AI-based drug target determination method, device, equipment and storage medium

Abstract

The present invention discloses a drug target determination method, device, equipment and storage medium based on AI, wherein a drug target determination method based on AI comprises the following steps: obtaining proteomic data of a tissue before medication to obtain first data, and obtaining proteomic data of the tissue after medication to obtain second data; comparing the first data and the second data to obtain difference data between the first data and the second data; analyzing the difference data based on a drug target recognition model to determine the drug target; in the above manner, obtaining expression spectrum data changes and expression amount data changes of the proteomic groups in the tissue before and after medication to obtain difference data with differences before and after medication, that is, differential proteomic data; thereafter, determining the drug target based on the drug target recognition model, and improving the accuracy of drug target determination by combining the changed proteomic group with artificial intelligence information.

Description

Technical Field

[0001] The present invention relates to the biological field, and in particular to an AI-based drug target determination method, device, equipment and storage medium. Background Art

[0002] At present, with the many advances in the field of genomics and proteomics, new drug targets continue to emerge, bringing new growth points to pharmaceutical companies and new hope to the patient groups that have not yet received adequate treatment. However, genomic studies have shown that there are 10,000 to 20,000 drug target proteins in the human body, while only about 500 targets have been discovered in the past 100 years. Therefore, the discovery and determination of drug targets has great prospects. In addition, proteomics can play an important role in obtaining information about disease development, drug target confirmation, drug action mechanism, etc. at the protein level. Therefore, research based on proteomics to determine drug targets is extremely important. However, since the application of new targets in humans has not been confirmed, new drug targets have inherent risks. Choosing the "wrong" target will not only lead to treatment failure, waste time and resources in clinical use, but also / or cause economic losses to the company. Therefore, it is particularly important to improve the accuracy of proteomics to determine drug targets.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present invention is to provide an AI-based drug target determination method, device, equipment and storage medium, aiming to solve the technical problem of improving the accuracy of proteomics-based drug target determination.

[0005] To achieve the above object, the present invention provides an AI-based drug target determination method, the AI-based drug target determination method comprising the steps of:

[0006] Obtaining proteomic data of the tissue before medication to obtain first data, and obtaining proteomic data of the tissue after medication to obtain second data, wherein the proteomic data includes proteomic expression spectrum data and proteomic expression amount data;

[0007] Comparing the first data with the second data to obtain difference data between the first data and the second data, wherein the difference data represents a difference in proteome between the proteome of the tissue before and after drug administration;

[0008] Based on the drug target recognition model, the difference data is analyzed to determine the drug target.

[0009] Preferably, before the steps of obtaining proteomic data of the tissue before medication to obtain the first data, and obtaining proteomic data of the tissue after medication to obtain the second data, the method comprises:

[0010] Collect tissue samples of the tissues mentioned before and after medication;

[0011] The tissue sample is subjected to mass spectrometry analysis to obtain the proteomic data.

[0012] Preferably, the proteomic data includes first proteomic data and second proteomic data, and the steps of obtaining the proteomic data of the tissue before medication to obtain the first data, and obtaining the proteomic data of the tissue after medication to obtain the second data, include:

[0013] Performing microscopic analysis on the first proteomic data to obtain the first data;

[0014] The second proteomic data is subjected to microscopic analysis to obtain the second data.

[0015] Preferably, before the step of analyzing the difference data based on the drug target recognition model to determine the drug target, the method comprises:

[0016] Obtaining a previous data set of proteomes in tissues before and after drug administration in previous trials, wherein the previous data set includes previous proteome data, previous difference data, and previous targets;

[0017] Based on the previous data set, the drug target recognition model is established.

[0018] Preferably, the step of establishing the drug target recognition model based on the previous data set includes:

[0019] Obtaining the previous data set and the initial training model;

[0020] Iteratively training the initial training model based on the previous data set to obtain an updated initial training model, and determining whether the updated initial training model meets a preset iteration end condition;

[0021] If the updated initial training model meets the preset iteration end condition, the updated initial training model is used as the drug target recognition model;

[0022] If the updated initial training model does not meet the iteration end condition, the step of iteratively training the initial training model based on the previous data set is returned until the updated initial training model meets the iteration end condition.

[0023] Preferably, the step of analyzing the difference data based on the drug target recognition model to determine the drug target includes:

[0024] Acquiring the difference data;

[0025] The difference data is input into the drug target recognition model to determine the drug target.

[0026] Preferably, after the step of analyzing the difference data based on the drug target recognition model to determine the drug target, the method comprises:

[0027] Receiving an optimization instruction corresponding to the operation of optimizing the drug target;

[0028] In response to the optimization instruction, the drug target is optimized.

[0029] In addition, to achieve the above-mentioned purpose, the present invention also provides an AI-based drug target determination device, the device comprising:

[0030] A first acquisition module acquires proteomic data of the tissue before medication to obtain first data, and acquires proteomic data of the tissue after medication to obtain second data, wherein the proteomic data includes proteomic expression spectrum data and proteomic expression amount data;

[0031] A comparison module, comparing the first data and the second data to obtain difference data between the first data and the second data, wherein the difference data represents a difference in proteome between the proteome of the tissue before and after medication;

[0032] The determination module analyzes the difference data based on the drug target recognition model to determine the drug target.

[0033] In addition, to achieve the above-mentioned purpose, the present application also provides an AI-based drug target determination device, which includes a memory, a processor, and an AI-based drug target determination program stored in the memory and executable on the processor, and the AI-based drug target determination program, when executed by the processor, implements the steps of the AI-based drug target determination method as described above.

[0034] In addition, to achieve the above-mentioned purpose, the present application also provides a computer-readable storage medium, on which an AI-based drug target determination program is stored. When the AI-based drug target determination program is executed by a processor, the steps of the AI-based drug target determination method as described above are implemented.

[0035] An AI-based drug target determination method, apparatus, device and readable storage medium proposed in an embodiment of the present invention include the following steps: obtaining proteomic data of a tissue before medication to obtain first data, and obtaining proteomic data of the tissue after medication to obtain second data, wherein the proteomic data includes proteomic expression spectrum data and proteomic expression level data; comparing the first data and the second data to obtain difference data between the first data and the second data, wherein the difference data represents the difference proteomic between the proteomic of the tissue before and after medication; analyzing the difference data based on a drug target recognition model to determine the drug target; in the above manner, obtaining the change in expression spectrum data and expression level data of the proteomic in the tissue before and after medication to obtain difference data with differences before and after medication, that is, differential proteomic data; thereafter, determining the drug target based on the drug target recognition model, and improving the accuracy of drug target determination by combining the changed proteomic with artificial intelligence information. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a schematic diagram of the terminal\device structure of the hardware operating environment involved in the embodiment of the present invention;

[0037] Figure 2 This is a flow chart of an embodiment of a drug target determination method based on AI of the present invention;

[0038] Figure 3 This is a schematic diagram of the functional modules of a preferred embodiment of the AI-based drug target determination device of the present invention.

[0039] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0040] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0041] The main solutions of the embodiments of the present invention are:

[0042] Thanks to existing technologies, proteomics can play an important role in obtaining information about disease development, drug target confirmation, drug action mechanism, etc. at the protein level. Therefore, research based on proteomics to determine drug targets is extremely important. However, since the application of new targets in humans has not yet been confirmed, new drug targets have inherent risks. Choosing the "wrong" target will not only lead to treatment failure in clinical use, waste time and resources, and / or cause economic losses to the company. Therefore, it is particularly important to improve the accuracy of proteomics to determine drug targets.

[0043] The present invention provides a solution to improve the accuracy of drug target determination based on proteomics.

[0044] like Figure 1 As shown, Figure 1 It is a schematic diagram of the terminal structure of the hardware operating environment involved in the embodiment of the present invention.

[0045] The terminal of the embodiment of the present invention can be a PC, or it can be a smart phone, a tablet computer, an e-book reader, an MP3 (Moving Picture Experts Group Audio Layer III) player, an MP4 (Moving Picture Experts Group Audio Layer IV) player, a portable computer, or other portable terminal devices with display function.

[0046] like Figure 1 As shown, the terminal may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory, or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0047] Optionally, the terminal may also include a camera, an RF (Radio Frequency) circuit, a sensor, an audio circuit, a WiFi module, and the like. Among them, sensors include light sensors, motion sensors, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display screen according to the brightness of the ambient light, and the proximity sensor may turn off the display screen and / or backlight when the mobile terminal is moved to the ear. As a type of motion sensor, the gravity acceleration sensor can detect the magnitude of acceleration in each direction (generally three axes), and can detect the magnitude and direction of gravity when stationary. It can be used for applications that identify the posture of the mobile terminal (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; of course, the mobile terminal may also be equipped with other sensors such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc., which will not be repeated here.

[0048] Those skilled in the art will understand that Figure 1 The terminal structure shown in the figure does not constitute a limitation on the terminal, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0049] like Figure 1 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an AI-based drug target determination program.

[0050] exist Figure 1 In the terminal shown, the network interface 1004 is mainly used to connect to the backend server and communicate data with the backend server; the user interface 1003 is mainly used to connect to the client (user end) and communicate data with the client; and the processor 1001 can be used to call the AI-based drug target determination program stored in the memory 1005 and perform the following operations:

[0051] Obtaining proteomic data of the tissue before medication to obtain first data, and obtaining proteomic data of the tissue after medication to obtain second data, wherein the proteomic data includes proteomic expression spectrum data and proteomic expression amount data;

[0052] Comparing the first data with the second data to obtain difference data between the first data and the second data, wherein the difference data represents a difference in proteome between the proteome of the tissue before and after drug administration;

[0053] Based on the drug target recognition model, the difference data is analyzed to determine the drug target.

[0054] Further, the processor 1001 may call the AI-based drug target determination program stored in the memory 1005, and further perform the following operations:

[0055] Collect tissue samples of the tissues mentioned before and after medication;

[0056] The tissue sample is subjected to mass spectrometry analysis to obtain the proteomic data.

[0057] Further, the processor 1001 may call the AI-based drug target determination program stored in the memory 1005, and further perform the following operations:

[0058] Performing microscopic analysis on the first proteomic data to obtain the first data;

[0059] The second proteomic data is subjected to microscopic analysis to obtain the second data.

[0060] Further, the processor 1001 may call the AI-based drug target determination program stored in the memory 1005, and further perform the following operations:

[0061] Obtaining a previous data set of proteomes in tissues before and after drug administration in previous trials, wherein the previous data set includes previous proteome data, previous difference data, and previous targets;

[0062] Based on the previous data set, the drug target recognition model is established.

[0063] Further, the processor 1001 may call the AI-based drug target determination program stored in the memory 1005, and further perform the following operations:

[0064] Obtaining the previous data set and the initial training model;

[0065] Iteratively training the initial training model based on the previous data set to obtain an updated initial training model, and determining whether the updated initial training model meets a preset iteration end condition;

[0066] If the updated initial training model meets the preset iteration end condition, the updated initial training model is used as the drug target recognition model;

[0067] If the updated initial training model does not meet the iteration end condition, the step of iteratively training the initial training model based on the previous data set is returned until the updated initial training model meets the iteration end condition.

[0068] Further, the processor 1001 may call the AI-based drug target determination program stored in the memory 1005, and further perform the following operations:

[0069] Acquiring the difference data;

[0070] The difference data is input into the drug target recognition model to determine the drug target.

[0071] Further, the processor 1001 may call the AI-based drug target determination program stored in the memory 1005, and further perform the following operations:

[0072] Receiving an optimization instruction corresponding to the operation of optimizing the drug target;

[0073] In response to the optimization instruction, the drug target is optimized.

[0074] Reference Figure 2 The first embodiment of the present invention provides a method for determining drug targets based on AI, a device, an apparatus, and a readable storage medium. The method for determining drug targets based on AI includes:

[0075] Step S10, obtaining proteomic data of the tissue before medication to obtain first data, and obtaining proteomic data of the tissue after medication to obtain second data, wherein the proteomic data includes proteomic expression spectrum data and proteomic expression amount data;

[0076] Step S20, comparing the first data and the second data to obtain difference data between the first data and the second data, wherein the difference data represents a difference in proteome between the proteome of the tissue before and after medication;

[0077] Step S30: analyzing the difference data based on the drug target recognition model to determine the drug target.

[0078] In this embodiment, drug targets are determined by analyzing the changes in expression profile data and expression level data of proteomes in tissues before and after medication, wherein the changed proteomes are combined with artificial intelligence information to improve the accuracy of drug target determination.

[0079] The specific steps are as follows:

[0080] Step S10, obtaining proteomic data of the tissue before medication to obtain first data, and obtaining proteomic data of the tissue after medication to obtain second data, wherein the proteomic data includes proteomic expression spectrum data and proteomic expression amount data;

[0081] In this embodiment, it should be noted that the proteome refers to all proteins expressed by a genome, or a cell or tissue. Proteomics refers to the science of studying the combination of proteins in cells, tissues or organisms and their changing laws, with the proteome as the research object. The study of the proteome can not only provide a material basis for the laws of life activities, but also provide a theoretical basis and solution for the elucidation and overcoming of the mechanisms of many diseases. Tissue refers to the body of the drug, and the tissue includes gene sites, receptors, enzymes, ion channels, nucleic acids and other biological macromolecules. After the drug acts on the tissue, the drug target is determined by detecting the changes in the proteome in the tissue, wherein the drug target refers to the binding site of the drug in the tissue, including fund sites, receptors, enzymes, ion channels, nucleic acids and other biological macromolecules.

[0082] Furthermore, the proteomic data includes first proteomic data and second proteomic data, and the step of obtaining the proteomic data of the tissue before medication to obtain the first data, and obtaining the proteomic data of the tissue after medication to obtain the second data, includes the following steps S11-S12:

[0083] Step S11, performing microscopic analysis on the first proteomic data to obtain the first data;

[0084] Step S12, performing microscopic analysis on the second proteomic data to obtain the second data.

[0085] In this embodiment, before and after medication, the tissue will have different proteomic changes, so the proteomic data obtained are differentiated, and the proteomic data in the tissue before medication is set as the first proteomic data, and the proteomic data in the tissue after medication is set as the second proteomic data. It should be noted that the proteomic data includes proteomic expression spectrum data and proteomic expression amount data. The first proteomic data is microscopically analyzed to obtain the first data, and the second proteomic data is analyzed to obtain the second data.

[0086] Step S20, comparing the first data and the second data to obtain difference data between the first data and the second data, wherein the difference data represents a difference in proteome between the proteome of the tissue before and after medication;

[0087] In this embodiment, since there are differences in the proteomic data in the tissue before and after the medication, the target of the drug is detected by comparing the proteomic expression spectrum data and the proteomic expression amount data. It can be understood that by comparing the first data and the second data, the difference data between the first data and the second data is obtained, and the difference data represents the difference between the proteomic groups in the tissue before and after the medication.

[0088] Step S30: analyzing the difference data based on the drug target recognition model to determine the drug target.

[0089] In this embodiment, the drug target identification model refers to a model for predicting drug targets, which is based on data obtained by artificial intelligence, records and analyzes differential data, and determines drug targets by analyzing the differential data between the proteomic data of tissues before and after medication. It can be understood that the general method is to compare the proteomic or modification differences between healthy tissues and diseased tissues or samples before and after drug administration to discover differential proteomic groups and then determine drug targets.

[0090] Furthermore, based on the drug target recognition model, the difference data is analyzed, and before the step of determining the drug target, the following steps S31-S32 are included:

[0091] Step S31, obtaining a previous data set of proteomes in tissues before and after drug administration in previous experiments, wherein the previous data set includes previous proteome data, previous difference data, and previous targets;

[0092] Step S32: establishing the drug target recognition model based on the previous data set.

[0093] In this embodiment, data of the same tissue and drug during the experiment are collected regularly, that is, the data of the proteome in the tissue before and after the drug is used, and this data is the past data. The past data specifically refers to all the data recorded during a test, such as the past data including past proteome data, past difference data and past targets. It should be noted that the data obtained from the tests conducted at different times, different tissues or different medications are different, and they are all past data. The past data obtained multiple times are sorted into a set to obtain a past data set. A drug target recognition model is established through the past data set, and then the drug target is determined through the drug target recognition model.

[0094] Furthermore, based on the drug target recognition model, the difference data is analyzed, and before the step of determining the drug target, the following steps S33-S34 are included:

[0095] Step S33, obtaining the difference data;

[0096] Step S34, inputting the difference data into the drug target recognition model to determine the drug target.

[0097] In this embodiment, differential data, that is, differential proteomes with differences before and after medication, are obtained. The past data sets of the drug recognition target model include past differential data. Therefore, the differential data are input into the drug target recognition model to obtain drug targets corresponding to the differential data.

[0098] In this embodiment, the AI-based drug target determination method of the present invention is applied to biomedicine and includes the following steps: obtaining proteomic data of a tissue before medication to obtain first data, and obtaining proteomic data of the tissue after medication to obtain second data, wherein the proteomic data includes proteomic expression spectrum data and proteomic expression level data; comparing the first data and the second data to obtain difference data between the first data and the second data, wherein the difference data represents the difference proteomic between the proteomic of the tissue before and after medication; analyzing the difference data based on a drug target recognition model to determine the drug target; in the above manner, obtaining the change in expression spectrum data and expression level data of the proteomic in the tissue before and after medication to obtain difference data with differences before and after medication, that is, differential proteomic data; thereafter, determining the drug target based on the drug target recognition model, and improving the accuracy of drug target determination by combining the changed proteomic with artificial intelligence information.

[0099] Further, based on the above first embodiment, a second embodiment of the drug target determination method based on AI of the present invention is proposed. In this embodiment, before obtaining the proteomic data of the tissue before medication to obtain the first data, and obtaining the proteomic data of the tissue after medication to obtain the second data, the method further includes the following steps S40-S41:

[0100] Step S40, collecting tissue samples of the tissue before and after medication;

[0101] Step S41, performing mass spectrometry analysis on the tissue sample to obtain the proteome data.

[0102] In this embodiment, before and after the drug acts on the tissue, tissue samples are collected to obtain a first sample and a second sample. The first sample and the second sample are analyzed to analyze the proteins in the sample. Usually, more than 10,000 proteins are analyzed at one time. The method for preparing peptides from clinical samples based on pressure cycling technology can extract 50 to 200 micrograms of peptides from a cubic millimeter of clinical tissue samples, which can meet the amount required for multiple mass spectrometry analyses of tissue samples. Subsequently, proteomic data is obtained through mass spectrometry analysis.

[0103] In this embodiment, tissue samples are obtained by sampling tissues before and after drug administration, and proteomic data are obtained based on tissue sample analysis, providing basic materials for subsequent proteomics-based determination of drug targets.

[0104] Further, based on the above first embodiment, a third embodiment of the drug target determination method based on AI of the present invention is proposed. In this embodiment, the drug target recognition model is established based on the previous data set, including the following steps S50-S53:

[0105] Step S50, obtaining the previous data set and the initial training model;

[0106] Step S51, iteratively training the initial training model based on the previous data set to obtain an updated initial training model, and determining whether the updated initial training model meets a preset iteration end condition;

[0107] Step S52, if the updated initial training model meets the preset iteration end condition, the updated initial training model is used as the drug target recognition model;

[0108] Step S53: If the updated initial training model does not meet the iteration end condition, return to the iterative training step of the initial training model based on the previous data set until the updated initial training model meets the iteration end condition.

[0109] In this embodiment, it should be noted that the initial training model is a neural network, which is an information processing data model similar to the synaptic structure of human brain nerve cells. The present invention iteratively trains the initial training model through the previous data set to obtain an updated initial training model. It can be understood that when the iterative training does not set the iteration end condition, it is a continuous training. Therefore, based on certain training requirements, a preset iteration end condition can be set, such as the number of iterations, training duration, training stop time, etc. When the iterative training of the initial training model meets the preset iteration end condition, the last initial training model is the drug target recognition model; if the updated initial training model does not meet the iteration end condition, it returns to the iterative training step of the initial training model based on the previous data set until the updated initial training model meets the iteration end condition.

[0110] Further, based on the above first embodiment, a fourth embodiment of the drug target determination method based on AI of the present invention is proposed. In this embodiment, after analyzing the difference data based on the drug target recognition model and determining the drug target, the method further includes the following steps S60-S61:

[0111] Step S60, receiving an optimization instruction corresponding to the operation of optimizing the drug target;

[0112] Step S61, responding to the optimization instruction, optimizing the drug target.

[0113] In this embodiment, an ideal drug should be able to specifically and effectively bind to the target of the disease, and be safe. The optimization of the drug target, that is, whether the proteome as the drug target is the best choice for the drug. Therefore, there may be multiple drug targets to be determined, and the drug targets can be optimized according to the needs. When the system receives the optimization instruction corresponding to the operation of optimizing the drug target, it responds to the optimization instruction and optimizes the drug target. Specifically, the above process of obtaining proteomic data before and after medication, differential data, and drug target recognition model, adopts the optimal algorithm for obtaining or analyzing the data in the above process, and can achieve the optimization of drug targets.

[0114] In this embodiment, the accuracy of drug target determination based on proteomics is improved by optimizing the drug target.

[0115] Reference Figure 3 The first embodiment of the drug target determination method based on AI of the present invention provides a drug target determination device based on AI. Figure 3 In the embodiment shown, the AI-based drug target determination device includes:

[0116] A first acquisition module 10 acquires proteomic data of the tissue before medication to obtain first data, and acquires proteomic data of the tissue after medication to obtain second data, wherein the proteomic data includes proteomic expression spectrum data and proteomic expression amount data;

[0117] A comparison module 20 compares the first data and the second data to obtain difference data between the first data and the second data, wherein the difference data represents a difference in proteome between the proteome of the tissue before and after medication;

[0118] The determination module 30 analyzes the difference data based on the drug target recognition model to determine the drug target.

[0119] Optionally, the AI-based drug target determination device further includes:

[0120] A collection module for collecting tissue samples of the tissues before and after medication;

[0121] The analysis module performs mass spectrometry analysis on the tissue sample to obtain the proteomic data.

[0122] Optionally, the acquisition module 10 further includes:

[0123] A first analysis submodule performs microscopic analysis on the first proteomic data to obtain the first data;

[0124] The second analysis submodule performs microscopic analysis on the second proteomic data to obtain the second data.

[0125] Optionally, the AI-based drug target determination device further includes:

[0126] The second acquisition module acquires the previous data sets of proteomes in tissues before and after drug administration in previous trials, wherein the previous data sets include previous proteome data, previous difference data and previous targets;

[0127] A modeling module is used to establish the drug target recognition model based on the previous data set.

[0128] Optionally, the modeling module includes:

[0129] A first acquisition submodule is used to acquire the previous data set and the initial training model;

[0130] A training submodule, iteratively training the initial training model based on the previous data set to obtain an updated initial training model, and determining whether the updated initial training model meets a preset iteration end condition;

[0131] An updating submodule, if the updated initial training model meets the preset iteration end condition, using the updated initial training model as the drug target recognition model;

[0132] The output submodule returns to the iterative training step of the initial training model based on the previous data set if the updated initial training model does not meet the iteration end condition until the updated initial training model meets the iteration end condition.

[0133] Optionally, the determining module 30 further includes:

[0134] A second acquisition submodule is used to acquire the difference data;

[0135] A determination submodule inputs the difference data into the drug target recognition model to determine the drug target.

[0136] Optionally, the AI-based drug target determination device further includes:

[0137] A receiving module receives an optimization instruction corresponding to the operation of optimizing the drug target;

[0138] The optimization module optimizes the drug target in response to the optimization instruction.

[0139] In addition, this application also provides an AI-based drug target determination device. Figure 1 As shown, Figure 1It is a structural diagram of the hardware operating environment involved in the embodiment of the present application.

[0140] In addition, an embodiment of the present invention also proposes a computer-readable storage medium, on which an AI-based drug target determination program is stored. When the AI-based drug target determination program is executed by a processor, the steps of the AI-based drug target determination method as described above are implemented.

[0141] The specific implementation methods of the computer-readable storage medium of the present application are basically the same as the embodiments of the above-mentioned AI-based drug target determination method, and will not be repeated here.

[0142] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0143] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0144] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0145] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A drug target determination method based on AI, characterized in that: The AI-based drug target determination method comprises the following steps: Obtaining a previous data set of proteomes in tissues before and after medication in previous trials, wherein the previous data set includes previous proteome data, previous difference data, and previous targets, and the data in the previous data set is data obtained from trials conducted at different times, in different tissues, or with different medications; Based on the previous data set, establishing the drug target recognition model; The step of establishing the drug target recognition model based on the previous data set includes: Get the initial training model; Iteratively training the initial training model based on the previous data set to obtain an updated initial training model, and determining whether the updated initial training model meets a preset iteration end condition; If the updated initial training model meets the preset iteration end condition, the updated initial training model is used as the drug target recognition model; If the updated initial training model does not meet the iteration end condition, returning to the step of iteratively training the initial training model based on the previous data set until the updated initial training model meets the iteration end condition; Obtaining proteomic data of the tissue before medication to obtain first data, and obtaining proteomic data of the tissue after medication to obtain second data, wherein the proteomic data includes proteomic expression spectrum data and proteomic expression amount data; Comparing the first data with the second data to obtain difference data between the first data and the second data, wherein the difference data represents a difference in proteome between the proteome of the tissue before and after drug administration; Based on the drug target recognition model, the difference data is analyzed to determine the drug target.

2. The AI-based drug target determination method according to claim 1, characterized in that: Before the steps of obtaining the proteomic data of the tissue before medication to obtain the first data, and obtaining the proteomic data of the tissue after medication to obtain the second data, the method includes: Collect tissue samples of the mentioned tissues before and after medication; The tissue sample is subjected to mass spectrometry analysis to obtain the proteomic data.

3. The AI-based drug target determination method according to claim 1, characterized in that: The proteomic data includes first proteomic data and second proteomic data. The steps of obtaining the proteomic data of the tissue before medication to obtain the first data, and obtaining the proteomic data of the tissue after medication to obtain the second data include: Performing microscopic analysis on the first proteomic data to obtain the first data; The second proteomic data is subjected to microscopic analysis to obtain the second data.

4. The AI-based drug target determination method according to claim 1, characterized in that: The step of analyzing the difference data based on the drug target recognition model to determine the drug target includes: Acquiring the difference data; The difference data is input into the drug target recognition model to determine the drug target.

5. The AI-based drug target determination method according to claim 1, characterized in that: After the step of analyzing the difference data based on the drug target recognition model to determine the drug target, the method comprises: Receiving an optimization instruction corresponding to the operation of optimizing the drug target; In response to the optimization instruction, the drug target is optimized.

6. A drug target determination device based on AI, characterized in that: The device comprises: A first acquisition module acquires proteomic data of the tissue before medication to obtain first data, and acquires proteomic data of the tissue after medication to obtain second data, wherein the proteomic data includes proteomic expression spectrum data and proteomic expression amount data; A comparison module, comparing the first data and the second data to obtain difference data between the first data and the second data, wherein the difference data represents a difference in proteome between the proteome of the tissue before and after medication; A determination module is provided to obtain a previous data set of proteomes in tissues before and after medication in previous experiments, wherein the previous data set includes previous proteome data, previous difference data and previous targets, and the data in the previous data set is data obtained from experiments conducted at different times, with different tissues or with different medications; an initial training model is obtained; the initial training model is iteratively trained based on the previous data set to obtain an updated initial training model, and it is determined whether the updated initial training model meets a preset iteration end condition; if the updated initial training model meets the preset iteration end condition, the updated initial training model is used as the drug target recognition model; if the updated initial training model does not meet the iteration end condition, the step of iteratively training the initial training model based on the previous data set is returned until the updated initial training model meets the iteration end condition; based on the drug target recognition model, the difference data is analyzed to determine the drug target.

7. An AI-based drug target determination device, characterized in that: The AI-based drug target determination device includes: a memory, a processor, and an AI-based drug target determination program stored in the memory and executable on the processor. When the AI-based drug target determination program is executed by the processor, the steps of the method described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an AI-based drug target determination program, and when the AI-based drug target determination program is executed by a processor, the steps of the AI-based drug target determination method as described in any one of claims 1 to 5 are implemented.

Images