Apparatus, method, and computer program for determining target gene in consideration of surface exposure level obtained from three-dimensional structure of fusion protein

Abstract

According to one of the solutions for solving the problem described above, it is possible to provide a surface exposure level based on the three-dimensional structure of a fusion protein. In addition, it is possible to output information on a cancer-causing mechanism on the basis of the surface exposure level of the fusion protein.

Description

Device, method and computer program for determining a target gene by considering the degree of surface exposure obtained from the three-dimensional structure of a fusion protein

[0001] The present disclosure relates to a device, method and computer program for determining a target protein by considering the degree of surface exposure obtained from a three-dimensional structure of a fusion protein, characterized in that the fusion protein is simulated to calculate an average degree of surface exposure, and the degree of activation of the fusion protein, cancer causative action information, etc. are determined by using the degree of surface exposure.

[0002] Gene fusion refers to the process of combining genes from two or more different organisms to create a single new gene. Gene fusion is a technique commonly used in genetic manipulation and genetic engineering research. It is utilized in fields such as creating genes with new characteristics or genes that perform specific functions.

[0003] Gene fusions can be utilized as a novel approach to predicting cancer causation. These methods can provide information on the occurrence and type of gene fusion. However, no information has been obtained regarding the structural characteristics of protein units related to gene fusions, or whether they have activating or inhibitory effects on diseases or cancers.

[0004] There is an emerging need to characterize the protein structure of gene fusions to utilize information on gene fusions in new drugs, treatments, and diagnostics.

[0005] The embodiments disclosed herein are intended to provide devices and methods.

[0006] According to embodiments of the present disclosure, a method for obtaining cancer causation information based on surface-related information of a fusion protein is disclosed, including: a step in which a fusion protein analysis device extracts first genetic data from a user's sample cell and converts the first genetic data into first protein sequence data; a step in which the fusion protein analysis device compares data on the first genetic data with genetic data of a normal cell corresponding to the sample cell to select information on a fusion protein generated in the user's genome; a step in which the fusion protein analysis device inputs information on the fusion protein to a structure generation module and outputs data on a three-dimensional structure of the fusion protein; a step in which the fusion protein analysis device inputs data on the three-dimensional structure of the fusion protein to a simulation module and outputs a surface exposure degree of the fusion protein; and a step in which the fusion protein analysis device inputs the surface exposure degree to a surface analysis module and outputs cancer causation information corresponding to the fusion protein.

[0007] The above cancer causal action information may include a probability value for whether it acts on the occurrence of cancer or the possibility of cancer occurrence.

[0008] According to embodiments of the present disclosure, the fusion protein analysis device may further include a step of setting the fusion protein as a target gene when the probability value for the possibility of cancer occurrence among the cancer causal action information exceeds a preset reference value.

[0009] The above surface analysis module can learn from a training data set including identification information of fusion proteins, surface-related information of fusion proteins, and cancer-causing action information of fusion proteins.

[0010] The above structure generation module may be Alphafold2.

[0011] The above simulation module may be MD (Molecular Dynamics).

[0012] According to embodiments of the present disclosure, a device includes a communication unit and a processor, wherein the processor extracts first genetic data from a user's sample cell, converts the first genetic data into first protein sequence data, compares data on the first genetic data with genetic data of a normal cell corresponding to the sample cell to select information on a fusion protein generated in the user's genome, inputs information on the fusion protein into a structure generation module to output data on a three-dimensional structure of the fusion protein, inputs data on the three-dimensional structure of the fusion protein into a simulation module to output a degree of surface exposure of the fusion protein, and inputs the degree of surface exposure into a surface analysis module to output cancer causal action information corresponding to the fusion protein.

[0013] A computer program according to an embodiment of the present invention can be stored in a medium to execute any one of the methods according to an embodiment of the present invention using a computer.

[0014] In addition, other methods for implementing the present invention, other systems, and computer-readable recording media recording a computer program for executing the above methods are further provided.

[0015] Other aspects, features and advantages other than those described above will become apparent from the following drawings, claims and detailed description of the invention.

[0016] Any of the aforementioned problem solving methods can provide a degree of surface exposure based on the three-dimensional structure of the fusion protein.

[0017] Additionally, cancer causal action information can be output based on the degree of surface exposure of the fusion protein.

[0018] FIG. 1 illustrates an analysis network system including a server and a user terminal according to one embodiment of the present disclosure.

[0019] FIG. 2 is a drawing for explaining the detailed configuration of a fusion protein analysis device according to embodiments of the present disclosure.

[0020] Figure 3 is a drawing showing the detailed structure of the characteristic determination unit (120).

[0021] FIG. 4 is a flowchart of a method for obtaining cancer causative action information based on surface-related information of a fusion protein according to embodiments of the present disclosure.

[0022] Figure 5a is an example diagram of data for a fusion protein.

[0023] Figure 5b is an example diagram of a fusion protein in which two fusion genes are combined.

[0024] Figure 5c is an example diagram of domain information of a one-dimensional fusion protein.

[0025] Figure 6a is an exemplary drawing of the three-dimensional structure of a fusion protein.

[0026] FIG. 6b is an exemplary diagram of one-dimensional sequence text data and three-dimensional structure text data generated according to embodiments of the present disclosure.

[0027] FIG. 7A is an exemplary drawing of a fusion protein structure generated according to embodiments of the present disclosure.

[0028] Figure 7b is an example drawing of the three-dimensional structure of a fusion protein generated by the simulation module.

[0029] The configuration and operation of the present invention will be described in detail with reference to embodiments of the present invention illustrated in the attached drawings below.

[0030] The present invention is capable of various modifications and embodiments. Specific embodiments are illustrated in the drawings and described in detail in the detailed description. The effects and features of the present invention, as well as the methods for achieving them, will become clearer with reference to the embodiments described in detail below, along with the drawings. However, the present invention is not limited to the embodiments disclosed below and can be implemented in various forms.

[0031] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings. When describing with reference to the drawings, identical or corresponding components are given the same drawing reference numerals, and redundant descriptions thereof will be omitted.

[0032] Hereinafter, the term “upper” or “upper” may include not only things that are directly above in contact, but also things that are above in a non-contact manner.

[0033] In the following examples, the terms first, second, etc. are not used in a limiting sense, but are used for the purpose of distinguishing one component from another.

[0034] In the examples below, singular expressions include plural expressions unless the context clearly indicates otherwise.

[0035] In the following examples, terms such as “include” or “have” mean that a feature or component described in the specification is present, and do not preclude the possibility that one or more other features or components may be added.

[0036] For convenience of explanation, the sizes of components in the drawings may be exaggerated or reduced. For example, the sizes and thicknesses of each component shown in the drawings are arbitrarily indicated for convenience of explanation, and thus the present invention is not necessarily limited to what is shown.

[0037] Additionally, terms such as “…part”, “…area”, etc. described in this specification may mean a unit that processes at least one function or operation.

[0038] As used herein, gene fusion refers to two separate genes fusing together to function as one, where multiple different genes encode a fusion protein through recombination (insertion, deletion, translocation, inversion, etc.). Gene fusion occurs due to structural abnormalities in chromosomes, and the resulting fusion protein is produced. The effects of gene fusion may vary depending on the location where the fusion occurs.

[0039] FIG. 1 illustrates an analysis network system including a server and a user terminal according to one embodiment of the present disclosure.

[0040] The analysis network system (1) of the present disclosure may include a server (20) and at least one user terminal (11 to 16). The server (20) may provide various online activities through the network. The server (20) may simultaneously provide online activities to at least one user terminal (11 to 16). Here, the online activities may include providing a data analysis service in response to a data analysis request. The data analysis service may output the degree of surface exposure of the fusion protein in response to an analysis request for the fusion protein, but is not limited thereto and may further include a three-dimensional structure of the fusion protein, characteristics of the fusion protein, etc.

[0041] According to one embodiment of the present disclosure, the server (20) may include a single server, a collection of servers, a cloud server, etc., but is not limited to the examples above. The server (20) provides various online activities and may include a database that stores data for the online activities. The server (20) may also include a payment server that generates and processes payment events. As described above, the server (20) may be a fusion protein analysis device.

[0042] According to one embodiment of the present disclosure, a network means a connection established (or formed) using any communication method, and may mean a communication network connected through any communication method that transmits and receives data between terminals or between terminals and servers.

[0043] "All communication methods" may include any communication method, including communication using a specific communication standard, specific frequency band, specific protocol, or specific channel. Examples include Bluetooth, BLE, Wi-Fi, Zigbee, 3G, LTE, and ultrasonic communication, and may encompass short-range communication, long-range communication, wireless communication, and wired communication. Of course, the above examples are not limited to these.

[0044] According to one embodiment of the present disclosure, a short-range communication method may refer to a communication method that allows communication only when a device (terminal or server) performing communication is within a certain range, and may include, for example, Bluetooth, NFC, etc. A long-range communication method may refer to a communication method that allows communication regardless of the distance between the devices performing communication. For example, a long-range communication method may refer to a method that allows communication even when two devices performing communication are at a certain distance or more through a repeater such as an AP, and may include a communication method using a cellular network (3G, LTE) such as SMS or phone. Of course, the present invention is not limited to the above examples. The meaning of receiving a service using a network may include the meaning that communication between a server and a terminal can be performed through any communication method.

[0045] Throughout the specification, at least one user terminal (11 to 16) may include various electronic devices such as a personal computer (11), a tablet (12), a cellular phone (13), a laptop (14), a smart phone (15), a TV (16), as well as personal digital assistants (PDAs), portable multimedia players (PMPs), navigation devices, and MP3 players, but is not limited to the above examples. As described above, at least one user terminal (11 to 16) may be a fusion protein analysis device.

[0046] According to one embodiment of the present disclosure, the server (20) can extract RNA from sample cells of a user infected with a disease and analyze the RNA through NGS (Next generation sequencing). The server (20) can detect data on gene fusion occurring in the user's RNA by comparing the analysis data with data on normal RNA. The data on gene fusion may include at least one of whether gene fusion occurred, the name of the fused gene, and information (identification information, location, structure, etc.) on the gene generated as a result of the fusion. The server (20) can obtain identification information on the fusion protein resulting from the gene fusion. The identification information on the fusion protein may include at least one of the location, structure, and name. The server (20) can measure the three-dimensional structure of the fusion protein based on the identification information on the fusion protein. The three-dimensional structure of the fusion protein can be measured using a structure generation module. The server (20) can generate data simulating the movement of the fusion protein over time based on the three-dimensional structure of the fusion protein. A simulation module can be used to simulate the movement of a fusion protein over time. The server (20) can calculate the surface exposure degree of the fusion protein based on the results of the simulation. The server (20) can learn the correlation between the surface exposure degree of the fusion protein and the user's disease, and output a correlation coefficient value with the user's disease based on the surface exposure information of the fusion protein newly acquired through such learning. The server (20) can use the surface exposure information of the fusion protein to determine a target gene to be used for treatment and generate data on the target gene. The server (20) can determine the target gene by determining whether the surface exposure degree of the fusion protein exceeds a preset reference value. The service exposure degree can refer to the size of the surface area exposed to the outside of the fusion protein.Here, the reference value may be a value determined by a model learned based on the surface exposure degree and functional classification information for the fusion proteins.

[0047] According to one embodiment of the present disclosure, one of at least one user terminal (11 to 16) can extract RNA from a sample cell of a user infected with a disease, analyze the RNA through NGS (Next generation sequencing), and generate analysis data. One of at least one user terminal (11 to 16) can compare the analysis data with data on normal RNA to detect data on a gene fusion occurring in the user's RNA. One of at least one user terminal (11 to 16) can obtain and receive identification information on a fusion protein resulting from the gene fusion. One of at least one user terminal (11 to 16) can measure a three-dimensional structure of the fusion protein based on the identification information on the fusion protein and generate data on the three-dimensional structure. Measuring the three-dimensional structure of the fusion protein can utilize a structure generation module. One of at least one user terminal (11 to 16) can simulate the movement of the fusion protein over time based on the three-dimensional structure of the fusion protein. Simulating the movement of the fusion protein over time can utilize a simulation module. At least one of the user terminals (11 to 16) can calculate the degree of surface exposure of the fusion protein based on the results of the simulation. At least one of the user terminals (11 to 16) can learn a correlation between the degree of surface exposure of the fusion protein and the user's disease, and can output a correlation coefficient value with the user's disease based on the newly acquired surface exposure information of the fusion protein through such learning. At least one of the user terminals (11 to 16) can determine a target gene to be utilized for treatment using the surface exposure information of the fusion protein.At least one user terminal (11 to 16) can determine a target gene by determining whether the surface exposure level of the fusion protein exceeds a preset threshold. Here, the threshold may be a value determined by a model learned based on the surface exposure level and functional classification information for the fusion proteins.

[0048] In addition, according to one embodiment of the present disclosure, the analysis network system (1) can extract RNA from a sample cell of a user infected with a disease and analyze the RNA through NGS (Next generation sequencing). The analysis network system (1) can detect a gene fusion occurring in the user's RNA by comparing the analysis data with data on normal RNA. The analysis network system (1) can obtain identification information on a fusion protein resulting from the gene fusion. The analysis network system (1) can measure a three-dimensional structure of the fusion protein based on the identification information on the fusion protein. Measuring the three-dimensional structure of the fusion protein can utilize a structure generation module. The analysis network system (1) can simulate the movement of the fusion protein over time based on the three-dimensional structure of the fusion protein. Simulating the movement of the fusion protein over time can utilize a simulation module. The analysis network system (1) can calculate the degree of surface exposure of the fusion protein based on the simulation result. The analysis network system (1) learns the correlation between the surface exposure degree of the fusion protein and the user's disease, and can output a correlation coefficient value with the user's disease from the surface exposure information of the fusion protein newly acquired through such learning. The analysis network system (1) can determine a target gene to be used for treatment using the surface exposure information of the fusion protein. The analysis network system (1) can determine the target gene by determining whether the surface exposure degree of the fusion protein exceeds a preset reference value. Here, the reference value may be a value determined by a model learned based on the surface exposure degree and functional classification information for the fusion proteins.

[0049] This is explained in more detail below.

[0050] FIG. 2 is a drawing for explaining the detailed configuration of a fusion protein analysis device according to embodiments of the present disclosure.

[0051] As illustrated in FIG. 2, a fusion protein analysis device (100) according to some embodiments may include a processor (110), an input / output unit (130), a memory (140), a communication unit (150), and a characteristic determination unit (200). However, not all of the components illustrated in FIG. 2 are essential components of the fusion protein analysis device (100). The fusion protein analysis device (100) may be implemented with more components than the components illustrated in FIG. 2, or may be implemented with fewer components than the components illustrated in FIG. 2. The fusion protein analysis device (100) may be a user terminal, a server, an analysis service network system, or a separate device.

[0052] According to one embodiment of the present disclosure, the processor (110) typically controls the overall operation of the fusion protein analysis device (100). For example, the processor (110) may control the components included in the fusion protein analysis device (100) by executing a program stored in the fusion protein analysis device (100).

[0053] According to one embodiment of the present disclosure, the processor (110) can extract RNA from a sample cell of a user infected with a disease by executing instructions stored in the characteristic determination unit (200), and analyze the RNA through NGS (Next generation sequencing). The processor (110) can compare the analysis data with data on normal RNA to detect a gene fusion occurring in the user's RNA. The processor (110) can obtain identification information on a fusion protein resulting from the gene fusion. The processor (110) can measure a three-dimensional structure of the fusion protein based on the identification information on the fusion protein. Measuring the three-dimensional structure of the fusion protein can utilize a structure generation module. The processor (110) can simulate the movement of the fusion protein over time based on the three-dimensional structure of the fusion protein and generate simulated data. Simulating the movement of the fusion protein over time can utilize a simulation module. The processor (110) can calculate the degree of surface exposure of the fusion protein based on the results of the simulation. The processor (110) learns the correlation between the surface exposure degree of the fusion protein and the user's disease, and can output a correlation coefficient value with the user's disease from the surface exposure information of the fusion protein newly acquired through such learning. The processor (110) can determine a target gene to be used for treatment using the surface exposure information of the fusion protein. The processor (110) can determine the target gene by determining whether the surface exposure degree of the fusion protein exceeds a preset reference value. Here, the reference value may be a value determined by a model learned based on the surface exposure degree and functional classification information for the fusion proteins.

[0054] The processor (110) is a component for controlling the overall operation of the fusion protein analysis device (100). Specifically, the processor (110) controls the overall operation of the fusion protein analysis device (100) using various programs stored in the storage medium (150) of the fusion protein analysis device (100). For example, the processor (110) may include a CPU, RAM, ROM, and a system bus. Here, the ROM is a component in which a command set for system booting is stored, and the CPU copies the stored operating system of the fusion protein analysis device (100) to RAM according to the command stored in the ROM and executes the O / S to boot the system. When the system booting is complete, the CPU can copy various stored applications to RAM and execute them to perform various operations. Although the fusion protein analysis device (100) has been described as including only one CPU, it may be implemented with multiple CPUs (or DSPs, SoCs, etc.) during implementation.

[0055] According to one embodiment of the present invention, the processor (110) may be implemented as a digital signal processor (DSP), a microprocessor, or a time controller (TCON) that processes digital signals. However, the present invention is not limited thereto, and may include one or more of a central processing unit (CPU), a micro controller unit (MCU), a micro processing unit (MPU), a controller, an application processor (AP), a communication processor (CP), or an ARM processor, or may be defined by the corresponding terms. In addition, the processor (110) may be implemented as a system on chip (SoC) or large scale integration (LSI) having a built-in processing algorithm, or may be implemented in the form of a field programmable gate array (FPGA).

[0056] According to one embodiment of the present disclosure, the input / output unit (130) can display an interface generated by the memory (140) of the fusion protein analysis device (100). According to one embodiment of the present invention, the input / output unit (130) can display a user interface for input user input. The input / output unit (130) can output stored graphic data, visual data, auditory data, and vibration data under the control of the memory (140).

[0057] The input / output unit (130) may be implemented as a display panel of various forms. For example, the display panel may be implemented as a display technology of various forms, such as a liquid crystal display (LCD), an organic light emitting diode (OLED), an active-matrix organic light-emitting diode (AM-OLED), a liquid crystal on silicon (LCoS), or a digital light processing (DLP). In addition, the input / output unit (130) may be coupled to at least one of the front area, the side area, and the rear area of ​​the display panel in the form of a flexible display.

[0058] The input / output unit (130) may be implemented as a touch screen with a layer structure. The touch screen may have a function of detecting not only a display function but also a touch input location, a touched area, and even a touch input pressure, and may also have a function of detecting not only a real touch but also a proximity touch.

[0059] The input / output unit (130) may include a user interface for inputting various information into the fusion protein analysis device (100).

[0060] According to one embodiment of the present disclosure, the memory (140) can store a program for processing and controlling the processor (110) and / or the characteristic determination unit (200), and can also store data input to or output from the fusion protein analysis device (100). According to one embodiment of the present disclosure, the memory (140) can store information regarding a user account, or information regarding a fusion protein. The memory (140) can store information regarding a normal sample, and information regarding a correlation coefficient between a fusion protein and a disease. The memory (140) can include a database storing the above information.

[0061] According to one embodiment of the present disclosure, the memory (140) may include at least one type of storage medium among a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., SD or XD memory, etc.), a RAM (Random Access Memory), a SRAM (Static Random Access Memory), a ROM (Read-Only Memory), an EEPROM (Electrically Erasable Programmable Read-Only Memory), a PROM (Programmable Read-Only Memory), a magnetic memory, a magnetic disk, and an optical disk. In addition, according to one embodiment of the present disclosure, programs stored in the memory (140) may be classified into a plurality of modules according to their functions.

[0062] According to one embodiment of the present disclosure, the communication unit (150) can communicate with an external device of the processor (110). For example, the communication unit (150) can communicate with an external device, such as a payment server or an authentication server, under the control of the processor (110). In addition, the communication unit (150) can also obtain user information or user input through communication with an external interface.

[0063] Figure 3 is a drawing showing the detailed structure of the characteristic determination unit (120).

[0064] The characteristic determination unit (120) may be in the form of a set of commands implementing a function or a program generated by compiling these commands. The characteristic determination unit (120) may include a sequence conversion unit (121), a three-dimensional structure generation unit (122), a surface degree calculation unit (123), an activation degree calculation unit (124), and a data output unit (125). At least one of the sequence conversion unit (121), the three-dimensional structure generation unit (122), the surface degree calculation unit (123), the activation degree calculation unit (124), and the data output unit (125) may be in the form of a set of commands written in a predetermined code or a program generated by compiling these commands.

[0065] The characteristic determination unit (120) can determine the correlation coefficient between the information on the user's fusion protein obtained by analyzing the sample cells and the user's disease.

[0066] The sequence conversion unit (121) can extract RNA from a sample cell of a user infected with a disease and analyze the RNA sequence through NGS (Next generation sequencing). For example, the sample cell of a user infected with a disease may be tissue, blood, saliva, sweat, etc. The sequence conversion unit (121) can convert the analyzed data into protein sequence data. The sequence conversion unit (121) can compare data on the user's RNA with data on the RNA of normal cells to select information on a fusion gene generated in the user's genome. The sequence conversion unit (121) can generate protein sequence data of the fusion gene. The protein sequence data may include data on a fusion protein in a region where the fusion gene is detected. The data generated by the sequence conversion unit (121) may include one or more fusion genes included in the user's RNA and data on a fusion protein included in each fusion gene. The protein sequence data generated by the sequence conversion unit (121) may be as illustrated in FIG. 5A. It may include information on the fusion gene, structure variation of the fusion gene, prediction confidence, reading frame, fused protein domains, cancer-related fusion, and target of proliferation. The sequence conversion unit (121) may generate an image of the fusion gene through NGS analysis, as illustrated in FIG. 5b. The fused protein domains may be obtained by searching a domain database. The domain database may be Pfam, LiterPro, etc. The domain information of the fusion protein is as illustrated in FIG. 5c.

[0067] The three-dimensional structure generation unit (122) can generate data on a three-dimensional protein structure by inputting protein sequence data into the structure generation module. The input protein sequence data may be for a fusion protein. The structure generation module may be Alphafold2, but is not limited thereto and various structure generation modules may be used. Through the three-dimensional structure generation unit (122), the three-dimensional structure of the fusion protein can be output as shown in Fig. 6a.

[0068] As illustrated in FIG. 6B, one-dimensional sequence text data (A1) and three-dimensional structure text data (A2) can be converted into text format and stored through embodiments of the present disclosure. The one-dimensional sequence text data (A1) is data obtained by performing NGS (Next generation sequencing) on ​​a user's RNA sequence, and may be in FASTA format. The three-dimensional structure data (A2) is data output from a structure generation module converted into text format, and may be in PDB format.

[0069] The surface output unit (123) can input data on the three-dimensional protein structure of the fusion protein into the simulation module to generate data that virtually shapes the fusion protein. The simulation module can simulate the dynamic movement of the fusion protein by considering the interaction between each atom in the fusion protein structure and generate simulated data. The surface output unit (123) can use the virtual model of the fusion protein generated according to the simulation results to produce surface-related information, such as the degree of surface exposure in the fusion protein. Through the simulation process, the surface output unit (123) can select the initial positions of the atoms forming the fusion protein, assign an initial movement velocity to each atom, and calculate the momentum according to the mass and assigned velocity of each atom. The surface output unit (123) can calculate the force applied to each atom according to the force existing between the atoms, and measure the movement and positional change of each atom according to this force. Through the above process, a virtual model of the fusion protein can be generated. The surface output unit (123) can determine the movement of the fusion protein through a virtual model and obtain the surface exposure area of ​​the fusion protein. The surface output unit (123) can calculate the surface exposure degree, surface shape, etc. for the surface exposure area. The surface output unit (123) can output surface-related information including the surface exposure degree, surface shape, etc. at one or more time points. The surface output unit (123) can determine an average value of one or more surface exposure degrees derived from the fusion protein as a representative surface exposure degree using a simulation module. The surface output unit (123) can determine an average value of one or more surface shapes derived from the fusion protein as a representative surface shape.

[0070] Here, surface exposure refers to the sum of the surface areas exposed to each molecule that makes up the protein. Surface exposure can be calculated as the sum of the surface areas exposed to each molecule, taking into account factors such as the radius from the center of each molecule and the distance between molecules. The surface area exposed to the outside of a molecule can be calculated using the formula for calculating the surface area of ​​a sphere.

[0071] The activation degree calculation unit (124) can obtain functional classification information of the fusion protein using identification information about the fusion protein. The functional classification information can include a first fusion gene, a second fusion gene, structure variation, prediction confidence, a reading frame, fused protein domains, cancer-related fusion, a target of proliferation, etc., as illustrated in FIG. 5A. The first fusion gene and the second fusion gene refer to two genes that make up the fusion protein. The activation degree calculation unit (124) can determine functional classification information of the fusion protein using a database such as a gene ontology.

[0072] Functional classification information for a protein may include information about whether the fusion protein is involved in a biological process or pathway, such as the fusion protein's name or ID value. In particular, this may include the extent to which the fusion protein has an oncogenic effect.

[0073] The activation degree calculation unit (124) can find terms related to the fusion protein and obtain functional classification information of the fusion protein based on the terms. The functional classification information of the fusion protein can include information on the fusion gene, structural variation, prediction confidence, reading frame, fused protein domains, cancer-related fusion, target of proliferation, etc.

[0074] The data output unit (125) can calculate the activation degree of the fusion protein based on the surface-related information and functional classification information of the fusion protein. Functional classification information that changes according to the surface exposure degree of the fusion protein can be selected, and the activation value of the fusion protein can be calculated based on the functional classification information that has a proportional or inverse relationship to the surface exposure degree. For example, if the cancer-related fusion increases as the surface exposure degree increases, the activation value of the fusion protein can be calculated by combining the values ​​of the surface exposure degree of the fusion protein and the cancer-related fusion degree. Even if the surface exposure degree increases, if the cancer-related fusion degree is a constant value, the activation value of the fusion protein can be calculated by considering the surface exposure degree.

[0075] The data output unit (125) can calculate the degree of cancer-causing activity of the fusion protein based on surface-related information of the fusion protein. For example, if the cancer-related fusion increases as the degree of surface exposure increases, the fusion protein can be classified as having a degree of cancer-causing activity calculated according to the degree of surface exposure. The value of cancer-related fusion according to the degree of surface exposure can be calculated based on the correlation coefficient between the value of the degree of surface exposure and the value of cancer-related fusion. If the degree of surface exposure exceeds a preset reference value, it is determined that the fusion protein acts as a cancer-causing activity, and the degree of cancer-causing activity can be calculated as 1 (TRUE). The degree of cancer-causing activity can be set as a value proportional to the degree of surface exposure.

[0076] The above processes can be output by the surface analysis module. The data output unit (125) can calculate the correlation coefficient between the surface-related information of the fusion protein and the functional classification information of the fusion protein, and can perform machine learning of the surface analysis module using the surface-related information of the fusion protein and the functional classification information of the fusion protein, the correlation coefficient between the surface-related information and the functional classification information, etc. as a training data set.

[0077] The surface analysis module can be trained using a training data set containing fusion protein identification information (name, ID, etc.), surface-related information, and cancer causal action information. The surface analysis module can be trained using machine learning or deep learning methods. The surface analysis module can be trained using methods such as reinforcement learning or unsupervised learning. The surface analysis module can be trained by inferring correlations between cancer types and fusion proteins.

[0078] For example, if the genomic data of a first user is acquired and the occurrence of a first fusion protein is confirmed in the genomic data, surface-related information of the first fusion protein can be calculated. Based on the surface-related information of the first fusion protein, information such as whether the first user is at risk of developing a cancer or the likelihood of developing a disease such as cancer, the degree of cancer-causing effect, etc. can be calculated and output. At this time, the presence or degree of cancer-causing effect can be calculated only for a specific cancer, that is, for each cancer type.

[0079] According to embodiments of the present disclosure, for gene fusion, surface-related information such as the degree of surface exposure of the fusion protein is obtained using the three-dimensional structure of the fusion protein and a virtual model of the fusion protein, and based on the surface-related information of the fusion protein, whether the fusion protein has an oncogenic effect, the degree of the oncogenic effect, etc. can be calculated. At this time, a surface analysis module trained by a method such as machine learning or deep learning can be used. The surface analysis module can be implemented to take the degree of identification of the fusion protein and the surface-related information as input and output the degree of activation of the fusion protein and information on the oncogenic effect. Through this, it is also possible to determine whether the fusion protein can be used as a target gene based on the oncogenic effect information of the fusion protein.

[0080] According to embodiments of the present disclosure, it is possible to determine whether a fusion protein can be used as a target gene for a specific cancer by using the degree of activation of the fusion protein and information on its cancer-causing action.

[0081] Here, the cancer-causing effect information may be a value determined by cancer type. For example, by analyzing the surface exposure of a fusion protein, cancer-causing effect information for breast cancer and cancer-causing effect information for lung cancer can be derived, respectively. The cancer-causing effect information may include whether the protein contributes to cancer development and a probability value for the likelihood of cancer development. The value for whether the protein contributes to cancer development may be set to either "Yes" or "No," and the probability value for the likelihood of cancer development may be a percentage.

[0082] FIG. 4 is a flowchart of a method for obtaining cancer causative action information based on surface-related information of a fusion protein according to embodiments of the present disclosure.

[0083] In S110, the fusion protein analysis device (100) can extract first genetic data of RNA from a sample cell of a user infected with a disease, and convert the first genetic data into first protein sequence data.

[0084] The fusion protein analysis device (100) can select information on a fusion gene generated in the user's genome by comparing data on the first genetic data with genetic data of normal cells corresponding to the sample cell. The fusion protein analysis device (100) can generate first protein sequence data of the fusion gene.

[0085] In S120, the fusion protein analysis device (100) can generate data on a three-dimensional protein structure by inputting first protein sequence data into a structure generation module. The input first protein sequence data may be for a fusion protein. The structure generation module may be Alphafold2, but is not limited thereto, and various structure generation modules may be used.

[0086] As illustrated in FIG. 6B, one-dimensional sequence text data (A1) and three-dimensional structure text data (A2) can be converted into text format and stored through embodiments of the present disclosure. The one-dimensional sequence text data (A1) is data obtained by performing NGS (Next generation sequencing) on ​​a user's RNA sequence, and may be in FASTA format. The three-dimensional structure data (A2) is data output from a structure generation module converted into text format, and may be in PDB format.

[0087] In S130, the fusion protein analysis device (100) can input data on the three-dimensional protein structure of the fusion protein into the simulation module to virtually model the fusion protein. The simulation module can simulate the dynamic movement of the fusion protein by considering the interaction between each atom in the fusion protein structure and generate simulated data. Through the simulation process, the fusion protein analysis device (100) can select the initial positions of the atoms forming the fusion protein, assign an initial movement velocity to each atom, and calculate the momentum according to the mass and assigned velocity of each atom. The fusion protein analysis device (100) can calculate the force applied to each atom according to the force existing between the atoms, and measure the movement and positional change of each atom according to this force. Through the above process, a virtual model of the fusion protein can be generated. Through the virtual model, the movement of the fusion protein can be known, and the surface exposure area of ​​the fusion protein can be acquired.

[0088] In S140, the fusion protein analysis device (100) can derive surface-related information from the fusion protein using a virtual model of the fusion protein generated based on the simulation results. The surface exposure degree, surface shape, etc. can be derived for the surface exposure area. The fusion protein analysis device (100) can derive the surface exposure degree, surface shape, etc. based on the virtual model.

[0089] The fusion protein analysis device (100) can output surface-related information including surface exposure degree, surface shape, etc. at one or more time points. The fusion protein analysis device (100) can determine an average value of one or more surface exposure degrees derived from the fusion protein as a representative surface exposure degree. The fusion protein analysis device (100) can determine an average value of one or more surface shapes derived from the fusion protein as a representative surface shape.

[0090] In S150, the fusion protein analysis device (100) can calculate the degree of activation of the fusion protein based on surface-related information of the fusion protein.

[0091] The fusion protein analysis device (100) can calculate the degree of cancer-causing action of a fusion protein based on surface-related information of the fusion protein.

[0092] The above information can be output by the surface analysis module. The fusion protein analysis device (100) can calculate a correlation coefficient between the surface-related information of the fusion protein and the functional classification information of the fusion protein, and can perform machine learning of the surface analysis module using the surface-related information of the fusion protein and the functional classification information of the fusion protein, the correlation coefficient between the surface-related information and the functional classification information, etc. as a training data set.

[0093] According to embodiments of the present disclosure, for gene fusion, surface-related information such as the degree of surface exposure of the fusion protein is obtained using the three-dimensional structure of the fusion protein and a virtual model of the fusion protein, and based on the surface-related information of the fusion protein, whether the fusion protein has an oncogenic effect, the degree of the oncogenic effect, etc. can be calculated. At this time, a surface analysis module trained by a method such as machine learning or deep learning can be used. The surface analysis module can be implemented to take the degree of identification of the fusion protein and the surface-related information as input and output the degree of activation of the fusion protein and information on the oncogenic effect. Through this, it is also possible to determine whether the fusion protein can be used as a target gene based on the oncogenic effect information of the fusion protein.

[0094] According to embodiments of the present disclosure, it is possible to determine whether a fusion protein can be used as a target gene for a specific cancer by using the degree of activation of the fusion protein and information on its cancer-causing action.

[0095] Figure 5a is an example diagram of data for a fusion protein.

[0096] This is an exemplary diagram of functional classification information for fusion proteins obtained and utilized in embodiments of the present disclosure. For example, a fusion protein with an index of 172 may be a result of a genetic fusion between the MYH9 gene and the ROS1 gene. Regarding the fusion protein with an index of 172, data such as the type of structural modification being a translocation and the prediction confidence being high can be obtained. For fusion proteins, information such as the reading frame and the domain of the fusion protein can be included in the functional classification information.

[0097] Figure 5b is an example diagram of a fusion protein in which two fusion genes are combined.

[0098] A fusion protein (FP) can be produced by combining a first gene (FG1) and a second gene (FG2).

[0099] Figure 5c is an example diagram of domain information of a one-dimensional fusion protein.

[0100] Figure 6a is an exemplary drawing of the three-dimensional structure of a fusion protein.

[0101] FIG. 6b is an exemplary diagram of one-dimensional sequence text data and three-dimensional structure text data generated according to embodiments of the present disclosure.

[0102] The one-dimensional sequence text data is as A1, and the text data for the three-dimensional structure is as A2.

[0103] FIG. 7A is an exemplary drawing of a fusion protein structure generated according to embodiments of the present disclosure.

[0104] Figure 7b is an example drawing of the three-dimensional structure of a fusion protein generated by the simulation module.

[0105] In addition, although the preferred embodiments of the present invention have been illustrated and described above, the present invention is not limited to the specific embodiments described above, and various modifications can be made by a person having ordinary skill in the art to which the present invention pertains without departing from the gist of the present invention claimed in the claims, and such modifications should not be understood individually from the technical idea or prospect of the present invention.

[0106] Therefore, the spirit of the present invention should not be limited to the embodiments described above, and not only the scope of the patent claims described below, but also all scopes equivalent to or equivalently modified from the scope of the patent claims are considered to fall within the scope of the spirit of the present invention.

Claims

1. A step of the fusion protein analysis device extracting first genetic data from a user's sample cell and converting the first genetic data into first protein sequence data; A step in which the fusion protein analysis device compares data on the first genetic data with genetic data of normal cells corresponding to the sample cells to select information on the fusion protein generated in the user's genome; A step in which the fusion protein analysis device inputs information about the fusion protein into a structure generation module and outputs data on the three-dimensional structure of the fusion protein; A step in which the fusion protein analysis device inputs data on the three-dimensional structure of the fusion protein into a simulation module and outputs the degree of surface exposure of the fusion protein; and A method for obtaining cancer causal action information based on surface-related information of a fusion protein, comprising: a step of the fusion protein analysis device inputting the degree of surface exposure into a surface analysis module and outputting cancer causal action information corresponding to the fusion protein; 2. In paragraph 1, The above cancer causal action information is, A method for obtaining cancer causative action information based on surface-related information of a fusion protein, including whether it acts on cancer development or a probability value for the possibility of cancer development.

3. In paragraph 1, A method for obtaining cancer causal action information based on surface-related information of a fusion protein, further comprising a step of setting the fusion protein as a target gene when the probability value for the possibility of cancer occurrence among the cancer causal action information exceeds a preset reference value.

4. In paragraph 1, The above surface analysis module, A method for acquiring cancer causal action information based on surface-related information of a fusion protein, wherein the method involves learning with a training data set including identification information of fusion proteins, surface-related information of fusion proteins, and cancer causal action information of fusion proteins.

5. In paragraph 1, The above structure generation module, A method for obtaining cancer causal action information based on surface-related information of a fusion protein, Alphafold2.

6. In paragraph 1, The above simulation module A method for obtaining cancer causal action information based on surface-related information of a fusion protein, MD (Molecular Dynamics).

7. Communications Department, including processor, The above processor, Extracting first genomic data from a user's sample cell, converting the first genomic data into first protein sequence data, By comparing the data for the first genetic data with the genetic data of normal cells corresponding to the sample cells, information on the fusion protein generated in the user's genome is selected. By inputting information about the above fusion protein into the structure generation module, data of the three-dimensional structure of the above fusion protein is output, By inputting data of the three-dimensional structure of the above fusion protein into the simulation module, the degree of surface exposure of the above fusion protein is output. A fusion protein analysis device that inputs the above surface exposure level into a surface analysis module and outputs cancer causal action information corresponding to the fusion protein.

8. In paragraph 7, The above cancer causal action information is, A fusion protein analysis device, comprising a probability value for whether or not the fusion protein acts on cancer development, or for the possibility of cancer development.

9. In paragraph 7, A fusion protein analysis device, wherein the processor sets the fusion protein as a target gene when the probability value for the possibility of cancer occurrence among the cancer causal action information exceeds a preset reference value.

10. In paragraph 7, The above surface analysis module, A fusion protein analysis device that learns using a training data set including identification information of fusion proteins, surface-related information of fusion proteins, and cancer-causing action information of fusion proteins.

11. In paragraph 7, The above structure generation module, Alphafold2, a fusion protein analysis device.

12. In paragraph 7, The above simulation module MD (Molecular Dynamics), a fusion protein analysis device.

13. A computer program stored in a computer-readable storage medium to execute the method of Article 7 using a computer.

Images