# US 2024/0203522 A1 · Method and computer program for predicting neoantigen by using peptide sequence and hla allele sequence

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

- Number: US 2024/0203522 A1
- Document ID: US20240203522A1
- Status: Published application
- Kind: A1
- Application number: 17/909,866
- Filed: 2020-12-23
- Published: 2024-06-20
- Earliest claimed: 2020-03-24
- Assignees: Theragen Bio Co., Ltd.
- Applicants: Theragen Bio Co., Ltd.
- Inventors: Seong-Eui HONG; Taesoon HWANG
- Web page: https://patentgrep.com/patent/US20240203522A1

## CPC

- G16B 15/30: Drug targeting using structural data; Docking or binding prediction
- G16B 40/20: Supervised data analysis
- G16B 35/00: ICT specially adapted for in silico combinatorial libraries of nucleic acids, proteins or peptides
- G16B: BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY

## Abstract

The present disclosure provides a method for predicting a neoantigen by using a peptide sequence and an HLA allele sequence, the method comprising the steps of: receiving a peptide sequence and an HLA allele sequence both extracted from a target cancer tissue as an input; outputting a first prediction value that predicts immunogenicity of the peptide sequence, by acquiring T cell activity data from the peptide sequence and inputting the T cell activity data into an immunogenicity prediction model; outputting a second prediction value that predicts a binding affinity of the peptide sequence and the HLA allele sequence, by acquiring binding data from the HLA allele sequence and inputting the binding data into a binding prediction model; outputting a third prediction value that predicts immune tolerance of the target cancer tissue, by inputting the T cell activity data and the binding data to an immune tolerance prediction model; and generating neoantigen information of a target cell by using the T cell activity data and the first to third prediction value.

## Claims

### Claim 1

A method of predicting a neoantigen by using a peptide sequence and an HLA allele sequence, the method comprising the steps of:
receiving a peptide sequence and an HLA allele sequence both extracted from a target cancer tissue as an input;
outputting a first prediction value that predicts immunogenicity of the peptide sequence, by acquiring T cell activity data from the peptide sequence and inputting the T cell activity data into an immunogenicity prediction model;
outputting a second prediction value that predicts a binding affinity of the peptide sequence and the HLA allele sequence, by acquiring binding data from the HLA allele sequence and inputting the binding data into a binding prediction model;
outputting a third prediction value that predicts immune tolerance of the target cancer tissue, by inputting the T cell activity data and the binding data to an immune tolerance prediction model; and
generating neoantigen information of a target cell by using the T cell activity data and the first to third prediction value.

### Claim 2 (depends on 1)

The method of claim 1, wherein at least one of the immunogenicity prediction model, the binding predictive model, and the immune tolerance prediction model is trained by a machine learning algorithm, based on a training data set including a peptide sequence and an HLA allele sequence present in a plurality of target cancer tissues.

### Claim 3 (depends on 2)

The method of claim 2, wherein the target cancer tissue includes a cell engineered to express a single HLA class I allele or single HLA class II allele.

### Claim 4 (depends on 2)

The method of claim 2, wherein the target cancer tissue includes a human cell obtained from or derived from a plurality of patients.

### Claim 5 (depends on 2)

The method of claim 2, wherein the target cancer tissue includes a fresh or frozen tumor cell obtained from a plurality of patients.

### Claim 6 (depends on 2)

The method of claim 2, wherein the target cancer tissue includes a fresh or frozen tissue cell obtained from a plurality of patients.

### Claim 7 (depends on 2)

The method of claim 2, wherein the target cancer tissue includes a peptide identified by using T-cell analysis.

### Claim 8 (depends on 2)

The method of claim 2, wherein the training data set includes at least one of data related to a proteomic sequence related to the target cancer tissue, data related to an HLA peptide sequence related to the target cancer tissue, binding data between a peptide and an HLA allele that are related to the target cancer tissue; data related to a transcriptome related to the target cancer tissue; and data related to a genome related to the target cancer tissue.

### Claim 9 (depends on 1)

The method of claim 1, wherein the immunogenicity prediction model is a model trained with the T cell activity data from the peptide sequence as an input and the immunogenicity of the peptide sequence as an output.

### Claim 10 (depends on 1)

The method of claim 1, wherein the binding prediction model is a model trained with the binding data from the HLA allele sequence and the peptide sequence as an input and the binding affinity of the peptide sequence and the HLA allele sequence as an output.

### Claim 11 (depends on 1)

The method of claim 1, wherein the immune tolerance prediction model is a model trained with the T cell activity data from the peptide sequence and the HLA allele sequence, and the binding data from the HLA allele sequence and the peptide sequence as an input and the immune tolerance between the peptide sequence and the HLA allele sequence.

### Claim 12 (depends on 1)

A computer program stored in a computer-readable storage medium for executing the method of claim 1 by using a computer.
