# US 2025/0329431 A1 · Method of predicting non-small cell lung cancer (nsclc) patient drugresponse or time until death or cancer progression from circulating tumordna (ctdna) utilizing signals from both baseline ctdna level and longitudinalchange of ctdna level over time

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

- Number: US 2025/0329431 A1
- Document ID: US20250329431A1
- Status: Published application
- Kind: A1
- Application number: 19/205,670
- Filed: 2025-05-12
- Published: 2025-10-23
- Earliest claimed: 2022-11-15
- Assignees: Guardant Health, Inc.
- Applicants: Guardant Health, Inc.
- Inventors: Bojan LOSIC; Katie Julia QUINN; Sean Gordon
- Web page: https://patentgrep.com/patent/US20250329431A1

## CPC

- G16H 20/17: delivered via infusion or injection
- G16H 50/30: for calculating health indices; for individual health risk assessment
- G06N 20/00: Machine learning
- G16B 20/20: Allele or variant detection, e.g. single nucleotide polymorphism [SNP] detection
- G16B 20/40: Population genetics; Linkage disequilibrium
- G16B 40/20: Supervised data analysis
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G16B: BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY

## Abstract

Provided herein are methods of determining a molecular response score for use in predictive models. The molecular response score may be used to monitor and guide administration of treatment to a subject.

## Claims

### Claim 1

A method, comprising:
receiving, by a computer system, genetic information of a subject comprising data taken at two or more time points and wherein cancer is detected in the subject;
extracting one or more features from the genetic information, the one or more features identified from a plurality of samples obtained from the subject;
generating, by a first classifier implemented by the computer system using a first machine learning algorithm, a first output indicating a first classification of the subject;
generating, by a second classifier implemented by the computer system using a second machine learning algorithm, a second output indicating a second classification of the subject;
identifying, by the computer system and from a population, additional subjects with genetic information that match the subject's genetic information based on the first classification and the second classification;
determining, by the computer system, at least one score with respect to the subject based additional subjects with matching genetic information;
determining, by the computer system, a composite score using the at least one score; and
determining, by a recommender implemented by the computer system, a recommendation indicating a treatment for the subject based on the composite score.

### Claim 2 (depends on 1)

The method of claim 1, wherein the one or more features comprise a first mutant allele fraction (MAF) and a second MAF, each from the at two or more time points.

### Claim 3 (depends on 2)

The method of claim 2, wherein the at least one score is based on a first mutant allele fraction (MAF) and a second MAF, a weighted mean of the first MAFs and a weighted mean of the second MAFs.

### Claim 4 (depends on 3)

The method of claim 3, wherein the at least one score is based on a ratio of the weighted mean of the first MAFs and the weighted mean of the second MAFs and the confidence interval.

### Claim 5 (depends on 2)

The method of claim 2, wherein the at least one score is based on a first mutant allele fraction (MAF) at the first time point and a second MAF at the second time point, a first central tendency measure of the first MAFs and a second central tendency measure of the second MAFs.

### Claim 6 (depends on 5)

The method of claim 5, wherein the at least one score is based on a ratio of the first central tendency measure at the first time point to the second central tendency measure at the second time point.

### Claim 7 (depends on 6)

The method of claim 6, wherein the central tendency measure is one or more of a: mean, median, or mode.

### Claim 8 (depends on 1)

The method of claim 1, further comprising comparing a molecular response score for the subject having the cancer to a predetermined cutoff point to identify that the subject is a likely responder to one or more therapies for the cancer when the molecular response score is below the predetermined cutoff point or that the subject is a likely non-responder to the one or more therapies for the cancer when the molecular response score is at or above the predetermined cutoff point.

### Claim 9 (depends on 8)

The method of claim 8, wherein the one or more therapies comprise one or more immunotherapies.

### Claim 10 (depends on 8)

The method of claim 8, further comprising administering one or more therapies for the cancer to the subject in view of the at least one score.

### Claim 11 (depends on 10)

The method of claim 10, further comprising discontinuing administering one or more therapies for the cancer to the subject in view of the at least one score.

### Claim 12 (depends on 1)

The method of claim 1, comprising using the at least one score as a prognostic biomarker and/or a predictive biomarker for the subject.

### Claim 13 (depends on 4)

The method of claim 4, comprising using a molecule count to calculate the standard deviation for a ratio in a set of MAF ratios.

### Claim 14 (depends on 4)

The method of claim 4, comprising propagating a variance through a ratio in a set of MAF ratios.

### Claim 15 (depends on 1)

The method of claim 1, further comprising excluding one or more germline and/or clonal hematopoietic variants when determining the mutant allele frequencies (MAFs).

### Claim 16 (depends on 2)

The method of claim 2, wherein the first time point comprises a pre-treatment time point and wherein the second time point comprises an on- or post-treatment time point.

### Claim 17 (depends on 1)

The method of claim 1, comprising generating the genetic information from nucleic acid molecules obtained from one or more tissues or cells in at least one sample.

### Claim 18 (depends on 17)

The method of claim 17, comprising generating the genetic information from cell-free nucleic acids (cfNAs) in the at least one sample.

### Claim 19 (depends on 18)

The method of claim 18, wherein the cfNAs comprise circulating tumor DNA (ctDNA).

### Claim 20 (depends on 1)

The method of claim 1, wherein the first and/or second classifier is each implemented by a machine learning algorithm.

### Claim 21 (depends on 20)

The method of claim 20, wherein the machine learning algorithm comprises a neural network, a support vector machine, a Hidden Markov Model, or a random forest model.

### Claim 22 (depends on 1)

The method of claim 1, wherein the at least one score corresponds to a level of responsiveness to a treatment from a plurality of levels of responsiveness to the treatment.

### Claim at position 23

-26. (canceled)

### Claim 27 (depends on 1)

A computer readable medium comprising non-transitory computer executable instructions which, when executed by at least one electronic processor, perform the method of claim 1.

### Claim 28 (depends on 1)

A system configured to perform the method of claim 1.
