KR100904220B1 - System, method and program for M cell target prediction of peptide sequence by mathematical model - Google Patents

Abstract

The present invention relates to a system and method for predicting M cell target of a peptide sequence using a mathematical model, and a recording medium storing the program.

The present invention comprises the steps of obtaining a sample of the peptide sequence targeting the M cells by using an experimental technique; Obtaining a sample of peptide sequences that do not target M cells based on these sequences; Storing each of the obtained samples as a set and then randomly extracting them in a predetermined ratio to classify them into a mathematical model training set and a mathematical model verification set; Assigning presenter values and activity values to individual peptide sequences; Training using a training peptide set and a mathematical model; Predicting M cell target for the validation peptide set using a trained mathematical model; It is a step of verifying a trained mathematical model, and it is possible to reduce the cost and time required by experiment by predicting the target of M peptide of the peptide by using the recording medium that stores the program in advance. It is a useful invention.

Mathematical model, peptide sequence, presenter, activity value, M cell target.

Description

System, method and program for M cell target prediction of peptide sequence by mathematical model}

1 is a block diagram showing an embodiment of an M cell target prediction system of a peptide sequence using a mathematical model according to the present invention,

Figure 2 is a flow chart showing one embodiment of a method for predicting M cell target of the peptide sequence using the mathematical model of the present invention,

Figure 3 is a flow chart showing an embodiment of a method for predicting M cell target of the peptide sequence using the mathematical model of the present invention,

4 is a flowchart of a method for retraining an M cell target prediction model of a peptide sequence in the present invention.

<Explanation of symbols for main parts of drawing>

10: microcomputer 11: program recording medium

12: CPU 13: input / output unit

20: input means 30: output means

The present invention relates to a system and method for predicting whether a peptide sequence targets an M cell using a mathematical model, and a recording medium storing the program.

In general, the path of infectious agents from the outside into the body is divided into the oral cavity, respiratory and genital tract and skin. The uptake of antigenic substances into the digestive tract through the oral cavity includes receptor mediated endocytosis through M cells present in the follicle associated epithelium (FAE) of the Peyer's patch. It can be divided into the path that enters between the tight junction (tight junction) between the intestinal epithelial (enterocyte) constituting the villi. The mucosal immune response, unlike the systemic immune response, absorbs macromolecules and microorganisms that are transported into the intestinal tract, resulting in antigen-specific immune responses that finally pass through the small intestine's epithelial cells. Induce secretion of type IgA (secretory IgA).

Specialized cells, called M cells, play a central role in secreting IgA, the end product of mucosal immune responses, through the epithelial cells of the small intestine, by absorbing several antigens present in the intestine through specific and nonspecific pathways.

The most efficient route for the administration of vaccines for the prevention of diseases that enter the mucous membranes of the small intestine through M cells, such as waterborne infectious diseases such as cholera, typhoid fever and bacterial dysentery, is the oral drug delivery that targets M cells. ) Is known to induce mucosal immune responses. Therefore, if a ligand capable of inducing specific transcytosis in M cells can be secured, it can be applied to an efficient oral vaccine delivery system that can activate mucosal immune response.

Oral administration method is the most ideal method in terms of ease of administration and high compliance with medications because of the low objection of patients and does not require a separate device such as skilled personnel or syringe, but some problems have been suggested in practical use. The first is the constraint on the size of the substance, the protein-based drug is composed of macromolecules (macromolecule) has a limitation in the biomembrane permeation. The following is lost through the action of various digestive enzymes secreted by the digestive system including the stomach while passing through the digestive system of the living body. Overcoming these factors and reaching the small intestine intact form, it is very difficult for the drug to be absorbed into the body by blocking the intestinal epithelial cell layer that selectively accepts foreign substances to function properly. Therefore, in order to commercialize the oral vaccine delivery system, improvement of problems such as low absorption rate of the vaccine, instability at the digestive tract and low membranous permeability should be preceded.

Recently, in the development of new drugs, peptides are one of the hottest research materials for developing new drugs due to their strong efficacy, little toxicity and side effects, and non-existence in the human body.

Taking advantage of these peptides, selecting peptides targeting M cells and applying them to oral vaccines can be a more efficient way to improve the low transport efficiency of existing protein-based drugs and vaccines. .

The prior art has a disadvantage in that it is very time-consuming and economical because it mainly depends on the method of finding peptides targeting M cells by directly administering the peptides to the living body.

As a way of making up for the shortcomings of these experimental methods, the development of a quantitative model of the correlation between structure and activity in the development of new drugs or new materials is one of the most useful methods for predicting the activity while reducing the cost of the experiment. Was used. However, until now, no program has been developed that can predict the target of M-peptide by applying this methodology. For this reason, there is an urgent need for the development of a technique for predicting whether or not to target the M cell of the peptide sequence, which is one of the activities that can increase the efficiency of drugs in drug delivery materials or drug development.

The present invention has been invented in view of the above circumstances, and provides a system and method for predicting whether or not a peptide sequence targets M cells using a mathematical model, and provides a recording medium storing the program to determine whether the peptide sequence targets M cells. The purpose is to present a model that predicts and verifies.

M cell target prediction system of the peptide sequence using the mathematical model of the present invention for achieving the above object comprises a microcomputer (10) consisting of a program recording medium (11), a CPU (12) and an input / output unit (13); Input means 20; In the M cell target prediction system of the peptide sequence using a mathematical model, characterized in that the output means 30, the program recording medium under the control of the microcomputer to operate, the program recording medium using an experimental technique Obtaining a sample of the peptide sequence targeting the M cell; Obtaining a sample of peptide sequences that do not target M cells based on these sequences; Storing each of the obtained samples as a set and then randomly extracting them in a predetermined ratio to classify them into a mathematical model training set and a mathematical model verification set; Assigning presenter values and activity values to individual peptide sequences; Training using training peptide sets and mathematical models; A process of predicting M cell targets for the validation peptide set using a trained mathematical model; And a process for verifying the trained mathematical model.

The program recording medium 11 includes a program for converting a peptide sequence of which a user wants to know whether or not to target an M cell into an amino acid descriptor, and a program for predicting whether to target an M cell using a trained mathematical model. When a user adds a new M cell target peptide sequence obtained by M-cell target activity by an experimental technique, the program is added to the original M cell target peptide set and then classified, and the expression value is added to the added peptide. A program that gives an activity value, a program that trains a mathematical model using a training peptide set, a program that can predict whether or not to target M cell targets for a test peptide set, and a program that verifies a trained mathematical model. Characterized in that it comprises a.

In addition, the method for predicting the M cell target of the peptide sequence using the mathematical model of the present invention for achieving the above object comprises the steps of obtaining a sample of the peptide sequence targeting the M cells by using an experimental technique; Obtaining a sample of a sequence of peptides that do not target M cells based on these sequences; Storing each of the obtained samples as a set and then randomly extracting them in a predetermined ratio to classify them into a mathematical model training set and a mathematical model verification set; Assigning presenter values and activity values to individual peptide sequences; Training using a training peptide set and a mathematical model; Predicting M cell target for the validation peptide set using a trained mathematical model; Verifying a trained mathematical model.

The mathematical model is a quantitative structure including regression analysis, machine learning, multiple regression analysis using genetic algorithm, partial least square method using genetic algorithm, partial least square method using principal component analysis, and multiple regression analysis using principal component analysis. A mathematical model method characterized in that it is a characteristic correlation method, and the machine learning method is a neural network, data mining, decision tree, inductive logic, case-based reasoning, pattern recognition, reinforcement learning, Bayesian network, hidden marker model, probability grammar Method, and in particular, a neural network technique.

The presenter value is a quantitative representation of molecular structure, amino acids, peptides, characterized in that it comprises at least one of binary amino acid descriptors, VHSE amino acid descriptors, Z3 amino acid descriptors, Z5 amino acid descriptors.

The data collected to build the machine learning model is in vivo , ex vivo is, data obtained from at least any one of the in vitro experiments, especially in using the phage display technique experiment vivo , ex vivo , in It is characterized in that the data obtained from at least one of the in vitro experiments. The peptide sequence is a sequence consisting of 2 to 12 peptides, more preferably 3 to 7 peptides, and the species to which the M cell target prediction method of the peptide sequence using the mathematical model of the present invention is applied are mammals, particularly humans. It is done.

In addition, the recording medium storing the M cell target prediction program of the peptide sequence using the mathematical model of the present invention includes the process of obtaining a sample of the peptide sequence targeting the M cells by using an experimental technique; Obtaining a sample of a peptide sequence that does not target M cells based on these sequences; Storing each of the obtained samples as a set and then randomly extracting them in a predetermined ratio to classify them into a mathematical model training set and a mathematical model verification set; Assigning presenter values and activity values to individual peptide sequences; Training using training peptide sets and mathematical models; A process of predicting M cell targets for the validation peptide set using a trained mathematical model; And a process for verifying the trained mathematical model.

The objects, features and advantages of the present invention will be more readily understood by reference to the accompanying drawings and the following detailed description.

Hereinafter, with reference to the accompanying drawings, a system and method for predicting M cell target of peptide sequence using the mathematical model of the present invention and a recording medium storing the program will be described in detail as a preferred embodiment.

1 is a block diagram showing an embodiment of the M cell target prediction system of the peptide sequence using the mathematical model according to the present invention, Figure 2 is an embodiment of a method for predicting M cell target of the peptide sequence using the mathematical model of the present invention As a flowchart showing an example, as shown in FIG. in vitro A sample (number) of M cell target peptide sequences is collected by M cell model and phage display experiment technique (step S1). Here, the length of the peptide sequence means the number of amino acids in one peptide, and the peptide sequence length 7 indicates a peptide having 7 amino acids. The number of peptide sequences collected is shown in Table 1 below.

Number of M cell target peptide sequences  Peptide sequence length                 Peptide Count   M cell target    M cell non-target   For training    Verification          3     1,225      1,225   1,930     520          4       980        980   1,568     392          5       735        735   1,174     296          6       490        490     782     198          7       245        245     396      94

In addition, the phage display peptide library used in step S1 is 'ph.D.-C7C ^TM (New England BioLab.)', Which is a kind of coat protein in the genome of M13 bacteriophage. More than hundreds of millions of different species obtained by infecting E. coli by artificially inserting gene sequences to express peptides of 7 random amino acid sequences at the ends of pIII-producing genes It consists of recombinant bacteriophage expressing peptides. On the other hand, the seven random amino acid sequences introduced into the M13 phage are designed to have cysteine residues on both sides to form a disulfide bond in the expression of the peptide, thereby forming a loop shape, thereby allowing the loop protein to form a loop shape. It is designed to induce strong bonding.

Phage display technique is 1.0 X 10 ¹¹ pfu phage-peptide library (~ 1,000 copies of individual recombinant phage clone) of in in vitro A transcytosis assay was performed on M cell models to select peptide sequences with significantly high transcytosis ability.

In addition, by using a program to select an arbitrary amino acid 7 amino acids for the length 7 of the M cell target peptide sequence was extracted and compared to the M cell target peptide set obtained in the experiment compared to the M cell if there is no peptide of the same sequence Classify as a set of non-target peptide sequences (step S2). The program for selecting any amino acid here uses a well-known program.

Next, classify a set of peptide sequences for machine learning training (step S3). This step (step S3) includes a process of making the population equal between two sets because the number of M cell target peptide sequence sets is less than the number of M cell non-target peptide sequence sets. In this step (step S3), for peptide sequence length 7, 245 M cell non-target peptides were obtained as shown in Table 1.

Then, approximately 80% of any peptide sequence is extracted from the set of M cell target peptides, approximately 80% of any peptide sequence is extracted from the non-M cell target peptide set, and the two are collected and classified as a set of machine learning training peptides ( Step S4).

As in step S4, approximately 20% of the remaining M cell target peptide set and the remaining 20% of the M cell non-target peptide set are collected and classified into a set of machine learning verification peptides (step S5).

As a result, as shown in Table 1, in the case of length 7 of the peptide sequence, the number of machine learning training peptides was 396 and the number of peptides for machine learning verification was 94.

Next, using the machine learning method, the step of training and acquiring the M cell-targeted peptide prediction model with the machine learning training set obtained in step S4 is performed (step S10). That is, in the step of arbitrarily changing the order in which the M cell target peptide set is input, the machine learning training so that the M cell target peptide sequence and the M cell non-target peptide sequence are alternated at equal ratios and entered into the machine learning training process as input values. The order of the dragon set is adjusted and input as an input value for the machine learning model training (step S11).

Thereafter, the individual peptide sequences included in the machine learning training set are converted into amino acid descriptor values (step S12). Wherein the amino acid presenter value includes at least one of binary amino acid presenter, VHSE amino acid presenter, Z3 amino acid presenter, Z5 amino acid presenter, and the binary amino acid presenter for an amino acid is defined as 19 " It is expressed by the number of 20 digits which consists of 0 "and one" 1 ", and it sets so that the order in which the value of" 1 "may be located may differ from each other for 20 amino acids. For peptide sequence length 7, it consists of 140 descriptors. For M cell target activity, M cell target peptide is 0.9 and M cell non-target peptide is 0.1.

As such, the conversion of individual peptide sequences included in the machine learning training set to the value of the presenter can be converted using the VHSE amino acid presenter, and the values defined therefor are shown in Table 2 below. VHSE descriptors consist of eight markers for one amino acid, which are known to represent the hydrophobicity, electronic, and steric properties of the amino acids, and 24 input values for peptide sequence length 3. It consists of.

VHSE Amino Acid Descriptor  Amino acids  VHSE 1  VHSE 2  VHSE 3  VHSE 4  VHSE 5  VHSE 6  VHSE 7  VHSE 8  Ala  A   0.15  -1.11  -1.35  -0.92   0.02  -0.91   0.36  -0.48  Arg  R  -1.47   1.45   1.24   1.27   1.55   1.47   1.30   0.83  Asn  N  -0.99   0.00  -0.37   0.69  -0.55   0.85   0.73  -0.80  Asp  D  -1.15   0.67  -0.41  -0.01  -2.68   1.31   0.03   0.56  Cys  C   0.18  -1.67  -0.46  -0.21   0.00   1.20  -1.61  -0.19  Gln  Q  -0.96   0.12   0.18   0.16   0.09   0.42  -0.20  -0.41  Glu  E  -1.18   0.40   0.10   0.36  -2.16  -0.17   0.91   0.02  Gly  G  -0.20  -1.53  -2.63   2.28  -0.53  -1.18   2.01  -1.34  His  H  -0.43  -0.25   0.37   0.19   0.51   1.28   0.93   0.65  Ile  I   1.27  -0.14   0.30  -1.80   0.30  -1.61  -0.16  -0.13  Leu  L   1.36   0.07   0.26  -0.80   0.22  -1.37   0.08  -0.62  Lys  K  -1.17   0.70   0.70   0.80   1.64   0.67   1.63   0.13  Met  M   1.01  -0.53   0.43   0.00   0.23   0.10  -0.86  -0.68  Phe  F   1.52   0.61   0.96  -0.16   0.25   0.28  -1.33  -0.20  Pro  P   0.22  -0.17  -0.50   0.05  -0.01  -1.34  -0.19   3.56  Ser  S  -0.67  -0.86  -1.07  -0.41  -0.32   0.27  -0.64   0.11  Thr  T  -0.34  -0.51  -0.55  -1.06  -0.06  -0.01  -0.79   0.39  Trp  W   1.50   2.06   1.79   0.75   0.75  -0.13  -1.01  -0.85  Tyr  Y   0.61   1.61   1.17   0.73   0.53   0.25  -0.96  -0.52  Val  V   0.76  -0.92  -0.17  -1.91   0.22  -1.40  -0.24  -0.03

Subsequently, machine learning training is performed using the experimental values of whether M cells are targeted for the machine learning training peptide set and the expression value of the peptide sequence as input values (step S13). The methods for machine learning include Neural Network, Data Mining, Decision Tree, Case Based Reasoning, Pattern Recognition, Reinforcement Learning For example, in the case of using a feed forward neural network, feed forward neural network learning training is performed using a set of machine learning training peptides. The structure of the feed forward neural network for machine learning is composed of an input layer, a hidden layer, and an output layer. The input layer is composed of input nodes, and the number of input nodes is determined by multiplying the number of peptide sequence lengths by the number of components of the presenter value, and one input node is a real or integer value of one presenter value component. One hidden layer is composed of 0 to 3 hidden nodes, and an output layer is composed of output nodes, and the number of output nodes is one. In the case of using the 20-digit binary amino acid descriptor for the peptide sequence length 7, the structure of the feedforward neural network is composed of 140 input nodes, and the input values of each node are 140 expression values "0" or "1" created in step S12. "to be. The structure of the feedforward neural network for all peptide sequence lengths may consist of an output layer with just one output node without using a hidden layer.

Next, through the appropriate machine learning training of the step S13 to obtain an M cell-targeted peptide prediction model that can predict whether the peptide sequence targets M cells (step S14).

Subsequently, using the M cell targeted peptide prediction model obtained in step S14 and the machine learning verification set obtained in step S5, the predicted value for M cell targeting of the peptide was obtained, and compared with the experimental value, M cell targeted peptide. Validate and evaluate the prediction model (step S20). This step S20 consists of steps S21 to S24, that is, first prepares an input value for the machine learning model verification (step S21). In step S21, the machine learning verification set obtained in step S5 is used as it is.

Subsequently, the peptide individual sequences included in the machine learning verification set are converted into the presenter values (step S22). In this case, the presenter uses the same presenter as the M cell targeted peptide prediction model obtained in the step S14 used in the training process of the step S13.

Subsequently, the amino acid presenter value for the peptide sequence is used as an input value as a set of machine learning verification peptides, and an M cell-targeted peptide prediction model obtained in step S14 is obtained in order to predict whether or not M cells are targeted (step S23). ).

Then, using the machine learning verification set to obtain the predicted value for the target M cell, and using this to verify the M cell target peptide prediction model obtained in step S23 and the results are shown in Table 3 below (step S24) ).

In step S22, using the presenter as a 20-digit binary amino acid presenter, a machine learning model was trained to execute step S24, and the results are shown in Table 3 below. As a result of performing the verification three times by arbitrarily changing the order of input values of the feed forward neural network, the responder action characteristic score for the peptide length 3 was 0.8678 ± 0.0062 for the training set and 0.8609 ± 0.0122 for the validation set.

Results of M Cell Target Prediction Model      Peptide sequence length               Responder Activity Score         For training (80%)          Verification (20%)             3      0.8678 ± 0.0062       0.8609 ± 0.0122             4      0.7644 ± 0.0025       0.7020 ± 0.0155             5      0.7984 ± 0.0110       0.7544 ± 0.0172             6      0.8571 ± 0.0048       0.7248 ± 0.0132             7      0.9314 ± 0,0101       0.6871 ± 0.0064

In step S22, using the presenter as a VHSE amino acid presenter to train the machine learning model to perform the step S24 and the results are shown in Table 4 below. The test was performed three times by randomly changing the order of input values of the feed forward neural network. As a result, the responder action characteristic score for the peptide length 3 was 0.8177 ± 0.0079 for the training set and 0.7974 ± 0.0187 for the validation set.

Results of M Cell Target Prediction Model      Peptide sequence length               Responder Activity Score         For training (80%)          Verification (20%)             3      0.8177 ± 0.0079       0.7974 ± 0.0187             4      0.7309 ± 0.0154       0.7064 ± 0.0083             5      0.8067 ± 0.0027       0.7449 ± 0.0193             6      0.8067 ± 0.0027       0.7433 ± 0.0205             7      0.8536 ± 0,0057       0.6710 ± 0.0464

Through this embodiment, it can be seen that the feedforward artificial neural network model composed of the input layer, the hidden layer, and the output layer with respect to the peptide sequence distinguished the actual M cell target peptide from the M cell non-target peptide.

Figure 3 is a flow chart showing an embodiment of a method for predicting the M cell target of the new peptide sequence using the machine learning method of the present invention, first input the peptide sequence to know the M cell target through the input means 20 to record the program The medium 11 is stored in the medium 11 (step S101).

Next, the individual peptide sequences inputted are converted into the expression values required by the trained prediction model (step S23) through the process of FIG. 2 (step S102).

After that, it applies to the M cell target prediction model consisting of the trained prediction model (step S23) (step S103).

To find out whether the target M cell is outputted whether the target M cell of the new peptide sequence input by the user (S104).

4 is a flowchart illustrating a method for retraining an M cell target prediction model according to the present invention. First, a new specific M cell target peptide sequence and an M cell non-target peptide sequence obtained by an experimental technique for M cell target activity value are obtained. The program recording medium 11 is stored through the input means 20 (step S201).

Subsequently, the machine learning model is trained by performing the steps S3 to S5 and the steps S10 and S20 of FIG. 2, and then verified and automated by comparing the comparison with the existing machine learning model (step S210). First, it is determined whether the newly input peptide sequences are the same as the already designated sequences, and these sequences are added and stored according to the activity value to the M cell target peptide set and the M cell non-target peptide set (step S211).

Next, by adding the newly input peptide sequence to the previously stored peptide sequence to classify the peptide sequence set for the machine learning training of step S3 of FIG. 2, and obtains the peptide set for machine learning training of step S4 , Obtain a set of peptides for the machine learning verification of step S5, train the M cell-targeted peptide prediction model using the machine learning method of step S10, and obtain an M cell-targeted peptide prediction model using the machine learning method of S20. Verify (S212).

Thereafter, the responder functional characteristic scores of the M cell-targeted peptide prediction model stored previously are compared with the responder functional characteristic scores of the M cell-targeted peptide predictive model obtained in step S212 (step S213).

Subsequently, the responder action characteristic score calculated in step S213 is output to the user, and based on this, the user stores the newly trained M cell targeted peptide prediction model (step S202).

In this way, the user can retrain and validate the mathematical model based prediction model using the newly acquired M cell target peptide sequence through experiments.

Although the present invention has been described as a preferred embodiment so far, the present invention is not limited thereto and can be variously modified and implemented within the scope not departing from the gist of the invention.

As described above, according to the present invention, whether or not M cell targets for peptide sequences as M cell target substances to improve the low transport efficiency of existing protein-based drugs and vaccines to be used as oral vaccines are always experimentally tested. There is a special advantage to reduce the cost and time required for experiments by predicting in advance by using the recording medium that stores the program without checking.

Claims (15)

A microcomputer 10 comprising a program recording medium 11, a CPU 12, and an input / output unit 13; Input means 20; In the M cell target prediction system of the peptide sequence using a mathematical model, characterized in that the output means 30, The program recording medium 11 operates under the control of the microcomputer 10, wherein the program recording medium 11 includes a process of obtaining a sample of a peptide sequence targeting M cells using an experimental technique; Obtaining a sample of peptide sequences that do not target M cells based on these sequences; Storing each of the obtained samples as a set and then randomly extracting them in a predetermined ratio to classify them into a mathematical model training set and a mathematical model verification set; Assigning presenter values and activity values to individual peptide sequences; Training using training peptide sets and mathematical models; A process of predicting M cell targets for the validation peptide set using a trained mathematical model; M cell target prediction system of peptide sequence using a mathematical model, characterized in that it comprises a process of validating a trained mathematical model. According to claim 1, wherein the program recording medium (11) when a user inputs a peptide sequence to know whether or not to target the M cell, the program converts it into an amino acid descriptor, and trained mathematical model to determine whether the M cell target A program for predicting and adding a new M cell target peptide sequence obtained by the user with the M cell target activity value by an experimental technique, the program is added to the original M cell target peptide set and then classified; Programs that give expression and activity values to peptides, programs that train mathematical models using training peptide sets, programs that allow predicting M cell targets for validation peptide sets, and trained mathematical The mathematical model includes a program for verifying the model. M predicted target cell system of a peptide sequence. Obtaining a sample of a peptide sequence targeting M cells using an experimental technique; Obtaining a sample of a sequence of peptides that do not target M cells based on these sequences; Storing each of the obtained samples as a set and then randomly extracting them in a predetermined ratio to classify them into a mathematical model training set and a mathematical model verification set; Assigning presenter values and activity values to individual peptide sequences; Training using a training peptide set and a mathematical model; Predicting M cell target for the validation peptide set using a trained mathematical model; M cell target prediction method of the peptide sequence using a mathematical model, characterized in that it comprises the step of verifying the trained mathematical model. 4. The mathematical model of claim 3, wherein the mathematical model includes regression analysis, machine learning, multiple regression analysis using genetic algorithm, partial least square method using genetic algorithm, partial least square method using principal component analysis, and multiple regression using principal component analysis. A method for predicting M cell target of a peptide sequence using a mathematical model, characterized in that it is a quantitative structure-characteristic correlation method including an analysis method. The mathematical model of claim 4, wherein the machine learning method is a neural network, data mining, decision tree, inductive logic, case-based reasoning, pattern recognition, reinforcement learning, Bayesian network, hidden Markov model, and a stochastic grammar method. M cell target prediction method of the peptide sequence used. 5. The method of claim 4, wherein the machine learning method is a neural network technique. 4. The method of claim 3, wherein the presenter value is a quantitative representation of molecular structure, amino acids, and peptides. The M cell of the peptide sequence of claim 7, wherein the presenter value comprises at least one of a binary amino acid presenter, a VHSE amino acid presenter, a Z3 amino acid presenter, and a Z5 amino acid presenter. Target prediction method. The method of claim 3, wherein the data collected to build the mathematical model is in vivo, ex vivo , in M cell target prediction method of the peptide sequence using a mathematical model, characterized in that the data obtained from at least one of the in vitro experiments. According to claim 3, wherein using the phage display technique experimental data collected in order to build the mathematical model in vivo , ex vivo , in M cell target prediction method of the peptide sequence using a mathematical model, characterized in that the data obtained from at least one of the in vitro experiments. The method of claim 3, wherein the peptide sequence is a sequence consisting of 2 to 12 peptides. According to claim 3, wherein the peptide sequence consists of 3 to 7 peptides M cell target prediction method of the peptide sequence using a mathematical model, characterized in that the column. A method for predicting M cell target of a peptide sequence using a mathematical model, wherein the species is a mammal to which the method for predicting M cell target of the peptide sequence according to claim 3 is applied. A method for predicting M cell target of a peptide sequence using a mathematical model, wherein the species is a human applying the method for predicting M cell target of the peptide sequence according to claim 3. Obtaining a sample of peptide sequences targeting M cells using experimental techniques; Obtaining a sample of peptide sequences that do not target M cells based on these sequences; Storing each of the obtained samples as a set and then randomly extracting them in a predetermined ratio to classify them into a mathematical model training set and a mathematical model verification set; Assigning presenter values and activity values to individual peptide sequences; Training using training peptide sets and mathematical models; A process of predicting M cell targets for the validation peptide set using a trained mathematical model; A recording medium storing an M cell target prediction program of a peptide sequence using a mathematical model, the process comprising verifying a trained mathematical model.

Images