

## CPC

- G01N 33/575: for cancer
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G01N 33/5091: {for testing the pathological state of an organism}
- G01N 33/6851: {Methods of protein analysis involving laser desorption ionisation mass spectrometry}
- G06F 18/24147: {Distances to closest patterns, e.g. nearest neighbour classification}
- G06F 18/24323: {Tree-organised classifiers}
- G16B 20/00: ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
- G16B 40/10: Signal processing, e.g. from mass spectrometry [MS] or from PCR
- G16B 40/20: Supervised data analysis
- G16H 10/40: for data related to laboratory analysis, e.g. patient specimen analysis
- G16H 50/30: for calculating health indices; for individual health risk assessment
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- G01N 2800/52: Predicting or monitoring the response to treatment, e.g. for selection of therapy based on assay results in personalised medicine; Prognosis
- G01N 2800/7028: Cancer
- G06F 18/2413: based on distances to training or reference patterns
- G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q)
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G16B: BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY

## Abstract

A blood-based sample from a cancer patient is subject to mass spectrometry and the resulting mass spectral data is classified with the aid of a computer to see if the patient is a member of a class of patients having a poor prognosis. If so, the mass spectral data is further classified with the aid of the computer by a second classifier which identifies whether the patient is nevertheless likely to obtain durable benefit from immunotherapy drugs, e.g., immune checkpoint inhibitors, anti-CTLA4 drugs, and high dose interleukin-2.

## Claims

### Claim 1

A method of detecting a class label in a lung cancer patient, a renal cell carcinoma patient, or a melanoma patient comprising:
(a) conducting a mass spectrometer test on a blood-based sample of the cancer patient to obtain a mass spectrum; obtaining integrated intensity values of selected features in the mass spectrum at one or more m/z ranges from a multitude of mass-spectral features listed in Table 25; using the integrated intensity values in a first stage classification algorithm using a training set comprising class-labeled spectra produced from blood-based samples from the same type of cancer patients to identify the patient as being in a class of patients determined to be a poor prognosis subgroup, and
(b) identifying the cancer patient as being in the class of patients determined to be a poor prognosis subgroup, and operating on the mass spectral data with a programmed computer implementing a second stage classification algorithm; wherein in the operating step the classifier compares the integrated intensity values with feature values of a reference set of class-labeled mass spectral data obtained from blood-based samples from a multitude of patients having the same type of cancer treated with an immunotherapy drug and detecting a class label for the sample.

### Claim 2 (depends on 1)

The method of claim 1, wherein the immunotherapy drug comprises an antibody drug blocking ligand activation of the PD-1 checkpoint protein, anti-CTLA4 drugs, high dose interleukin-2, and combination therapies.

### Claim 3 (depends on 1)

The method of claim 1, wherein the immunotherapy drug comprises a combination of two immunotherapy drugs.

### Claim 4

A method of guiding treatment of lung cancer patient, a renal cell carcinoma patient, or a melanoma patient comprising the steps of:
(a) conducting a mass spectrometer test on a blood-based sample of the cancer patient to obtain a mass spectrum; obtaining integrated intensity values of selected features in the mass spectrum at one or more m/z ranges as shown in Table 25; using the integrated intensity values in a first stage classification algorithm using a training set comprising class-labeled spectra produced from blood-based samples from the same type of cancer patients to identify the patient as being in a class of patients determined to be a poor prognosis subgroup, and
(b) identifying the patient as being in the class of patients determined to be a poor prognosis subgroup, obtaining integrated intensity values of selected features in the mass spectrum at one or more m/z ranges as shown in the table and using the integrated intensity values in a second stage classification algorithm using a training set comprising class-labeled spectra produced from blood-based samples from the same type of cancer patients treated with an immunotherapy drug to obtain a class label of Late or the equivalent which guides treatment of the patient to an immunotherapy drug.

### Claim 5 (depends on 4)

The method of claim 4, wherein the immunotherapy drug comprises an antibody drug blocking ligand activation of the PD-1 checkpoint protein, anti-CTLA4 drugs, high dose interleukin-2, and combination therapies.

### Claim 6 (depends on 4)

The method of claim 4, wherein the immunotherapy drug comprises a combination of two immunotherapy drugs.

### Claim 7

A method indicating the relative likelihood of success of an immunotherapy treatment for a lung cancer patient, a renal cell carcinoma patient, or a melanoma patient comprising the steps of:
(a) conducting a mass spectrometer test on a blood-based sample of the cancer patient to obtain a mass spectrum; obtaining integrated intensity values of selected features in the mass spectrum at one or more m/z ranges as shown in Table 25 using the integrated intensity values in a first stage classification algorithm using a training set comprising class-labeled spectra produced from blood-based samples from the same type of cancer patients to identify the patient as being in a class of patients determined to be a poor prognosis subgroup,
(b) identifying the patient as being in the class of patients determined to be a poor prognosis subgroup, using the integrated intensity values as shown in the table in a second stage classification algorithm using a training set comprising class-labeled spectra produced from blood-based samples from the same type of cancer patients treated with an immunotherapy drug to a class label of Late or the equivalent which identifies the patient as likely to have durable benefit from an immunotherapy drug; and
(c) determining that the patient having a class label of Late or the equivalent is likely to respond to an immunotherapy drug.

### Claim 8 (depends on 7)

The method of claim 7, wherein the immunotherapy drug comprises an antibody drug blocking ligand activation of the PD-1 checkpoint protein, anti-CTLA4 drugs, high dose interleukin-2, and combination therapies.

### Claim 9 (depends on 7)

The method of claim 7, wherein the immunotherapy drug comprises a combination of two immunotherapy drugs.
