KR20230031760A - Method of identify epitope candidate - Google Patents

Abstract

The present disclosure is a method for a purpose of deriving an antigenic determinant candidate based on an amino acid sequence of an antigen which comprises the following steps of: generating a plurality of amino acid sub-sequences based on the amino acid sequence of the antigen; generating feature values for the plurality of amino acid sub-sequences; and deriving at least one antigenic determinant candidate based on the feature values for the plurality of amino acid sub-sequences.

Description

Method for deriving antigenic determinant candidates {METHOD OF IDENTIFY EPITOPE CANDIDATE}

The present disclosure relates to methods for deriving antigenic determinant candidates based on the amino acid sequence of an antigen.

In order to recognize an antigen in the human immune system, various delivery vehicles for delivering an antigenic determinant (epitope) such as a virus like partible (VLP) to the human body have been developed and used. At this time, the antigenic determinant is a part of the amino acid sequence of an antigen that is a target of the body's immune system, and plays an important role in recognizing the antigen by the antibody.

Specifically, when the body's immune system recognizes an antigen, it can activate B-cells and T-cells to kill the antigen. For example, when an antigenic determinant matched with cancer is injected into the human body of a cancer patient, the death of cancer cells can be induced by activating B-cells or T-cells.

However, since cancers have specific antigens for each type of cancer, experimental methods in deriving each antigenic determinant for each specific antigen are physically and costly difficult.

Therefore, there is a need for a method of deriving an amino acid sequence corresponding to an antigenic determinant within the amino acid sequence for each antigen in a virtual environment using a computer processor prior to experiments in a physical environment.

The present disclosure addresses the problem of deriving antigenic determinant candidates based on the amino acid sequence of an antigen.

The purpose of the present disclosure is not limited to the above-mentioned purpose, and other objects and advantages of the present disclosure not mentioned above can be understood by the following description and will be more clearly understood by the embodiments of the present disclosure. Further, it will be readily apparent that the objects and advantages of the present disclosure may be realized by means of the instrumentalities and combinations indicated in the claims.

According to an embodiment of the present disclosure for realizing the above object, a method for deriving an antigenic determinant candidate including at least one processor is disclosed. The method comprises generating a plurality of amino acid sub-sequences based on the amino acid sequence of the antigen; generating feature values for the plurality of amino acid sub-sequences; and deriving at least one antigenic determinant candidate based on feature values for the plurality of amino acid sub-sequences.

In an alternative embodiment, generating the plurality of amino acid sub-sequences comprises extracting, based on the amino acid sequence of the antigen, a plurality of amino acid sub-sequences that satisfy an amino acid sub-sequence condition; The amino acid sub-sequence condition may be a condition including N or more and M or less consecutive amino acids.

In an alternative embodiment, the amino acid sequence of the antigen comprises L amino acids, and extracting, based on the amino acid sequence of the antigen, a plurality of amino acid sub-sequences that satisfy an amino acid sub-sequence condition: Sequentially determining amino acids from the first amino acid to the (L-M+1)th amino acid of the amino acid sequence of as starting points of extraction; And by performing an operation of extracting N to M consecutive amino acids for each of the sequentially determined (L-M+1) starting points, (L-M+1) (M-N+1) number of lower - may include extracting sequences.

In an alternative embodiment, the amino acid sequence of the antigen includes L amino acids, and based on the amino acid sequence of the antigen, extracting a plurality of different amino acid sub-sequences that satisfy an amino acid sub-sequence condition: determining K first starting points at intervals of a predetermined number of amino acids in the amino acid sequence of the antigen; For each of the K first starting points, extracting mid-sequences including J consecutive amino acids; and extracting the plurality of amino acid sub-sequences based on the K intermediate-sequences.

In an alternative embodiment, extracting the plurality of amino acid sub-sequences based on the mid-sequences comprises: for each of the K mid-sequences: from the first amino acid of each mid-sequence (J- Amino acids up to the M+1)th amino acid are sequentially determined as second starting points, and N to M consecutive amino acids are extracted for each of the sequentially determined (J−M+1) second starting points. extracting (J-M+1)(M-N+1) sub-sequences by performing an operation; and extracting K(J-M+1)(M-N+1) sub-sequences from the K mid-sequences. In an alternative embodiment, the step of deriving the at least one antigenic determinant candidate comprises, for each of the K mid-sequences, one sub-sequence among sub-sequences included in each mid-sequence, respectively. Determining a representative antigenic determinant candidate of the mid-sequence of; and comparing the determined K representative antigenic determinant candidates.

In an alternative embodiment, deriving the at least one antigenic determinant candidate comprises determining a plurality of probability values based on feature values for the plurality of amino acid sub-sequences; and excluding amino acid sub-sequences corresponding to probability values less than or equal to a threshold value among the plurality of probability values.

In an alternative embodiment, the step of deriving the at least one antigenic determinant candidate comprises selecting as antigenic determinant candidates amino acid sub-sequences corresponding to probability values exceeding the threshold; identifying antigenic determinant candidates overlapping at least a predetermined ratio among the selected antigenic determinant candidates as a group to be eliminated; and integrating the antigenic determinant candidates belonging to the group to be eliminated redundancy into one representative antigenic determinant candidate, wherein the one representative antigenic determinant candidate has a probability value determined among the candidates belonging to the candidate antigenic determinant belonging to the group to be eliminated redundancy. It may correspond to the highest antigenic determinant candidate.

In an alternative embodiment, generating the feature values comprises extracting feature values for the plurality of amino acid sub-sequences based on a feature extractor, wherein the feature extractor comprises a recurrent neural neural network (RNN) Network), a Convolutional Neural Network (CNN), or a Transformer-based neural network model, and the feature extractor is derived from a masked language model (MLM) or auto encoder model learned on the basis of a protein database. can be pre-learned.

In an alternative embodiment, deriving the at least one antigenic determinant candidate comprises deriving the at least one antigenic determinant candidate based on a classifier and feature values for the plurality of amino acid sub-sequences; However, the classifier may include one of extreme gradient boosting (XGB), support vector machines (SVM), random forest, or neural network models.

In an alternative embodiment, the feature extractor and the classifier are learned based on learning data comprising antigenic determinants and non-antigenic determinants for antigens, wherein the learning data includes antigenic determinants and non-antigenic determinants of unified length. can include

In an alternative embodiment, unifying the lengths of the antigenic determinant and the non-antigenic determinant may include padding based on the maximum length of the antigenic determinant and the non-antigenic determinant.

According to an embodiment of the present disclosure for realizing the above object, an apparatus is disclosed. The device may include a processor including one or more cores; and memory; wherein the processor generates a plurality of amino acid sub-sequences based on an amino acid sequence of an antigen, generates feature values for the plurality of amino acid sub-sequences, and generates the plurality of amino acid sub-sequences; At least one antigenic determinant candidate may be derived based on feature values for amino acid sub-sequences.

According to an embodiment of the present disclosure for realizing the above object, a computer program stored in a computer readable storage medium is disclosed. The computer program causes operations to derive a candidate epitope, the operations comprising: generating a plurality of amino acid sub-sequences based on an amino acid sequence of an antigen; generating feature values for the plurality of amino acid sub-sequences; and deriving at least one antigen determinant candidate based on feature values of the plurality of amino acid sub-sequences.

The present disclosure can derive antigenic determinant candidates based on the amino acid sequence of an antigen. Specifically, based on the amino acid sequence of the antigen, a classification algorithm can be used to extract sub-sequences, and a neural network model can be used to derive antigenic determinant candidates.

1 is a block diagram of a computing device for deriving an antigenic determinant candidate according to an embodiment of the present disclosure.
Figure 2 is a schematic diagram for explaining an antigenic determinant prior to describing an embodiment of the present disclosure.
3 is a schematic diagram illustrating a network function, according to an embodiment of the present disclosure.
4 is a flowchart illustrating a method for a processor to derive an antigenic determinant candidate based on an amino acid sequence of an antigen, according to an embodiment of the present disclosure.
5 is a schematic diagram illustrating a method for a processor to generate an amino acid sub-sequence based on an amino acid sequence of an antigen, according to an embodiment of the present disclosure.
6 is a schematic diagram illustrating a method for a processor to generate mid-sequences to generate amino acid sub-sequences based on an amino acid sequence of an antigen, according to an embodiment of the present disclosure.
7 is a flowchart illustrating a method of generating an amino acid sub-sequence based on an intermediate-sequence, according to an embodiment of the present disclosure.
8 is a flowchart illustrating a method for a processor to generate antigenic determinant candidates based on feature values for amino acid sub-sequences, according to an embodiment of the present disclosure.
9 is a schematic diagram illustrating a method for a processor to derive an antigenic determinant candidate based on an amino acid sequence of an antigen, according to an embodiment of the present disclosure.
10 is a schematic diagram illustrating a method for a processor to learn a feature extractor, according to an embodiment of the present disclosure.
11 is a simplified and general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

Various embodiments for deriving antigenic determinant candidates are now described with reference to the figures. In this specification, various descriptions are presented to provide an understanding of the present disclosure. However, it is apparent that these embodiments may be practiced without these specific details.

As used herein, the terms “component,” “module,” “system,” and the like refer to a computer-related entity, hardware, firmware, software, a combination of software and hardware, or an execution of software. 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.

Additionally, 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 "comprising" 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” should be interpreted as meaning “when only A is included”, “when only B is included” and “when A and B are combined”.

Skilled artisans will further understand that the various illustrative logical blocks, components, modules, circuits, means, logics, and algorithm steps described in connection with the embodiments disclosed herein may be implemented in electronic hardware, computer software, or both. It should be recognized that it can be implemented with combinations of To clearly illustrate the interchangeability of hardware and software, various illustrative components, blocks, configurations, 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 make or use the present disclosure. 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 disclosure is not limited to the embodiments presented herein. This disclosure is to be interpreted in the widest light consistent with the principles and novel features presented herein.

In the present disclosure, network functions, artificial neural networks, and neural networks may be used interchangeably.

In the present disclosure, amino acid sequence data of an antigen may be understood as data having a one-dimensional structure including consecutive amino acids from the '1' cell to the 'A' cell. At this time, when the processor of the present disclosure performs the operation based on the amino acid sequence of the antigen having the length of 'A', the operation can be performed by '1' column from the '1' column to the 'A' column, Each column of the amino acid sequence of the antigen may include one amino acid. In the present disclosure, an amino acid may refer to each amino acid included in columns of amino acid sequence data of an antigen, and the expression “Xth amino acid” may refer to an amino acid included in the X column of amino acid sequence data. . In addition, the expression 'starting point' related to the amino acid sequence of the present disclosure is an amino acid at which the operation is first started when the processor performs an operation including extraction based on the amino acid sequence, and when performing a repetitive operation, after the operation is finished. Means the amino acid to start over. For example, it is assumed that a simple reading operation is performed based on an arbitrary amino acid sequence having a length of 10 having amino acids from '1' to '10' (eg, amino acids from 0 to 9 based on the starting index). At this time, 10 starting points including the [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]th amino acids can be determined. At this time, when the '1'th amino acid (eg, the amino acid at the starting index 0) is determined as the starting point, the [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]th amino acid is read and the '5'th amino acid is read. [5, 6, 7, 8, 9, 10] amino acids can be read when an amino acid (eg, the amino acid at the starting index 4) is determined as the starting point.

The expression amino acid sub-sequence is used in this disclosure to refer to a subset of an antigen's amino acid sequence. Amino acid sub-sequences are also subsets of mid-sequences. That is, 'antigen amino acid sequence' ⊃ 'sub-sequence' or 'antigen amino acid sequence' ⊃ 'intermediate-sequence' ⊃ 'sub-sequence'.

'N' used in the present disclosure may mean the minimum length that can be an antigenic determinant, and 'M' may mean the maximum length that can be an antigenic determinant. At this time, 'N' and 'M' are variables that can affect the performance and prediction accuracy of the processor 110, and can be initialized according to the user's judgment.

1 is a block diagram of a computing device for deriving an antigenic determinant candidate according to an embodiment of the present disclosure.

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 may include a processor 110 , a memory 130 , and a network unit 150 .

The processor 110 may include one or more cores, and includes a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU) of a computing device. unit), data analysis, and processors for deep learning. The processor 110 may read a computer program stored in the memory 130 and process data for machine learning 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 an embodiment of the present disclosure, the 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.

According to an embodiment of the present disclosure, the memory 130 may store any type of information generated or determined by the processor 110 and any type of information received by the network unit 150 .

According to an embodiment of the present disclosure, the memory 130 is a flash memory type, a hard disk type, a multimedia card micro type, or a card type memory (eg, SD or XD memory, etc.), RAM (Random Access Memory, RAM), SRAM (Static Random Access Memory), ROM (Read-Only Memory, ROM), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory) -Only Memory), a magnetic memory, a magnetic disk, and an optical disk may include at least one type of storage medium. 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 above description of the memory is only an example, and the present disclosure is not limited thereto.

The network unit 150 according to an embodiment of the present disclosure includes a Public Switched Telephone Network (PSTN), x Digital Subscriber Line (xDSL), Rate Adaptive DSL (RADSL), Multi Rate DSL (MDSL), and VDSL ( Various wired communication systems such as Very High Speed DSL), Universal Asymmetric DSL (UADSL), High Bit Rate DSL (HDSL), and Local Area Network (LAN) may be used.

In addition, the network unit 150 presented in this specification includes Code Division Multi Access (CDMA), Time Division Multi Access (TDMA), Frequency Division Multi Access (FDMA), Orthogonal Frequency Division Multi Access (OFDMA), SC-FDMA ( Single Carrier-FDMA) and other systems.

In the present disclosure, the network unit 150 may be configured regardless of its communication mode, such as wired and wireless, and may be configured with various communication networks such as a personal area network (PAN) and a wide area network (WAN). can In addition, the network may be the known World Wide Web (WWW), or may use a wireless transmission technology used for short-range communication, such as Infrared Data Association (IrDA) or Bluetooth. The techniques described herein may also be used in other networks mentioned above.

Figure 2 is a schematic diagram for explaining an antigenic determinant prior to describing an embodiment of the present disclosure.

Concepts of terms for describing embodiments of the present disclosure will be described with reference to FIG. 2 .

FIG. 2 shows the combined antigen 200 and antibody 203, and the antigen 200 and antibody 203 each include an antigenic determinant 201 and a paratope 202 on their binding surfaces. The antigen 200 includes an antibody 203 or an antigenic determinant 201 that is specifically attached to a T-cell receptor. When it binds to the paratope (202) of (203), immune activity is induced, resulting in a corresponding immune response. At this time, in order for the antibody 203 to recognize the antigen 200 normally, an antigenic determinant 201 having specificity for each antigen 200 capable of properly binding to the paratope 202 of the antibody 203 is required. . For example, when an antigenic determinant 201 of a cancer cell (antigen, 200) matched with a paratope 202 of an antibody 203 is injected into a human body for a cancer patient, the cancer cell (antigen, 200) is killed. Apoptosis of cancer cells (antigen, 200) can be induced by activating B-cells or T-cells. However, since each type of cancer has a specific antigen 200, it is necessary to derive each antigenic determinant 201 according to each cancer.

In the present disclosure, it is assumed that there is an amino acid sequence corresponding to the antigenic determinant 201 as a part of the amino acid sequence included in the antigen 200, and a subset of the amino acid sequence included in the remaining antigen 200 excluding the antigenic determinant 201 are defined as non-antigenic determinants. For example, assuming that there is 'GGTVGA', which is an amino acid sequence of any antigen 200, and 'GGT' is the antigenic determinant 201, some amino acid sequences corresponding to 'VGA' and 'GA' can be understood as a non-antigenic determinant. At this time, the processor 110 learns the antigenic determinant 201 as correct answer data and the non-antigen determinant as incorrect answer data as learning data of the neural network model for determining the antigenic determinant 201, and thus the antigenic determinant 201 ) data, non-antigen determinants with an overwhelmingly large number can be used for neural network model learning.

3 is a schematic diagram illustrating a network function according to an embodiment of the present disclosure.

Throughout this specification, 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.

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.

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. In other words, it can identify the latent structure of a photo, text, video, sound, or music (e.g., what objects are in the photo, what the content and emotion of the text are, what the content and emotion of the audio are, etc.). . Deep neural networks include convolutional neural networks (CNNs), recurrent neural networks (RNNs), auto encoders, generative adversarial networks (GANs), and restricted boltzmann machines (RBMs). machine), a deep belief network (DBN), a Q network, a U network, a Siamese network, a Generative Adversarial Network (GAN), a Transformer, and the like. The description of the deep neural network described above is only an example, and the present disclosure is not limited thereto.

In one embodiment of the present disclosure, the network function may include an autoencoder. An autoencoder may be a type of artificial neural network for outputting output data similar to input data. An auto-encoder may include at least one hidden layer, and an odd number of hidden layers may be disposed between input and output layers. The number of nodes of each layer may be reduced from the number of nodes of the input layer to an intermediate layer called the bottleneck layer (encoding), and then expanded symmetrically with the reduction from the bottleneck layer to the output layer (symmetrical to the input layer). Autoencoders can perform non-linear dimensionality reduction. The number of input layers and output layers may correspond to dimensions after preprocessing of input data. In the auto-encoder structure, the number of hidden layer nodes included in the encoder may decrease as the distance from the input layer increases. If the number of nodes in the bottleneck layer (the layer with the fewest nodes located between the encoder and decoder) is too small, a sufficient amount of information may not be conveyed, so more than a certain number (e.g., more than half of the input layer, etc.) ) may be maintained.

The neural network may be trained using at least one of supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning. 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.

A neural network can be trained in a way that minimizes output errors. In learning 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 teacher learning, the learning data in which the correct answer is labeled is used for each learning data (ie, the labeled learning data), and in the case of comparative teacher learning, the correct answer may not be labeled in each learning data. That is, for example, learning data in the case of teacher learning about data classification may be data in which each learning data is labeled with a category. Labeled training data is input to the neural network, and an error can be calculated by comparing the output (category) of the neural network and the label of the training data. As another example, in the case of comparative history 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). 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 on 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. To prevent overfitting, methods such as increasing the training data, regularization, inactivating some nodes in the network during the learning process, and using a batch normalization layer should be applied. can

According to an embodiment of the present disclosure, a computer readable medium storing a data structure is disclosed.

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, computational model, neural network, network function, and neural network 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 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 acquired from the neural network, activation function associated with each node or layer of the neural network, and A loss function for learning may be included. 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 the neural network learning process and/or input data input to the neural network after learning has been completed. 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. The computing device may transmit and receive data through a network by serializing the data structure. 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, Trie, m-way search tree, 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.

In addition, a neural network is a type of transfer learning method, and may perform pre-learning based on a specific data set, and perform additional learning based on a data set that is partly similar to the specific data or completely new. In this case, the pre-learning may mean that learning is performed for all layers, but the additional learning may mean that re-learning is performed for the last layer or some layers. The transfer learning method is effective when the number of learning data is small, and has the advantage of higher accuracy than learning with a small amount of data.

In addition, as a type of additional transfer learning method of neural networks, a neural network model of an unsupervised learning method such as an auto-encoder model is used as a pre-learning model, and after pre-learning, weights of some layers are extracted, so that different neural network models are formed. Branches can be additionally trained in some layers. In this case, the different neural networks may include not only an unsupervised learning type neural network but also a supervised learning type neural network. Transfer learning using the aforementioned pre-learning model has the advantage of being able to utilize large-scale data that makes it difficult to manually determine the correct answer.

The autoencoder model may generate feature values through dimensionality reduction. In addition, in the process of extracting feature values, a non-linear relationship between each dimension of the input data may be considered. In addition, the auto-encoder model compresses data into a space with a dimension smaller than that of the original input data, restores the original data, and outputs the restored data. In the process, features of the learning data are extracted and displayed in the latent space. In this case, the expression type of the data in the latent space is referred to as a latent variable, and the auto-encoder model can be learned through a process of minimizing the difference between input data and output data. In this case, the difference between the input data and the output data may be an error value. That is, it can be seen that the restoration error value is affected by the data set for learning and the type of input data. In addition, it can be seen that the restoration error value is affected by the number of times of learning, and is influenced by the shape of an encoder performing compression and a decoder performing restoration.

4 is a flowchart illustrating a method for a processor to derive an antigenic determinant candidate based on an amino acid sequence of an antigen, according to an embodiment of the present disclosure.

Referring to FIG. 4, an embodiment of a method for deriving an antigenic determinant candidate based on an amino acid sequence of an antigen is disclosed.

Referring to step S400, the processor 110 of the computer device 100 according to an embodiment of the present disclosure may generate a plurality of amino acid sub-sequences based on the amino acid sequence of the antigen. Specifically, generating the plurality of amino acid sub-sequences by the processor 110 extracts a plurality of amino acid sub-sequences satisfying an amino acid sub-sequence condition based on the amino acid sequence of the antigen, and -Sequence condition may be a condition including N or more and M or less consecutive amino acids. In this case, the amino acid sub-sequence means an amino acid sequence extracted from the amino acid sequence of the antigen, and may be a subset of the amino acid sequence of the antigen. In addition, the continuous amino acid sequence may refer to an amino acid sequence having a linear structure among linear or non-linear structures, which is one of the criteria for classifying amino acid sequences. For example, a plurality of amino acid sub-sequences based on the amino acid sequence of an antigen, when the amino acid sequence of the antigen is [G, G, T, V, G, G, A], the corresponding amino acid sub-sequence is [ G, G, T, V, G, G], [G, T, V, G, G] and [G, G, T]. At this time, the amino acid sub-sequence does not include completely identical sequences (eg, [G, G, T, V], [G, G, T, V]), but partially overlaps amino acid sequences (eg, [G, G, T, V], [G, G, T, V, G]) may be included. Thereafter, the partially overlapping amino acid sequences may be removed by a redundancy removal module according to the degree of overlap.

Subsequently, referring to step S401, the processor 110 may generate feature values for the plurality of amino acid sub-sequences. In this case, when deriving the at least one antigenic determinant candidate, the processor 110 may determine a plurality of probability values based on feature values for the plurality of amino acid sub-sequences. At this time, the probability values determined based on the feature values for the amino acid sub-sequence are output based on a neural network model including a transformer, a recurrent neural network (RNN), a convolution neural network (CNN), and the like, It may be learned to receive an amino acid sub-sequence and calculate a probability and a feature value that the amino acid sub-sequence is an antigenic determinant of a corresponding antigen. At this time, the antigenic determinant probability and feature value calculated from the amino acid sub-sequence may be used as criteria for classifying as an antigenic determinant candidate.

Subsequently, referring to step S402, the processor 110 may derive at least one antigenic determinant candidate based on probabilities and feature values of antigenic determinants for the plurality of amino acid sub-sequences. In addition, the processor 110 may remove amino acid sub-sequences corresponding to probability values less than or equal to a threshold value among the plurality of probability values. For example, the processor 110 may remove an amino acid sub-sequence classified as less than a predetermined probability by a classifier among the plurality of amino acid sub-sequences from being considered in the future. Specifically, when the probability threshold is '0.8', among the amino acid sub-sequences in which the probabilities of each amino acid sub-sequence are '0.78', '0.9' and '0.65', the amino acid sub-sequence corresponding to the probability '0.9'. Amino acid sub-sequences other than the sequence can be removed from further consideration. At this time, the processor 110 may select remaining amino acid sub-sequences other than the removed amino acid sub-sequence as antigenic determinant candidates. Additionally, the processor 110 identifies antigenic determinant candidates that overlap a predetermined ratio or more among the antigenic determinant candidates classified through the above-mentioned series of processes as a target group for deduplication, and selects the antigenic determinant candidates belonging to the target group for deduplication. Integrating as a representative antigenic determinant candidate of , it is possible to output a final antigenic determinant candidate that has undergone a series of processes. For example, [G, T, V, G, V], [G, T, V, G, T], [G, T, V, G, A], and the probabilities of the antigenic determinant candidates being '0.7', '0.65', and '0.9', respectively, the processor 110 selects [G, T, V, G, A] with the highest probability. Similar antigenic determinant candidates except for can be removed.

5 is a schematic diagram illustrating a method for a processor to generate an amino acid sub-sequence based on an amino acid sequence of an antigen, according to an embodiment of the present disclosure.

It has been described above that a plurality of amino acid sub-sequences can be generated based on the amino acid sequence of the antigen with reference to S400 of FIG. 4 . In this regard, referring to FIG. 5 , one embodiment of a method for a processor to generate an amino acid sub-sequence based on an amino acid sequence of an antigen is disclosed.

In the generating of the plurality of amino acid sub-sequences (S400), based on the amino acid sequence 500 of the antigen, a plurality of amino acid sub-sequences 510 satisfying the amino acid sub-sequence 510 condition are extracted. Including the step of doing, the amino acid sub-sequence 510 condition may be a condition that includes more than N and less than M contiguous amino acids.

Specifically, the amino acid sequence 500 of the antigen includes L amino acids, and based on the amino acid sequence 500 of the antigen, a plurality of amino acid sub-sequences satisfying the amino acid sub-sequence 510 condition are extracted. can do. At this time, the amino acids from the first amino acid (eg, the amino acid whose starting index is 0 in FIG. 5) to the (L-M+1)th amino acid (eg, the amino acid whose starting index is L-M in FIG. 5) of the amino acid sequence of the antigen It can be determined as the starting points of extraction sequentially (For reference, the reason why the last starting point determined for extraction is the L-M + 1st amino acid is that when setting the L-M + 1st and subsequent amino acids as the starting point, This is because it is impossible to extract consecutive M amino acids based on the set starting point). In addition, the operation of extracting N to M consecutive amino acids for each of the sequentially determined (L-M + 1) starting points is performed (M-N + 1) times, (L-M + 1) (M-N+1) sub-sequences can be extracted.

Taking a specific carcinoma as an antigen, for example, the processor 110 selects an amino acid present at the first position of the antigen as a starting point, based on an antigen having an amino acid sequence length of 1000 for a specific carcinoma, and subcategories having a length of 20 to 30 -Sequences can be extracted. At this time, the amino acid of the amino acid sequence present in the first position is selected as a starting point, and sub-sequences having a length of 20 to 30 may be extracted while moving one amino acid in the direction of the 1000th amino acid. In addition, the processor 110 may repeat the above series of processes of extracting the amino acid sub-sequence until an amino acid sub-sequence having a length of 20 to 30 cannot be generated. Consequently, processor 110 may generate (1000-30+1)*(30-20+1)=10,681 amino acid sub-sequences from one antigen.

6 is a schematic diagram illustrating a method for a processor to generate mid-sequences to generate amino acid sub-sequences based on an amino acid sequence of an antigen, according to an embodiment of the present disclosure. 7 is a flowchart illustrating a method of generating an amino acid sub-sequence based on an intermediate-sequence, according to an embodiment of the present disclosure.

Previously, it has been described that a plurality of amino acid sub-sequences can be generated based on the amino acid sequence of the antigen with reference to S400 of FIG. 4 . In this regard, referring to FIGS. 6-7 , one embodiment of a method for processor 110 to generate mid-sequences to generate amino acid sub-sequences based on an amino acid sequence of an antigen is disclosed. The amino acid sequence 600 of the antigen may include L amino acids. Also, the processor 110 may extract a plurality of different amino acid sub-sequences that satisfy an amino acid sub-sequence condition based on the amino acid sequence 600 of the antigen. At this time, the processor 110 may determine K first starting points at intervals of a predetermined number of amino acids in the amino acid sequence 600 of the antigen. For example, as shown in FIG. 6 , the processor 110 may determine L//(2(M-N)) first starting points at intervals of 2(M-N). In addition, the processor 110, 3 (M-N), 4 (M-N), ... L//(3(M-N)), L//(4(M-N)), . . . at intervals such as P(M-N). L//(P(M-N)) number of first starting points may be determined. (At this time, the formula 'a//b' indicates the quotient excluding the remainder when a is divided by b. For example, '5// 2' is 2.) For reference, when the interval between the first starting points is configured as a multiple of (M-N) (ie, when the interval is configured as a parameter dependent on M and N), the processor 110 performs the operation process Since the number of independent parameters considered in can be relatively reduced, computation efficiency can be increased, and in the process of controlling the important parameters M and N, the interval between the first starting points can also be controlled in conjunction with each other, so that the control process Phase efficiency can also be increased. Also, the processor 110 may extract K mid-sequences 700 including J consecutive amino acids for each of the K first starting points. For example, the processor 110 may extract K mid-sequences 700 including M+(M−N)=2M−N consecutive aminos for each of the K first starting points. On the other hand, when the number of amino acids included in each mid-sequence is determined based on "a relational expression utilizing M and N", as discussed above, computational efficiency and control efficiency can be increased. Also, the processor 110 may extract the plurality of amino acid sub-sequences based on the K mid-sequences 700 . Specifically, for each of the K mid-sequences 700, the processor 110 sequentially provides amino acids from the first amino acid to the (J-M+1)th amino acid of each mid-sequence 700. 2 starting points are determined, and an operation of extracting N to M consecutive amino acids for each of the sequentially determined (J - M + 1) second starting points is performed (M - N + 1) times (M-N+1)(M-N+1) sub-sequences can be extracted. (For reference, the reason why the last starting point determined for extraction is the J-M+1st amino acid is that when the amino acid after J-M+1 is set as the second starting point, based on the set second starting point, M This is because it is impossible to extract two amino acids.) As a result, the processor 110 calculates K(M-N+1)(M-N+1) sub-sequences for the K mid-sequences 700. -Sequences can be extracted.

For example, the processor 110 converts 20 (K = 20) sequences at intervals of 50 amino acids (preset interval = 50) from the amino acid sequence 600 of an antigen including 1000 (L = 1000) amino acids. First starting points can be determined. In addition, the processor 110 may extract 20 mid-sequences 610 and 700 including 40 (J=40) consecutive amino acids for each of the first starting points. Then, the processor 110 may extract the plurality of amino acid sub-sequences based on the mid-sequences 700 . Specifically, for each of the 20 mid-sequences 700, the processor 110 selects the 11th (J-M+1=40-30+1=11) from the first amino acid of each mid-sequence 700. ) Amino acids up to the amino acid are sequentially determined as second starting points, and 20 (N = 20) to 30 (M = 30) consecutive amino acids for each of the sequentially determined 11 second starting points 121 sub-sequences can be extracted by performing the extraction operation 11 times (M-N+1=30-20+1=11). Also, the processor 110 may extract 2420 sub-sequences from the 20 mid-sequences 700 .

According to one embodiment of the present disclosure, all sub-sequences are based on intermediate-sequences (serving as an intermediate medium of extraction) and a plurality of starting points (appropriately harmonizing the hopping operation and the sequential extraction operation). Consumption of computational resources and time resources, which may occur when searching for them individually, is prevented, and at the same time, sufficient searching for determining antigenic determinant candidates can be performed.

8 is a flowchart illustrating a method for a processor to generate antigenic determinant candidates based on feature values for amino acid sub-sequences, according to an embodiment of the present disclosure.

Referring to FIG. 8, an embodiment of a method for generating antigenic determinant candidates based on feature values for amino acid sub-sequences of antigens is disclosed.

Referring to FIG. 8, the method for the processor 110 to derive at least one antigenic determinant candidate based on feature values for the plurality of amino acid sub-sequences, described above with reference to step S402 of FIG. explained in detail. Referring to step S800, the processor 110 may determine a plurality of probability values based on feature values for the plurality of amino acid sub-sequences in order to derive the determinant candidate. Also, referring to step S802, the processor 110 may exclude amino acid sub-sequences corresponding to probability values less than or equal to a threshold value among the plurality of probability values. Subsequently, referring to step S802, when the processor 110 derives the at least one antigenic determinant candidate, amino acid sub-sequences corresponding to probability values exceeding the threshold may be selected as antigenic determinant candidates. Also, referring to step S803, the processor 110 may identify antigenic determinant candidates overlapping at least a predetermined ratio among the selected antigenic determinant candidates as a group to be removed. Finally, referring to step S804, the processor 110 may combine antigenic determinant candidates belonging to the duplicate removal target group into one representative antigenic determinant candidate. In this case, the one representative antigenic determinant candidate may correspond to an antigenic determinant candidate having the highest determined probability value among antigenic determinant candidates belonging to the duplicate removal target group.

On the other hand, according to an embodiment of the present disclosure, representative antigenic determinant candidates may be determined based on the “intermediate-sequences” looked at above, and a final antigenic determinant candidate may be determined based on comparison between them. For example, according to one embodiment of the present disclosure, for each of the K mid-sequences, one sub-sequence predicted to have the highest probability value among sub-sequences included in each of the mid-sequences is Representative antigenic determinant candidates for each intermediate-sequence may be determined, and through this process, K representative epitope-determining candidates for K intermediate-sequences may be determined. The determined K representative epitope determination candidates may be compared with each other based on various criteria such as a probability value, and a final antigenic determinant candidate may be determined based on the comparison. According to one embodiment of the present disclosure, since analysis can be performed by integrating sub-sequences included in a specific intermediate-sequence, which are likely to exhibit similar characteristics, into a single representative sub-sequence, computational and time resources are reduced. can be used more efficiently.

9 is a schematic diagram illustrating a method for a processor to derive an antigenic determinant candidate based on an amino acid sequence of an antigen, according to an embodiment of the present disclosure.

Referring to FIG. 9 , an embodiment of a method for a processor to derive an antigenic determinant candidate based on an amino acid sequence of an antigen is disclosed.

Processor 110 may use feature extractor 901 to generate feature values 902 based on the antigen's amino acid sub-sequence. In this case, the feature extractor 901 may include a recurrent neural network (RNN), a convolutional neural network (CNN), or a transformer-based neural network model including an input layer, an output layer, and a plurality of hidden layers.

Also, the processor 110 may derive at least one antigenic determinant candidate 904 using the classifier 903 based on the feature value 902 . The classifier 903 may perform binary classification to classify whether the antigenic determinant candidate 904 or not the antigenic determinant candidate 904 is based on the feature value 902 . For example, the classifier 903 returns a value less than '0.5' as '0' (false) based on '0.5' for the feature value 902 received based on a sigmoid activation function, '0.5' or more may be returned as '1' (true). At this time, the activation function included in the classifier 903 may be learned using a threshold value as a learnable weight according to the input feature value 902 and whether or not it has been learned. In this case, the classifier 903 may include an additional neural network model or machine learning model as well as an activation function.

Further, the processor 110 may generate a final antigenic determinant candidate 906 filtered using the redundancy removal module based on the at least one antigenic determinant candidate 904 . Specifically, the processor 110 selects antigenic determinant candidates 904 based on the redundancy removal module, and among the selected antigenic determinant candidates 904, the antigenic determinant candidates 904 that overlap a predetermined ratio or more are subject to redundancy removal. group can be identified. In addition, the processor 110 may combine the antigenic determinant candidates 904 belonging to the duplicate removal target group into one final antigenic determinant candidate 906 . At this time, the final antigenic determinant candidate 906 removes the remaining antigenic determinant candidates 904 except for the antigenic determinant candidates 904 with the highest probability among the antigenic determinant candidates 904 belonging to the duplicate removal target group, and integrates them into the final antigenic determinant candidate 906. can include

10 is a schematic diagram illustrating a method for a processor to learn a feature extractor, according to an embodiment of the present disclosure.

Referring to FIG. 10 , an embodiment of a method for a processor to learn a feature extractor using a pre-learning model is disclosed.

The processor 110 may initialize weights of the pretrained model 1001 based on the protein database 1000 . At this time, the pre-learning model 1001 can efficiently learn vast amounts of data by learning the protein database 1000 in an unsupervised learning method. In this case, the pre-learning model 1001 may use an auto-encoder method or a masked language model (MLM) neural network model that masks part of data input to the model in order to perform unsupervised learning. The auto-encoder model may include an encoding process and a decoding process. At this time, in the encoding process, only core feature information of the input data may be learned through the hidden layer and the rest may be lost. Subsequently, in the decoding process, the output value of the hidden layer is restored, and output data similar to the input data, although not identical to the input data, is output. At this time, an error value is output by calculating the difference between the input data and the output data, and learning can be performed by back-propagation based on the error value. In this process, the autoencoder does not require the correct answer data of the input data separately, so it is suitable for learning based on limited data.

The feature extractor 1012 may be pre-trained based on weights extracted from some layers (eg, output layers) of the pre-learning model. In addition, the feature extractor 1012 and the classifier 1014 are learned based on learning data including the antigenic determinant 1010 and the non-antigen determinant 1011 for an antigen, and the learning data has a uniform length. It may include an antigenic determinant and a non-antigenic determinant. (In the present disclosure, a subset of amino acid sequences other than the antigenic determinant 1010 within the amino acid sequence for a specific antigen is referred to as a non-antigenic determinant.) In addition, the length of the antigenic determinant 1010 and the non-antigenic determinant 1011 Unifying may include padding based on the maximum length of the antigenic determinant 1010 and the non-antigen determinant 1011. For example, when the length of the one containing the most amino acids among the antigenic determinant 1010 and the non-antigenic determinant 1011 is 'M', the antigenic determinant 1010 and the non-antigenic determinant 1011 less than the length of M It may include filling in garbage data such as '0' to converge to the length of 'M'.

The classifier 1014 may include one of extreme gradient boosting (XGB), support vector machines (SVM), random forest, or neural network models. In this case, the classifier may be trained to output a value of 1 to 0 by comparing the feature value 1013 output from the feature extractor 1012 with a threshold value. At this time, the threshold value may be a weight (parameter) that can be learned.

11 is a simplified and general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

Although the present disclosure has been described above as being generally embodied by a computing device, those skilled in the art will understand that the present disclosure may be combined with computer executable instructions and/or other program modules that may be executed on one or more computers and/or with hardware. It will be appreciated that it can be implemented as a combination of software.

Generally, program modules include routines, programs, components, data structures, etc. that perform particular tasks or implement particular abstract data types. In addition, it will be appreciated by those skilled in the art that the methods of the present disclosure may be used in single-processor or multiprocessor computer systems, minicomputers, mainframe computers as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, and the like. It will be appreciated that other computer system configurations may be implemented, including (each of which may be operative in connection with one or more associated devices).

The described embodiments of the present disclosure may be practiced in a distributed computing environment 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.

Computers typically include 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 1100 implementing various aspects of the present disclosure is shown including a computer 1102, which includes a processing unit 1104, a system memory 1106, and a system bus 1108. do. System bus 1108 couples system components, including but not limited to system memory 1106 , to processing unit 1104 . Processing unit 1104 may be any of a variety of commercially available processors. Dual processor and other multiprocessor architectures may also be used as the processing unit 1104.

System bus 1108 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 1106 includes read only memory (ROM) 1110 and random access memory (RAM) 1112 . A basic input/output system (BIOS) is stored in non-volatile memory 1110, such as ROM, EPROM, or EEPROM, and is a basic set of information that helps transfer information between components within computer 1102, such as during startup. contains routines. RAM 1112 may include high-speed RAM, such as static RAM for caching data.

Computer 1102 includes an internal hard disk drive (HDD) 1114 (e.g., EIDE, SATA), which internal hard disk drive 1114 may be configured for external use in a suitable chassis (not shown). , a magnetic floppy disk drive (FDD) 1116 (e.g., for reading from or writing to removable diskette 1118), and an optical disk drive 1120 (e.g., a CD-ROM disk ( 1122) or for reading from or writing to other high-capacity optical media such as DVD). The hard disk drive 1114, magnetic disk drive 1116, and optical disk drive 1120 are connected to the system bus 1108 by a hard disk drive interface 1124, magnetic disk drive interface 1126, and optical drive interface 1128, respectively. ) can be connected to The interface 1124 for external drive implementation includes at least one or both of USB (Universal Serial Bus) 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 1102, drives and media correspond to storing any data in a suitable digital format. Although the description of computer readable 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, and cartridges. It will be appreciated that other tangible computer readable media such as , , and the like may also be used in the exemplary operating environment and that any such media may include computer executable instructions for performing the methods of the present disclosure. .

A number of program modules may be stored on the drive and RAM 1112, including an operating system 1130, one or more application programs 1132, other program modules 1134, and program data 1136. All or portions of the operating system, applications, modules and/or data may be cached in RAM 1112. It will be appreciated that the present disclosure 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 1102 through one or more wired/wireless input devices, such as a keyboard 1138 and a pointing device such as a mouse 1140. 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 1104 through an input device interface 1142 that is connected to the system bus 1108, 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 1144 or other type of display device is also connected to the system bus 1108 through an interface such as a video adapter 1146. In addition to the monitor 1144, computers typically include other peripheral output devices (not shown) such as speakers, printers, and the like.

Computer 1102 may operate in a networked environment using logical connections to one or more remote computers, such as remote computer(s) 1148 via wired and/or wireless communications. Remote computer(s) 1148 may be a workstation, computing device computer, router, personal computer, handheld computer, microprocessor-based entertainment device, peer device, or other common network node, and generally includes It includes many or all of the components described for, but for simplicity, only memory storage device 1150 is shown. The logical connections shown include wired/wireless connections to a local area network (LAN) 1152 and/or a larger network, such as a wide area network (WAN) 1154 . 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 1102 connects to local network 1152 through wired and/or wireless communication network interfaces or adapters 1156. Adapter 1156 may facilitate wired or wireless communications to LAN 1152 , which includes a wireless access point installed therein to communicate with wireless adapter 1156 . When used in a WAN networking environment, computer 1102 may include a modem 1158, be connected to a communicating computing device on WAN 1154, or establish communications over WAN 1154, such as over the Internet. have other means. A modem 1158, which may be internal or external and a wired or wireless device, is connected to the system bus 1108 through a serial port interface 1142. In a networked environment, program modules described for computer 1102, or portions thereof, may be stored on remote memory/storage device 1150. 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 1102 is any wireless device or entity that is deployed and operating in wireless communication, eg, printers, scanners, desktop and/or portable computers, portable data assistants (PDAs), communication satellites, wireless detectable tags associated with 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.

Wi-Fi (Wireless Fidelity) makes it possible to connect to the Internet without wires. Wi-Fi is a wireless technology, such as a cell phone, that allows such devices, eg, computers, to transmit and receive data both indoors and outdoors, i.e. anywhere within coverage of a base station. Wi-Fi networks use a radio technology called IEEE 802.11 (a, b, g, etc.) to provide secure, reliable, and high-speed wireless connections. Wi-Fi can be used to connect computers to each other, to the Internet, and to wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in the unlicensed 2.4 and 5 GHz radio bands, for example, at 11 Mbps (802.11a) or 54 Mbps (802.11b) data rates, or in products that include both bands (dual band) .

Those skilled in the art will understand that information and signals may be represented using any of a variety of different technologies and techniques. For example, data, instructions, instructions, information, signals, bits, symbols and chips that may be referenced in the above description are voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields s or particles, or any combination thereof.

Those skilled in the art will understand that the various illustrative logical blocks, modules, processors, means, circuits, and algorithm steps described in connection with the embodiments disclosed herein are electronic hardware, (for convenience) , may be implemented by various forms of program or design code (referred to herein as software) or a combination of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the particular application and the design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

Various embodiments presented herein may be implemented as a method, apparatus, or article of manufacture using standard programming and/or engineering techniques. The term article of manufacture includes a computer program, carrier, or media accessible from any computer-readable storage device. For example, computer-readable storage media include magnetic storage devices (eg, hard disks, floppy disks, magnetic strips, etc.), optical disks (eg, CDs, DVDs, etc.), smart cards, and flash memory devices (eg, EEPROM, cards, sticks, key drives, etc.), but are not limited thereto. Additionally, various storage media presented herein include one or more devices and/or other machine-readable media for storing information.

It is to be understood that the specific order or hierarchy of steps in the processes presented is an example of example 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 this disclosure. The accompanying method claims present elements of the various steps in a sample order, but are not meant to be limited to the specific order or hierarchy presented.

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

Claims (14)

A method for deriving an epitope candidate, performed by a computing device including at least one processor, comprising:
generating a plurality of amino acid sub-sequences based on the amino acid sequence of the antigen;
generating feature values for the plurality of amino acid sub-sequences; and
deriving at least one antigenic determinant candidate based on feature values for the plurality of amino acid sub-sequences;
including,
method.
According to claim 1,
Generating the plurality of amino acid sub-sequences comprises:
Based on the amino acid sequence of the antigen, extracting a plurality of amino acid sub-sequences that satisfy an amino acid sub-sequence condition.
Including,
The amino acid sub-sequence condition is a condition comprising N or more and M or less consecutive amino acids,
method.

According to claim 2,
The amino acid sequence of the antigen comprises L amino acids,
Based on the amino acid sequence of the antigen, extracting a plurality of amino acid sub-sequences that satisfy the amino acid sub-sequence condition:
sequentially determining amino acids from the first amino acid to the (L-M+1)th amino acid of the amino acid sequence of the antigen as starting points for extraction; and
For each of the sequentially determined (L-M+1) starting points, an operation of extracting N to M consecutive amino acids is performed, and (L-M+1)(M-N+1) sub- extracting sequences;
including,
method.
According to claim 2,
The amino acid sequence of the antigen comprises L amino acids,
Based on the amino acid sequence of the antigen, extracting a plurality of different amino acid sub-sequences that satisfy the amino acid sub-sequence condition:
determining K first starting points at intervals of a predetermined number of amino acids in the amino acid sequence of the antigen;
For each of the K first starting points, extracting a mid-sequence comprising J consecutive amino acids; and
extracting the plurality of amino acid sub-sequences based on the extracted K mid-sequences;
including,
method.
According to claim 4,
Extracting the plurality of amino acid sub-sequences based on the mid-sequences comprises:
For each of the K mid-sequences:
Amino acids from the first amino acid to the (J-M+1)th amino acid of each mid-sequence are sequentially determined as second starting points, and
By performing an operation of extracting N to M consecutive amino acids for each of the sequentially determined (J−M+1) second starting points, (J−M+1)(M−N+1) extracting sub-sequences; and
extracting K(J-M+1)(M-N+1) sub-sequences for the K mid-sequences;
including,
method.
According to claim 4,
Deriving the at least one antigenic determinant candidate,
For each of the K mid-sequences, determining one of the sub-sequences included in each mid-sequence as a representative antigenic determinant candidate of each mid-sequence; and
comparing the determined K representative antigenic determinant candidates;
including,
method.
According to claim 1,
Deriving the at least one antigenic determinant candidate,
determining a plurality of probability values based on feature values for the plurality of amino acid sub-sequences; and
Excluding amino acid sub-sequences corresponding to probability values below a threshold value among the plurality of probability values;
including,
method.
According to claim 7,
Deriving the at least one antigenic determinant candidate,
selecting amino acid sub-sequences corresponding to probability values exceeding the threshold as antigenic determinant candidates;
identifying antigenic determinant candidates overlapping at least a predetermined ratio among the selected antigenic determinant candidates as a group to be eliminated; and
integrating antigenic determinant candidates belonging to the redundancy removal target group into one representative antigenic determinant candidate;
Including more,
The one representative antigenic determinant candidate corresponds to an antigenic determinant candidate having the highest determined probability value among antigenic determinant candidates belonging to the duplicate removal target group,
method.
According to claim 1,
The step of generating the feature values is,
extracting feature values for the plurality of amino acid sub-sequences based on a feature extractor;
Including,
The feature extractor,
Including a recurrent neural network (RNN), a convolutional neural network (CNN), or a transformer-based neural network model,
The feature extractor is pre-trained from a Masked Language model (MLM) or an auto encoder model learned based on a protein database.
method.
According to claim 9,
Deriving the at least one antigenic determinant candidate,
deriving the at least one antigenic determinant candidate based on feature values for the plurality of amino acid sub-sequences and a classifier;
Including,
The classifier,
including one of Extreme Gradient Boosting (XGB), Support Vector Machines (SVM), Random Forest, or Neural Network models;
method.
According to claim 10,
The feature extractor and the classifier are learned based on learning data including an antigenic determinant and a non-antigen determinant for an antigen,
The learning data is an antigenic determinant and a non-antigenic determinant having a unified length.
including,
method.
According to claim 11,
Unifying the lengths of the antigenic determinant and the non-antigenic determinant,
Padding based on the maximum length of the antigenic determinant and the non-antigenic determinant,
containing
method.
As a device,
a processor comprising one or more cores; and
Memory;
including,
the processor,
generating a plurality of amino acid sub-sequences based on the amino acid sequence of the antigen;
generating feature values for the plurality of amino acid sub-sequences, and
Deriving at least one antigenic determinant candidate based on feature values for the plurality of amino acid sub-sequences
Device.
A computer program stored on a computer readable storage medium causing the computer program to perform operations for deriving an epitope candidate, the operations comprising:
generating a plurality of amino acid sub-sequences based on the amino acid sequence of the antigen;
generating feature values for the plurality of amino acid sub-sequences; and
deriving at least one antigenic determinant candidate based on feature values for the plurality of amino acid sub-sequences;
including,
A computer program stored on a computer readable storage medium.

Images