Paper-based gene chip sample application method and device, storage medium and equipment

Abstract

The invention provides a paper-based gene chip sample application method and device, a storage medium and equipment, the method is applied to an ink-jet sample application system, the ink-jet sample application system obtains incoming material quality control data of a paper-based gene chip to be subjected to sample application from a manufacturing execution system, target chip features are extracted from the incoming material quality control data, and the target chip features are applied to a paper-based gene chip sample application system. The target chip features are input into a pre-trained parameter generation model, the parameter generation model predicts optimal sample application parameters according to the chip features, and then an ink-jet printing head is controlled to carry out sample application on the paper-based gene chip according to the sample application parameters generated by the parameter generation model. Therefore, the AI technology is utilized to dynamically adjust the sample application parameters according to the characteristics of the chip, the sample application quality is improved, the requirement of manual intervention is reduced, and the working efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of gene chip technology, and in particular to a paper-based gene chip spotting method, device, storage medium and equipment. Background Art

[0002] As a high-throughput DNA analysis and detection method, gene chips are widely used in gene expression, disease diagnosis, drug screening and other fields. The spotting process is a key step in gene chip experiments, which directly affects the signal strength and data quality of the chip. Paper-based gene chips are gene chips made of paper-based materials. The characteristics of paper-based gene chips, such as uneven thickness and pore size, can easily limit the spotting accuracy. The traditional solution mainly addresses this problem by manually adjusting the control parameters. However, this method is highly dependent on the operator's experience. In most scenarios, the spotting quality and work efficiency are low. Summary of the Invention

[0003] The purpose of this application is to provide a paper-based gene chip spotting method, device, storage medium and equipment, aiming to solve the problems of the paper-based gene chip spotting method in the related art that is highly dependent on the operator's experience and has low spotting quality and work efficiency.

[0004] In a first aspect, the present application provides a paper-based gene chip spotting method, which is applied to an inkjet spotting system; the method comprises: obtaining incoming quality control data of a paper-based gene chip to be spotted from a manufacturing execution system, and extracting target chip features from the incoming quality control data; processing the target chip features through a pre-trained parameter generation model to generate target spotting parameters; during the training process, the parameter generation model learns to predict the optimal spotting parameters based on the input chip features; and according to the target spotting parameters, controlling the inkjet print head of the inkjet spotting system to spot the paper-based gene chip.

[0005] In the above implementation process, a method for spotting paper-based gene chips in an inkjet spotting system is provided. In this method, incoming quality control data of the paper-based gene chips to be spotted is obtained from the manufacturing execution system. Target chip features are extracted from this incoming quality control data. These target chip features are then input into a pre-trained parameter generation model. The parameter generation model then predicts optimal spotting parameters based on the chip features. The inkjet printhead is then controlled to spot the paper-based gene chips based on the spotting parameters generated by the parameter generation model. In this way, AI technology is used to dynamically adjust spotting parameters based on chip characteristics, improving spotting quality, reducing the need for manual intervention, and thus increasing work efficiency.

[0006] Furthermore, in some examples, before extracting the target chip features from the incoming material quality control data, the process includes: cleaning and standardizing the incoming material quality control data.

[0007] In the above implementation process, after obtaining the IQC data from the MES system, the IQC data is preprocessed, including data cleaning and standardization, which can improve the data quality and thus improve the accuracy of subsequent model analysis.

[0008] Furthermore, in some examples, the target chip characteristics include at least one of the following: porosity, pore size, surface roughness, droplet magnification factor; and the spotting parameters include: driving voltage, droplet volume, and ejection frequency.

[0009] In the above implementation process, options for key features characterizing the characteristics of the paper-based gene chip are provided, and at least one of porosity, pore size, surface roughness and droplet magnification factor is selected as the target chip feature to generate target spotting parameters, which can improve the spotting effect; at the same time, options for important control parameters of the inkjet print head are provided. During spotting, the driving voltage, droplet volume and ejection frequency of the inkjet print head are dynamically adjusted according to the characteristics of the paper-based gene chip to ensure that the volume and shape of the droplets ejected each time meet the requirements.

[0010] Furthermore, in some examples, the parameter generation model includes a decision tree model; the decision tree model is used to predict a droplet driving waveform pattern based on input chip characteristics; the droplet driving waveform pattern corresponds to a set of spotting parameters.

[0011] In the above implementation process, the decision tree model is used to predict the optimal spotting parameters according to the chip characteristics, which can effectively improve the spotting quality.

[0012] Furthermore, in some examples, controlling the inkjet print head of the inkjet spotting system to spot the paper-based gene chip according to the target spotting parameters includes: transmitting the target spotting parameters to a data filtering module of the inkjet spotting system, so that the data filtering module converts the target spotting parameters into a waveform signal recognizable by the inkjet print head of the inkjet spotting system, and then transmitting the waveform signal to the inkjet print head, so that the inkjet print head spots the paper-based gene chip according to the waveform signal.

[0013] In the above implementation process, the data filtering module is made independent, and the target sampling parameters generated by AI are passed to the data filtering module, which converts them into waveform signals that can be recognized by the inkjet print head. This can reduce the coupling between the print head and the system, reduce the complexity of system integration and maintenance, and thus reduce development and maintenance costs.

[0014] Furthermore, in some examples, the process by which the data filtering module converts the target spotting parameters into waveform signals recognizable by the inkjet print head of the inkjet spotting system includes: loading a configuration file of the inkjet print head; recording the waveform parameters and hardware limitations supported by the inkjet print head in the configuration file; dynamically loading a driver module corresponding to the inkjet print head according to the configuration file; retrieving the waveform parameters corresponding to the target spotting parameters in the configuration file, and verifying the retrieved waveform parameters; and when the waveform parameters pass the verification, calling the driver module to generate a waveform signal.

[0015] In the above implementation process, a specific method for parameter conversion is provided for the data filtering module. Through the plug-in driver architecture, adding a new print head only requires adding a configuration file and a driver module, without modifying the core code. Moreover, through the combination of configuration files and driver plug-ins, new models of print heads can be quickly adapted, so that it can be suitable for production environments where multiple models of print heads coexist.

[0016] Furthermore, in some examples, the method further includes: monitoring the spraying state of each droplet in real time; the spraying state includes the droplet shape, volume, and position; and outputting an alarm signal if the monitoring result indicates an abnormal spraying state.

[0017] In the above implementation process, the gene chip spotting process is quality monitored, and the injection status of each droplet is monitored in real time, including the droplet shape, volume and position. If an abnormal injection status is detected, an alarm signal is immediately issued. In this way, the operator can take corresponding treatment measures for the abnormal situation in a timely manner, thereby improving the sampling quality.

[0018] Furthermore, in some examples, the method further includes: recording the target chip characteristics, the target spotting parameters, and the monitoring results after associating them, and uploading the recorded data to the manufacturing execution system.

[0019] During the above implementation process, the system can record the injection data of each droplet, such as position, volume and shape, in combination with the chip characteristics and sampling parameters corresponding to the current sampling process, to facilitate subsequent analysis and optimization. This data can also be uploaded to the MES system for production management and quality traceability.

[0020] Furthermore, in some examples, the method further includes: adding qualified data from the recorded data to a training set of the parameter generation model; and periodically retraining the parameter generation model using the latest accumulated training set.

[0021] In the above implementation, the parameter generation model can be trained online using an incremental learning approach. Whenever a new sampling task is completed and feedback data is obtained, qualified data from this data is immediately added to the training set. The model is then periodically retrained using the latest accumulated training set to capture the latest pattern changes. This improves model performance and contributes to improved sampling quality.

[0022] In a second aspect, the present application provides a paper-based gene chip spotting device, which is applied to an inkjet spotting system; the device includes: an acquisition module, which is used to obtain incoming quality control data of the paper-based gene chip to be spotted from a manufacturing execution system, and extract target chip features from the incoming quality control data; a generation module, which is used to process the target chip features through a pre-trained parameter generation model to generate target spotting parameters; during the training process, the parameter generation model learns to predict the optimal spotting parameters based on the input chip features; and a control module, which is used to control the inkjet print head of the inkjet spotting system to spot the paper-based gene chip according to the target spotting parameters.

[0023] In a third aspect, the present application provides an electronic device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in any one of the first aspects when executing the computer program.

[0024] In a fourth aspect, the present application provides a computer-readable storage medium having instructions stored thereon. When the instructions are executed on a computer, the computer executes the method as described in any one of the first aspects.

[0025] In a fifth aspect, the present application provides a computer program product, which, when running on a computer, enables the computer to execute the method as described in any one of the first aspects.

[0026] Other features and advantages disclosed in the present application will be described in the following description, or some features and advantages can be inferred or determined without doubt from the description, or can be learned by implementing the above-mentioned technology disclosed in the present application.

[0027] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0029] Figure 1 A flow chart of a paper-based gene chip spotting method provided in an embodiment of the present application;

[0030] Figure 2 A schematic diagram of the architecture of a spotting system for implementing a non-contact spotting solution for a paper-based gene chip based on an inkjet print head provided in an embodiment of the present application;

[0031] Figure 3 A schematic diagram of the structure of a data filter module provided in an embodiment of the present application;

[0032] Figure 4 A block diagram of a paper-based gene chip spotting device provided in an embodiment of the present application;

[0033] Figure 5 This is a structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0034] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0035] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0036] Paper-based gene chips are made from paper-based materials. Currently, the spotting process for paper-based gene chips is generally achieved using contact-based spotting technology called reverse dot hybridization. This technology offers advantages such as relatively simple operation and low equipment costs, but its limitations and potential problems should not be ignored. For example, differences in the characteristics of paper-based gene chips, such as uneven thickness and pore size, can easily limit spotting accuracy. This technology is typically implemented through manual adjustment of control parameters to address this issue. However, this approach is highly dependent on operator experience and is prone to human error, resulting in poor spotting quality. Furthermore, manual adjustments require repeated testing and verification, leading to low work efficiency.

[0037] To address the above issues, the present invention provides a paper-based gene chip spotting solution. This solution obtains incoming quality control data for paper-based gene chips from a manufacturing execution system (MES). The target chip features are extracted from this incoming quality control data and input into an AI model. The AI ​​model then predicts optimal spotting parameters based on the chip characteristics, and the inkjet printhead then performs the spotting operation according to these parameters. In this way, AI technology dynamically adjusts spotting parameters based on chip characteristics, improving spotting quality, reducing the need for manual intervention, and thus increasing work efficiency.

[0038] Next, the embodiments of the present application are introduced:

[0039] like Figure 1 As shown, Figure 1 This is a flow chart of a paper-based gene chip spotting method provided in an embodiment of the present application. The method is applied to an inkjet spotting system. A core component of the inkjet spotting system is an inkjet print head, which is responsible for spraying the biomolecule solution in the form of extremely small droplets onto the paper-based gene chip to achieve gene chip spotting. In this embodiment, the inkjet print head can be driven by piezoelectricity, which can achieve non-contact spotting to eliminate scratches or other forms of physical damage on the chip surface caused by physical contact, avoid cross-contamination between different samples, and thus improve the accuracy and reliability of the experimental results.

[0040] The method comprises:

[0041] Step 101: Obtaining incoming quality control data of a paper-based gene chip to be spotted from a manufacturing execution system, and extracting target chip features from the incoming quality control data;

[0042] Incoming quality control (IQC) is the process by which companies conduct quality inspections and controls on raw materials, components, or products provided by suppliers. In this embodiment, the IQC data for paper-based gene chips refers to the data collected from IQC of experimental materials and equipment before conducting gene chip experiments. During implementation, after the inkjet spotting system is started and initialized, it can be connected to the Manufacturing Execution System (MES) through a network interface to obtain the relevant IQC data of the paper-based gene chip to be spotted, and then extract the key features that characterize the characteristics of the paper-based gene chip, namely the target chip features.

[0043] In some embodiments, before extracting target chip features from incoming quality control data, the process may include cleaning and standardizing the incoming quality control data. Specifically, after acquiring IQC data from the MES system, the data is preprocessed. This preprocessing includes data cleaning and standardization. Data cleaning removes duplicate data and corrects errors and missing values, thereby ensuring data accuracy. Data standardization converts data in different units, formats, or ranges into a unified format, making the data more uniform, comparable, and easier to process. This improves data quality and, consequently, the accuracy of subsequent model analysis.

[0044] In some embodiments, the target chip characteristics mentioned in this step may include at least one of the following: porosity, pore size, surface roughness, and droplet magnification factor. During spotting, these characteristics directly impact the deposition, diffusion, and fixation of droplets ejected by the inkjet printhead, thereby affecting spotting accuracy, resolution, and functional performance. Therefore, selecting at least one of these characteristics as the target chip characteristic and using them to generate target spotting parameters can improve spotting performance. Of course, in other embodiments, the target chip characteristics may also include other characteristics, such as chip thickness, density, etc.

[0045] Step 102: Process the target chip features using a pre-trained parameter generation model to generate target spotting parameters; during the training process, the parameter generation model learns to predict optimal spotting parameters based on the input chip features;

[0046] In this embodiment, an AI model is trained to generate optimal spotting parameters based on the chip characteristics of the paper-based gene chip. The spotting parameters here can be considered as control parameters of the inkjet print head of the inkjet spotting system. When there is a new spotting task, the system can use the AI ​​model to process the extracted target chip features, thereby generating target spotting parameters suitable for the paper-based gene chip to be spotted.

[0047] In some embodiments, the spotting parameters mentioned in this step may include drive voltage, droplet volume, and jetting frequency. These parameters are important control parameters for the inkjet printhead. During spotting, the drive voltage, droplet volume, and jetting frequency of the inkjet printhead are dynamically adjusted based on the characteristics of the paper-based gene chip to ensure that the droplet volume and shape of each jet meet the requirements.

[0048] Furthermore, in some embodiments, the parameter generation model mentioned in this step may include a decision tree model; the decision tree model is used to predict a droplet drive waveform pattern based on the input chip characteristics; the droplet drive waveform pattern corresponds to a set of spotting parameters. The decision tree model is a supervised learning algorithm based on a tree structure for decision-making and prediction. Its core idea is to simulate the human decision-making process, decompose complex problems into a series of simple judgments (nodes), and ultimately form an intuitive decision path. During implementation, a decision tree model is trained using historical data and expert knowledge. Since the output of the decision tree model is usually a single target value, different drive voltages, droplet volumes, and spray frequencies are combined into multiple droplet drive waveform patterns. For example, multiple droplet drive waveform patterns include fire1 mode, fire2 mode, fire3 mode, etc., where fire3 mode corresponds to a droplet volume of 12pL, a drive voltage of 20V, and a spray frequency of 10kHz. In this way, based on the trained decision tree model, the optimal spotting parameters can be generated according to the chip characteristics. The specific model training process can be found in the introduction of the training method of the decision tree model in the relevant technology, and this application will not go into details here.

[0049] Step 103: Control the inkjet print head of the inkjet spotting system to spot the paper-based gene chip according to the target spotting parameters.

[0050] In this embodiment, after the optimal spotting parameters are generated by the AI ​​algorithm, the control system of the inkjet spotting system controls the inkjet print head to perform the spotting operation according to the spotting parameters. The spotting parameters are dynamically optimized based on the characteristics of the paper-based gene chip to be spotted, and thus can effectively improve the spotting accuracy and improve the spotting quality.

[0051] In some embodiments, this step may include: passing the target spotting parameters to the data filtering module of the inkjet spotting system, so that the data filtering module converts the target spotting parameters into a waveform signal recognizable by the inkjet print head of the inkjet spotting system, and then passes the waveform signal to the inkjet print head, so that the inkjet print head spots the paper-based gene chip according to the waveform signal. The data filtering (Fliter) module here can be an independent software module or circuit board block. The control system passes the target spotting parameters to the data filtering module, which converts them into a waveform signal recognizable by the inkjet print head to ensure that the inkjet print head can execute correctly. In this process, by making the data filtering module independent, the coupling between the print head and the system can be reduced, the complexity of system integration and maintenance can be reduced, and thus the development and maintenance costs can be reduced.

[0052] Furthermore, in some embodiments, the process of the data filtering module converting the target dot pattern parameters into a waveform signal recognizable by the inkjet print head of the inkjet dot pattern system may include: loading a configuration file of the inkjet print head; recording the waveform parameters and hardware limitations supported by the inkjet print head in the configuration file; dynamically loading a driver module corresponding to the inkjet print head according to the configuration file; retrieving the waveform parameters corresponding to the target dot pattern parameters from the configuration file and verifying the retrieved waveform parameters; and when the waveform parameters pass the verification, calling the driver module to generate the waveform signal. In other words, when converting the parameters, the data filtering module may first load the configuration file of the inkjet print head to obtain the waveform parameters and hardware limitations supported by the target dot pattern parameters, then dynamically load the corresponding driver module, input the dot pattern parameters generated by the AI, and retrieve the corresponding waveform parameters from the configuration file. The waveform parameters here may include voltage and pulse width. Based on the retrieval results, the data filtering module verifies whether the voltage is within a preset voltage range and whether the pulse width is within a preset pulse width range. If the verification passes, the driver module is called to generate the waveform signal. Otherwise, an error message is displayed to avoid damage to the print head. In this way, through the plug-in driver architecture, adding a new print head only requires adding a configuration file and a driver module, without modifying the core code. Moreover, through the combination of configuration files and driver plug-ins, new models of print heads can be quickly adapted, making it suitable for production environments where multiple models of print heads coexist.

[0053] In order to enrich and enhance the functions of the inkjet spotting system, this application also provides the following improvements:

[0054] In some embodiments, the system may further include: real-time monitoring of the ejection state of each droplet; the ejection state includes the droplet shape, volume, and position; and outputting an alarm signal if the monitoring result indicates an abnormal ejection state. That is, the inkjet spotting system may be integrated with a camera to monitor the quality of the gene chip spotting process. During implementation, the inkjet spotting system may monitor the ejection state of each droplet in real time, including the droplet shape, volume, and position. The droplet shape may be expressed as circularity, aspect ratio, etc., the droplet shape may be estimated through image analysis, and the droplet position may be represented by X and Y coordinates. If an abnormal ejection state is detected, such as a droplet deviating from the target position or an irregular droplet shape, the control system immediately issues an alarm signal. This allows the operator to promptly take appropriate measures to address the abnormality, thereby improving the spotting quality.

[0055] Furthermore, some embodiments may also include correlating the target chip characteristics, target spotting parameters, and monitoring results, recording the data, and uploading the recorded data to the manufacturing execution system. In other words, the system can record the ejection data of each droplet, such as position, volume, and shape, in conjunction with the chip characteristics and spotting parameters corresponding to the current spotting process, to facilitate subsequent analysis and optimization. This data can also be uploaded to the MES system for production management and quality traceability.

[0056] In addition, some embodiments may also include: adding qualified data from the recorded data to the training set of the parameter generation model; and regularly retraining the parameter generation model using the latest accumulated training set. In other words, the parameter generation model can be trained online using an incremental learning approach. Whenever a new spotting task is completed and feedback data is obtained, qualified data from the data is immediately added to the training set. The model is then regularly retrained using the latest accumulated training set to capture the latest pattern changes. This improves model performance and facilitates improved spotting quality.

[0057] An embodiment of the present application provides a method for spotting paper-based gene chips in an inkjet spotting system. In this method, incoming quality control data for the paper-based gene chips to be spotted is obtained from a manufacturing execution system. Target chip features are extracted from this incoming quality control data. These target chip features are then input into a pre-trained parameter generation model. The parameter generation model then predicts optimal spotting parameters based on the chip features. The inkjet printhead is then controlled to spot the paper-based gene chips based on the spotting parameters generated by the parameter generation model. In this way, AI technology is used to dynamically adjust spotting parameters based on chip characteristics, improving spotting quality and reducing the need for manual intervention, thereby increasing work efficiency.

[0058] In order to explain the solution of this application in more detail, a specific embodiment is introduced below:

[0059] This embodiment provides a non-contact spotting solution for paper-based gene chips based on an inkjet print head. The architecture of the spotting system involved in this solution is as follows: Figure 2As shown, the spotting system includes an inkjet print head 21, an ink supply system 22, a motion control platform 23, a control system 24, and a data filter module 25. The control system 24 integrates an MES system 26 and an AI module 27. The inkjet print head 21 uses a piezoelectric drive to achieve non-contact spotting; the ink supply system 22 has a built-in circulating liquid supply device to ensure solution stability. During the sample preparation stage, DNA probe solutions of different concentrations need to be prepared and loaded into the ink supply system 22; the motion control platform 23 is a high-precision XY motion platform that can accurately control the spotting position. In this embodiment, the experimental equipment also includes a paper-based gene chip, which is a carrier for spotting.

[0060] The workflow of this program includes:

[0061] S201, system startup and initialization;

[0062] Specifically, the user starts the entire device through the control panel or remote control system, and the device self-test program begins to check the status of various subsystems, such as the inkjet print head 21, the ink supply system 22, the motion control platform 23, etc., to ensure that all components are working properly;

[0063] During the initialization phase, the inkjet print head 21 is automatically cleaned and calibrated to ensure that each nozzle is unobstructed and the initial voltage waveform parameters are adjusted. The ink supply system 22 is activated, and the built-in pump begins to operate to ensure that the biomolecule solution is evenly distributed in the liquid reservoir and that impurities are removed through the filter. The motion control platform is reset to zero, and the servo motor and encoder are calibrated to ensure the accuracy of subsequent motion control.

[0064] S202, obtaining IQC data, AI identification and generating sampling parameters;

[0065] Specifically, the system is connected to the MES system 26 through a network interface to obtain relevant IQC data of the paper-based gene chip to be spotted. In one experiment, the paper-based gene chip has the following characteristics: a high porosity of 65%; a large pore size of 8 μm; a low surface roughness of 2 μm; and a droplet magnification factor of 5;

[0066] Based on the above IQC data, AI module 27 performs the following processing: cleaning and standardizing the IQC data; extracting key features such as porosity, pore size, surface roughness, and droplet magnification factor from the pre-processed IQC data; processing the extracted key features based on a trained decision tree model to generate target spotting parameters. The decision tree model is trained using historical data and expert knowledge, and can predict optimal spotting parameters based on chip characteristics. In this way, AI module 27 can determine whether to increase the droplet volume to ensure adequate coverage based on the chip's porosity, pore size, surface roughness, and droplet magnification factor.

[0067] The output of the decision tree model can be a droplet driving waveform pattern, which can correspond to a set of sampling parameters. For example, if the droplet driving waveform pattern output by the decision tree model is fire3 mode, it means that the droplet volume is 12pL, the driving voltage is 20V, and the spraying frequency is 10kHz.

[0068] S203, converting the number of dots and performing the dotting operation;

[0069] Specifically, the AI ​​module 27 sends the generated optimal sampling parameters to the data filter module 25, which converts them into driving waveforms that can be recognized by the inkjet print head 21. The structure of the data filter module 25 is as follows: Figure 3 As shown, it includes a configuration management submodule 31, a driver plug-in submodule 32, a parameter conversion submodule 33 and a waveform generation submodule 34, wherein:

[0070] The configuration management submodule 31 is used to load the configuration file of the inkjet print head 21, which includes the waveform parameters and hardware limitations supported by the print head;

[0071] The driver plug-in submodule 32 is used to dynamically load the corresponding driver module according to the driver type in the configuration file. For example, if the inkjet print head 21 is a Kyocera model KJ4B, if the value of the drive_type field in the configuration file is "FPGA_A", then FPGA_Driver_A is loaded to generate a dedicated protocol waveform signal for the Kyocera model KJ4B. If the value of the drive_type field in the configuration file is "UNIVER_I2C", then UNIVER_I2C is loaded to generate an I2C standard communication method to drive the print head.

[0072] The parameter conversion submodule 33 is used to retrieve and verify the corresponding waveform parameters in the configuration file based on the sampling parameters generated by the AI ​​module 27. The waveform parameters include voltage and pulse width. The parameter conversion submodule 33 verifies whether the retrieved voltage is within the range of [10V, 30V] and whether the pulse width is within the range of [1μs, 3μs]. If so, the verification passes.

[0073] The waveform generation submodule 34 is used to implement protocol adaptation and real-time output of the waveform signal. When the parameter verification passes, the driver module is called to generate the waveform signal. If drive_type = UNIVER_I2C, the waveform generation submodule 34 sends the waveform signal to the inkjet print head 21 via the I2C standard communication method. If drive_type = FPGA_A, the FPGA hardware module converts the waveform signal into a level signal that can be recognized by the inkjet print head 21 and sends it to the inkjet print head 21.

[0074] During the spotting process, the data filter module 25 issues a command, and the piezoelectric element of the inkjet print head 21 is electrically deformed, squeezing the liquid in the liquid storage chamber to form tiny droplets. The droplets are sprayed to the predetermined location in a non-contact manner, avoiding mechanical damage and cross contamination. The multiple nozzles of the inkjet print head 21 operate simultaneously, and the spraying time and frequency of each nozzle are independently controlled to ensure that each droplet lands accurately at the predetermined location.

[0075] At the same time, the motion control platform 23 accurately moves the inkjet print head 21 according to the preset path. The servo motor and encoder provide real-time feedback of position information. The control system 24 dynamically adjusts the position of the inkjet print head 21 based on the feedback information to ensure high-precision printing.

[0076] S204, quality monitoring and feedback;

[0077] Specifically, the system integrates a camera to monitor the spray status of each droplet in real time, including its shape, volume, and position, to analyze the spotting effect. If an abnormality is detected, such as a droplet deviating from the target position or an irregular droplet shape, the control system 24 immediately issues an alarm signal;

[0078] For each spotting task, the control system 24 automatically records the following information: droplet position, droplet volume, droplet shape, timestamp, porosity, pore size, surface roughness, droplet magnification factor, parameter settings used (such as Fire3 mode), and information indicating whether the spotting effect is qualified. The control system 24 uploads this data to the MES system 26 for production management and quality traceability. After the spotting task is completed and feedback data is obtained, the control system 24 adds the qualified data to the training set and regularly retrains the decision tree model using the latest accumulated training set.

[0079] This embodiment has at least the following advantages: by adopting non-contact inkjet print head technology and combining it with an intelligent control system, the accuracy, efficiency, and reliability of paper-based gene chip preparation can be significantly improved, which not only reduces errors caused by human operation but also improves overall work efficiency; the data filter module is used as an independent software module or circuit board block to reduce the coupling between the print head and the system, which can achieve rapid switching of print heads of different brands and performances, thereby improving system versatility and development efficiency.

[0080] Corresponding to the embodiments of the aforementioned method, the present application also provides embodiments of a paper-based gene chip spotting device and a terminal for its application:

[0081] like Figure 4 As shown, Figure 4 This is a block diagram of a paper-based gene chip spotting device provided in an embodiment of the present application, which is applied to an inkjet spotting system; the device includes:

[0082] An acquisition module 41 is configured to acquire incoming quality control data of a paper-based gene chip to be spotted from a manufacturing execution system, and extract target chip features from the incoming quality control data;

[0083] The generation module 42 is used to process the target chip characteristics through a pre-trained parameter generation model to generate target spotting parameters; during the training process, the parameter generation model learns to predict the optimal spotting parameters based on the input chip characteristics;

[0084] The control module 43 is used to control the inkjet print head of the inkjet spotting system to spot the paper-based gene chip according to the target spotting parameters.

[0085] The implementation process of the functions and effects of each module in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.

[0086] This application also provides an electronic device, see Figure 5 , Figure 5 This is a block diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include a processor 510, a communication interface 520, a memory 530, and at least one communication bus 540. The communication bus 540 is used to enable direct communication between these components. The communication interface 520 of the electronic device in this embodiment of the present application is used to communicate signaling or data with other node devices. The processor 510 may be an integrated circuit chip with signal processing capabilities.

[0087] The processor 510 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor, or the processor 510 can also be any conventional processor.

[0088] The memory 530 may be, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc. The memory 530 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 510, the electronic device can perform the above-mentioned operations. Figure 1 The various steps involved in the method embodiment.

[0089] Optionally, the electronic device may further include a storage controller and an input / output unit.

[0090] The memory 530, storage controller, processor 510, peripheral interface, and input / output units are electrically connected to each other directly or indirectly to enable data transmission or interaction. For example, these components can be electrically connected to each other via one or more communication buses 540. The processor 510 is used to execute executable modules stored in the memory 530, such as software function modules or computer programs included in the electronic device.

[0091] The input and output unit is used to provide users with the ability to create tasks and to create optional time periods or preset execution times for the tasks to enable interaction between the user and the server. The input and output unit can be, but is not limited to, a mouse and a keyboard.

[0092] I understand. Figure 5 The structure shown is only for illustration, and the electronic device may also include Figure 5 More or fewer components than shown, or with Figure 5 Different configurations shown. Figure 5 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0093] An embodiment of the present application further provides a storage medium having instructions stored thereon. When the instructions are run on a computer, the computer program is executed by a processor to implement the method described in the method embodiment. To avoid repetition, details are not given here.

[0094] The present application also provides a computer program product, which, when running on a computer, enables the computer to execute the method described in the method embodiment.

[0095] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions and operations of the devices, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0096] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0097] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0098] The foregoing is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included within the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined or explained in subsequent figures.

[0099] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

[0100] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

Claims

1. A paper-based gene chip spotting method, characterized in that: Applied to an inkjet spotting system; the method comprises: Obtaining incoming quality control data of a paper-based gene chip to be spotted from a manufacturing execution system, and extracting target chip features from the incoming quality control data; The target chip features are processed by a pre-trained parameter generation model to generate target spotting parameters; during the training process, the parameter generation model learns to predict the optimal spotting parameters based on the input chip features; According to the target spotting parameters, the inkjet print head of the inkjet spotting system is controlled to spot the paper-based gene chip.

2. The method according to claim 1, characterized in that Before extracting the target chip features from the incoming material quality control data, the method includes: The incoming material quality control data is cleaned and standardized.

3. The method according to claim 1, characterized in that The target chip characteristics include at least one of the following: Porosity, pore size, surface roughness, droplet magnification factor; The spotting parameters include: driving voltage, droplet volume and spraying frequency.

4. The method according to claim 3, characterized in that The parameter generation model includes a decision tree model; the decision tree model is used to predict a droplet driving waveform pattern according to input chip characteristics; the droplet driving waveform pattern corresponds to a set of spot sampling parameters.

5. The method according to claim 3, characterized in that The step of controlling the inkjet print head of the inkjet spotting system to spot the paper-based gene chip according to the target spotting parameters comprises: The target spotting parameters are transmitted to a data filtering module of the inkjet spotting system, so that the data filtering module converts the target spotting parameters into a waveform signal recognizable by an inkjet print head of the inkjet spotting system, and then transmits the waveform signal to the inkjet print head, so that the inkjet print head spots the paper-based gene chip according to the waveform signal.

6. The method according to claim 5, characterized in that The process of converting the target spotting parameters into a waveform signal recognizable by the inkjet print head of the inkjet spotting system by the data filtering module includes: Loading a configuration file of the inkjet print head; wherein the configuration file records waveform parameters and hardware limitations supported by the inkjet print head; Dynamically loading a driver module corresponding to the inkjet print head according to the configuration file; Retrieving waveform parameters corresponding to the target sampling parameters in the configuration file, and verifying the retrieved waveform parameters; When the waveform parameters pass the verification, the driving module is called to generate a waveform signal.

7. The method according to claim 1, characterized in that The method further comprises: Real-time monitoring of the spraying state of each droplet; the spraying state includes the droplet shape, volume and position; If the monitoring result shows that an abnormal injection state exists, an alarm signal is output.

8. The method according to claim 7, characterized in that The method further comprises: The target chip characteristics, the target spotting parameters and the monitoring results are associated and recorded, and the recorded data is uploaded to the manufacturing execution system.

9. The method according to claim 8, characterized in that The method further comprises: adding qualified data from the recorded data to a training set of the parameter generation model; The parameter generation model is retrained periodically using the latest accumulated training set.

10. A paper-based gene chip spotting device, characterized in that: The device is applied to an inkjet spotting system; the device comprises: An acquisition module is used to obtain the incoming quality control data of the paper-based gene chip to be spotted from the manufacturing execution system, and extract the target chip features from the incoming quality control data; A generation module is used to process the target chip features using a pre-trained parameter generation model to generate target spotting parameters; during the training process, the parameter generation model learns to predict the optimal spotting parameters based on the input chip features; The control module is used to control the inkjet printing head of the inkjet spotting system to spot the paper-based gene chip according to the target spotting parameters.

11. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

12. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method according to any one of claims 1 to 9 is implemented.

Images