# US 2025/0095783 A1 · Method for obtaining antibody sequence

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

- Number: US 2025/0095783 A1
- Document ID: US20250095783A1
- Status: Published application
- Kind: A1
- Application number: 18/967,512
- Filed: 2024-12-03
- Published: 2025-03-20
- Earliest claimed: 2024-05-28
- Assignees: Beijing Baidu Netcom Science Technology Co., Ltd.
- Applicants: Beijing Baidu Netcom Science Technology Co., Ltd.
- Inventors: Jie GAO; Jing HU; Xiaomin FANG; Xiaonan ZHANG
- Web page: https://patentgrep.com/patent/US20250095783A1

## CPC

- G16B 30/20: Sequence assembly
- G16B 30/00: ICT specially adapted for sequence analysis involving nucleotides or amino acids
- G16B 30/10: Sequence alignment; Homology search
- 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
- G16B 40/20: Supervised data analysis
- G16B: BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY

## Abstract

A method for obtaining an antibody sequence includes: obtaining first features of amino acids at different sequence positions according to an antigen multiple sequence alignment (MSA) sequence, an antibody MSA sequence, and a concatenated sequence of the antigen MSA sequence and the antibody MSA sequence; obtaining second feature of the amino acids at different 3D coordinates according to a graph constructed according to a reference antigen-antibody complex; fusing the first features of amino acids at different sequence positions with the second features of amino acids at 3D coordinates corresponding to the different sequence positions, and obtaining probability information of each of the amino acids at different positions in the antibody sequence according to fused features; and obtaining a target antibody sequence according to the amino acids and their probability information at different positions in the antibody sequence.

## Claims

### Claim 1

A method for obtaining an antibody sequence, comprising:
performing Multiple Sequence Alignment (MSA) on an antigen sequence and an initial antibody sequence respectively to obtain an antigen MSA sequence and an antibody MSA sequence;
concatenating the antigen MSA sequence and the antibody MSA sequence, and obtaining first features of amino acids at different sequence positions in a concatenated sequence according to respective attribute features of the amino acids in the concatenated sequence, the antigen MSA sequence and the antibody MSA sequence;
constructing a graph according to connectivity relationships among amino acids in a reference antigen-antibody complex, and obtaining second features of the amino acids at different 3D coordinates in the reference antigen-antibody complex according to respective attribute features of the amino acids in the graph;
fusing the first features of amino acids at different sequence positions with the second features of amino acids at 3D coordinates corresponding to the different sequence positions, and obtaining probability information of each of the amino acids at different positions in the antibody sequence according to fused features; and
obtaining a target antibody sequence according to the amino acids and their probability information at different positions in the antibody sequence.

### Claim 2 (depends on 1)

The method according to claim 1, wherein obtaining the first features of amino acids at different sequence positions in the concatenated sequence according to respective attribute features of the amino acids in the concatenated sequence, the antigen MSA sequence and the antibody MSA sequence comprises:
obtaining an iterative MSA sequence from the antigen MSA sequence and the antibody MSA sequence;
obtaining multiple amino acid pair features according to attribute feature pairs of multiple amino acid pairs contained in the iterative MSA sequence;
updating the respective attribute features of the amino acids at different sequence positions in the concatenated sequence using the multiple amino acid pair features;
returning to the step of obtaining an iterative MSA sequence from the antigen MSA sequence and the antibody MSA sequence after obtaining updated attribute features of the amino acids at different sequence positions in the concatenated sequence; and
repeating the above processes until all antigen MSA sequence and antibody MSA sequence have been selected, and taking final updated attribute features as the first features of the amino acids.

### Claim 3 (depends on 1)

The method according to claim 1, wherein obtaining the second features of the amino acids at different 3D coordinates in the reference antigen-antibody complex according to respective attribute features of the amino acids in the graph comprises:
determining adjacent amino acids having connectivity relationships with each amino acid in the graph;
updating attribute feature of each amino acid using attribute features of the adjacent amino acids to obtain updated attribute feature of each amino acid;
determining a 3D coordinate of each amino acid in the reference antigen-antibody complex according to its position in the graph, and taking the updated attribute features of amino acids at different positions as the second features of amino acids at different 3D coordinates.

### Claim 4 (depends on 1)

The method according to claim 1, wherein obtaining the target antibody sequence according to the amino acids and their probability information at different positions in the antibody sequence comprises:
obtaining multiple first candidate antibody sequences according to the amino acids and their probability information at different positions in the antibody sequence;
scoring the multiple first candidate antibody sequences and selecting multiple second candidate antibody sequences from the multiple first candidate antibody sequences according to the scoring results; and
verifying functional indicators of the multiple second candidate antibody sequences, and selecting a second candidate antibody sequence with optimal functional indicators as the target antibody sequence.

### Claim 5 (depends on 1)

The method according to claim 1, wherein obtaining first features of amino acids at different sequence positions in the concatenated sequence according to respective attribute features of the amino acid in the concatenated sequence, the antigen MSA sequence and the antibody MSA sequence comprises:
inputting the antigen MSA sequence and the antibody MSA sequence into a first feature extraction module of an antibody design model;
obtaining the first features of amino acids at different sequence positions in the concatenated sequence according to a result output by the first feature extraction module.

### Claim 6 (depends on 1)

The method according to claim 1, wherein constructing the graph according to connectivity relationships among amino acids in the reference antigen-antibody complex, and obtaining the second features of the amino acids at different 3D coordinates in the reference antigen-antibody complex according to respective attribute features of the amino acids in the graph comprises:
inputting the reference antigen-antibody complex into a second feature extraction module of an antibody design model; and
obtaining the second features of amino acids at different 3D coordinates in the reference antigen-antibody complex according to a result output by the second feature extraction module.

### Claim 7 (depends on 1)

The method according to claim 1, wherein fusing the first features of amino acids at different sequence positions with the second features of amino acids at 3D coordinates corresponding to the different sequence positions, and obtaining probability information of each of the amino acids at different positions in the antibody sequence according to fused features comprises:
inputting the first features of amino acids at different sequence positions and the second features of amino acids at 3D coordinates corresponding to the different sequence positions into a feature fusion module of an antibody design model; and
obtaining probability information of each of the amino acids at different positions in the antibody sequence according to a result output by the feature fusion module.

### Claim 8 (depends on 1)

The method according to claim 1, wherein the first features are obtained by inputting the antigen MSA sequence and the antibody MSA sequence into a first feature extraction module of an antibody design model;
the second features are obtained by inputting the reference antigen-antibody complex into a second feature extraction module of the antibody design model; and
the probability information of each of the amino acids at different positions are obtained by inputting the first features and the second features into a feature fusion module of the antibody design model.

### Claim 9 (depends on 8)

The method according to claim 8, wherein the antibody design model is trained by:
obtaining multiple data samples, wherein each data sample contains a sample antigen MSA sequence, a sample antibody MSA sequence, a sample antigen-antibody complex, and a labeled antibody sequence;
constructing a neural network model containing the first feature extraction module, the second feature extraction module, and the feature fusion module;
inputting the sample antigen MSA sequence, the sample antibody MSA sequence, and the sample antigen-antibody complex into the neural network model, and obtaining a predicted antibody sequence according to a result output by the neural network model; and
calculating a loss function value according to the predicted antibody sequence and the labeled antibody sequence, and adjusting parameters of the neural network model using the loss function value to obtain the antibody design model.

### Claim 10 (depends on 9)

The method according to claim 9, wherein inputting the sample antigen MSA sequence, sample antibody MSA sequence, and sample antigen-antibody complex into the neural network model, and obtaining the predicted antibody sequence according to the result output by the neural network model comprises:
inputting the sample antigen MSA sequence and sample antibody MSA sequence into the first feature extraction module, and obtaining first sample features of amino acids at different sample sequence positions in the sample concatenated sequence output by the first feature extraction module;
inputting the sample antigen-antibody complex into the second feature extraction module, and obtaining second sample features of amino acids at different sample 3D coordinates in the sample antigen-antibody complex output by the second feature extraction module; and
inputting the first sample features of amino acids at different sample sequence positions and the second sample features of amino acids at different sample 3D coordinates into the feature fusion module, and obtaining the predicted antibody sequence according to sample probability information of each of the amino acids at different positions in the sample antibody sequence output by the feature fusion module.

### Claim 11

An electronic device, comprising:
at least one processor; and
a memory communicatively connected to the at least one processor;
wherein the memory stores instructions executable by the at least one processor to perform a method for obtaining an antibody sequence, comprising:
performing Multiple Sequence Alignment (MSA) on an antigen sequence and an initial antibody sequence respectively to obtain an antigen MSA sequence and an antibody MSA sequence;
concatenating the antigen MSA sequence and the antibody MSA sequence, and obtaining first features of amino acids at different sequence positions in a concatenated sequence according to respective attribute features of the amino acids in the concatenated sequence, the antigen MSA sequence and the antibody MSA sequence;
constructing a graph according to connectivity relationships among amino acids in a reference antigen-antibody complex, and obtaining second features of the amino acids at different 3D coordinates in the reference antigen-antibody complex according to respective attribute features of the amino acids in the graph;
fusing the first features of amino acids at different sequence positions with the second features of amino acids at 3D coordinates corresponding to the different sequence positions, and obtaining probability information of each of the amino acids at different positions in the antibody sequence according to fused features; and
obtaining a target antibody sequence according to the amino acids and their probability information at different positions in the antibody sequence.

### Claim 12 (depends on 11)

The electronic device according to claim 11, wherein obtaining the first features of amino acids at different sequence positions in the concatenated sequence according to respective attribute features of the amino acids in the concatenated sequence, the antigen MSA sequence and the antibody MSA sequence comprises:
obtaining an iterative MSA sequence from the antigen MSA sequence and the antibody MSA sequence;
obtaining multiple amino acid pair features according to attribute feature pairs of multiple amino acid pairs contained in the iterative MSA sequence;
updating the respective attribute features of the amino acids at different sequence positions in the concatenated sequence using the multiple amino acid pair features;
returning to the step of obtaining an iterative MSA sequence from the antigen MSA sequence and the antibody MSA sequence after obtaining updated attribute features of the amino acids at different sequence positions in the concatenated sequence; and
repeating the above processes until all antigen MSA sequence and antibody MSA sequence have been selected, and taking final updated attribute features as the first features of the amino acids.

### Claim 13 (depends on 11)

The electronic device according to claim 11, wherein obtaining the second features of the amino acids at different 3D coordinates in the reference antigen-antibody complex according to respective attribute features of the amino acids in the graph comprises:
determining adjacent amino acids having connectivity relationships with each amino acid in the graph;
updating attribute feature of each amino acid using attribute features of the adjacent amino acids to obtain updated attribute feature of each amino acid;
determining a 3D coordinate of each amino acid in the reference antigen-antibody complex according to its position in the graph, and taking the updated attribute features of amino acids at different positions as the second features of amino acids at different 3D coordinates.

### Claim 14 (depends on 11)

The electronic device according to claim 11, wherein obtaining the target antibody sequence according to the amino acids and their probability information at different positions in the antibody sequence comprises:
obtaining multiple first candidate antibody sequences according to the amino acids and their probability information at different positions in the antibody sequence;
scoring the multiple first candidate antibody sequences and selecting multiple second candidate antibody sequences from the multiple first candidate antibody sequences according to the scoring results; and
verifying functional indicators of the multiple second candidate antibody sequences, and selecting a second candidate antibody sequence with optimal functional indicators as the target antibody sequence.

### Claim 15 (depends on 11)

The electronic device according to claim 11, wherein obtaining first features of amino acids at different sequence positions in the concatenated sequence according to respective attribute features of the amino acid in the concatenated sequence, the antigen MSA sequence and the antibody MSA sequence comprises:
inputting the antigen MSA sequence and the antibody MSA sequence into a first feature extraction module of an antibody design model;
obtaining the first features of amino acids at different sequence positions in the concatenated sequence according to a result output by the first feature extraction module.

### Claim 16 (depends on 11)

The electronic device according to claim 11, wherein constructing the graph according to connectivity relationships among amino acids in the reference antigen-antibody complex, and obtaining the second features of the amino acids at different 3D coordinates in the reference antigen-antibody complex according to respective attribute features of the amino acids in the graph comprises:
inputting the reference antigen-antibody complex into a second feature extraction module of an antibody design model; and
obtaining the second features of amino acids at different 3D coordinates in the reference antigen-antibody complex according to a result output by the second feature extraction module.

### Claim 17 (depends on 11)

The electronic device according to claim 11, wherein fusing the first features of amino acids at different sequence positions with the second features of amino acids at 3D coordinates corresponding to the different sequence positions, and obtaining probability information of each of the amino acids at different positions in the antibody sequence according to fused features comprises:
inputting the first features of amino acids at different sequence positions and the second features of amino acids at 3D coordinates corresponding to the different sequence positions into a feature fusion module of an antibody design model; and
obtaining probability information of each of the amino acids at different positions in the antibody sequence according to a result output by the feature fusion module.

### Claim 18 (depends on 11)

The electronic device according to claim 11, wherein the first features are obtained by inputting the antigen MSA sequence and the antibody MSA sequence into a first feature extraction module of an antibody design model;
the second features are obtained by inputting the reference antigen-antibody complex into a second feature extraction module of the antibody design model; and
the probability information of each of the amino acids at different positions are obtained by inputting the first features and the second features into a feature fusion module of the antibody design model, and
wherein the antibody design model is trained by:
obtaining multiple data samples, wherein each data sample contains a sample antigen MSA sequence, a sample antibody MSA sequence, a sample antigen-antibody complex, and a labeled antibody sequence;
constructing a neural network model containing the first feature extraction module, the second feature extraction module, and the feature fusion module;
inputting the sample antigen MSA sequence, the sample antibody MSA sequence, and the sample antigen-antibody complex into the neural network model, and obtaining a predicted antibody sequence according to a result output by the neural network model; and
calculating a loss function value according to the predicted antibody sequence and the labeled antibody sequence, and adjusting parameters of the neural network model using the loss function value to obtain the antibody design model.

### Claim 19 (depends on 18)

The electronic device according to claim 18, wherein inputting the sample antigen MSA sequence, sample antibody MSA sequence, and sample antigen-antibody complex into the neural network model, and obtaining the predicted antibody sequence according to the result output by the neural network model comprises:
inputting the sample antigen MSA sequence and sample antibody MSA sequence into the first feature extraction module, and obtaining first sample features of amino acids at different sample sequence positions in the sample concatenated sequence output by the first feature extraction module;
inputting the sample antigen-antibody complex into the second feature extraction module, and obtaining second sample features of amino acids at different sample 3D coordinates in the sample antigen-antibody complex output by the second feature extraction module; and
inputting the first sample features of amino acids at different sample sequence positions and the second sample features of amino acids at different sample 3D coordinates into the feature fusion module, and obtaining the predicted antibody sequence according to sample probability information of each of the amino acids at different positions in the sample antibody sequence output by the feature fusion module.

### Claim 20

A non-transitory computer-readable storage medium storing computer instructions for executing a method for obtaining an antibody sequence, comprising:
performing Multiple Sequence Alignment (MSA) on an antigen sequence and an initial antibody sequence respectively to obtain an antigen MSA sequence and an antibody MSA sequence;
concatenating the antigen MSA sequence and the antibody MSA sequence, and obtaining first features of amino acids at different sequence positions in a concatenated sequence according to respective attribute features of the amino acids in the concatenated sequence, the antigen MSA sequence and the antibody MSA sequence;
constructing a graph according to connectivity relationships among amino acids in a reference antigen-antibody complex, and obtaining second features of the amino acids at different 3D coordinates in the reference antigen-antibody complex according to respective attribute features of the amino acids in the graph;
fusing the first features of amino acids at different sequence positions with the second features of amino acids at 3D coordinates corresponding to the different sequence positions, and obtaining probability information of each of the amino acids at different positions in the antibody sequence according to fused features; and
obtaining a target antibody sequence according to the amino acids and their probability information at different positions in the antibody sequence.
