CN115497564A - Antigen identification model establishing method and antigen identification method - Google Patents

Antigen identification model establishing method and antigen identification method Download PDF

Info

Publication number
CN115497564A
CN115497564A CN202211066490.6A CN202211066490A CN115497564A CN 115497564 A CN115497564 A CN 115497564A CN 202211066490 A CN202211066490 A CN 202211066490A CN 115497564 A CN115497564 A CN 115497564A
Authority
CN
China
Prior art keywords
antigen
neural network
tcr
training
pmhc
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202211066490.6A
Other languages
Chinese (zh)
Inventor
张靖
樊瑜波
何雨菲
徐志远
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beihang University
Original Assignee
Beihang University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beihang University filed Critical Beihang University
Priority to CN202211066490.6A priority Critical patent/CN115497564A/en
Publication of CN115497564A publication Critical patent/CN115497564A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
    • G16B30/00—ICT specially adapted for sequence analysis involving nucleotides or amino acids
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
    • G16B40/00—ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Physics & Mathematics (AREA)
  • Biotechnology (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Public Health (AREA)
  • Bioethics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Epidemiology (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Proteomics, Peptides & Aminoacids (AREA)
  • Peptides Or Proteins (AREA)

Abstract

The invention provides an antigen identification model establishing method and an antigen identification method, and relates to the technical field of neural networks and immune response prediction. The invention relates to a method for establishing an antigen identification model, which comprises the following steps: constructing a neural network, wherein the neural network comprises a TCR feature extraction neural network, a pMHC feature extraction neural network and an antigen identification neural network; constructing a data set, wherein the data set comprises TCRCDR3, HLAI and antigen sequences; and inputting the data set into a neural network, and training the neural network to establish an antigen identification model. The technical scheme of the invention can realize the characteristic extraction of the sequence information of the TCRCDR3, the HLAI and the antigen, thereby identifying the related antigen of the activated T cell.

Description

Antigen identification model establishing method and antigen identification method
Technical Field
The invention relates to the technical field of neural networks and immune response prediction, in particular to an antigen identification model establishing method and an antigen identification method.
Background
Immunotherapy is a new technology that can be used in cancer treatment. The most important step in this method is the activation of the adaptive immune response in humans, i.e. the recognition and destruction of diseased cells by mediating cytotoxic T lymphocytes.
In the prior art, T cell antigen identification is generally performed by using a direct detection method, a modeling prediction method and a machine learning method, however, the data used in the implementation process of the methods are limited, so that the peptide fragments capable of being identified are very limited, and due to the complexity of the reaction, the understanding of which antigen can activate the immune reaction of T lymphocytes is still very limited.
Disclosure of Invention
The technical problem to be solved by the invention is how to realize the identification of relevant antigens of activated T cells.
In order to solve the above problems, the present invention provides a method for establishing an antigen identification model, comprising: constructing a neural network, wherein the neural network comprises a TCR feature extraction neural network, a pMHC feature extraction neural network and an antigen identification neural network; constructing a data set, wherein the data set comprises TCR CDR3, HLA I, and an antigen sequence; and inputting the data set into the neural network, and training the neural network to establish an antigen identification model.
Preferably, the TCR CDR3, HLA I and antigen sequences in the data set are described using Z descriptors, and the described matrices are normalized to determine a TCR CDR3 sequence matrix, an HLA I sequence matrix and an antigen sequence matrix, respectively.
Preferably, inputting the data set into the neural network, and training the neural network, includes: taking the TCR CDR3 sequence matrix as a training set, and training the TCR feature extraction neural network; inputting the TCR CDR3 sequence matrix into a trained TCR feature extraction neural network to obtain a TCR feature vector;
training the pMHC feature extraction neural network by taking the HLA I sequence matrix and the antigen sequence matrix as training sets; inputting the HLA I sequence matrix and the antigen sequence matrix into a trained pMHC feature extraction neural network to obtain a pMHC feature vector;
and taking the TCR characteristic vector and the pMHC characteristic vector as a training set, and training the antigen identification neural network.
Preferably, before the training of the antigen identification neural network, the identification antigen model building method further includes: and balancing a training set consisting of the TCR characteristic vector and the pMHC characteristic vector by adopting a SMOTE algorithm.
Preferably, training the antigen-identifying neural network comprises: and taking the binding state of the TCR characteristic vector and the pMHC characteristic vector as a classification label.
Preferably, the training set of TCR and pMHC feature vectors comprises artificial negative binding data.
Preferably, the TCR feature extraction neural network comprises an encoder module, a feature extraction module and a decoder module;
the convolutional layer module adopted by the encoder module comprises four Cov1D layers;
the characteristic extraction module comprises a full connection layer for outputting TCR sequence characteristics;
the decoder module includes four Conv1D layers.
Preferably, the pMHC feature extraction neural network comprises an HLA feature extraction module, an antigen feature extraction module, a feature extraction module and a tag training module;
the HLA feature extraction module comprises four Cov1D layers, a Reshape layer and a full connection layer;
the antigen feature extraction module comprises four Cov1D layers, a Reshape layer and a full connection layer;
the characteristic extraction module comprises a full connection layer for outputting pMHC sequence characteristics;
the label training module comprises two full-connection layers.
Preferably, the antigen identification neural network comprises a TCR feature learning module, a pMHC feature learning module and an output module;
the TCR feature learning module comprises two full connection layers;
the pMHC feature learning module comprises two full connection layers;
the output module adopts three full-connection layers for outputting antigen identification results.
The method for establishing the antigen identification model realizes the target of identifying the relevant antigens of the activated T cells by describing sequence characteristics, adopting different neural networks to perform dimensionality reduction extraction on the sequence characteristics, adopting a supervised deep learning neural network and learning the dimensionality reduced sequence characteristics; meanwhile, in order to ensure the training effect of the model, the training data set is reconstructed in an SMOTE mode, so that the data of the training set is more balanced, the overfitting of a small amount of data is avoided, and the model effect is improved; in addition, under the condition of fixing the model structure, various training set and test set proportions are tried, each proportion is trained for multiple times, and the model is proved to have higher stability and prediction accuracy by the common high verification rate; finally, a series of neural networks designed by the invention can perform feature extraction on the sequence information of TCR CDR3, HLA I and antigen, thereby identifying the relevant antigen of the activated T cell.
The invention also provides a method for identifying an antigen, which comprises the following steps: obtaining TCR CDR3, HLA I and an antigen sequence which need to be detected, inputting the TCR CDR3, HLA I and the antigen sequence which need to be detected into an identification antigen model established by the identification antigen model establishing method, and obtaining an identification result of the antigen. The advantages of the antigen identification method and the antigen identification model establishment method are the same compared with the prior art, and are not repeated herein.
Drawings
FIG. 1 is a flow chart of a method for establishing an antigen identification model according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a TCR feature extraction neural network according to an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a pMHC feature extraction neural network according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of the structure of an antigen-identifying neural network according to an embodiment of the present invention;
FIG. 5 is a schematic flow chart of the identification of antigens associated with activated T cells according to an embodiment of the present invention;
FIG. 6 is a schematic structural diagram of an apparatus for establishing an antigen model according to an embodiment of the present invention;
FIG. 7 is a second schematic structural diagram of an antigen identification model building apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
As shown in fig. 1, an embodiment of the present invention provides a method for establishing an antigen identification model, including the following steps: constructing a neural network, wherein the neural network comprises a TCR feature extraction neural network, a pMHC feature extraction neural network and an antigen identification neural network; constructing a data set, wherein the data set comprises TCR CDR3, HLA I, and an antigen sequence; inputting the data set into the neural network, and training the neural network to establish an identification antigen model.
Specifically, the method for establishing the identification antigen model comprises the following steps: and constructing a TCR feature extraction neural network, taking a TCR CDR3 sequence matrix as the input of a TCR feature extraction module, and carrying out unsupervised training. Training a self-encoder neural network capable of extracting the characteristics of the TCR sequence; a pMHC feature extraction neural network, wherein an HLA I sequence matrix and an antigen sequence matrix are used as the input of a pMHC feature extraction module, and a convolutional layer-based neural network capable of extracting the features of the pMHC sequence is trained; and the antigen identification neural network, the TCR characteristic vector and the pMHC characteristic vector are used as training sets, and the known combination state of the TCR characteristic vector and the pMHC characteristic vector is used as a classification label to train the antigen identification neural network.
And constructing a data set, describing TCR CDR3, HLA I and antigen sequences in the data set by adopting a Z descriptor, and normalizing the described matrixes to respectively determine a TCR CDR3 sequence matrix, an HLA I sequence matrix and an antigen sequence matrix.
Inputting the data set into a neural network, training the neural network to establish an identification antigen model, taking a TCR CDR3 sequence matrix as a training set, and extracting TCR characteristics from the neural network for training; inputting the TCR CDR3 sequence matrix into the trained TCR feature extraction neural network to obtain a TCR feature vector;
taking the HLA I sequence matrix and the antigen sequence matrix as training sets, and training the pMHC characteristic extraction neural network; inputting the HLA I sequence matrix and the antigen sequence matrix into a trained pMHC feature extraction neural network to obtain a pMHC feature vector;
and taking the TCR characteristic vector and the pMHC characteristic vector as a training set to train the antigen identification neural network.
In the embodiment, a neural network is constructed, a data set is input into the constructed neural network, the neural network is trained to obtain a feature vector, the feature vector is used as a training set to train the antigen identification neural network, an antigen identification model is established, and the aim of identifying the antigens related to the activated T cells is fulfilled.
Preferably, the method for establishing the identification antigen model further comprises: and describing TCR CDR3, HLA I and antigen sequences in the data set by adopting a Z descriptor, and normalizing the described matrixes to respectively determine a TCR CDR3 sequence matrix, an HLA I sequence matrix and an antigen sequence matrix.
Specifically, the Z descriptor is a highly condensed descriptor derived from Principal Component Analysis (PCA) of 29 experimental or calculated physicochemical properties of all naturally occurring amino acids, each amino acid in the protein sequence being represented by three Z descriptors, representing the hydrophobicity, spatial properties and polarity of the amino acid, respectively; each protein sequence is depicted as a matrix of 3*N, where N represents the protein sequence length. In the normalized matrix, each value is between-1 and 1.
In this embodiment, by performing normalization processing on the described matrix, subsequent data processing is more convenient, and the learning speed is increased.
Preferably, the inputting the data set into the neural network, training the neural network, includes:
taking the TCR CDR3 sequence matrix as a training set, and training the TCR feature extraction neural network; inputting the TCR CDR3 sequence matrix into a trained TCR feature extraction neural network to obtain a TCR feature vector;
training the pMHC characteristic extraction neural network by taking the HLA I sequence matrix and the antigen sequence matrix as training sets; inputting the HLA I sequence matrix and the antigen sequence matrix into a trained pMHC feature extraction neural network to obtain a pMHC feature vector;
and taking the TCR characteristic vector and the pMHC characteristic vector as a training set, and training the antigen identification neural network.
Specifically, the binding affinity of HLA and antigen is used as a training label of the module to carry out neural network training, and the binding affinity is a value between 0 and 1. The closer the numerical value is to 1, the higher the binding affinity of the two is, otherwise, the lower the binding affinity of the two is, through the step, the neural network can reduce the dimension of a two-dimensional matrix of HLA characteristics and a two-dimensional matrix of antigen characteristics through characteristic extraction, and the binding characteristics are extracted according to the binding affinity. Extracted pMHC sequence features this feature is represented by a series of vectors of length 50.
Preferably, before the training of the antigen identification neural network, the identification antigen model building method further includes: and balancing a training set consisting of the TCR characteristic vector and the pMHC characteristic vector by adopting a SMOTE algorithm.
Specifically, the balancing processing is performed on the training set by using the SMOTE algorithm, which further includes: and constructing a new few types of samples, and combining the new samples and the original data into a new training set. In the published data set, the reports of the combined negative data are less, the over-fitting problem occurs in the process of training the deep learning network due to the imbalance problem, and the STOME randomly selects adjacent samples according to the existing few samples to synthesize a new few samples as a training set to train the neural network.
In this embodiment, a SMOTE algorithm is used to perform a balance processing on a training set, a few class samples are analyzed and simulated, and a new sample that is simulated manually is added to a data set, so that the classes in the original data set are not seriously unbalanced any more, thereby solving the imbalance problem and preventing the overfitting problem.
Preferably, said training said antigen identifying neural network comprises: and taking whether the TCR characteristic vector and the pMHC characteristic vector can be combined or not as classification labels.
Specifically, the obtained TCR characteristic vector and the pMHC characteristic vector are used as a training set to train the antigen identification neural network, the known combination state of the TCR characteristic vector and the pMHC characteristic vector is used as a classification label, the neural network training of the antigen identification module is carried out, and the classification label is represented by 0 and 1 and respectively represents the combination negativity and the combination positivity of the TCR characteristic vector and the pMHC characteristic vector.
In the embodiment, the classification labels are adopted to respectively represent the combination states of the two, so that the neural network can better identify the antigen in the subsequent training learning.
Preferably, training the antigen discriminating neural network further comprises: and testing the trained neural network on a test set.
Specifically, the neural network structure is kept unchanged, the data proportion of the number verification set and the test set is changed, each proportion is trained for 50 times, the trained neural network is tested on the test set, and the network with the best effect is selected to serve as a final antigen identification module.
In the embodiment, multiple times of training are adopted, and the verification rate of the model is continuously kept at a higher level under the condition that the model parameters are changed, so that the accuracy and the stability of the model are ensured.
Preferably, the training set of TCR and pMHC feature vectors comprises artificial negative binding data.
Specifically, random substitutions of any one or more amino acids in the TCR sequences in the study database were made and, if the sequence was not present in the database of true TCR sequences, it was placed as an artificial negative TCR sequence in the negative TCR sequence library. Any TCR sequence in the negative TCR sequence library is matched with any known pMHC sequence, and then the combined negative TCR-pMHC pair can be obtained.
In the embodiment, a small amount of artificial negative binding data is added in the training set, so that the characteristic that the antigen identification neural network learns the artificial negative binding data can be realized, the network can learn more error patterns, and the training is more accurate.
Preferably, as shown in fig. 2, the TCR feature extraction neural network comprises an encoder module, a feature extraction module and a decoder module;
the convolutional layer module adopted by the encoder module comprises four Cov1D layers;
the characteristic extraction module comprises a full connection layer for outputting TCR sequence characteristics;
the decoder module includes four Conv1D layers.
In particular, the neural network is a self-encoder neural network. The network is an unsupervised training, and parameters are updated by comparing the similarity degree of input and output, so that the similarity degree of the input and output reaches a specified threshold value; the structures of the encoder module and the decoder module are in mirror symmetry; the convolution kernel sizes of the former Conv1D layers in the encoder module are 3, and the convolution kernel sizes of the latter Conv1D layers are 2.
In this embodiment, the TCR sequence feature extraction module and the sub-module can effectively extract a TCR CDR3 sequence matrix to improve the training effect on the neural network.
Preferably, as shown in fig. 3, the pMHC feature extraction neural network includes an HLA feature extraction module, an antigen feature extraction module, a feature extraction module, and a tag training module;
the HLA feature extraction module comprises four Cov1D layers, a Reshape layer and a full connection layer;
the antigen feature extraction module comprises four Cov1D layers, a Reshape layer and a full connection layer;
the characteristic extraction module comprises a full connection layer for outputting pMHC sequence characteristics;
the label training module comprises two full-connection layers.
Specifically, the convolution kernel size of the Conv1D layer in the HLA feature extraction module is 2, the convolution kernel size of the Conv1D layer in the antigen feature extraction module is 2, and the Reshape layer reduces the two-dimensional structure of the convolution layer output result into a one-dimensional structure.
In this embodiment, according to the pMHC sequence feature extraction module and the sub-module, the TCR CDR3 sequence matrix can be effectively extracted, so as to improve the training effect on the neural network.
Preferably, as shown in fig. 4, the antigen identification neural network includes a TCR characteristic learning module, a pMHC characteristic learning module and an output module;
the TCR feature learning module comprises two full connection layers;
the pMHC feature learning module comprises two full connection layers;
the output module adopts three full-connection layers for outputting antigen identification results.
Specifically, the input of the network is the output results of the TCR sequence feature extraction network and the pMHC sequence feature extraction network.
In this embodiment, the antigen sequence matrix can be effectively extracted according to the antigen identification module, so as to improve the training effect on the neural network.
As shown in fig. 5, another embodiment of the present invention further provides a method for identifying an antigen, comprising: obtaining TCR CDR3, HLA I and an antigen sequence which need to be detected, inputting the TCR CDR3, HLA I and the antigen sequence which need to be detected into an identification antigen model established by the identification antigen model establishing method, and obtaining an identification result of the antigen.
As shown in fig. 6, another embodiment of the present invention further provides an apparatus for identifying an antigen model, including: the building module is used for building a neural network, wherein the neural network comprises a TCR feature extraction neural network, a pMHC feature extraction neural network and an antigen identification neural network; also for constructing a construction data set, wherein the data set comprises TCR CDR3, HLA I and the antigen sequence; and the training module is used for inputting the data set into the neural network and training the neural network so as to establish an identification antigen model.
As shown in fig. 7, another embodiment of the present invention provides an apparatus for identifying an antigen model, comprising: the memory for storing a computer program; the processor, when executing the computer program, is adapted to carry out the method of identifying an antigen as described above.
Another embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program, and when the computer program is read and executed by a processor, the method for establishing an antigen model or identifying an antigen as described above is implemented.
Although the present disclosure has been described above, the scope of the present disclosure is not limited thereto. Various changes and modifications may be effected therein by one of ordinary skill in the pertinent art without departing from the spirit and scope of the present disclosure, and these changes and modifications are intended to be within the scope of the present disclosure.

Claims (10)

1. An identification antigen model building method, comprising:
constructing a neural network, wherein the neural network comprises a TCR feature extraction neural network, a pMHC feature extraction neural network and an antigen identification neural network;
constructing a data set, wherein the data set comprises TCR CDR3, HLA I, and an antigen sequence;
and inputting the data set into the neural network, and training the neural network to establish an antigen identification model.
2. The method of claim 1, further comprising:
and describing TCR CDR3, HLA I and antigen sequences in the data set by adopting a Z descriptor, and normalizing the described matrixes to respectively determine a TCR CDR3 sequence matrix, an HLA I sequence matrix and an antigen sequence matrix.
3. The method of claim 2, wherein inputting the data set into the neural network, training the neural network comprises:
taking the TCR CDR3 sequence matrix as a training set, and training the TCR feature extraction neural network; inputting the TCR CDR3 sequence matrix into a trained TCR feature extraction neural network to obtain a TCR feature vector;
training the pMHC characteristic extraction neural network by taking the HLA I sequence matrix and the antigen sequence matrix as training sets; inputting the HLA I sequence matrix and the antigen sequence matrix into a trained pMHC feature extraction neural network to obtain a pMHC feature vector;
and taking the TCR characteristic vector and the pMHC characteristic vector as a training set, and training the antigen identification neural network.
4. The method of claim 3, wherein before the training of the antigen-identifying neural network, the method further comprises:
and balancing a training set consisting of the TCR characteristic vector and the pMHC characteristic vector by adopting a SMOTE algorithm.
5. The method of claim 3, wherein training the antigen-identifying neural network comprises:
and taking the binding state of the TCR characteristic vector and the pMHC characteristic vector as a classification label.
6. The method of claim 3, wherein the training set of TCR and pMHC signature vectors comprises artificial negative binding data.
7. The method of claim 1, wherein the TCR feature extraction neural network comprises an encoder module, a feature extraction module, and a decoder module;
the convolutional layer module adopted by the encoder module comprises four Cov1D layers;
the characteristic extraction module comprises a full connection layer for outputting TCR sequence characteristics;
the decoder module includes four layers of Conv1D layers.
8. The method for building an identification antigen model according to claim 1, wherein the pMHC feature extraction neural network comprises an HLA feature extraction module, an antigen feature extraction module, a feature extraction module, and a tag training module;
the HLA feature extraction module comprises four Cov1D layers, a Reshape layer and a full connection layer;
the antigen feature extraction module comprises four Cov1D layers, a Reshape layer and a full connection layer;
the characteristic extraction module comprises a full connection layer for outputting pMHC sequence characteristics;
the label training module comprises two full-connection layers.
9. The method for building an antigen-identifying model according to claim 1, wherein the antigen-identifying neural network comprises a TCR feature learning module, a pMHC feature learning module, and an output module;
the TCR feature learning module comprises two full connection layers;
the pMHC feature learning module comprises two full connection layers;
the output module adopts three full-connection layers for outputting antigen identification results.
10. A method for identifying an antigen, comprising:
obtaining TCR CDR3, HLA I and an antigen sequence to be detected, inputting the TCR CDR3, HLA I and the antigen sequence to be detected into an identification antigen model established by the identification antigen model establishing method of any one of claims 1 to 9, and obtaining an identification result of the antigen.
CN202211066490.6A 2022-09-01 2022-09-01 Antigen identification model establishing method and antigen identification method Pending CN115497564A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211066490.6A CN115497564A (en) 2022-09-01 2022-09-01 Antigen identification model establishing method and antigen identification method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211066490.6A CN115497564A (en) 2022-09-01 2022-09-01 Antigen identification model establishing method and antigen identification method

Publications (1)

Publication Number Publication Date
CN115497564A true CN115497564A (en) 2022-12-20

Family

ID=84468609

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211066490.6A Pending CN115497564A (en) 2022-09-01 2022-09-01 Antigen identification model establishing method and antigen identification method

Country Status (1)

Country Link
CN (1) CN115497564A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117095825A (en) * 2023-10-20 2023-11-21 鲁东大学 Human immune state prediction method based on multi-instance learning

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117095825A (en) * 2023-10-20 2023-11-21 鲁东大学 Human immune state prediction method based on multi-instance learning
CN117095825B (en) * 2023-10-20 2024-01-05 鲁东大学 Human immune state prediction method based on multi-instance learning

Similar Documents

Publication Publication Date Title
CN111598881B (en) Image anomaly detection method based on variational self-encoder
CN109829430B (en) Cross-modal pedestrian re-identification method and system based on heterogeneous hierarchical attention mechanism
Salman et al. Classification of real and fake human faces using deep learning
CN111507370A (en) Method and device for obtaining sample image of inspection label in automatic labeling image
CN109919252B (en) Method for generating classifier by using few labeled images
CN105095863A (en) Similarity-weight-semi-supervised-dictionary-learning-based human behavior identification method
CN114743600B (en) Deep learning prediction method of target-ligand binding affinity based on gated attention mechanism
CN112364974B (en) YOLOv3 algorithm based on activation function improvement
CN110414587A (en) Depth convolutional neural networks training method and system based on progressive learning
CN114330650A (en) Small sample characteristic analysis method and device based on evolutionary element learning model training
CN113762417A (en) Method for enhancing HLA antigen presentation prediction system based on deep migration
CN113838524B (en) S-nitrosylation site prediction method, model training method and storage medium
CN115497564A (en) Antigen identification model establishing method and antigen identification method
CN108229505A (en) Image classification method based on FISHER multistage dictionary learnings
US11397868B2 (en) Fungal identification by pattern recognition
CN114610924A (en) Commodity picture similarity matching search method and system based on multi-layer classification recognition model
CN111177388A (en) Processing method and computer equipment
Khunratchasana et al. Thai digit handwriting image classification with convolutional neural networks
Nanditha et al. Classification of animals using toy images
CN115064217A (en) Protein immunogenicity classifier construction method, prediction method, device and medium
CN109145554A (en) A kind of recognition methods of keystroke characteristic abnormal user and system based on support vector machines
Yücel et al. Classification of tea leaves diseases by developed CNN, feature fusion, and classifier based model
CN113627522A (en) Image classification method, device and equipment based on relational network and storage medium
CN104778479B (en) A kind of image classification method and system based on sparse coding extraction
Hu et al. Deep learning-based classification of protein subcellular localization from immunohistochemistry images

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination