Method, device, storage medium, and system for rapid classification of mass spectrometry peaks

Abstract

The present invention relates to a method, apparatus, storage medium, and system for rapid classification of mass spectrometry peaks. The method includes: obtaining a number of mass spectrometry peak sample data fed back by a mass spectrometer; and clustering the number of sample data by using the Brain-State-in-a-Box model. By clustering the number of sample data by using the Brain-State-in-a-Box model, it helps scientific researchers to pre-screen the mass spectrometry peaks, relieve the pressure on scientific researchers, and is also of great benefit to the analysis of substances. Scientific researchers can also train the clusterer according to their needs, and by continuously increasing the number of samples, improve the clustering accuracy and increase the number of classes.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and particularly to a method, device, storage medium, and system for rapid classification of mass spectrometry peaks. Background Art

[0002] Triple quadrupole mass spectrometers are important scientific instruments in the fields of materials, medicine, pharmacy, etc. During the analysis process using a mass spectrometer, there are various substances, and the corresponding spectra are also diverse. Generally, the spectral shapes corresponding to different substances are different. As shown in Figure 1 are three mass spectrometry graphs with different shapes. It is generally impossible for scientific researchers or analysts to remember the shapes of these tens of millions of mass spectrometry graphs. Especially for an unknown substance, it is difficult to quickly classify it according to the shape of the mass spectrometry peaks. For inexperienced scientific researchers, it lacks an important direction for analyzing substances. Therefore, it takes more time for analysis, reducing the experimental efficiency. Similarly, other scientific researchers need to repeat this process, resulting in a large amount of repetitive work, which greatly reduces the experimental efficiency.

[0003] This application aims to establish a systematic method and implementation system for rapid classification of mass spectrometry peaks. Summary of the Invention

[0004] To achieve the above objects and other advantages of the present invention, the first object of the present invention is to provide a method for rapid classification of mass spectrometry peaks, including the following steps:

[0005] Obtain a number of mass spectrometry peak sample data fed back by a mass spectrometer;

[0006] Cluster the number of sample data using the brain-state-in-a-box model.

[0007] Preferably, it further includes the step of:

[0008] Train the brain-state-in-a-box model; the equation of the brain-state-in-a-box model is as follows:

[0009] y(n) = x(n) + βWx(n) (1)

[0010]

[0011] where x(n) is the state vector; β is a positive constant, i.e., the feedback coefficient; W is the weight matrix of a single-layer linear neural network; y(n) is the intermediate vector of the generated system state vector; is a non-linear vector function, i.e., the activation function.

[0012] Preferably, the activation function is defined as follows:

[0013]

[0014] Preferably,

[0015] The variation of the weight matrix W of the single-layer linear neural network is as follows:

[0016]

[0017] Update the weight matrix based on the variation of W in Equation (4):

[0018] W k = W k-1 + ηΔW (5).

[0019] Preferably, when classifying the plurality of sample data by using the brain-in-a-box state model, it includes the steps of:

[0020] S201: Obtain a training set for training the brain-in-a-box state model, where the training set is a set of standard mass spectrometry peaks {a 1 , a 2 , …, a M} that have been classified; and initialize the weight matrix: W 0 = I, where I is the identity matrix;

[0021] S202: Update the weight matrix according to Equation (6),

[0022]

[0023] where a k is the k-th element of the training set {a 1 , a 2 , …, a M}, η is a positive constant; W k-1 is the weight matrix generated in the previous iteration process, and W k is the weight matrix updated and generated in this iteration;

[0024] S203: When k = M, execute W = W M , and enter S204; when k < M, return to S202;

[0025] S204: Assign the initial state x(0) of the system to the collected mass spectrometry peak vector x(n), and enter S205;

[0026] S205: Substitute W, β, x(n) into the following formula:

[0027] y(n) = x(n) + βWx(n) (1)

[0028]

[0029] S206: When ||x(n + 1) - x(n)|| ≤ ε, proceed to S207; where: x(n + 1) is the current system state vector, x(n) is the system state vector of the previous iteration, and ε is the threshold constant;

[0030] S207: Compare the final system state x(n + 1) generated in S206 with the training set {a 1 , a 2 , …, a M}. When ||x(n + 1) - a k || ≤ ε, then the mass spectrometry peak x belongs to the type to which a k belongs. If ||x(n + 1) - a k || > ε for x(n + 1) and all elements of the training set, then the mass spectrometry peak x does not belong to any type included in the training set.

[0031] Preferably, in S206, when ||x(n + 1) - x(n)|| > ε, return to S205.

[0032] The second object of the present invention is to provide a mass spectrometry peak fast classification device, including:

[0033] An acquisition unit configured to acquire the scanning data of the imaging target by the mass spectrometer;

[0034] A processing unit configured to cluster the scanning data using the brain state in a box model.

[0035] The third object of the present invention is to provide a mass spectrometry peak fast classification device, including: a memory on which program code is stored; a processor coupled to the memory, and when the program code is executed by the processor, the above - described method is implemented.

[0036] The fourth object of the present invention is to provide a computer - readable storage medium on which program instructions are stored, and when the program instructions are executed, the above - described mass spectrometry peak fast classification method is implemented.

[0037] The fifth object of the present invention is to provide a mass spectrometry peak classification system, including the above - described mass spectrometry peak fast classification device; the mass spectrometry peak fast classification device is connected to a display device.

[0038] Compared with the prior art, the beneficial effects of the present invention are:

[0039] The present invention provides a method for rapid classification of mass spectrometry peaks. The method includes: obtaining a number of sample data of mass spectrometry peaks fed back by a mass spectrometer; and clustering the number of sample data by using the brain - in - a - box state model. By clustering the number of sample data by using the brain - in - a - box state model, it helps scientific researchers to pre - screen the mass spectrometry peaks, relieve the pressure on scientific researchers, and is also very beneficial for the analysis of substances. Scientific researchers can also train the clusterer according to their needs. By continuously increasing the number of samples, the clustering accuracy can be improved and the number of classes can be increased.

[0040] The above description is only an overview of the technical solution of the present invention. In order to be able to understand the technical means of the present invention more clearly and to be implemented in accordance with the content of the description, the following takes the preferred embodiments of the present invention and combines them with the accompanying drawings for detailed description as follows. The specific implementation manner of the present invention is given in detail by the following embodiments and their accompanying drawings. Brief Description of the Drawings

[0041] The accompanying drawings described herein are used to provide a further understanding of the present invention, and constitute a part of this application. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0042] Figure 1 are spectrograms of three different shapes;

[0043] Figure 2 is a flow chart of the method for rapid classification of mass spectrometry peaks;

[0044] Figure 3 is a schematic diagram of the structure of the brain - in - a - box state model;

[0045] Figure 4 are four mass spectrograms made by HTQ - 2020 in an embodiment;

[0046] Figure 5 is a schematic diagram of a clustering working process;

[0047] Figure 6 is a schematic diagram of the device for rapid classification of mass spectrometry peaks in Embodiment 2;

[0048] Figure 7 is a schematic diagram of the device for rapid classification of mass spectrometry peaks in Embodiment 3. Detailed Description of the Preferred Embodiments

[0049] Next, in combination with the accompanying drawings and the specific implementation manner, the present invention will be further described. It should be noted that, on the premise of no conflict, any combination of the following described embodiments or technical features can form a new embodiment.

[0050] In the following description, suffixes such as "module", "component", or "unit" used to denote elements are only for facilitating the description of the present invention and have no specific meaning in themselves. Therefore, "module", "component", or "unit" can be used interchangeably.

[0051] The present invention relates to a method for rapid classification of mass spectrometry peaks, including the following steps, as Figure 2 shown:

[0052] S101: Obtain a number of mass spectrometry peak sample data fed back by a mass spectrometer;

[0053] Since this method is used for rapid classification of different-shaped spectrograms, several generally refer to three or more spectrograms with different shapes.

[0054] S102: Cluster a number of sample data using the brain-state-in-a-box model.

[0055] By executing S101 - S102, rapid classification of multiple mass spectra can be achieved through the brain-state-in-a-box model, helping researchers pre-screen mass spectrometry peaks, reducing the pressure on researchers, and being of great benefit to substance analysis.

[0056] In some embodiments, it further includes the step:

[0057] Step 103: Train the brain-state-in-a-box model; specifically, the brain-state-in-a-box model can be trained according to requirements, and by continuously increasing the number of samples, the clustering accuracy can be improved and the number of classes can be increased.

[0058] In some embodiments, the brain-state-in-a-box model involved in S102 is a recurrent neural network structure, and the schematic diagram of this structure is as Figure 3 shown. In addition, assuming there are n neurons in the model, the state vector of the model is n-dimensional, and the algorithm of the brain-state-in-a-box model (also known as the BSB model) is defined by the following two equations:

[0059] y(n) = x(n) + βWx(n) (1)

[0060]

[0061] where x(n) is the state vector; β is a positive constant, i.e., the feedback coefficient; W is the weight matrix of a single-layer linear neural network; y(n) is the intermediate vector of the generated system state vector; is a non-linear vector function, i.e., the activation function.

[0062] When specifically running this equation, it should be noted that:

[0063] (1) Select a certain pattern vector x(0) as an initial state vector and input it into the BSB model.

[0064] (2) Calculate y(n) based on the current state x(n), as well as β and W.

[0065] (3) Truncate y(n) using the activation function to obtain x(n + 1).

[0066] (4) Repeat steps (2) and (3) until the model reaches a stable state.

[0067] In some embodiments, the activation function in S102 is defined as follows:

[0068]

[0069] In some embodiments, the change in the weight matrix W of the single-layer linear neural network in S102 is as follows:

[0070]

[0071] Update the weight matrix based on the change in W in Equation (4):

[0072] W k = W k-1 + ηΔW (5)

[0073] In some embodiments, when classifying a number of sample data using the in-box brain state model, the steps include:

[0074] Step 201: Obtain a training set for training the in-box brain state model, which is composed of the classified standard mass spectrometry peaks {a 1 , a 2 , …, a M}; and initialize the weight matrix: W 0 = I, where I is the identity matrix. The identity matrix is a square matrix, and the elements on the diagonal from the upper left corner to the lower right corner (i.e., the main diagonal) are all 1, and the rest are 0;

[0075] Step 202: Update the weight matrix according to Equation (6),

[0076]

[0077] where a k is the k-th element of the training set {a 1 , a 2 , …, a M}, η is a positive constant; W k-1 is the weight matrix generated in the previous iteration process, and W k is the weight matrix updated and generated in this iteration;

[0078] Step 203: When k = M, execute W = W M, proceed to step 204; when k < M, return to step 202;

[0079] Step 204: Assign the initial state x(0) of the system to the collected mass spectrometry peak vector x(n), and proceed to step 205;

[0080] Step 205: Substitute W, β, x(n) into the following formula:

[0081] y(n) = x(n) + βWx(n) (1)

[0082]

[0083] Step 206: When ||x(n + 1) - x(n)|| ≤ ε, proceed to step 207; where: x(n + 1) is the current system state vector, x(n) is the system state vector of the previous iteration, and ε is the threshold constant. In some embodiments, it can be set as ε = 0.01;

[0084] Step 207: Compare the final system state x(n + 1) generated in step 206 with the training set {a 1 , a 2 , …, a M}. When ||x(n + 1) - a k || ≤ ε, then the mass spectrometry peak x belongs to the type to which a k belongs. If ||x(n + 1) - a k || > ε for x(n + 1) and all elements of the training set, then the mass spectrometry peak x does not belong to any type included in the training set.

[0085] In some embodiments, in step 206, when ||x(n + 1) - x(n)|| > ε, return to execute step 205 to make the model in step 205 reach a stable state.

[0086] Steps 201 - 207 can be used for the rapid classification of several samples; it can also be used for training the in - box brain model. By continuously increasing the number of samples, the clustering accuracy can be improved and the number of classes can be increased.

[0087] In some embodiments, as Figure 4 shown, taking the HTQ - 2020 triple quadrupole mass spectrometer as an example, four different mass spectrometry graphs are classified. By executing the above steps, these four mass spectrometry graphs are divided into three types. From the effect, the clustering result for the mass spectrometry peaks is still acceptable.

[0088] When executing the above steps, the specific convergence process is as follows Figure 5As shown, starting from the input mass spectrometry peaks as the starting point, continuously move towards the corresponding "corner points". When the system state reaches the "corner points", the system is in equilibrium.

[0089] Example Two

[0090] As Figure 6 shown, a mass spectrometry peak rapid classification device 100 includes:

[0091] An acquisition unit 101, which is configured to acquire the scanning data of the mass spectrometer for the imaging target;

[0092] A processing unit 102, which is configured to perform clustering on the scanning data by using the box brain state model.

[0093] For the detailed descriptions of the above respective units, reference can be made to the corresponding descriptions in the above method embodiments, and details will not be elaborated here.

[0094] The mass spectrometry peak rapid classification device is implemented based on an improved box brain state model; in some embodiments, the mass spectrometry peak rapid classification device is a mass spectrometry peak clusterer of a triple quadrupole mass spectrometer.

[0095] Example Three

[0096] As Figure 7 shown, a mass spectrometry peak rapid classification device 200 is presented in the form of a general computing device; including but not limited to: a memory 201, a processor 202; wherein,

[0097] The memory 201 stores program codes thereon; the processor 202 is connected to the memory 201, and when the program codes are executed by the processor 202, the mass spectrometry peak rapid classification method in Example One is implemented.

[0098] The mass spectrometry peak rapid classification device 200 may further include a bus connecting different system components (including the memory 201 and the processor 202), a display unit, etc. Among them, the bus can represent one or more of several types of bus structures, including a memory unit bus or a memory unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any bus structure in multiple bus structures.

[0099] Example Four

[0100] A mass spectrometry peak classification system includes the mass spectrometry peak rapid classification devices in Example Two and Example Three; the mass spectrometry peak rapid classification device is connected to a display device. For the detailed description of the display device, reference can be made to the prior art, and details will not be elaborated here.

[0101] Example Five

[0102] Through the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software or by a combination of software and necessary hardware. The technical solutions according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (such as a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on the network, including several computer program instructions to enable a computing device (such as a personal computer, a server, or a network device, etc.) to execute the above method according to the embodiments of the present application.

[0103] The number of devices and the processing scale described here are used to simplify the description of the present invention. The applications, modifications, and variations of the present invention are obvious to those skilled in the art.

[0104] Although the embodiments of the present invention have been disclosed as above, they are not limited to the applications listed in the specification and the embodiments. It can be fully applied to various fields suitable for the present invention. For those skilled in the art, additional modifications can be easily made. Therefore, without departing from the general concept defined by the claims and the equivalent scope, the present invention is not limited to the specific details and the illustrated and described examples here.

[0105] The devices, electronic devices, non-volatile computer storage media provided in the embodiments of this specification correspond to the methods. Therefore, the devices, electronic devices, and non-volatile computer storage media also have beneficial technical effects similar to the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the corresponding devices, electronic devices, and non-volatile computer storage media will not be elaborated here.

[0106] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) or software improvements (improvements to method flows). However, with the development of technology, many method flow improvements today can be regarded as direct improvements to hardware circuit structures. Almost all designers obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement to a method flow cannot be implemented using a hardware entity module. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is an integrated circuit whose logical function is determined by the user programming the device. Designers can program themselves to "integrate" a digital system onto a single PLD, without having to ask a chip manufacturer to design and fabricate a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compiler used in program development and writing. The original code before compilation also has to be written in a specific programming language, which is called a Hardware Description Language (HDL), and there is not just one type of HDL, but many, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. Currently, the most commonly used are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also be aware that by simply performing a little logical programming on the method flow using the above-mentioned several hardware description languages and programming it into an integrated circuit, it is easy to obtain the hardware circuit that implements the logical method flow.

[0107] The controller can be implemented in any suitable manner. For example, the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program code (such as software or firmware) executable by the (micro)processor, logic gates, switches, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of the controller include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that, in addition to implementing the controller in the form of pure computer-readable program code, it is entirely possible to logically program the method steps to enable the controller to be implemented in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. to achieve the same function. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be regarded as the structures within the hardware component. Or even, the devices for implementing various functions can be regarded as either software modules for implementing the method or the structures within the hardware component.

[0108] The systems, devices, modules, or units illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0109] For the convenience of description, when describing the above devices, they are described separately as various units according to their functions. Of course, when implementing one or more embodiments of this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0110] Those skilled in the art should understand that the embodiments of this specification can be provided as a method, a system, or a computer program product. Therefore, the embodiments of this specification can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0111] This specification is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the specification. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general purpose computers, special purpose computers, embedded processors, or other programmable data processing devices to produce a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices produce means for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in one block or multiple blocks.

[0112] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufacture including instruction means that implement the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in one block or multiple blocks.

[0113] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in one block or multiple blocks.

[0114] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0115] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash RAM. The memory is an example of computer-readable media.

[0116] A computer-readable medium includes both permanent and non-permanent, removable and non-removable media and can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to store information accessible by a computing device. As defined herein, a computer-readable medium does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0117] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0118] This specification can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The specification can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0119] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and reference can be made to the corresponding parts of the method embodiments for relevant details.

[0120] The above is only for the embodiments of this specification and is not intended to limit one or more embodiments of this specification. For those skilled in the art, various changes and modifications can be made to one or more embodiments of this specification. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included within the scope of the claims of one or more embodiments of this specification. One or more embodiments of this specification, one or more embodiments of this specification, one or more embodiments of this specification, one or more embodiments of this specification.

Claims

1. A method for rapid classification of mass spectrometry peaks, characterized in that, it includes the following steps: Obtain a number of mass spectrometry peak sample data fed back by a mass spectrometer; Use the brain-state-in-a-box model to cluster the number of sample data; The brain-state-in-a-box model equation is as follows: y(n) = x(n) + βWx(n) (1) where \(x(n)\) is the state vector; \(\beta\) is a positive constant, namely the feedback coefficient; \(W\) is the weight matrix of the single-layer linear neural network; \(y(n)\) is the intermediate vector of the generated system state vector; is a non-linear vector function, namely the activation function; When using the brain-state-in-a-box model to cluster the number of sample data, it includes the steps: S201: Obtain a training set for training the in-box brain state model, where the training set is a classified standard mass spectrometry peak {a 1 , a 2 , …, a M}; and initialize the weight matrix: W 0 = I, where I is the identity matrix; S202: Update the weight matrix according to formula (6), where a k is the k-th element of the training set {a 1 , a 2 , …, a M}, η is a positive constant; W k-1 is the weight matrix generated in the previous iteration, and W k is the weight matrix updated in this iteration; S203: When k = M, execute W = W M , and enter S204; when k < M, return to S202; S204: Assign the initial state x(0) of the system to the collected mass spectrometry peak vector x(n), and enter S205; S205: Substitute W, β, x(n) into the following formula: y(n) = x(n) + βWx(n) (1) S206: When ||x(n + 1) - x(n)|| ≤ ε, enter S207; where: x(n + 1) is the current system state vector, x(n) is the system state vector of the previous iteration, and ε is the threshold constant; S207: Compare the final system state x(n+1) generated in S206 with the training set {a 1 , a 2 , …, a M}. When ||x(n+1) - a k || ≤ ε, the mass spectrometry peak x belongs to the type to which a k belongs. If ||x(n+1) - a k || > ε for x(n+1) and all elements of the training set, the mass spectrometry peak x does not belong to any type included in the training set.

2. The method for rapid classification of mass spectrometry peaks according to claim 1, characterized in that, the activation function is defined as follows:

3. The method for rapid classification of mass spectrometry peaks according to claim 1, characterized in that, in S206, when ||x(n + 1) - x(n)|| > ε, return to S205.

4. A device for rapid classification of mass spectrometry peaks, characterized in that, it includes: An acquisition unit configured to obtain a number of mass spectrometry peak sample data fed back by a mass spectrometer; A processing unit configured to use the brain-state-in-a-box model to cluster a number of sample data; The brain-state-in-a-box model equation is as follows: y(n) = x(n) + βWx(n) (1) where \(x(n)\) is the state vector; \(\beta\) is a positive constant, i.e., the feedback coefficient; \(W\) is the weight matrix of the single-layer linear neural network; \(y(n)\) is the intermediate vector of the generated system state vector; is a non-linear vector function, i.e., the activation function; When using the brain-state-in-a-box model to cluster the number of sample data, it includes the steps: S201: Obtain a training set for training the in-box brain state model, where the training set is a classified standard mass spectrometry peak {a 1 , a 2 , …, a M}; and initialize the weight matrix: W 0 = I, where I is the identity matrix; S202: Update the weight matrix according to formula (6), where a k is the k-th element of the training set {a 1 , a 2 , …, a M}, η is a positive constant; W k-1 is the weight matrix generated in the previous iteration, and W k is the weight matrix updated in this iteration; S203: When k = M, execute W = W M , and enter S204; when k < M, return to S202; S204: Assign the initial state x(0) of the system to the collected mass spectrometry peak vector x(n), and enter S205; S205: Substitute W, β, x(n) into the following formula: y(n) = x(n) + βWx(n) (1) S206: When ||x(n + 1) - x(n)|| ≤ ε, enter S207; where: x(n + 1) is the current system state vector, x(n) is the system state vector of the previous iteration, and ε is the threshold constant; S207: Compare the final system state x(n + 1) generated in S206 with the training set {a 1 , a 2 , …, a M}. When ||x(n + 1) - a k || ≤ ε, the mass spectrometry peak x belongs to the type to which a k belongs. If ||x(n + 1) - a k || > ε for x(n + 1) and all elements of the training set, the mass spectrometry peak x does not belong to any type included in the training set.

5. A device for rapid classification of mass spectrometry peaks, characterized in that, it includes: A memory on which program code is stored; A processor connected to the memory, and when the program code is executed by the processor, the method described in any one of claims 1 to 3 is implemented.

6. A computer-readable storage medium, characterized in that, program instructions are stored thereon, and when the program instructions are executed, the method for rapid classification of mass spectrometry peaks described in any one of claims 1 - 3 is implemented.

7. A mass spectrometry peak classification system, characterized in that, it includes the device for rapid classification of mass spectrometry peaks described in claim 4 or 5; the device for rapid classification of mass spectrometry peaks is connected to a display device.

Images