Method for predicting immunogenicity of neoantigen epitopes and device using the same

Abstract

The present invention relates to a method for predicting the immunogenicity of a neoantigen epitope and an apparatus using the same. The method for predicting the immunogenicity of a mutant epitope according to the present invention may include the steps of calculating the degree of influence of factors involved in the biological process for a mutant epitope and characteristics of the epitope on the immunogenicity of the mutant epitope, calculating the degree of influence of factors involved in the biological process for a non-mutated epitope corresponding to the mutant epitope and characteristics of the epitope on the immunogenicity of the non-mutated epitope, calculating a differential index based on the value calculated for the mutant epitope and the value calculated for the non-mutated epitope, and inputting the value calculated for the mutant epitope and the calculated differential index into a pre-trained artificial intelligence model to predict the immunogenicity of the mutant epitope.

Description

[Technical Field]

[0001] The present invention relates to a method for predicting the immunogenicity of neoantigen epitopes and an apparatus using the same, and more specifically to a method for predicting the immunogenicity of neoantigen epitopes by comparing mutated neoantigen epitopes with non-mutated epitopes and an apparatus using the same. [Background technology]

[0002] Neoantigens are antigens that arise from mutations and are expressed in tumor cells / tissues but not in normal cells. When the normal sequence is altered by mutation, immune cells recognize the altered sequence as a new antigen / epitope, triggering an immune response. Such neoantigens are used as therapeutic vaccines and are used in immunotherapy and response prediction. Various factors involved in numerous biological processes, such as MHC binding affinity, proteasomal cleavage, TAP transporter efficiency, pMHC stability, and T-cell receptor interaction, as well as characteristics of neoantigen epitopes, such as hydrophobicity, similarity to known epitopes, and dissimilarity to self-proteome, can affect the in silico prediction of neoantigen epitopes that exhibit CD8+ T-cell immunogenicity. Therefore, we predicted the immunogenicity of neoantigen epitopes using various factors involved in biological processes caused by mutations and / or the characteristics of neoantigen epitopes. Summary of the Invention [Problem to be solved by the invention]

[0003] To date, methods have been developed that use various factors and / or epitope characteristics involved in numerous biological processes individually, as well as methods that combine a small number of factors and / or characteristics to predict epitopes that will induce an immune response. The differential agretopicity index (DAI) is one of the factors used to predict the immunogenicity of epitopes.

[0004] The DAI is defined as the ratio of the MHC affinity of a mutated epitope (also called a "peptide") to that of a non-mutated (or wild-type) epitope. Predicting immunogenicity using the DAI may be more effective than predicting immunogenicity using only the MHC affinity of a neoepitope or mutant epitope. This is because even if a mutated epitope has a preference for certain factors, such as MHC binding affinity, it does not necessarily exhibit immunogenicity. Even if a non-mutated epitope itself has a tendency to bind well to MHC, it can act to prevent immune responses against self-epitopes through the immune system's negative selection / central tolerance process, i.e., to prevent normal cells from being attacked by immune cells. Therefore, measuring the difference in the characteristics of a mutation compared to a normal, non-mutated epitope is crucial for predicting the immunogenicity of an epitope.

[0005] Differences between mutated and non-mutated epitopes may not only affect binding affinity, but also the various biological processes involved in the epitope's induction of an immune response. For example, while non-mutated and mutated epitopes may have similar MHC binding affinities, mutations may affect the efficiency / response of proteasomal cleavage, TAP transporter efficiency, pMHC stability, and T-cell receptor interaction.

[0006] Therefore, the present invention proposes a method and an apparatus for predicting the immunogenicity of mutated epitopes using differential indices (i.e., the ratio or difference between the measured values ​​of mutated and non-mutated epitopes) for a number of biological processes and epitope / neoepitope characteristics. [Means for solving the problem]

[0007] The method for predicting the immunogenicity of a mutant epitope according to the present invention may include the steps of calculating the degree of influence of each of the factors involved in the biological process for the mutant epitope and the characteristics of the epitope on the immunogenicity of the mutant epitope, calculating the degree of influence of each of the factors involved in the biological process for the non-mutated epitope corresponding to the mutant epitope and the characteristics of the epitope on the immunogenicity of the non-mutated epitope, calculating a differential index based on the value calculated for the mutant epitope and the value calculated for the non-mutated epitope, and inputting the value calculated for the mutant epitope and the calculated differential index into a pre-trained artificial intelligence model to predict the immunogenicity of the mutant epitope.

[0008] The method for predicting the immunogenicity of a mutant epitope according to the present invention may further include performing at least one of standardization and normalization on the calculated value for the mutant epitope and the calculated differential index before inputting the calculated value into the trained artificial intelligence model.

[0009] In the method for predicting the immunogenicity of a mutant epitope according to the present invention, the differential index may include at least one of the ratio (RATIO) of the value calculated for the mutant epitope to the value calculated for the non-mutated epitope, and the difference (DIFFERENCE) between the value calculated for the mutant epitope and the value calculated for the non-mutated epitope.

[0010] In the method for predicting the immunogenicity of a mutant epitope according to the present invention, the differential index may be a differential index for at least one of phosphorylation, hydrophobicity, similarity to known epitopes, dissimilarity to the self-proteome, epitope stability, antigen processing, MHC I binding affinity, pMHC stability, immunity, inflammatory response, B-cell linear epitope, and B-cell conformational epitope.

[0011] In the method for predicting the immunogenicity of a mutated epitope according to the present invention, the step of calculating the degree of influence of factors involved in biological processes and epitope characteristics on immunogenicity for the mutated epitope and the non-mutated epitope may be a step of calculating using an algorithm, program, or tool.

[0012] In the method for predicting the immunogenicity of a mutant epitope according to the present invention, the biological process comprises an antigen processing stage, an antigen presentation stage, an immune stage, and a tumor microenvironment, and the factors involved in the tumor microenvironment may be at least one of an inflammatory response, a B-cell linear epitope, and a B-cell conformational epitope.

[0013] The computer-readable recording medium for predicting the immunogenicity of a mutant epitope according to the present invention may have a computer program recorded thereon for performing at least one of the above-mentioned methods.

[0014] The apparatus for predicting the immunogenicity of a mutant epitope according to the present invention includes an input / output device for receiving a mutant epitope or outputting a result of predicting the immunogenicity of the mutant epitope; a storage device for storing a differential index calculated based on factors involved in biological processes and characteristics of the epitopes for the mutant epitope and non-mutated epitope, and an artificial intelligence model trained to predict the immunogenicity of the mutant epitope using the differential index calculated based on factors involved in biological processes and characteristics of the epitope for the mutant epitope; and a storage device for storing an artificial intelligence model trained to predict the immunogenicity of the mutant epitope using the differential index calculated based on factors involved in biological processes and characteristics of the epitope for the mutant epitope, calculating the degree of influence of each of factors involved in biological processes and characteristics of the epitope for the non-mutated epitope corresponding to the mutant epitope on the immunogenicity of the non-mutated epitope, calculating the degree of influence of each of factors involved in biological processes and characteristics of the epitope for the non-mutated epitope corresponding to the mutant epitope on the immunogenicity of the non-mutated epitope, calculating a differential index based on the calculated value for the mutant epitope and the calculated value for the non-mutated epitope, and calculating a differential index based on the calculated value for the mutant epitope and the calculated differential index. The method may include a computing device that uses the index as input to a pre-trained artificial intelligence model to predict the immunogenicity of the mutant epitope. [Effects of the Invention]

[0015] According to the present invention, it is possible to multifacetedly consider the numerous biological processes caused by mutations and the characteristics of epitopes / neoepitopes, thereby making it possible to predict the immunogenicity of mutated epitopes with higher accuracy than when immunogenicity is predicted using only mutated epitopes alone. Highly accurately predicted immunogenic epitopes are expected to have higher efficacy and fewer side effects in the development of neoantigen-based vaccines. [Brief explanation of the drawings]

[0016] [Figure 1] FIG. 1 illustrates an example of a biological process in tumor cells. [Figure 2] FIG. 1 illustrates a number of biological process elements and neoantigen properties that can influence the immunogenicity of neoantigens. [Figure 3] FIG. 1 shows an example of a process for learning the immunogenicity of mutant epitopes using an artificial intelligence model. [Figure 4] FIG. 1 shows an example of a process for predicting the immunogenicity of a mutant epitope using an artificial intelligence model. [Figure 5] FIG. 1 shows an example of a block diagram of an apparatus for predicting the immunogenicity of mutant epitopes using an artificial intelligence model. DETAILED DESCRIPTION OF THE INVENTION

[0017] The following embodiments are merely for the purpose of explaining the present invention in more detail, and in light of the gist of the present invention, it will be obvious to those skilled in the art that the scope of the present invention is not limited to these embodiments. The present invention should be understood as including all modifications, equivalents, and alternatives that fall within the technical idea and technical scope described below.

[0018] As used herein, singular terms should be construed as including plural terms unless the context clearly dictates otherwise, and terms such as "comprises" should be understood to mean the presence of stated features, numbers, steps, operations, components, parts, or combinations thereof, but not to exclude the presence or additional possibility of one or more other features, numbers, steps, operations, components, parts, or combinations thereof. Also, the term "and / or" means the inclusion of a combination of two or more associated stated items or any two or more associated stated items.

[0019] In performing a method or method of operation, the processes / steps constituting the method may be performed in an order different from that described, unless the context clearly dictates a particular order. That is, the processes / steps may be performed in the order described, substantially simultaneously, or in the reverse order. FIG. 1 shows an example of a biological process in tumor cells.

[0020] Referring to Figure 1, the biological process of tumor cells can be divided into three stages: antigen processing, antigen presentation, and immunogenicity. The tumor microenvironment (TME) surrounding tumor cells can also affect the biological process and can therefore be considered part of the tumor cell biological process. While the biological process of tumor cells is the same as or similar to that of general cells, various factors can affect the generation and / or characteristics of epitopes at each stage.

[0021] The antigen processing stage occurs when DNA in the tumor cell nucleus is transcribed into mRNA and released into the cytoplasm. The transcribed mRNA is converted into peptides and binds to MHC class I. The DNA of tumor cells can be altered due to factors such as mutation. After mRNA is translated and synthesized into protein, it can be cleaved into peptides by the proteasome. The cleaved peptides are transported into the rough endoplasmic reticulum by the TAP transporter and bind to MHC class I.

[0022] In the antigen presentation step, peptides generated in the antigen processing step bind to MHC class I and are presented on the cell surface as peptide-MHC complexes.

[0023] The immunogenic stage is the stage at which peptide-MHC complexes displayed on the cell surface are recognized by T cells.

[0024] The tumor microenvironment (TME) is the environment surrounding cells, which may be surrounded by blood vessels, immune cells, fibroblasts, bone marrow-derived inflammatory cells, lymphocytes, signaling molecules, and extracellular matrix. Tumor cells can affect the tumor microenvironment by releasing extracellular signals, promoting neovascularization, and inducing peripheral immune tolerance, which in turn can affect tumor cell growth and / or metastasis. For example, when the disease inducing an immune response is cancer, the clonality of the sample may affect the immunogenicity of the epitope. The distribution / ratio of immune cells, tumor-infiltrating lymphocytes, RNA expression, and other factors may also affect the immunogenicity of the generated epitope. FIG. 2 is a diagram illustrating the properties of epitopes and elements of many biological processes that can affect the immunogenicity of an epitope.

[0025] In addition to the biological processes described in Figure 1, the immunogenicity of an epitope can also be influenced by its properties. For example, negative factors that affect the human body, such as the toxicity or allergenicity of an epitope, can affect the immunogenicity of an epitope. Factors that affect the immunogenicity of an epitope can occur one at a time, or multiple factors can affect the epitope simultaneously and / or sequentially.

[0026] Below we detail several factors in epitope properties and biological processes that influence the immunogenicity of epitopes.

[0027] Among the epitope characteristics, factors that affect immunogenicity include functional impact by mutations, phosphorylation (PTM), hydrophobicity (hydrophobicity or physicochemical hydrophobicity), similarity to known epitopes, dissimilarity to self (human reference)-proteome, and peptide stability.

[0028] Below, specific programs / algorithms / tools, etc. for determining the degree of influence of each factor on the immunogenicity of an epitope will be described as examples, but are not limited to these.

[0029] The functional impact of mutations is a factor that indicates the effect of tumor-causing somatic mutations on protein function. Epitopes containing mutations with large functional impacts will be naturally eliminated by existing immune cells, while epitopes containing mutations with relatively small functional impacts may exhibit immunogenicity at a higher frequency. To confirm the extent to which the functional impact of mutations affects the immunogenicity of epitopes, for example, PROVEAN or / and PolyPhen-2 programs can be used.

[0030] Phosphorylation is a factor that indicates the degree to which the MHC class I ligand of the epitope whose immunogenicity is to be predicted is phosphorylated. To confirm the degree to which phosphorylation affects the immunogenicity of an epitope, for example, the NetMHCphosPan program can be used.

[0031] Hydrophobicity is a factor that indicates whether the epitope whose immunogenicity is to be predicted is hydrophobic or not. To confirm the degree of influence of hydrophobicity on the immunogenicity of an epitope, a program called ProtFP can be used.

[0032] Similarity to known epitopes is a factor that indicates whether the epitope whose immunogenicity is to be predicted is similar to an epitope known to be immunogenic (or non-immunogenic). To confirm the extent to which similarity to known epitopes affects the immunogenicity of an epitope, for example, the blastP program can be used.

[0033] The dissimilarity to the self-proteome with a human reference is a factor indicating whether the epitope for which immunogenicity is to be predicted is dissimilar to the self-proteome. Here, the self-proteome can be the self-proteome with a human reference. To confirm the extent to which the dissimilarity to the self-proteome with a human reference affects the immunogenicity of the epitope, for example, the pairwise2 module of the Python Bio package can be used.

[0034] Epitope stability (or peptide stability) is a factor that indicates the stability of the epitope itself. Traditionally, the binding stability of peptide-MHC has been used, but the stability of the epitope itself has not been used. If the epitope stability is low, the opportunity to bind / interact with MHC molecules decreases, and the possibility of immunogenicity decreases. To confirm the extent to which epitope stability affects the immunogenicity of an epitope, for example, ProtParam can be used.

[0035] During antigen processing, proteasomal cleavage and / or TAP transporter efficiency can be used to predict the immunogenicity of an epitope. For example, the NetCTLpan program can be used to determine the extent to which proteasomal cleavage and TAP transporter efficiency affect the immunogenicity of an epitope.

[0036] During the antigen presentation stage of the biological process, MHC I binding affinity and / or pMHC stability are at least partially used to predict epitopes that will elicit an immune response.

[0037] MHC class I binding affinity is a factor that indicates the degree to which an epitope whose immunogenicity is to be predicted binds to MHC class I. To confirm the degree to which MHC class I binding affinity affects the immunogenicity of an epitope, programs such as NetMHCpan and / or MHCflurry can be used.

[0038] pMHC stability is a factor that indicates the peptide-MHC stability of an epitope. To confirm the extent to which pMHC stability affects the immunogenicity of an epitope, for example, the NetMHCstabpan program can be used.

[0039] In the immunogenicity stage of the biological process, immunogenicity is used to predict epitopes that will induce an immune response. To confirm the extent to which immunogenicity affects the immunogenicity of an epitope, at least one of IEDB, PRIME, DeepHLApan, and DeepImmuno can be used.

[0040] In the tumor microenvironment, at least one of the following factors can be considered as predictors of epitopes that induce an immune response: inflammatory response, B-cell linear epitopes, and B-cell conformational epitopes.

[0041] Immune cells can regulate immune responses by secreting inflammatory substances such as cytokines. The ability of an epitope to induce such cytokines can be assessed, and if the epitope induces too much or too little cytokines, the immune response can be suppressed. To determine the extent to which the inflammatory response affects the immunogenicity of an epitope, at least one of PIP-EL, AIPpred, and IFNepitope can be used.

[0042] Tumor-causing somatic mutations can be recognized by B-cells. B-cells can recognize both linear epitopes in the form of peptides and conformational epitopes in protein structures. B-cell linear epitopes are elements that indicate potential linear epitopes, and B-cell conformational epitopes are elements that indicate potential conformational epitopes. To determine the extent to which B-cell linear epitopes affect the immunogenicity of an epitope, for example, the Bepipred program can be used. To determine the extent to which B-cell conformational epitopes affect the immunogenicity of an epitope, for example, Discope can be used. FIG. 3 shows an example of a process for learning the immunogenicity of mutant epitopes using an artificial intelligence model.

[0043] Immunogenic and non-immunogenic mutant epitopes are used to study and evaluate the CD8+ T-cell immunogenicity of neoantigens. These can be published data and / or proprietary or produced data. Published data can be obtained using, for example, dbPepNeo and NEPdb. Because it is necessary to calculate the differential index between mutant and non-mutated epitopes, data collection can be limited to tumor neoantigen epitopes. In other words, pathogen-derived epitopes, for which information on mutant and non-mutated epitopes cannot be directly or indirectly extracted, can be excluded because a differential index cannot be calculated.

[0044] Factors involved in the numerous biological processes that affect the immunogenicity of a mutant epitope and the characteristics of the mutant epitope include the characteristics of the mutant epitope, antigen processing, antigen presentation, immunity (or T-cell recognition), and the tumor microenvironment (TME). More specifically, these include the functional impact of the mutation, PTM (phosphorylation, ubiquitination, glycosylation, etc.), sequence similarity to known epitopes, dissimilarity to the self-proteome, epitope (peptide) stability, proteasomal cleavage, TAP transporter efficiency, MHC class I / II binding affinity, pMHC stability, immunity (T-cell receptor recognition), inflammatory response, B-cell linear epitopes, and B-cell conformational epitopes. If the disease being studied is cancer, the clonality of the sample may also be included, as may other TME factors besides inflammation (distribution / ratio of immune cells, tumor-infiltrating lymphocytes, RNA expression, etc.). Furthermore, negative factors that the epitope may have on the human body, such as toxicity and / or allergenicity, may also be included. According to one embodiment, a number of biological processes and epitope characteristics may be partially selected and utilized.

[0045] Among the detailed factors contributing to the immunogenicity of a mutated epitope, factors that can be used to calculate a differential index include at least one of phosphorylation, hydrophobicity, similarity to known epitopes, dissimilarity to the self-proteome, epitope stability, antigen processing, MHC I binding affinity, pMHC stability, immune and inflammatory responses, B-cell linear epitopes, and B-cell conformational epitopes. The functional impact of a mutation is excluded from the factors that can be used to calculate a differential index, because the functional impact of a mutation itself measures the effect of the mutated epitope on the protein relative to the non-mutated epitope. In one embodiment, antigen processing can be a single factor, but it can also be divided into two factors: proteasomal cleavage and TAP transporter efficiency.

[0046] Learning can be performed by integrating all elements simultaneously, or by learning each element individually. For example, if there is insufficient data matching all elements, learning can be performed only for elements for which data exists. The data input to learning is the value measured for each element using a program / algorithm / tool. The program / algorithm / tool ​​may be at least one of those described in Figure 2, or may be a separately developed program / algorithm / tool. If one element is measured using multiple programs / algorithms / tools, each can be used as an input. In another example, multiple elements can be measured and input using a single program / algorithm / tool.

[0047] The immunogenic / non-immunogenic epitopes used for learning consist of pairs of mutated and non-mutated epitopes, and the immunogenicity of mutated epitopes can be predicted using values ​​derived for each element of mutated and non-mutated epitopes using collected or developed algorithms / tools.

[0048] In the present invention, the differential index of the mutated epitope and the non-mutated epitope for each element can be calculated as RATIO and DIFFERENCE and used as input for learning. Either one or both can be used. The following [Equation 1] and [Equation 2] show the RATIO and DIFFERENCE in mathematical form. [Number 1]

[0049]

number

[0050] Differential indexes for various factors involved in numerous biological processes that affect the immunogenicity of mutant epitopes and the properties of mutant epitopes can be named as follows, but are not limited to these:

[0051] -Phosphorylation (one of PTM): Differential phosphorylation index (DPI) -Hydrophobicity:Differential hydrophobicity index(DHI) -Similarity to known epitopes: Differential sequence similarity index (DSSI) -Dissimilarity to self-proteome: Differential dissimilarity index (DDI) -Peptide (epitope) stability: Differential peptide stability index (DPSI) -Proteasomal cleavage: Differential cleavage index (DCI) -TAP transport efficiency: Differential TAP index (DTI) -Antigen processing: Differential antigen processing index (DAPI) -MHC I binding affinity:Differential agretopicity index(DAI) -pMHC stability: Differential stability index (DSI) -Immunogenicity (T-cell receptor interaction): Differential immunogenicity index (DII) -Inflammatory response: Differential inflammatory response index (DIRI) -B-cell linear epitope:Differential B-cell linear epitope index(DBLI) -B-cell conformational epitope: Differential B-cell conformational epitope index (DBCI) For a mutant epitope, factors involved in various biological processes and characteristics of the epitope are measured using a program / algorithm / tool, and statistically significant factors are selected from the values ​​calculated using [Equation 1] and [Equation 2], encoded, and trained using machine learning or statistical methods. Before encoding, standardization and / or normalization can be performed on each factor and the values ​​calculated using [Equation 1] and [Equation 2]. Values ​​derived using a program / algorithm / tool ​​can be used after standardization and / or normalization, as the range and resolution of the values ​​vary depending on each factor or the applied program / algorithm / tool.

[0052] The ratios and / or differences for each element may be utilized in whole or in part by statistical evaluation. For example, learning may be performed using the ratios and differences for all elements simultaneously, or / and statistical significance may be examined / evaluated among them, and learning may be performed using only partially significant values. According to one embodiment, the addition or subtraction of programs / algorithms / tools and / or individual elements may vary depending on the target disease. For example, different combinations of elements and / or programs / algorithms / tools may be formed depending on the type of cancer.

[0053] The artificial intelligence model used for learning can be a neural network, deep learning, logistic regression, AdaBoost, LogitBoost, XgBoost, support vector machine, random forest, or other methods, and is not limited to a specific machine learning algorithm or statistical method. Ensemble machine learning methods (e.g., bagging, stacking, voting, boosting, etc.) that integrate various machine learning algorithms and statistical methods can also be used. By performing integrated learning using this machine learning method, the weights of the factors that predict immunogenic mutant epitopes, which is the ultimate goal, can be determined, and learning can be performed using all factors involved in biological processes, epitope characteristics, and the differences between mutant and non-mutated epitopes.

[0054] The performance of the artificial intelligence model generated by the above learning can be evaluated by conventional cross validation, leave-one-out validation, or validation using independent data, and its performance can be evaluated using experimental methods such as in vitro, in vivo, and clinical testing targeting the predicted mutant epitopes.

[0055] The result of the artificial intelligence model is a predicted immunogenicity value for the mutated epitope. The predicted immunogenicity value for the mutated epitope indicates the probability that the epitope is immunogenic or non-immunogenic, and can be a value between 0 and 1. For example, if the predicted immunogenicity value for the mutated epitope is close to 1, it can be determined to be immunogenic, and if it is close to 0, it can be determined to be non-immunogenic.

[0056] According to another embodiment, the result of the AI ​​model may be a determination as to whether a mutant epitope is immunogenic. The AI ​​model may compare the predicted immunogenicity value for the mutant epitope with a reference value to determine whether the mutant epitope is immunogenic or non-immunogenic. The reference value may vary depending on any one or a combination of tumor type, purpose, and situation. FIG. 4 shows an example of a process for predicting the immunogenicity of a mutant epitope using an artificial intelligence model.

[0057] Referring to Figure 4, a method for predicting the immunogenicity of a mutant epitope according to one embodiment of the present invention may include a step / process (S410) of calculating the degree to which factors involved in the biological process for the mutant epitope and the characteristics of the epitope each affect the immunogenicity of the mutant epitope.

[0058] The method for predicting the immunogenicity of a mutated epitope may include a step / process (S420) of calculating the degree to which factors involved in the biological process and characteristics of the epitope affect the immunogenicity of the non-mutated epitope corresponding to the mutated epitope.

[0059] The method for predicting the immunogenicity of a mutant epitope may include a step / process (S430) of calculating a differential index based on a value calculated for the mutant epitope and a value calculated for the non-mutated epitope. The differential index may include at least one of the ratio (RATIO) between the value calculated for the mutant epitope and the value calculated for the non-mutated epitope, or the difference (DIFFERENCE) between the value calculated for the mutant epitope and the value calculated for the non-mutated epitope. The differential index may be a differential index for at least one of phosphorylation, hydrophobicity, similarity to known epitopes, dissimilarity to the self-proteome, epitope stability, antigen processing, MHC I binding affinity, pMHC stability, immunity, inflammatory response, B-cell linear epitope, and B-cell conformational epitope.

[0060] The method for predicting the immunogenicity of a mutant epitope may include a step / process (S440) of inputting the calculated value for the mutant epitope and the calculated differential index into a pre-trained artificial intelligence model to predict the immunogenicity of the mutant epitope. The method for predicting the immunogenicity of a mutant epitope may further perform at least one of standardization and normalization on the calculated value for the mutant epitope and the calculated differential index before inputting the calculated values ​​into the trained artificial intelligence model. FIG. 5 shows an example of a block diagram of a device for predicting the immunogenicity of a mutant epitope using an artificial intelligence model.

[0061] Referring to FIG. 5, the device for predicting the immunogenicity of a mutant epitope using an artificial intelligence model may be comprised of an input / output device 510, a storage device 520, and a computing device 530.

[0062] The input / output device 510 (or input / output device) may be configured to receive input of a mutant epitope or to output the results of predicting the immunogenicity of a mutant epitope. The input / output device 510 may be configured to receive input of a mutant epitope from a user or from another device. Although the input / output device 510 is shown here as a single device, it may also be configured as separate devices. For example, the input device may be a mouse and / or a keyboard, and the output device may be a display such as a monitor or a speaker.

[0063] The storage device 520 can store an AI model trained to predict the immunogenicity of a mutant epitope using a differential index calculated based on factors involved in biological processes and epitope characteristics for the mutant epitope and non-mutated epitope, and a value calculated based on factors involved in biological processes and epitope characteristics for the mutant epitope. The storage device 520 can store programs / algorithms / tools necessary for data processing in addition to the AI ​​learning model.

[0064] The calculation device 530 calculates the degree of influence of each of the factors involved in the biological process for the mutated epitope and the characteristics of the epitope on the immunogenicity of the mutated epitope, calculates the degree of influence of each of the factors involved in the biological process for the non-mutated epitope corresponding to the mutated epitope and the characteristics of the epitope on the immunogenicity of the non-mutated epitope, calculates a differential index based on the value calculated for the mutated epitope and the value calculated for the non-mutated epitope, and inputs the value calculated for the mutated epitope and the calculated differential index into a pre-trained artificial intelligence model to predict the immunogenicity of the mutated epitope.

[0065] The computing device 530 may further perform at least one of standardization and normalization on the calculated value for the mutant epitope and the calculated differential index before inputting the calculated value into the trained artificial intelligence model.

[0066] Here, the device for predicting the immunogenicity of a mutant epitope using an AI model is described as comprising an input / output device 510, a storage device 520, and a computing device 530. However, multiple components may be combined into one component, and one component may be combined into multiple components. In addition, the device for predicting the immunogenicity of a mutant epitope using an AI model may further include a communication device, etc.

[0067] The differential index may include at least one of the ratio (RATIO) of the value calculated for the mutated epitope to the value calculated for the non-mutated epitope, or the difference (DIFFERENCE) between the value calculated for the mutated epitope and the value calculated for the non-mutated epitope, and may be a differential index for at least one of phosphorylation, hydrophobicity, similarity to known epitopes, dissimilarity to the self-proteome, epitope stability, antigen processing, MHC I binding affinity, pMHC stability, immunity, inflammatory response, B-cell linear epitope, and B-cell conformational epitope. The following describes one embodiment of predicting the immunogenicity of a mutant epitope using the above-described method.

[0068] To learn and evaluate the immunogenicity of epitopes, data on immunogenic and non-immunogenic epitopes against neoepitopes occurring in tumors were collected from public databases and / or papers.

[0069] Table 1 below shows the number of training datasets (training datasets) and evaluation datasets (evaluation datasets).

[0070] [Table 1] In this study, a total of 315 immunogenic epitopes (positive) and 4,067 non-immunogenic epitopes (negative) (i.e., epitopes and MHC I alleles that bind to them) collected from dbPepNeo, NEPdb, PRIME data, and INeo-Epp data (Table 1) were used as the training set. 79 immunogenic epitopes (positive) and 3,125 non-immunogenic epitopes (negative) collected from McPAS-TCR, VDJdb, IEDB t-cell db, and TESLA consortium data were used as the independent set. To predict the immunogenicity of epitopes, factors involved in each biological process and epitope characteristics were calculated for mutated and non-mutated epitopes using the programs and methods shown in Table 2.

[0071] [Table 2] The aforementioned DIFFERENCE and RATIO were then calculated based on the values ​​calculated for the mutated and non-mutated epitopes using the programs and methods listed in Table 2. The ability to distinguish immunogenic and non-immunogenic epitopes using at least one of the values ​​calculated for the mutated epitopes using the programs and methods listed in Table 2, DIFFERENCE, and RATIO was confirmed based on AUC, prAUC, and P-value (Wilcoxon rank-sum test, P<0.05). Only statistically significant factors were input into the AI ​​learning model.

[0072] [Table 3] Referring to Table 3, among the factors involved in the biological process of a mutant epitope and the epitope characteristics, all factors except for TAP efficiency are statistically significant factors in determining whether the epitope is immunogenic. Regarding DIFFERENCE, among the factors involved in the biological process and the epitope characteristics, dissimilarity to the self-proteome, hydrophobicity, MHC flurry (processing score), MHC flurry (presentation score), and PRIME (%Rank) are statistically significant factors in determining whether the epitope is immunogenic. Regarding RATIO, among the factors involved in biological processes and epitope characteristics, dissimilarity to the self-proteome, NetMHCpan (%Rank_EL), NetMHCpan (%Rank_BA), MHCflurry (processing score), NetMHCStabPan (%Rank_Stab), PRIME (%Rank), and NetMHCphosPan (Rnk_EL) are statistically significant factors in determining whether an epitope is immunogenic.

[0073] A total of 30 factors (immunogenicity-related biological processes and epitope characteristics) that were statistically significant for the epitopes in the training dataset / evaluation dataset were organized into a two-dimensional matrix and subjected to machine learning analysis (analysis using an artificial intelligence learning model). In this embodiment, various machine learning algorithms were analyzed using the Weka program, and a final model was generated by integrating and selecting multiple machine learning algorithms. In this embodiment, the final model was selected based on the average probability of model results from nine machine learning algorithms: LogitBoost, BayesNet, CSForest, AdaBoost, Logistic, PART, NaiveBayes, RandomForest, and SMO. To compare and evaluate the performance improvement of the present invention, publicly available immunogenicity-related programs were run on the same data to compare their performance.

[0074] Table 4 below shows the evaluation results of the epitope immunogenicity prediction performance for the training dataset, and Table 5 shows the evaluation results of the epitope immunogenicity prediction performance for the evaluation dataset.

[0075] [Table 4]

[0076] [Table 5] In the case of the present invention, these are the results of 10-fold cross-validation, while in the case of existing publicly available programs and algorithms, they are the results of evaluation on the entire data. Referring to [Table 4], it can be seen that the method according to the present invention exhibits superior prediction accuracy in terms of AUC, prAUC, F-measure, etc. compared to existing publicly available programs and algorithms. Referring to [Table 5], it can be seen that the method according to the present invention exhibits superior prediction accuracy in terms of AUC, prAUC, F-measure, etc. compared to existing publicly available programs and algorithms, even for the evaluation dataset not used for training.

[0077] Table 6 shows the results of comparing the performance of a model that includes all elements with a model that excludes DIFFERENCE and RATIO.

[0078] [Table 6] Because the number of samples for immunogenic and non-immunogenic epitopes was not the same, we used prAUC, a more appropriate performance comparison method, as the standard. Table 6 shows that the model including DIFFERENCE and RATIO performed better than the model excluding DIFFERENCE and RATIO, confirming that the differential index (DIFFERENCE and RATIO) contributes to predicting immunogenic epitopes. Although specific aspects of the present invention have been described in detail above, it will be apparent to those skilled in the art that these specific technical details are merely preferred embodiments and do not limit the scope of the present invention. Therefore, the true scope of the present invention is to be defined by the appended claims and their equivalents.

Claims

1. calculating the degree to which each of the factors involved in the biological process for the mutated epitope and the characteristics of the epitope influences the immunogenicity of the mutated epitope; Calculating the degree to which factors involved in biological processes and characteristics of epitopes affect the immunogenicity of the non-mutated epitopes corresponding to the mutated epitopes; calculating a differential index based on the value calculated for the mutated epitope and the value calculated for the non-mutated epitope; A method for predicting the immunogenicity of a mutant epitope, comprising: inputting the calculated value for the mutant epitope and the calculated differential index into a pre-trained artificial intelligence model to predict the immunogenicity of the mutant epitope.

2. The method for predicting the immunogenicity of a mutant epitope according to claim 1, further comprising the step of performing at least one of standardization and normalization on the calculated value for the mutant epitope and the calculated differential index before inputting the calculated value into the trained artificial intelligence model.

3. The differential index is The method for predicting the immunogenicity of a mutated epitope according to claim 1, comprising at least one of the following: a ratio (RATIO) of the value calculated for the mutated epitope to the value calculated for the non-mutated epitope; and a difference (DIFFERENCE) between the value calculated for the mutated epitope and the value calculated for the non-mutated epitope.

4. The differential index is The method for predicting the immunogenicity of a mutant epitope according to claim 1, wherein the differential index is a differential index for at least one of phosphorylation, hydrophobicity, similarity to known epitopes, dissimilarity to the self-proteome, epitope stability, antigen processing, MHC I binding affinity, pMHC stability, immunity, inflammatory response, B-cell linear epitope, and B-cell conformational epitope.

5. The step of calculating the degree of influence of factors involved in biological processes and characteristics of epitopes on immunogenicity for the mutated epitope and the non-mutated epitope, respectively, comprises: A method for predicting the immunogenicity of a mutant epitope according to claim 1, comprising the step of calculating using an algorithm, program or tool.

6. The biological process is It consists of the antigen processing stage, antigen presentation stage, immune stage, and tumor microenvironment. The method for predicting the immunogenicity of a mutant epitope according to claim 1, wherein the factor involved in the tumor microenvironment is at least one of an inflammatory response, a B-cell linear epitope, and a B-cell conformational epitope.

7. A computer-readable recording medium having recorded thereon a computer program for carrying out the method according to any one of claims 1 to 6.

8. an input / output device that receives input of a mutant epitope or outputs the result of predicting the immunogenicity of the mutant epitope; a storage device for storing an artificial intelligence model trained to predict the immunogenicity of a mutant epitope using a differential index calculated based on factors involved in biological processes and characteristics of the epitopes for the mutant epitope and the non-mutated epitope, and a value calculated based on factors involved in biological processes and characteristics of the epitope for the mutant epitope; An apparatus for predicting the immunogenicity of a mutant epitope, comprising: a computing device that calculates the degree of influence of each of the factors involved in the biological process for a mutant epitope and the characteristics of the epitope on the immunogenicity of the mutant epitope; calculates the degree of influence of each of the factors involved in the biological process for a non-mutated epitope corresponding to the mutant epitope and the characteristics of the epitope on the immunogenicity of the non-mutated epitope; calculates a differential index based on the value calculated for the mutant epitope and the value calculated for the non-mutated epitope; and inputs the value calculated for the mutant epitope and the calculated differential index into a pre-trained artificial intelligence model to predict the immunogenicity of the mutant epitope.

Images