KR102547977B1 - Apparatus and method for generating tcr information corresponding to pmhc using artificial intelligence - Google Patents

Abstract

A method of training an artificial intelligence-based predictive model performed by a computing device is disclosed. The method corresponds to first input data corresponding to a major histocompatibility complex (MHC), second input data corresponding to a peptide, and CDR3 of a T Cell Receptor (TCR) corresponding to the MHC and the peptide Obtaining third input data that is - the first input data includes amino acids of a first sequence corresponding to the MHC, and the second input data includes amino acids of a second sequence corresponding to the peptide, And the third input data includes amino acids of a third sequence corresponding to the CDR3 - grouping process and segmentation for the first input data, the second input data, and the third input data ( generating a training data set by performing preprocessing including a segmenting process, and using the training data set, the artificial intelligence-based predictive model obtains the first input data and the second input data and training the artificial intelligence-based prediction model to generate a prediction result including the third input data from

Description

Method and apparatus for generating TCR information corresponding to pMHC using artificial intelligence technology

The present disclosure relates to artificial intelligence technology, and more specifically to analyzing the relationship between a peptide-major histocompatibility complex (pMHC) and T Cell Receptor (TCR) using artificial intelligence technology.

The major histocompatibility complex is a genetic locus that encodes 'MHC molecules' that function in the immune system. MHC molecules can exist in type 1 (class I) and type 2 (class II).

Immunopeptidome refers to a set of peptides expressed on the cell surface, and for example, the immunopeptidome may refer to a combination of MHC-related peptides.

Human Leukocyte Antigen (HLA) is a glycoprotein molecule produced by the human Major Histocompatibility Complex (MHC) gene. HLA does not exist in mature erythrocytes, but is expressed in immature erythroblasts and is expressed on the surface of all tissue cells in the human body, including blood cells such as leukocytes and/or platelets. The MHC gene is present in all vertebrates, and the human MHC gene is referred to as the HLA gene, and the product expressed therefrom is referred to as HLA.

MHC genes are involved in self and non-self recognition, immune response to antigen stimulation, regulation of cellular and humoral immunity, and susceptibility to disease. HLA, a product of the MHC gene, is the second most important antigen next to the ABO blood type in survival of the transplanted organ in solid organ transplantation. HLA is known to play the most important role in transplantation success or failure in bone marrow transplantation. Therefore, recognizing the difference in HLA immunologically can be seen as the first step of the rejection action for the transplanted tissue. In addition, in transfusion therapy, HLA and antibodies play an important role in the occurrence of various side effects such as platelet transfusion refractory, febrile nonhemorrhagic transfusion side effects, acute lung injury, and graft-versus-host disease after transfusion.

HLA, like MHC, can be largely classified into Class I and Class II. Class I is classified into HLA-A, HLA-B, and HLA-C, and is expressed in most nucleated cells and platelets, and antigen recognition when cytotoxic T cells recognize and remove virus-infected cells or tumor cells. ) is essential for HLA Class II is classified into HLA-DR, HLA-DQ, and HLA-DP, and is expressed in B cells, monocytes, dendritic cells, and activated T cells. and induces a humoral immune response, and is known to be essential when recognizing antigens expressed in antigen-presenting cells. HLA is a gene that shows the largest polymorphism among genes possessed by humans, and there is a frequency difference between races and ethnic groups.

When peptides derived from proteins derived from infectious microorganisms or proteins specific to cancer cells bind to MHC and are presented on the cell surface, T cells recognize them and trigger an immune response to eliminate infected cells or cancer cells. As such, T cells are key regulators (players) that determine specific immune responses to foreign substances that do not exist in the normal human body. Therefore, the prediction of TCR (T Cell Receptor) that binds to pMHC can be used for the development of personalized vaccines for the prevention of infectious diseases or cancer.

Korean Registered Patent No. 10-2322832

The present disclosure has been made in response to the above background art, and is intended to more efficiently and/or more accurately predict or identify a TCR capable of binding to pMHC.

The technical problems of the present disclosure are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the description below.

According to one embodiment of the present disclosure, a method of training an artificial intelligence-based predictive model performed by a computing device is disclosed. The method: first input data corresponding to a major histocompatibility complex (MHC), second input data corresponding to a peptide, and CDR3 of a T Cell Receptor (TCR) corresponding to the MHC and the peptide Obtaining third input data that is - the first input data includes amino acids of a first sequence corresponding to the MHC, and the second input data includes amino acids of a second sequence corresponding to the peptide, and the third input data includes amino acids of a third sequence corresponding to the CDR3; generating a training data set by performing preprocessing including a grouping process and a segmenting process on the first input data, the second input data, and the third input data; and using the training data set, the artificial intelligence-based predictive model generates a prediction result including the third input data from the first input data and the second input data. It may include the step of learning.

In an embodiment, the prediction result may further include V type and J type of the TCR corresponding to the first input data and the second input data.

In one embodiment, the grouping process may generate tokens having a length corresponding to each of the amino acid sequences of different lengths by analyzing the frequency of occurrence of each of the amino acid sequences of different lengths.

In one embodiment, the grouping process comprises: generating a first token group for a first set of amino acid sequences obtained by analyzing the frequency of occurrence for amino acid sequences having a first length; And a second set obtained by analyzing the frequency of occurrence of amino acid sequences having a second length shorter than the first length in a state in which the amino acid sequences of the first set included in the first group are excluded. It may include generating a second token group comprising amino acid sequences of. Tokens included in the first token group may have the first length, and tokens included in the second token group may have the second length.

In one embodiment, the occurrence frequency is: a value quantitatively representing a probability that a specific amino acid sequence is found within one CDR3 sequence; Alternatively, it may include a value quantitatively representing the ratio of the number of times a specific amino acid sequence is found in all CDR3s to the number of all CDR3s.

In an embodiment, tokenization may be performed on each of the first input data, the second input data, and the third input data based on the tokens generated by the grouping process.

In an embodiment, the segmenting process may include first learning including first tokens corresponding to the first input data and third tokens corresponding to the third input data with a separator token interposed therebetween. A second training data set including a data set and second tokens corresponding to the second input data and third tokens corresponding to the third input data may be generated with a separator token interposed therebetween. Here, the third tokens are used as correct answer data in the learning process of the prediction model, and the first training data set and the second training data set can be learned by different artificial intelligence networks in the prediction model. .

In one embodiment, the segmenting process may include first tokens corresponding to the first input data, second tokens corresponding to the second input data, and between the first tokens and the second tokens. Generating a third learning data set, including a first delimiter token positioned at the location, third tokens corresponding to the third input data, and a second delimiter token positioned between the second tokens and the third tokens. can do. Here, the third tokens may be used as correct answer data in the learning process of the prediction model.

In one embodiment, the grouping process comprises: obtaining a CDR3 list from an external database or a database included in the computing device; determining a first occurrence frequency in the CDR3 list for each of the amino acid sets of which the length of the amino acid sequence is K; determining a first amino acid set having the first frequency of occurrence equal to or greater than a predetermined first threshold value among amino acid sets having a length of K of the amino acid sequence; determining a second frequency of occurrence in the CDR3 list for each of the amino acid sets of which the length of the amino acid sequence is K-1; determining a second amino acid set whose second frequency of occurrence is greater than or equal to a predetermined second threshold value among amino acid sets having a length of the amino acid sequence of K−1; and performing tokenization with a length of K for the first set of amino acids and performing tokenization with a length of K−1 for the second set of amino acids. Here, K is a natural number equal to or greater than 2, and the first threshold value and the second threshold value may have the same or different values.

In one embodiment, the step of determining the second frequency of occurrence may include, for each of the amino acid sets having a length of K-1, the amino acid sequence within a range excluding the first amino acid set from the CDR3 list. and determining the second frequency of occurrence.

In one embodiment, the grouping process comprises: obtaining a CDR3 list from an external database or a database included in the computing device; Among the amino acid sets having an amino acid sequence length of N-M, the M+1 amino acid set whose frequency of occurrence in the CDR3 list is equal to or greater than a predetermined threshold is included in the token list, and the M+1 amino acid set is included in the CDR3 list. constructing the token list, in a manner removing from, where M is an integer greater than or equal to 0, and N-M is a natural number greater than 2; After the step of constructing the token list is performed, increasing the value of M by 1 and determining whether an end condition is satisfied, and constructing the token list when the end condition is not satisfied. Re-performing, and if the end condition is satisfied, performing tokenization by generating a token corresponding to each of the amino acid sets with an amino acid sequence length corresponding to each of the amino acid sets included in the token list. can include

In one embodiment, the terminating condition may include a first terminating condition corresponding to N−M≤1.

In one embodiment, the termination condition includes a second termination condition corresponding to N-M≤2, and the performing of the tokenization may include the number of tokens corresponding to the type of amino acids having a length of 1 in the amino acid sequence. It may further include performing the tokenization in an additional generating manner.

In one embodiment, the predetermined threshold value may be varied to have a negative correlation with the size of the value of N−M.

In one embodiment, the artificial intelligence-based prediction model may include a recurrent neural network (RNN), a long short term memory (LSTM) network, or a bidirectional encoder representations from transformers (BERT).

In one embodiment, the step of learning the artificial intelligence-based predictive model is semi-supervised learning (semi-supervised learning) to match the masked amino acids after applying a mask to some of the amino acids among the amino acid sequences. learning) may be included.

In one embodiment, the step of learning the artificial intelligence-based prediction model is, after applying a mask to amino acids included in the amino acids of the third sequence corresponding to the CDR3 among amino acid sequences, the half matching the masked amino acids - It may include the step of performing supervised learning.

In one embodiment, the step of learning the artificial intelligence-based predictive model may include applying the mask to a different location in units of epochs or in units of epochs when the prediction model is learned over a plurality of epochs. It may include applying the mask of a different size to .

In one embodiment, the step of learning the artificial intelligence-based predictive model may include, when a plurality of masks exist for one training data, the artificial intelligence-based predictive model selects one mask from among the plurality of masks. When predicting, one can apply an amino acid X representing all amino acids or the average value of amino acids to another mask.

In one embodiment, the step of learning the artificial intelligence-based predictive model includes the third input data, which is experimentally determined to have no immunogenicity with respect to the first input data and the second input data. and learning the artificial intelligence-based predictive model by using it as correct answer data. Here, the third input data may not be randomly generated during the learning process of the artificial intelligence-based predictive model.

In one embodiment, a computer program stored on a computer readable storage medium is disclosed. The computer program, when executed by a computing device, causes the computing device to perform operations for learning an artificial intelligence-based predictive model, the operations comprising: first input data corresponding to a major histocompatibility complex (MHC), peptide Obtaining second input data corresponding to and third input data corresponding to CDR3 of the TCR corresponding to the MHC and the peptide, wherein the first input data includes amino acids of a first sequence corresponding to the MHC, , wherein the second input data includes amino acids of a second sequence corresponding to the peptide, and the third input data includes amino acids of a third sequence corresponding to the CDR3; generating a training data set by performing preprocessing including a grouping process and a segmenting process on the first input data, the second input data, and the third input data; and using the training data set, the artificial intelligence-based predictive model generates a prediction result including the third input data from the first input data and the second input data. It may include an operation to learn.

A computing device according to an embodiment is disclosed. The computing device may include at least one processor; and memory. The at least one processor: first input data corresponding to the major histocompatibility complex (MHC), second input data corresponding to the peptide, and third input data corresponding to the MHC and CDR3 of the TCR corresponding to the peptide Obtaining - the first input data includes amino acids of a first sequence corresponding to the MHC, the second input data includes amino acids of a second sequence corresponding to the peptide, and the third input data contains the amino acids of the third sequence corresponding to the CDR3; generating a training data set by performing preprocessing including a grouping process and a segmenting process on the first input data, the second input data, and the third input data; and using the training data set, the artificial intelligence-based predictive model generates a prediction result including the third input data from the first input data and the second input data. You can perform an operation to learn.

The method and apparatus according to an embodiment of the present disclosure can more efficiently and/or more accurately predict or identify a TCR capable of binding to pMHC.

1 schematically illustrates a block configuration diagram of a computing device according to an embodiment of the present disclosure.
2 illustrates an exemplary structure of an artificial intelligence-based model according to an embodiment of the present disclosure.
3 exemplarily illustrates a method of learning a predictive model that generates a prediction result including a CDR3 sequence of a TCR according to an embodiment of the present disclosure.
Figure 4 exemplarily illustrates a method for generating a prediction result comprising a CDR3 sequence of a TCR according to an embodiment of the present disclosure.
5 illustratively illustrates a grouping process according to one embodiment of the present disclosure.
6 illustratively illustrates a segmenting process according to an embodiment of the present disclosure.
7 is a schematic diagram of a computing environment according to one embodiment of the present disclosure.

Various embodiments are described with reference to the drawings. In this specification, various descriptions are presented to provide an understanding of the present disclosure. Prior to describing specific details for the implementation of the present disclosure, it should be noted that configurations not directly related to the technical gist of the present disclosure have been omitted within the scope of not distracting from the technical gist of the present invention. In addition, the terms or words used in this specification and claims have meanings consistent with the technical idea of the present invention based on the principle that the inventor can define the concept of appropriate terms in order to best describe his/her invention. concept should be interpreted.

As used herein, the terms "component", "module", "system", "unit", and the like refer to a computer-related entity, hardware, firmware, software, a combination of software and hardware, or an execution of software, and are interchangeable. can possibly be used. For example, a component may be, but is not limited to, a procedure, processor, object, thread of execution, program, and/or computer running on a processor. For example, both an application running on a computing device and a computing device may be components. One or more components may reside within a processor and/or thread of execution. A component can be localized within a single computer. A component may be distributed between two or more computers. Also, these components can execute from various computer readable media having various data structures stored thereon. Components may be connected, for example, via signals with one or more packets of data (e.g., data and/or signals from one component interacting with another component in a local system, distributed system) to other systems and over a network such as the Internet. data being transmitted) may communicate via local and/or remote processes.

In addition, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or”. That is, unless otherwise specified or clear from the context, “X employs A or B” is intended to mean one of the natural inclusive substitutions. That is, X uses A; X uses B; Or, if X uses both A and B, "X uses either A or B" may apply to either of these cases. Also, the term "and/or" as used herein should be understood to refer to and include all possible combinations of one or more of the listed related items.

Also, the terms "comprises" and/or "comprising" should be understood to mean that the features and/or components are present. However, it should be understood that the terms "comprises" and/or "comprising" do not exclude the presence or addition of one or more other features, elements, and/or groups thereof. Also, unless otherwise specified or where the context clearly indicates that a singular form is indicated, the singular in this specification and claims should generally be construed to mean "one or more".

In addition, the term "at least one of A or B" or "at least one of A and B" means "includes only A", "includes only B", "includes A and B in combination" should be interpreted as meaning

Those skilled in the art will further understand that the various illustrative logical components, blocks, modules, circuits, means, logics, and algorithms described in connection with the embodiments disclosed herein may be electronic hardware, computer software, or combinations of both. It should be recognized that it can be implemented as To clearly illustrate the interchangeability of hardware and software, various illustrative components, blocks, means, logics, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented in hardware or as software depends on the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application. However, such implementation decisions should not be interpreted as causing a departure from the scope of this disclosure.

The description of the presented embodiments is provided to enable any person skilled in the art to use or practice the present invention. Various modifications to these embodiments will be apparent to those skilled in the art of this disclosure. The general principles defined herein may be applied to other embodiments without departing from the scope of this disclosure. Thus, the present invention is not limited to the embodiments presented herein. The present invention is to be accorded the widest scope consistent with the principles and novel features set forth herein.

In the present disclosure, terms expressed as Nth, such as first, second, or third, are used to distinguish at least one entity. For example, entities represented as first and second may be the same as or different from each other.

In the present disclosure, for convenience of description, human leukocyte antigen (HLA) is exemplarily used as an example for MHC. Therefore, the description of HLA or MHC used below is an example for expressing a description of MHC or HLA, and the scope of the present disclosure will be determined based on the content described in the claims, through examples of HLA. The scope of the right should not be construed as limited to HLA. As such, HLA and MHC in the present disclosure may be used interchangeably.

As used in the present disclosure, the term “human leukocyte antigen (HLA)” is a glycoprotein molecule produced by the human MHC gene, and is a gene that shows the largest polymorphism among genes possessed by humans. HLA typing, which determines the HLA type, can be used very actively in various fields such as organ transplantation, immunotherapy, disease-related research, paternity tests such as paternity, forensic use, and genetic research.

An HLA type in the present disclosure may include, for example, an HLA-A type, an HLA-B type, and/or an HLA-C type.

In one embodiment, the conjugate of MHC and peptide may mean a peptide antigen presenting complex through MHC class I molecules through processing through proteasome in antigen presenting cell (APC). The proteasome is composed of two units, LMP-2 and LMP-7 (low molecular weight polypeptide). These two proteasome units are located near the TAP-1 and TAP-2 genes in the MHC gene. The proteasome subunits are particularly important for the degradation of peptides bound to MHC I molecules. When cells are treated with the cytokine interferon gamma (IFN-γ), the expression of LMP-2 and LMP-7 can be induced. Expression of LMP-2 and LMP-7 results in a change in the substrate specificity of the proteasome, increasing its ability to degrade into peptides. IFN-γ increases the expression of proteins related to antigen presentation, such as MHC I and MECL-1, as well as LMP proteins, so that antigen presentation can be increased in antigen-presenting cells.

MHC I molecules bind not only to peptide antigens degraded by the proteasome, but also to peptides produced by proteolytic enzymes present in the endoplasmic reticulum.

Tapasin serves as a bridge between TAP-1 (transporter associated with antigen processing) and MHC I, which has a stable tertiary structure in the endoplasmic reticulum (ER). It leaves the Shin and TAP proteins and becomes a complete peptide-MHC class I complex.

There are two types of T cell receptor (TCR), mainly composed of TCRα and TCRβ. The TCRα chain is located on chromosome 14, and the TCRβ chain is located at an independent locus on chromosome 7. Similar to the immunoglobulin (Ig) heavy chain, TCRβ is composed of a V gene segment, a D gene segment, a J gene segment, and a C gene segment, and the TCRα chain has a D gene segment similar to an Ig light chain. It is composed of V, J, and C gene segments.

The recombination process of the TCR is similar to that of the B cell receptor. The TCRα chain is encoded by the V, J and C gene segments, similar to the immunoglobulin light chain, and the TCRβ chain binds DJ to V-D-J, which is formed by V-D-J. formed through genetic recombination. The linkage of V-(D)-J is mediated by RAG-1 and RAG-2 (recombination-activating gene).

The hairpin structure is cleaved by an endonuclease, and a complementary P-nucleotide is added to the short strand of DNA formed at this time. In addition, 1 to 20 nucleotides can be randomly added to the cleavage ends, which are called N-nucleotides, and this process is mediated by TdT (terminal deoxynucleotide transferase). P- and N-nucleotides increase the diversity of T-cell receptors.

T cells recognize only foreign antigens presented on the cell surface, and the activity of mature peripheral T cells is initiated by the interaction between antigens and peptides presented at the peptide binding cleft of TCR and MHC molecules.

In particular, most immune profiling focuses on the analysis of the CDR3 region within the TCR sequence. The CDR3 region is an important region involved in the interaction between an antigen and a receptor, and is identified with the most mutations.

1 schematically illustrates a block configuration diagram of a computing device 100 according to one embodiment of the present disclosure.

Computing device 100 according to an embodiment of the present disclosure may include a processor 110 and a memory 130 .

The configuration of the computing device 100 shown in FIG. 1 is only a simplified example. In one embodiment of the present disclosure, the computing device 100 may include other components for performing a computing environment of the computing device 100, and only some of the disclosed components may constitute the computing device 100.

The computing device 100 in the present disclosure may mean any type of node constituting a system for implementing embodiments of the present disclosure. The computing device 100 may refer to any type of user terminal or any type of server. Components of the aforementioned computing device 100 are exemplary and some may be excluded or additional components may be included. For example, when the aforementioned computing device 100 includes a user terminal, an output unit (not shown) and an input unit (not shown) may be included within the scope of the computing device 100 .

The computing device 100 in the present disclosure may perform technical features according to embodiments of the present disclosure to be described later. For example, the computing device 100 may generate a prediction result including the CDR3 sequence of the TCR corresponding to the input data using an artificial intelligence-based prediction model using input data corresponding to MHC and peptide. For example, the computing device 100 may obtain information on MHC and peptides from a sample obtained from a subject, and generate a prediction result corresponding to CDR3 of the TCR based on the information on MHC and peptides.

In one embodiment of the present disclosure, the computing device 100 may obtain a result of base sequence analysis (eg, Next Generation Sequencing) from a server or an external entity. In another embodiment, the computing device 100 may perform nucleotide sequence analysis on genetic data (eg, DNA or RNA) obtained from a biological sample derived from a subject. The term used in the present disclosure, sequencing may be performed by any type of technique capable of analyzing the sequence of bases, for example, whole genome sequencing, whole exome It may include, but is not limited to, whole exome sequencing or whole transcriptome sequencing.

As used in the present disclosure, a subject may refer to a subject or individual for obtaining a biological sample containing a major histocompatibility complex (MHC), a peptide, and/or a complex thereof.

As used in the present disclosure, the term, sample, can be used without limitation as long as it is obtained from an individual or subject whose MHC type is to be determined, and for example, cells or tissues obtained by biopsy, blood, whole blood, serum, plasma, saliva, It may be cerebrospinal fluid, various secretions, urine and/or feces, and the like. Preferably, the sample may be selected from the group consisting of blood, plasma, serum, saliva, nasal fluid, sputum, ascites, vaginal secretion and/or urine, and more preferably blood, plasma or serum. The sample may be pre-treated prior to use in detection or diagnosis. For example, pretreatment methods may include homogenization, filtration, distillation, extraction, concentration, inactivation of interfering components, and/or addition of reagents, and the like. In the present disclosure, a biological sample may be tissue, cell, whole blood, and/or blood, but is not limited thereto.

In one embodiment, the processor 110 may include at least one core, and may include a central processing unit (CPU) or a general purpose graphics processing unit (GPGPU) of the computing device 100 . , a processor for data analysis and/or processing, such as a tensor processing unit (TPU).

The processor 110 may read the computer program stored in the memory 130 to generate a prediction result including the CDR3 sequence of the TCR according to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, the processor 110 may perform an operation for learning a neural network. The processor 110 is used for neural network learning, such as processing input data for learning in deep learning (DL), extracting features from input data, calculating errors, and updating neural network weights using backpropagation. calculations can be performed. At least one of the CPU, GPGPU, and TPU of the processor 110 may process learning of the network function. For example, the CPU and GPGPU can process learning of network functions and data classification using network functions. In addition, in one embodiment of the present disclosure, learning of a network function and data classification using a network function may be processed by using processors of a plurality of computing devices together. In addition, a computer program executed in a computing device according to an embodiment of the present disclosure may be a CPU, GPGPU or TPU executable program.

Additionally, the processor 110 may typically handle overall operations of the computing device 100 . For example, the processor 110 processes data, information, signals, etc. input or output through components included in the computing device 100 or drives an application program stored in a storage unit, thereby providing appropriate information or information to the user. A function can be provided or processed.

According to one embodiment of the present disclosure, memory 130 may store any type of information generated or determined by processor 110 and any type of information received by computing device 100 . According to one embodiment of the present disclosure, the memory 130 may be a storage medium that stores computer software that causes the processor 110 to perform operations according to embodiments of the present disclosure. Accordingly, the memory 130 may refer to computer readable media for storing software codes necessary for performing embodiments of the present disclosure, data subject to execution of the codes, and results of execution of the codes.

According to an embodiment of the present disclosure, the memory 130 may refer to any type of storage medium. For example, the memory 130 may be a flash memory type, a hard disk type ), multimedia card micro type, card type memory (eg SD or XD memory, etc.), RAM (Random Access Memory, RAM), SRAM (Static Random Access Memory), ROM (Read-Only memory, ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, and optical disk. The computing device 100 may operate in relation to a web storage that performs a storage function of the memory 130 on the Internet. The description of the above memory is only an example, and the memory 130 used in the present disclosure is not limited to the above example.

The communication unit (not shown) in the present disclosure may be configured regardless of its communication mode, such as wired and wireless, and may be configured in various communication networks such as a personal area network (PAN) and a wide area network (WAN). can be configured. In addition, the network unit 150 may operate based on the known World Wide Web (WWW), and a wireless transmission technology used for short-range communication such as Infrared Data Association (IrDA) or Bluetooth. can also be used.

The computing device 100 in the present disclosure may include any type of user terminal and/or any type of server. Accordingly, embodiments of the present disclosure may be performed by a server and/or a user terminal.

A user terminal may include any type of terminal capable of interacting with a server or other computing device. User terminals include, for example, mobile phones, smart phones, laptop computers, personal digital assistants (PDAs), slate PCs, tablet PCs, and ultrabooks. can include

A server may include any type of computing system or computing device, such as, for example, microprocessors, mainframe computers, digital processors, portable devices and device controllers, and the like.

In a further embodiment, the aforementioned server may refer to an entity that stores and manages TCR information, immunopeptidome information, peptide sequence information, base sequence information, or gene information. The server is used to store immunopeptidome information, peptide sequence information, positional amino acid identifier information, nucleotide sequence information, gene information or database (eg, McPas, TCR3F, Huarc, VDJdb, IMGT) reliability information, etc. It may include a storage unit (not shown), and the storage unit may be included in a server or may exist under the management of a server. As another example, the storage unit may exist outside the server and may be implemented in a form capable of communicating with the server. In this case, the storage unit may be managed and controlled by another external server different from the server.

2 illustrates an exemplary structure of an artificial intelligence-based model according to an embodiment of the present disclosure.

Throughout this specification, the terms predictive model, artificial intelligence-based predictive model, artificial intelligence model, artificial intelligence-based model, computational model, neural network, network function, and neural network may be used interchangeably.

A neural network may consist of a set of interconnected computational units, which may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network includes one or more nodes. Nodes (or neurons) constituting neural networks may be interconnected by one or more links.

In a neural network, one or more nodes connected through a link may form a relative relationship of an input node and an output node. The concept of an input node and an output node is relative, and any node in an output node relationship with one node may have an input node relationship with another node, and vice versa. As described above, an input node to output node relationship may be created around a link. More than one output node can be connected to one input node through a link, and vice versa.

In a relationship between an input node and an output node connected through one link, the value of data of the output node may be determined based on data input to the input node. Here, a link interconnecting an input node and an output node may have a weight. The weight may be variable, and may be changed by a user or an algorithm in order to perform a function desired by the neural network. For example, when one or more input nodes are interconnected by respective links to one output node, the output node is set to a link corresponding to values input to input nodes connected to the output node and respective input nodes. An output node value may be determined based on the weight.

As described above, in the neural network, one or more nodes are interconnected through one or more links to form an input node and output node relationship in the neural network. Characteristics of the neural network may be determined according to the number of nodes and links in the neural network, an association between the nodes and links, and a weight value assigned to each link. For example, when there are two neural networks having the same number of nodes and links and different weight values of the links, the two neural networks may be recognized as different from each other.

A neural network may be composed of a set of one or more nodes. A subset of nodes constituting a neural network may constitute a layer. Some of the nodes constituting the neural network may form one layer based on distances from the first input node. For example, a set of nodes having a distance of n from the first input node may constitute n layers. The distance from the first input node may be defined by the minimum number of links that must be passed through to reach the corresponding node from the first input node. However, the definition of such a layer is arbitrary for explanation, and the order of a layer in a neural network may be defined in a method different from the above. For example, a layer of nodes may be defined by a distance from a final output node.

In one embodiment of the present disclosure, a set of neurons or nodes may be defined as a layer.

An initial input node may refer to one or more nodes to which data is directly input without going through a link in relation to other nodes among nodes in the neural network. Alternatively, in a relationship between nodes based on a link in a neural network, it may mean nodes that do not have other input nodes connected by a link. Similarly, the final output node may refer to one or more nodes that do not have an output node in relation to other nodes among nodes in the neural network. Also, the hidden node may refer to nodes constituting the neural network other than the first input node and the last output node.

In the neural network according to an embodiment of the present disclosure, the number of nodes in the input layer may be the same as the number of nodes in the output layer, and the number of nodes decreases and then increases again as the number of nodes progresses from the input layer to the hidden layer. can In addition, the neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes of the input layer may be less than the number of nodes of the output layer and the number of nodes decreases as the number of nodes increases from the input layer to the hidden layer. there is. In addition, the neural network according to another embodiment of the present disclosure is a neural network in which the number of nodes in the input layer may be greater than the number of nodes in the output layer, and the number of nodes increases as the number of nodes increases from the input layer to the hidden layer. can A neural network according to another embodiment of the present disclosure may be a neural network in the form of a combination of the aforementioned neural networks.

A deep neural network (DNN) may refer to a neural network including a plurality of hidden layers in addition to an input layer and an output layer. Deep neural networks can reveal latent structures in data. That is, the structure of a photograph, text, video, audio, protein sequence structure, gene sequence structure, peptide sequence structure, music potential structure (e.g., what objects are in the picture, what the content and emotion of the text are, audio What is the content and emotion of , etc.), and/or the binding affinity between the peptide and MHC can be grasped. Deep neural networks include convolutional neural networks (CNNs), recurrent neural networks (RNNs), auto encoders, generative adversarial networks (GANs), restricted Boltzmann machines ( It may include a restricted boltzmann machine (RBM), a deep belief network (DBN), a Q network, a U network, a Siamese network, and the like. The description of the deep neural network described above is only an example, and the present disclosure is not limited thereto.

As an example, the AI-based predictive model of the present disclosure may include a Recurrent Neural Network (RNN), a Long Short Term Memory (LSTM) network, or a Bidirectional Encoder Representations from Transformers (BERT). can

The artificial intelligence-based predictive model of the present disclosure may be represented by a network structure of any of the foregoing structures including an input layer, a hidden layer, and an output layer.

A neural network that can be used in the artificial intelligence-based model of the present disclosure is at least one of supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. can be learned in this way. Learning of the neural network may be a process of applying knowledge for the neural network to perform a specific operation to the neural network. For example, the predictive model according to an embodiment of the present disclosure applies a mask to some of the amino acids of the amino acid sequences, and then matches the masked amino acids. Semi-supervised learning can be learned in a way

A neural network can be trained in a way that minimizes output errors. In the learning of the neural network, the learning data is repeatedly input into the neural network, the output of the neural network for the training data and the error of the target are calculated, and the error of the neural network is transferred from the output layer of the neural network to the input layer in the direction of reducing the error. It is a process of updating the weight of each node of the neural network by backpropagating in the same direction. In the case of supervised learning, each learning data is labeled with the correct answer (ie, labeled learning data), and in the case of unsupervised learning, the correct answer may not be labeled in each learning data. That is, for example, learning data in the case of supervised learning related to data classification may be data in which each learning data is labeled with a category. Labeled training data is input to a neural network, and an error may be calculated by comparing an output (category) of the neural network and a label of the training data. As another example, in the case of unsupervised learning for data classification, an error may be calculated by comparing input learning data with a neural network output. The calculated error is back-propagated in a reverse direction (ie, from the output layer to the input layer) in the neural network, and the connection weight of each node of each layer of the neural network may be updated according to the back-propagation. The amount of change in the connection weight of each updated node may be determined according to a learning rate. The neural network's computation of input data and backpropagation of errors can constitute a learning cycle (epoch). The learning rate may be applied differently according to the number of iterations of the learning cycle of the neural network. For example, a high learning rate may be used in the early stage of neural network training to increase efficiency by allowing the neural network to quickly obtain a certain level of performance, and a low learning rate may be used in the late stage to increase accuracy.

In neural network learning, generally, training data can be a subset of real data (ie, data to be processed using the trained neural network), and therefore, errors for training data are reduced, but errors for real data are reduced. There may be incremental learning cycles. Overfitting is a phenomenon in which errors for actual data increase due to excessive learning on training data. For example, a phenomenon in which a neural network that has learned a cat by showing a yellow cat does not recognize that it is a cat when it sees a cat other than yellow may be a type of overfitting. Overfitting can act as a cause of increasing the error of machine learning algorithms. Various optimization methods can be used to prevent such overfitting. In order to prevent overfitting, methods such as increasing the training data, regularization, inactivating some nodes in the network during learning, and using a batch normalization layer are methods. can be applied

A computer readable medium storing a data structure according to an embodiment of the present disclosure is disclosed. The above-described data structure may be stored in a storage unit in the present disclosure, executed by a processor, and transmitted and received by a communication unit.

Data structure can refer to the organization, management, and storage of data that enables efficient access and modification of data. Data structure may refer to the organization of data to solve a specific problem (eg, data retrieval, data storage, data modification in the shortest time). A data structure may be defined as a physical or logical relationship between data elements designed to support a specific data processing function. A logical relationship between data elements may include a connection relationship between user-defined data elements. A physical relationship between data elements may include an actual relationship between data elements physically stored in a computer-readable storage medium (eg, a persistent storage device). The data structure may specifically include a set of data, a relationship between data, and a function or command applicable to the data. Through an effectively designed data structure, a computing device can perform calculations while using minimal resources of the computing device. Specifically, the computing device can increase the efficiency of operation, reading, insertion, deletion, comparison, exchange, and search through an effectively designed data structure.

The data structure can be divided into a linear data structure and a non-linear data structure according to the shape of the data structure. A linear data structure may be a structure in which only one data is connected after one data. Linear data structures may include lists, stacks, queues, and decks. A list may refer to a series of data sets in which order exists internally. The list may include a linked list. A linked list may be a data structure in which data are connected in such a way that each data is connected in a single line with a pointer. In a linked list, a pointer can contain information about connection to the next or previous data. A linked list can be expressed as a singly linked list, a doubly linked list, or a circular linked list depending on the form. A stack can be a data enumeration structure that allows limited access to data. A stack can be a linear data structure in which data can be processed (eg, inserted or deleted) at only one end of the data structure. The data stored in the stack may be a LIFO-Last in First Out (Last in First Out) data structure. A queue is a data listing structure that allows limited access to data, and unlike a stack, it can be a data structure (FIFO-First in First Out) in which data stored later comes out later. A deck can be a data structure that can handle data from either end of the data structure.

The nonlinear data structure may be a structure in which a plurality of data are connected after one data. The non-linear data structure may include a graph data structure. A graph data structure can be defined as a vertex and an edge, and an edge can include a line connecting two different vertices. A graph data structure may include a tree data structure. The tree data structure may be a data structure in which one path connects two different vertices among a plurality of vertices included in the tree. That is, it may be a data structure that does not form a loop in a graph data structure.

Throughout this specification, artificial intelligence-based models, computational models, neural networks, network functions, and neural networks may be used interchangeably. Hereinafter, a neural network is unified and described. The data structure may include a neural network. And the data structure including the neural network may be stored in a computer readable medium. The data structure including the neural network may also include preprocessed data for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation function associated with each node or layer of the neural network, and neural network It may include a loss function for learning of . A data structure including a neural network may include any of the components described above. That is, the data structure including the neural network includes preprocessed data for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation function associated with each node or layer of the neural network, and neural network. It may be configured to include all or any combination thereof, such as a loss function for learning of . In addition to the foregoing configurations, the data structure comprising the neural network may include any other information that determines the characteristics of the neural network. In addition, the data structure may include all types of data used or generated in the computational process of the neural network, but is not limited to the above. A computer readable medium may include a computer readable recording medium and/or a computer readable transmission medium. A neural network may consist of a set of interconnected computational units, which may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network includes one or more nodes.

The data structure may include data input to the neural network. A data structure including data input to the neural network may be stored in a computer readable medium. Data input to the neural network may include training data input during a neural network learning process and/or input data input to a neural network that has been trained. Data input to the neural network may include pre-processed data and/or data subject to pre-processing. Pre-processing may include a data processing process for inputting data to a neural network. Accordingly, the data structure may include data subject to pre-processing and data generated by pre-processing. The foregoing data structure is only an example, and the present disclosure is not limited thereto.

The data structure may include the weights of the neural network. (In this specification, weights and parameters may be used in the same meaning.) Also, a data structure including weights of a neural network may be stored in a computer readable medium. A neural network may include a plurality of weights. The weight may be variable, and may be changed by a user or an algorithm in order to perform a function desired by the neural network. For example, when one or more input nodes are interconnected by respective links to one output node, the output node is set to a link corresponding to values input to input nodes connected to the output node and respective input nodes. A data value output from an output node may be determined based on the weight. The foregoing data structure is only an example, and the present disclosure is not limited thereto.

As a non-limiting example, the weights may include weights that are varied during neural network training and/or weights for which neural network training has been completed. The variable weight in the neural network learning process may include a weight at the time the learning cycle starts and/or a variable weight during the learning cycle. The weights for which neural network learning has been completed may include weights for which learning cycles have been completed. Accordingly, the data structure including the weights of the neural network may include a data structure including weights that are variable during the neural network learning process and/or weights for which neural network learning is completed. Therefore, it is assumed that the above-described weights and/or combinations of weights are included in the data structure including the weights of the neural network. The foregoing data structure is only an example, and the present disclosure is not limited thereto.

The data structure including the weights of the neural network may be stored in a computer readable storage medium (eg, a memory or a hard disk) after going through a serialization process. Serialization can be the process of converting a data structure into a form that can be stored on the same or another computing device and later reconstructed and used. A computing device may serialize data structures to transmit and receive data over a network. The data structure including the weights of the serialized neural network may be reconstructed on the same computing device or another computing device through deserialization. The data structure including the weights of the neural network is not limited to serialization. Furthermore, the data structure including the weights of the neural network is a data structure for increasing the efficiency of operation while minimizing the resource of the computing device (for example, B-Tree, R-Tree, Trie, m-way search tree in a nonlinear data structure) , AVL tree, Red-Black Tree). The foregoing is only an example, and the present disclosure is not limited thereto.

The data structure may include hyper-parameters of the neural network. Also, the data structure including the hyperparameters of the neural network may be stored in a computer readable medium. A hyperparameter may be a variable variable by a user. Hyperparameters include, for example, learning rate, cost function, number of learning cycle iterations, weight initialization (eg, setting the range of weight values to be targeted for weight initialization), hidden unit number (eg, the number of hidden layers and the number of nodes in the hidden layer). The foregoing data structure is only an example, and the present disclosure is not limited thereto.

A transformer may be considered as a network function for a predictive model according to an embodiment of the present disclosure. As an example, the predictive model may be operated based on a transformer. Such a predictive model may be operated using, for example, a recurrent neural network to which an attention algorithm is applied or a transformer to which an attention algorithm is applied.

In one embodiment, a transformer may consist of an encoder that encodes the embedded data and a decoder that decodes the encoded data. The transformer may have a structure that receives a series of data and outputs a series of data of different types through encoding and decoding steps. In one embodiment, the series of data can be processed into a form operable by a transformer. A process of processing a series of data into a form in which a transformer can operate may include an embedding process. Expressions such as data token, embedding vector, and embedding token may refer to embedded data in a form that can be processed by a transformer.

In order for the transformer to encode and decode a series of data, encoders and decoders within the transformer may be processed using an attention algorithm. The Attention Algorithm is to obtain the similarity of one or more keys for a given query, reflect the given similarity to each key and corresponding value, and then reflect the similarity to the value ( Values) may mean an algorithm that calculates an attention value by weighting.

Depending on how to set the query, key, and value, various types of attention algorithms can be classified. For example, when attention is obtained by setting the same query, key, and value, this may mean a self-attention algorithm. In order to process a series of input data in parallel, when the dimension of the embedding vector is reduced and individual attention heads are obtained for each divided embedding vector to obtain attention, this means a multi-head attention algorithm. can do.

In one embodiment, a transformer may consist of modules that perform a plurality of multi-head self-attention algorithms or multi-head encoder-decoder algorithms. In one embodiment, the transformer may also include additional elements other than the attention algorithm, such as an embedding layer, a normalization layer, and a softmax layer. Methods for constructing transformers using the attention algorithm may include methods disclosed in Vaswani et al., Attention Is All You Need, 2017 NIPS, which is incorporated herein by reference.

Transformers can be applied to various data domains such as embedded natural language, embedded sequence information, segmented image data, and audio waveforms to convert a series of input data into a series of output data. In order to convert data having various data domains into a series of data that can be input to the transformer, the transformer can embed the data. Transformers can process additional data representing relative positional or phase relationships between a set of input data. Alternatively, a series of input data may be embedded by additionally reflecting vectors representing a relative positional relationship or phase relationship between input data to the series of input data. In one example, the relative positional relationship between a series of input data may include, but is not limited to, word order in a natural language sentence, relative positional relationship of each segmented image, temporal sequence of segmented audio waveforms, and the like. . A process of adding information representing a relative positional relationship or phase relationship between a series of input data may be referred to as positional encoding.

One example of how to embed data and transform it into a transformer is disclosed in Dosovitskiy, et al., AN IMAGE IS WORTH 16X16 WORDS: TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE, which document is incorporated herein by reference.

3 exemplarily illustrates a method of learning a predictive model that generates a prediction result including a CDR3 sequence of a TCR according to an embodiment of the present disclosure.

In one embodiment, the steps shown in FIG. 3 may be performed by computing device 100 . In a further embodiment, the steps in FIG. 3 may be implemented by a plurality of entities, such that some of the steps shown in FIG. 3 are performed in a user terminal and others are performed in a server.

In one embodiment, the computing device 100 includes first input data corresponding to the major histocompatibility complex (MHC), second input data corresponding to the peptide, and first input data corresponding to the MHC and CDR3 of the TCR corresponding to the peptide. 3 Input data may be acquired (310).

For example, the first input data includes amino acids of a first sequence corresponding to the MHC, the second input data includes amino acids of a second sequence corresponding to the peptide, and the third input data includes amino acids of a second sequence corresponding to the CDR3 It may contain the amino acids of the corresponding third sequence.

As another example, the first input data and the second input data may be integrated with each other. Accordingly, the first input data and the second input data integrated may represent an amino acid sequence representing an MHC-peptide complex.

As another example, the first input data, the second input data, and/or the third input data may include a form of a nucleic sequence.

In one example, an amino acid sequence may include a group of identifiers representing, for example, amino acids.

In one embodiment, the first input data, the second input data and/or the third input data may be obtained from a public database and/or experimental result data.

In an additional embodiment, the input data may include input data to which Blosum encoding or one-hot encoding is applied to an amino acid sequence.

In a further embodiment, the input data may include a first characteristic representing polarity between amino acids, a second characteristic representing the size of amino acids, a third characteristic representing hydrophobicity or hydrophilicity of amino acids, and a fourth characteristic representing the presence or absence of electric charge in amino acids. , or at least one of the fifth characteristics indicating whether the amino acid is aromatic or aliphatic.

In one embodiment, the computing device 100 performs preprocessing including a grouping process and a segmenting process on the first input data, the second input data, and the third input data, A training data set may be created (320).

In one embodiment, pre-processing may include a grouping process and a segmenting process. The grouping process may include grouping amino acid sequences in N units. The segmenting process may refer to a process of combining grouped groups. A training data set is a data set generated based on a grouping process and a segmenting process, and may be used for learning a predictive model.

In one embodiment, the grouping process may include a process of generating tokens having a length corresponding to each of the amino acid sequences of different lengths by analyzing the frequency of occurrence of each of the amino acid sequences of different lengths. Here, the length of the amino acid sequence may correspond to the number of amino acids included in the amino acid sequence. For example, when the length of an amino acid sequence is 4, the number of amino acids included in the amino acid sequence may be 4.

In one example, the grouping process may include a tokenization process. That is, tokenization may be performed on each of the first input data, the second input data, and the third input data based on the tokens generated by the grouping process.

In one embodiment, the occurrence frequency may represent a value quantitatively representing the probability that a specific amino acid sequence is found within one CDR3 sequence. In one embodiment, the frequency of appearance may represent a value quantitatively representing the ratio of the number of times a specific amino acid sequence is found in all CDR3s to the number of all CDR3s.

In one embodiment, the grouping process comprises generating a first token group for a first set of amino acid sequences obtained by analyzing the frequency of occurrence for amino acid sequences having a first length; A second set comprising a second set of amino acid sequences obtained by analyzing the frequency of occurrence of amino acid sequences having a second length shorter than the first length in a state in which the included first set of amino acid sequences are excluded. 2 It may include creating a token group. Here, tokens included in the first token group may have a first length and tokens included in the second token group may have a second length.

The grouping process will be described later with reference to FIG. 5 .

In one embodiment, the segmenting process may refer to a process of combining grouped groups. In one example, the segmenting process may include a process of combining tokens to create a training data set. The segmenting process may include, for example, segment embedding.

In one embodiment, the segmenting process may include a first training data set including first tokens corresponding to the first input data and third tokens corresponding to the third input data with a separator token therebetween; and a second learning data set including second tokens corresponding to the second input data and third tokens corresponding to the third input data with the separator token interposed therebetween. Here, the third tokens may be used as correct answer data in the learning process of the predictive model. The prediction model combines the first inference result based on the first training data set and the second inference result based on the second training data set, and the first input data corresponding to MHC and the second input data corresponding to peptide It may be learned to output third input data corresponding to CDR3 corresponding to the input data. Here, the prediction model may include a first prediction model learned based on the first training data set and a second prediction model learned based on the second training data set. In this embodiment, the third input data may be output or learned to output the third input data based on the output of the first prediction model and the output of the second prediction model.

In one embodiment, the computing device 100 uses the training data set to cause an artificial intelligence-based predictive model to generate a prediction result including third input data from the first input data and the second input data. An intelligence-based predictive model may be trained (330).

In one embodiment, the prediction result may further include V type and J type of TCR as well as CDR3 corresponding to the first input data and the second input data.

In one embodiment, the prediction model may be operated based on any type of learning method for generating a prediction result including the third input data from the first input data and the second input data.

For example, the learning method may include semi-supervised learning in which a mask is applied to amino acids of some of the amino acid sequences and then the masked amino acids are matched.

For example, the learning method may include semi-supervised learning to match the masked amino acids after applying a mask to amino acids included in the amino acids of the third sequence corresponding to CDR3 among the amino acid sequences. In this example, the learning method according to an embodiment of the present disclosure applies a mask to amino acids corresponding to CDR3, and to amino acids of the first sequence corresponding to MHC and amino acids of the second sequence corresponding to the peptide. A method of not applying a mask may be included.

In a further embodiment, a learning method for learning a predictive model includes, when the predictive model is learned over a plurality of epochs, applying a mask to a different location on a per-epoch basis or applying a mask of a different size on a per-epoch basis. method can be included. For example, in a first epoch, a mask of a first size may be applied to at least some of amino acids corresponding to CDR3 corresponding to a first position, and in a second epoch different from the first epoch, a second mask different from the first position A mask of a second size may be applied to at least some of the amino acids corresponding to the CDR3 corresponding to the position.

In a further embodiment, the predictive model may be trained to output output data corresponding to CDR3 based on input data representing a conjugate of MHC and a peptide.

In one embodiment, MHC and peptides capable of binding or each of MHC and peptides may be obtained through a public database (eg, VDJdb. McPas. TCR3D, Huarc). In an additional embodiment, bindable MHC and peptides may be determined by a separate artificial intelligence-based model that takes MHC and peptides as inputs and outputs whether bindable or not.

Figure 4 exemplarily illustrates a method for generating a prediction result comprising a CDR3 sequence of a TCR according to an embodiment of the present disclosure. For example, the steps shown in FIG. 4 may be performed by computing device 100 .

In one embodiment, after learning of the predictive model 470 is completed, the predictive model 470 receives the first input data 410a corresponding to MHC and the second input data 420a corresponding to peptide, CDR3 The third input data 430a corresponding to can be output. In an additional embodiment, after learning of the predictive model 470 is completed, the predictive model 470 receives first input data 410a corresponding to MHC and second input data 420a corresponding to peptide, CDR3 , V-type and J-type third input data 430a can be output.

In one embodiment, the prediction model 470 may be trained to output CDR3 and/or V type/J type corresponding to the peptide and MHC based on the training data 460 .

In one embodiment, the first input data 410a may include an amino acid sequence corresponding to MHC. The second input data 420a may include an amino acid sequence corresponding to a peptide. The third input data 430a may include an amino acid sequence corresponding to CDR3, V-type and/or J-type. In the process of learning the prediction model 470, the third input data 430a is CDR3 capable of combining with the first input data 410a corresponding to MHC and the second input data 420a corresponding to peptide (added to this V type and J type) may be included. That is, data on CDR3 corresponding to MHC and peptides may be pre-acquired, and learning of the predictive model 470 may be performed based on the pre-acquired data.

In one embodiment, grouping process 440 may generate tokens 410b, 420b, and 430b corresponding to input data 410a, 420a, and 430a. In one embodiment, the grouping process 440 generates a first token 410b corresponding to the first input data 410a, generates a second token 420b corresponding to the second input data 420a, and , And a third token 430b corresponding to the third input data 430a may be generated.

In one embodiment, the grouping process 440 includes a process for dividing the input data into smaller units or sizes, where the divided units may correspond to tokens.

In one embodiment, the segmenting process 450 may include a process of creating a training data set 460 based on tokens.

The segmenting process 450 according to an embodiment of the present disclosure generates a training data set 460 that includes first input data 410a corresponding to MHC and third input data 430a corresponding to CDR3. can do. In this learning data set 460, the third input data 430a corresponding to the first input data 410a may be used as correct answer data. The segmenting process 450 may generate a training data set 460 including second input data 420a corresponding to a peptide and third input data 430a corresponding to CDR3. In this learning data set 460, the third input data 430a corresponding to the second input data 420a may be used as correct answer data. In this embodiment, the segmenting process 450 generates two types of training data sets 460, and the two types of training data sets 460 are independently applied to the predictive model 470. can In this case, the prediction model 470 may be a single integrated model or may be composed of a plurality of separate models for receiving and processing each training data set 470 .

The segmenting process 450 according to an embodiment of the present disclosure includes first input data 410a corresponding to MHC, second input data 420a corresponding to peptide, and third input data 430a corresponding to CDR3. It is possible to generate a training data set 460 including ). In this learning data set 460, the third input data 430a corresponding to the first input data 410a and the second input data 420a may be used as correct answer data. In this embodiment, the segmenting process 450 may generate input data in a concatenated form of the first input data 410a and the second input data 420a, and the third input data 430a as the above. The learning data set 460 may be created in a way of using it as correct answer data corresponding to the input data. In this case, input data in an integrated form may be generated through a segmenting process, for example, in such a way that amino acid sequences corresponding to MHC and amino acid sequences corresponding to peptides are concatenated with each other.

In one embodiment, the concatenated first and second input data may be used in the inference process of the predictive model 470, and CDR3 corresponding to the concatenated input data may be output. In one embodiment, in the inference process of the predictive model 370, the first input data and the second input data are obtained by combining CDR3 for the first input data and CDR3 for the second input data or inputting them to another model. Corresponding CDR3 can be output.

5 illustratively illustrates a grouping process according to one embodiment of the present disclosure.

In one embodiment, the grouping process may obtain the CDR3 list 510 from an external database or a database included on the computing device. As an example, the CDR3 list 510 may include amino acid sequences corresponding to existing CDR3s.

In one embodiment, the amino acid sequences included in the CDR3 list 510 are various numbers (K) of, for example, 7 amino acids, 8 amino acids, 9 amino acids, 10 amino acids, or 11 amino acids. It may consist of amino acids. Amino acids of this particular length may be referred to as an amino acid set. For example, assuming that the total number of amino acids is 20, an amino acid sequence having a length of 4 may exist in a total number of 20 to the 4th power. A combination of one amino acid contained in a number to the fourth power of 20 may be referred to as an amino acid set. In this situation, the number of amino acid sets of length 4 can total 20 to the fourth power.

In one embodiment, for each of the amino acid sets of which the length of the amino acid sequence is K, the frequency of occurrence in the CDR3 list 510 may be determined. A process of determining how many amino acid sets of a specific length appear or exist within the range of amino acid sequences included in the CDR3 list 510 may be referred to as frequency analysis 500 in FIG. 5 .

In one embodiment, specific amino acid sequences among amino acid sequences included in the CDR3 list 510 may be tokenized through the frequency of occurrence analysis 500 . The computing device 100 may include the tokenized amino acid sequences into the token list 520 during the grouping process. Token list 520 may include tokens generated through a grouping process.

In one embodiment, the computing device 100 determines a first amino acid set having a first occurrence frequency equal to or greater than a predetermined first threshold value among amino acid sets having an amino acid sequence length K, and determines the first set of amino acids in the CDR3 list 510. Appearance frequency division (500) can be performed in such a way that the length is reduced by a specific unit (eg, 1) based on K while excluding 1 amino acid set, and the frequency of appearance for each of the amino acid sets of the reduced length is determined. there is. In this example, the computing device 100 determines a second frequency of occurrence in the CDR3 list 510 for each of the amino acid sets having an amino acid sequence length K-1 after the first set of amino acids is determined, and And among amino acid sets having an amino acid sequence length of K−1, a second amino acid set having the second occurrence frequency equal to or greater than a predetermined second threshold value may be determined. The computing device 100 performs tokenization of the length of K for the first amino acid sets determined according to the result of the occurrence frequency analysis 500 for the amino acid set of length K, and the amino acid set of length K-1. Tokenization of a length of K-1 may be performed on the second set of amino acids determined according to the result of the frequency of occurrence analysis (500). Tokens generated as a result of tokenization may be stored in the token list 520 . Here, K is a natural number greater than or equal to 1 or a natural number greater than or equal to 2, and the first threshold value and the second threshold value may have the same or different values.

In one embodiment, the grouping process may obtain the CDR3 list 510 from an external database or a database included in the computing device. The grouping process includes in the token list 520 the M+1th amino acid set whose frequency of occurrence in the CDR3 list 510 is equal to or greater than a predetermined threshold, among the sets of amino acids whose amino acid sequence length is N-M, and The token list 520 may be constructed in such a way that M+1 amino acid sets are removed from the CDR3 list 510. The grouping process, after constructing the token list 520, may increment the value of M by 1 and determine whether the termination condition is satisfied. The grouping process repeats the step of constructing the token list when the end condition is not satisfied, and when the end condition is satisfied, the amino acid sequence length corresponding to each of the amino acid sets included in the token list 520. Tokenization may be performed by generating a token corresponding to each of the sets. Here, M is an integer greater than or equal to 0, and N-M may be a natural number greater than 2.

The termination condition according to an embodiment of the present disclosure may include a condition for determining whether to additionally perform the frequency analysis 500 while reducing the length of the amino acid sequence or to end the frequency analysis 500 here. can

For example, the termination condition may include a first termination condition corresponding to N−M≤1. The computing device 100 may end the frequency of occurrence analysis 500 without increasing the value of M when the above termination condition is satisfied based on the current values of N and M.

As another example, the end condition may include a second end condition corresponding to N−M≤2. Additionally, the grouping process may perform tokenization by additionally generating a number of tokens corresponding to the type of amino acids having a length of 1 in the amino acid sequence. For example, an amino acid sequence having a length of 1 may include 21 amino acids obtained by adding X amino acids to 20 amino acids. As another example, the amino acids of which the length of the amino acid sequence is 1 may include any kind of amino acids that can represent one amino acid.

In one embodiment, the threshold value used in the frequency of occurrence analysis 500 may be varied to have a negative correlation with the size of the value of N-M. For example, when the value of N-M is large, the size of the threshold may be relatively low.

As shown in FIG. 5 , occurrence frequency analysis (500) may extract amino acid sets having a length of 4 having an occurrence frequency of x% or more for amino acid sets having a length of n=4 (530). Although n=4 is illustrated in FIG. 5 for convenience of explanation, it will be clear to those skilled in the art that amino acid sequences of various lengths may be used depending on the embodiment.

In one embodiment, the computing device 100 may include the extracted amino acid sets of length 4 in the token list 520 and remove them from the CDR3 list 510 (540). For example, step 550 may proceed with excluding amino acid sets having a length of 4 extracted from among the amino acid sequences included in the CDR3 list 510 .

In one embodiment, the computing device 100 may subtract 1 from n to extract amino acid sets having a length of 3 having an appearance frequency of x% or more for amino acid sets of n=3 (550). Here, the threshold value for the frequency of occurrence is exemplified as x% in the same way as in step 530, but it is also possible to use different threshold values for each step according to implementation aspects. For example, the threshold value may be set to have a negative correlation (eg, inversely proportional or linear decrease, etc.) with the magnitude of n. As such, through the negative correlation between the threshold value and the amino acid length, tokenization of long amino acid sequences can be sufficiently secured.

In one embodiment, the computing device 100 may include the extracted amino acid sets of length 3 in the token list 520 and remove them from the CDR3 list 510 (560). For example, step 570 may proceed with excluding amino acid sets having a length of 3 extracted from among the amino acid sequences included in the CDR3 list 510 . That is, in step 570, the appearance frequency of n=2 amino acid sets within the range of the CDR3 list 510 excluding the extracted amino acid sets corresponding to length 4 and the extracted amino acid sets corresponding to length 3 is x % or more amino acid sets of length 2 can be extracted. For example, assuming that there are 20 types of amino acids in total, the total number of amino acid sets corresponding to a length of 2 may be 20 ² =400. Among the 400 types of amino acid sets, amino acid sets having a frequency of x% or more appearing in the CDR3 list 510 in which previously extracted amino acid sets are removed may be extracted in step 570.

In one embodiment, the computing device 100 may include the extracted amino acid sets of length 2 in the token list 520 and remove them from the CDR3 list 510 (580). For example, step 590 may proceed with excluding amino acid sets having a length of 2 extracted from among the amino acid sequences included in the CDR3 list 510 .

In one embodiment, computing device 100 may include each of the single amino acids of length n=1 into token list 520 (590). That is, for amino acids having a length of n=1, all types of amino acids having a length of 1 may be included in the token list 520.

Since grouping or tokenization is performed in the above-described manner, the technique according to an embodiment of the present disclosure is universal and consistent when performing more accurate prediction of CDR3 corresponding to MHC and peptides containing amino acid sequences. You can use localized tokens.

In one embodiment, tokens generated based on the grouping process according to the embodiment of FIG. 5 may have a length corresponding to the length of the amino acid sequence (ie, the value of n). In one embodiment, by using tokens generated based on the grouping process according to the embodiment of FIG. 5, in the learning process and / or inference process, first input data corresponding to MHC, second input data corresponding to peptides, and Tokenization of the third input data corresponding to CDR3 may be performed. That is, the technique according to an embodiment of the present disclosure performs tokenization through the frequency of occurrence analysis 500 for amino acid sequences included in the CDR3 list 510, and performs tokenization into MHC, peptide, and CDR3 can be applied to all

6 illustratively illustrates a segmenting process according to an embodiment of the present disclosure.

Reference number 610 represents a training data set with MHC and peptides as questions and CDR3 as the correct answer according to an embodiment of the present disclosure.

Reference number 620 denotes a first training data set 630 with MHC as a question and CDR3 as an answer and a second training data set (640 with peptide as a question and CDR3 as an answer), according to another embodiment of the present disclosure. ).

According to an embodiment, the first input data (t1, t2, t3, ... tn) corresponding to MHC and the second input data (t'1, t'2, t'3, ... t'n) corresponding to the peptide ) as question (0) and the third input data (t''1, t''2, t''3, ... t''n) corresponding to CDR3 as answer (1) A learning data set 610 is disclosed. Here, each of CLS, t1, t2, t3, t'1, t'2, t'3, SEP, t''1, t''2, and t''3 may correspond to one token.

According to one embodiment, the first input data (t1, t2, t3, ... tn) corresponding to MHC is set as question (0), and the third input data (t''1, t' corresponding to CDR3) A first learning data set 630 with '2, t''3, ... t''n as the correct answer (1) is disclosed. The second input data (t'1, t'2, t'3, ... t'n) is used as the question (0), and the third input data (t''1, t''2, t' corresponding to CDR3) A second learning data set 640 with '3, ... t''n) as the correct answer (1) is disclosed. Here, each of CLS, t1, t2, t3, t'1, t'2, t'3, SEP, t''1, t''2, and t''3 may correspond to one token. In this embodiment, the first training data 630 and the second training data 640 may be learned through different models. Through post-processing of the results learned through different models, the CDR3 sequence corresponding to the peptide and MHC can finally be generated.

The CLS token in the present disclosure represents a token indicating the start of a sentence, and the SEP may represent a delimiter token inserted between tokens to distinguish tokens.

As such, the segmenting process of the present disclosure may generate a training data set for learning a predictive model by combining the generated tokens with a separator token and a start token.

A predictive model in the present disclosure may mean an artificial intelligence-based generation model. As an example, the predictive model may include a recurrent neural network (RNN), a long short term memory (LSTM) network, or a bidirectional encoder representations from transformers (BERT).

In one embodiment, in a language model such as BERT, in Next Sentence Prediction (NSP), a question (0) and an answer (1) are randomly generated in most cases. In the learning process of the predictive model according to an embodiment of the present disclosure, it is experimentally determined that immunogenicity does not exist for the data corresponding to question (0) (false) and immunogenicity is determined to exist (false) true) CDR3 data can be used as the correct answer (1). That is, CDR3 data is not randomly generated during the learning process of the artificial intelligence-based predictive model. Since most of the amino acid sequences will have a false value when generated randomly, it is difficult to implement effective learning, and more efficient prediction model learning can be achieved through the technique according to an embodiment of the present disclosure.

In one embodiment of the present disclosure, a masked learning method may be used in a process of learning a predictive model. After applying a mask to some amino acids among the amino acid sequences included in the training data sets 610 and 620, semi-supervised learning matching the masked amino acids may be performed. The object to which the mask is applied may be limited to amino acid sequences corresponding to the correct answer (1). Accordingly, the accuracy of the predictive model for predicting CDR3 corresponding to the received peptide and MHC can be further increased.

In one embodiment of the present disclosure, multiple masks may be applied to one training data set. In this case, a masked learning method may be implemented by applying X amino acids representing all amino acids or an average of amino acids to another mask in a process of matching one mask among a plurality of masks. Accordingly, since a feature called X amino acid is used even in a situation where a plurality of masks exist, prediction accuracy for masked data can be higher.

A technique according to an example of the present disclosure may be performed in a manner of using a pretrained model by semi-supervised learning and applying fine tuning of the supervised learning method. A technique according to one example of this disclosure may be implemented by a predictive model that includes one or more encoders and/or decoders. A technique according to an example of the present disclosure is a Masked Learning method for masking some tokens to make a predictive model fit, and a Next Sentence Prediction for matching a context or a next specific token when two sets of tokens or two tokens are given. method can be used.

For example, in one embodiment of the present disclosure, amino acid sequences corresponding to peptides and / or MHC or tokens corresponding to peptides and / or MHC are input and the length of the corresponding TCR is output. The model can further be utilized. As another example, in one embodiment of the present disclosure, amino acid sequences corresponding to peptides and / or MHC or tokens corresponding to peptides and / or MHC are input and the length of the corresponding CDR3 is output. Artificial intelligence-based model can be further utilized. As another example, in one embodiment of the present disclosure, artificial amino acid sequences corresponding to peptides and / or MHC or tokens corresponding to peptides and / or MHC are input and output corresponding V and J types. Intelligence-based models can further be utilized. As another example, in one embodiment of the present disclosure, amino acid sequences corresponding to peptides and / or MHC or tokens corresponding to peptides and / or MHC are input and the corresponding V type and J type of CDR3 An artificial intelligence-based model that outputs the length of a random insertion sequence can be additionally utilized. The technique according to an embodiment of the present disclosure, using this additional artificial intelligence model, can obtain information on the corresponding CDR3 and / or V type and J type from the peptide and / or MHC, and CDR3 and / or Masked learning for the predictive model can be performed by inputting the information on the V type and the J type. In this case, the predictive model may be learned by applying a mask to at least some of the tokens or sequences related to CDR3 and predicting tokens or sequences corresponding to the applied mask. In the example described in the previous figures, such an artificial intelligence-based model may be further utilized. Accordingly, an artificial intelligence-based model receives an amino acid sequence and/or a token corresponding to a peptide and/or MHC and outputs CDR3-related information, and a prediction model that takes the CDR3-related information as an input finally produces a peptide and/or a token. Alternatively, it may be learned to output the sequence of CDR3 by inputting an amino acid sequence and/or token corresponding to MHC. In a further embodiment of the present disclosure, the predictive model may be designed to include the artificial intelligence-based additional models described above. Accordingly, two models may exist inside the prediction model, and the first model may obtain information on the corresponding CDR3 and / or V type and J type from the corresponding peptide and / or MHC from the peptide and / or MHC. In addition, the amino acid sequence of CDR3 may be output through a second model among prediction models using information on CDR3 and/or V type and J type as input.

The Next Sentence Prediction method in the present disclosure is, for example, recognizing amino acid sequences corresponding to peptides as one Sentence and recognizing amino acid sequences corresponding to CDR3 as one Sentence, thereby learning to predict CDR3 from a peptide. can include For example, the Next Sentence Prediction method in the present disclosure is a process of learning to predict CDR3 from MHC by recognizing amino acid sequences corresponding to MHC as one sentence and recognizing amino acid sequences corresponding to CDR3 as one sentence. can include For example, the Next Sentence Prediction method in the present disclosure is a process of learning to predict CDR3 from pMHC by recognizing amino acid sequences corresponding to pMHC as one sentence and recognizing amino acid sequences corresponding to CDR3 as one sentence. can include For example, the Next Sentence Prediction method in the present disclosure recognizes amino acid sequences corresponding to MHC as one sentence, recognizes amino acid sequences corresponding to peptides as one sentence, and recognizes amino acid sequences corresponding to CDR3 as one sentence. By recognizing it as a sentence, it may include a process of learning to predict CDR3 corresponding to the peptide and MHC. According to this embodiment, as described above, in the masking process, the masking target may be limited to amino acid sequences and/or tokens corresponding to CDR3.

7 is a schematic diagram of a computing environment according to one embodiment of the present disclosure.

A component, module or unit in this disclosure includes routines, procedures, programs, components, data structures, etc. that perform particular tasks or implement particular abstract data types. In addition, those skilled in the art will understand that the methods presented in this disclosure can be used in single-processor or multiprocessor computing devices, minicomputers, mainframe computers as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, and the like ( It will be fully appreciated that each of these may be implemented with other computer system configurations, including those that may be operative in connection with one or more associated devices.

Embodiments described in this disclosure may also be practiced in distributed computing environments where certain tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

A computing device typically includes a variety of computer readable media. Computer readable media can be any medium that can be accessed by a computer, including volatile and nonvolatile media, transitory and non-transitory media, removable and non-transitory media. Includes removable media. By way of example, and not limitation, computer readable media may include computer readable storage media and computer readable transmission media.

Computer readable storage media are volatile and nonvolatile media, transitory and non-transitory, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. includes media Computer readable storage media may include RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital video disk (DVD) or other optical disk storage device, magnetic cassette, magnetic tape, magnetic disk storage device or other magnetic storage device. device, or any other medium that can be accessed by a computer and used to store desired information.

A computer readable transmission medium typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism. Including all information delivery media. The term modulated data signal means a signal that has one or more of its characteristics set or changed so as to encode information within the signal. By way of example, and not limitation, computer readable transmission media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared, and other wireless media. Combinations of any of the above are also intended to be included within the scope of computer readable transmission media.

An exemplary environment 2000 implementing various aspects of the present invention is shown comprising a computer 2002, which includes a processing unit 2004, a system memory 2006 and a system bus 2008. do. Computer 200 herein may be used interchangeably with a computing device. System bus 2008 couples system components, including but not limited to system memory 2006, to processing unit 2004. Processing unit 2004 may be any of a variety of commercially available processors. Dual processors and other multiprocessor architectures may also be used as the processing unit 2004.

System bus 2008 may be any of several types of bus structures that may additionally be interconnected to a memory bus, a peripheral bus, and a local bus using any of a variety of commercial bus architectures. System memory 2006 includes read only memory (ROM) 2010 and random access memory (RAM) 2012 . The basic input/output system (BIOS) is stored in non-volatile memory 2010, such as ROM, EPROM, EEPROM, etc. BIOS is a basic set of information that helps transfer information between components within the computer 2002, such as during startup. contains routines. RAM 2012 may also include high-speed RAM, such as static RAM, for caching data.

The computer 2002 may also read from an internal hard disk drive (HDD) 2014 (eg EIDE, SATA), a magnetic floppy disk drive (FDD) 2016 (eg a removable diskette 2018), or for writing to them), SSDs and optical disk drives 2020 (for example, for reading CD-ROM disks 2022 or reading from or writing to other high capacity optical media such as DVDs) include The hard disk drive 2014, magnetic disk drive 2016, and optical disk drive 2020 are connected to the system bus 2008 by the hard disk drive interface 2024, magnetic disk drive interface 2026, and optical drive interface 2028, respectively. ) can be connected to The interface 2024 for external drive implementation includes, for example, at least one or both of Universal Serial Bus (USB) and IEEE 1394 interface technologies.

These drives and their associated computer readable media provide non-volatile storage of data, data structures, computer executable instructions, and the like. In the case of computer 2002, drives and media correspond to storing any data in a suitable digital format. Although the description of computer-readable storage media above refers to HDDs, removable magnetic disks, and removable optical media such as CDs or DVDs, those skilled in the art can use zip drives, magnetic cassettes, flash memory cards, cartridges, It will be appreciated that other types of computer-readable storage media, such as those of other types, may also be used in the exemplary operating environment and that any such media may contain computer-executable instructions for performing the methods of the present invention. .

A number of program modules may be stored on the drive and RAM 2012, including an operating system 2030, one or more application programs 2032, other program modules 2034, and program data 2036. All or portions of the operating system, applications, modules and/or data may also be cached in RAM 2012. It will be appreciated that the present invention may be implemented in a variety of commercially available operating systems or combinations of operating systems.

A user may enter commands and information into the computer 2002 through one or more wired/wireless input devices, such as a keyboard 2038 and a pointing device such as a mouse 2040. Other input devices (not shown) may include a microphone, IR remote control, joystick, game pad, stylus pen, touch screen, and the like. Although these and other input devices are often connected to the processing unit 2004 through an input device interface 2042 that is connected to the system bus 2008, a parallel port, IEEE 1394 serial port, game port, USB port, IR interface, may be connected by other interfaces such as the like.

A monitor 2044 or other type of display device is also connected to the system bus 2008 through an interface such as a video adapter 2046. In addition to the monitor 2044, computers typically include other peripheral output devices (not shown) such as speakers, printers, and the like.

Computer 2002 may operate in a networked environment using logical connections to one or more remote computers, such as remote computer(s) 2048 via wired and/or wireless communications. Remote computer(s) 2048 may be workstations, server computers, routers, personal computers, handheld computers, microprocessor-based entertainment devices, peer devices, or other common network nodes, and generally relate to computer 2002. Although many or all of the described components are included, for brevity, only memory storage device 2050 is shown. The logical connections shown include wired/wireless connections to a local area network (LAN) 2052 and/or a larger network, such as a wide area network (WAN) 2054 . Such LAN and WAN networking environments are common in offices and corporations and facilitate enterprise-wide computer networks, such as intranets, all of which can be connected to worldwide computer networks, such as the Internet.

When used in a LAN networking environment, computer 2002 is connected to local network 2052 through wired and/or wireless communication network interfaces or adapters 2056. Adapter 2056 may facilitate wired or wireless communications to LAN 2052, which also includes a wireless access point installed therein to communicate with wireless adapter 2056. When used in a WAN networking environment, computer 2002 may include a modem 2058, be connected to a communications server on WAN 2054, or other means of establishing communications over WAN 2054, such as over the Internet. have Modem 2058, which can be internal or external and wired or wireless, is connected to system bus 2008 through serial port interface 2042. In a networked environment, program modules described for computer 2002, or portions thereof, may be stored in remote memory/storage device 2050. It will be appreciated that the network connections shown are exemplary and other means of establishing a communication link between computers may be used.

Computer 1602 is any wireless device or entity that is deployed and operating in wireless communication, such as printers, scanners, desktop and/or portable computers, portable data assistants (PDAs), communication satellites, and associated with wireless detectable tags. It operates to communicate with arbitrary equipment or places and telephones. This includes at least Wi-Fi and Bluetooth wireless technologies. Thus, the communication may be a predefined structure as in conventional networks or simply an ad hoc communication between at least two devices.

It is to be understood that the specific order or hierarchy of steps in the processes presented is an example of exemplary approaches. Based upon design priorities, it is to be understood that the specific order or hierarchy of steps in the processes may be rearranged within the scope of the present disclosure. The method claims of this disclosure present elements of the various steps in a sample order, but are not meant to be limited to the specific order or hierarchy presented.

Claims (22)

As a method of training an artificial intelligence-based predictive model performed by a computing device,
First input data corresponding to major histocompatibility complex (MHC), second input data corresponding to peptide, and third input corresponding to CDR3 of T Cell Receptor (TCR) corresponding to the MHC and the peptide obtaining data - the first input data includes amino acids of a first sequence corresponding to the MHC, the second input data includes amino acids of a second sequence corresponding to the peptide, and the third input data includes amino acids of a second sequence corresponding to the peptide; the input data includes amino acids of the third sequence corresponding to the CDR3;
Generating a training data set by performing preprocessing including a grouping process and a segmenting process on the first input data, the second input data, and the third input data:
Using the training data set, the artificial intelligence-based predictive model generates a prediction result including the third input data from the first input data and the second input data, the artificial intelligence-based predictive model learning step;
including,
method. According to claim 1,
The prediction result further includes a V type and a J type of the TCR corresponding to the first input data and the second input data.
method. According to claim 1,
The grouping process,
By analyzing the frequency of appearance for each of the amino acid sequences of different lengths, tokens having lengths corresponding to each of the amino acid sequences of different lengths are generated.
method. According to claim 3,
The grouping process is:
generating a first token group for a first set of amino acid sequences obtained by analyzing the frequency of occurrence of amino acid sequences having a first length; and
A second set obtained by analyzing the frequency of occurrence of amino acid sequences having a second length shorter than the first length in a state in which the amino acid sequences of the first set included in the first token group are excluded Generating a second token group comprising amino acid sequences of;
includes, and
Tokens included in the first token group have the first length and tokens included in the second token group have the second length,
method. According to claim 3,
The frequency of occurrence is:
A value quantitatively representing the probability that a specific amino acid sequence is found within one CDR3 sequence; or
A value quantitatively representing the ratio of the number of times a specific amino acid sequence is found in all CDR3s to the number of all CDR3s;
including,
method. According to claim 3,
Based on the tokens generated by the grouping process, tokenization is performed on each of the first input data, the second input data, and the third input data.
method. According to claim 6,
The segmenting process,
A first training data set including first tokens corresponding to the first input data and third tokens corresponding to the third input data with a separator token interposed therebetween, and the separator token interposed therebetween generating a second training data set including second tokens corresponding to the second input data and third tokens corresponding to the third input data;
Here, the third tokens are used as correct answer data in the learning process of the prediction model, and
The first training data set and the second training data set are learned by different artificial intelligence networks within the prediction model.
method. According to claim 6,
The segmenting process,
First tokens corresponding to the first input data, second tokens corresponding to the second input data, a first delimiter token located between the first tokens and the second tokens, the third input generating a third training data set comprising third tokens corresponding to data and a second separator token positioned between the second tokens and the third tokens;
Here, the third tokens are used as correct answer data in the learning process of the prediction model.
method. According to claim 1,
The grouping process is:
obtaining a CDR3 list from an external database or a database included in the computing device;
determining a first occurrence frequency in the CDR3 list for each of the amino acid sets of which the length of the amino acid sequence is K;
determining a first amino acid set having the first frequency of occurrence equal to or greater than a predetermined first threshold value among amino acid sets having a length of K of the amino acid sequence;
determining a second frequency of occurrence in the CDR3 list for each of the amino acid sets of which the length of the amino acid sequence is K-1;
determining a second amino acid set whose second frequency of occurrence is greater than or equal to a predetermined second threshold value among amino acid sets having a length of the amino acid sequence of K−1; and
performing tokenization with a length of K for the first set of amino acids and tokenization with a length of K-1 for the second set of amino acids;
Including, where K is a natural number of 2 or more, and the first threshold value and the second threshold value have the same or different values from each other,
method. According to claim 9,
Determining the second frequency of appearance,
determining the second occurrence frequency within a range excluding the first amino acid set from the CDR3 list, for each of the amino acid sets of which the length of the amino acid sequence is K-1;
including,
method. According to claim 1,
The grouping process is:
obtaining a CDR3 list from an external database or a database included in the computing device;
Among the amino acid sets of which the length of the amino acid sequence is NM, the M+1 amino acid set whose frequency of occurrence in the CDR3 list is equal to or greater than a predetermined threshold is included in the token list, and the M+1 amino acid set is included in the CDR3 list constructing the token list, in a manner removing from, where M is an integer greater than or equal to 0, and NM is a natural number greater than 2;
After the step of constructing the token list is performed, increasing the value of M by 1 and determining whether an end condition is satisfied;
If the termination condition is not satisfied, re-performing the constructing the token list; and
If the termination condition is satisfied, performing tokenization by generating a token corresponding to each of the amino acid sets with an amino acid sequence length corresponding to each of the amino acid sets included in the token list;
including,
method. According to claim 11,
The termination condition includes a first termination condition corresponding to NM≤1,
method. According to claim 11,
The termination condition includes a second termination condition corresponding to NM≤2,
The step of performing the tokenization,
Further comprising the step of performing the tokenization by additionally generating a number of tokens corresponding to the type of amino acids having a length of 1 in the amino acid sequence.
method. According to claim 11,
The predetermined threshold value is varied to have a negative correlation with the magnitude of the value of NM.
method. According to claim 1,
The artificial intelligence-based predictive model,
Including Recurrent Neural Networks (RNNs), Long Short Term Memory (LSTMs) networks, or Bidirectional Encoder Representations from Transformers (BERTs),
method. According to claim 1,
The step of learning the artificial intelligence-based predictive model,
After applying a mask to some amino acids of the amino acid sequences, performing semi-supervised learning to match the masked amino acids;
including,
method. 17. The method of claim 16,
The step of learning the artificial intelligence-based predictive model,
After applying a mask to amino acids included in amino acids of a third sequence corresponding to the CDR3 among amino acid sequences, performing the semi-supervised learning to match the masked amino acids;
including,
method. 17. The method of claim 16,
The step of learning the artificial intelligence-based predictive model,
applying the mask to different positions in units of epochs or applying the masks having different sizes in units of epochs when the predictive model is learned over a plurality of epochs;
including,
method. According to claim 1,
The step of learning the artificial intelligence-based predictive model,
When a plurality of masks exist for one training data, when the artificial intelligence-based prediction model predicts one mask among the plurality of masks, amino acid X representing the average value of amino acids or all amino acids in another mask apply, and
The plurality of masks are applied to some amino acids among the amino acids of the first sequence, the amino acids of the second sequence, and the amino acids of the third sequence,
method. According to claim 1,
The step of learning the artificial intelligence-based predictive model,
Training the artificial intelligence-based predictive model by using third input data experimentally determined to have no immunogenicity as answer data for the first input data and the second input data;
includes, and
In the learning process of the artificial intelligence-based predictive model, the third input data is not randomly generated,
method. A computer program stored on a computer-readable storage medium, which, when executed by a computing device, causes the computing device to perform operations for learning an artificial intelligence-based predictive model, the operations comprising:
Obtaining first input data corresponding to the major histocompatibility complex (MHC), second input data corresponding to the peptide, and third input data corresponding to the MHC and CDR3 of the TCR corresponding to the peptide - the first The input data includes amino acids of a first sequence corresponding to the MHC, the second input data includes amino acids of a second sequence corresponding to the peptide, and the third input data includes amino acids of a second sequence corresponding to the CDR3. 3 contains the sequence of amino acids;
generating a training data set by performing pre-processing including a grouping process and a segmenting process on the first input data, the second input data, and the third input data;
Using the training data set, the artificial intelligence-based predictive model generates a prediction result including the third input data from the first input data and the second input data, the artificial intelligence-based predictive model action to learn;
including,
A computer program stored on a computer readable storage medium. As a computing device,
at least one processor; and
Memory;
Including,
The at least one processor is:
Obtaining first input data corresponding to the major histocompatibility complex (MHC), second input data corresponding to the peptide, and third input data corresponding to the MHC and CDR3 of the TCR corresponding to the peptide - the first The input data includes amino acids of a first sequence corresponding to the MHC, the second input data includes amino acids of a second sequence corresponding to the peptide, and the third input data includes amino acids of a second sequence corresponding to the CDR3. 3 contains the sequence of amino acids;
generating a training data set by performing pre-processing including a grouping process and a segmenting process on the first input data, the second input data, and the third input data;
Using the training data set, the artificial intelligence-based predictive model is trained such that the artificial intelligence-based predictive model generates a prediction result including the third input data from the first input data and the second input data. action to make;
to do,
computing device.

Images