Automatic control method and device for nucleic acid extraction and library preparation and storage medium

Abstract

The invention relates to the technical field of biological extraction. The invention discloses an automatic control method and device for nucleic acid extraction and library preparation and a storage medium. The method comprises the following steps: acquiring to-be-analyzed process card information; predicting process card prediction information corresponding to nucleic acid extraction and library preparation through the target analytical model; generating a target process flow and target material information from the to-be-analyzed process card information through the process card prediction information; the target technological process is packaged in a segment program to generate a segment program combination file, and the segment program combination file is transmitted to a target module through a bus; and controlling the target module to automatically perform nucleic acid extraction operation or library preparation operation according to the segment program combination file. According to the method, the technological process can be automatically generated, and the accuracy of nucleic acid extraction and library preparation in automatic control is improved.

Description

Technical Field

[0001] The present application relates to the field of biological extraction technology, and in particular to an automated control method, device and storage medium for nucleic acid extraction and library preparation. Background Art

[0002] Traditional nucleic acid extraction and library preparation processes usually require a lot of manual operations. Although many devices have achieved automated operations and the application of fully automatic nucleic acid extraction workstations has greatly simplified the operating process, the work of experimenters in the experiment is still indispensable. In the nucleic acid extraction and library preparation experiments, the experimenter needs to accurately set the operating parameters and extraction schemes of the workstation according to the specific needs of the experiment and the characteristics of the samples. The accurate completion of these steps depends on the experimenter's deep professional knowledge and rich practical experience, resulting in low accuracy of nucleic acid extraction and library preparation in automated control.

[0003] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose an automated control method, device and storage medium for nucleic acid extraction and library preparation, which can automatically generate a process flow and improve the accuracy of nucleic acid extraction and library preparation in automated control.

[0005] To achieve the above objectives, one aspect of the embodiments of the present application provides an automated control method for nucleic acid extraction and library preparation, the method comprising the following steps:

[0006] Get the process card information to be parsed;

[0007] Predicting the process card prediction information corresponding to the nucleic acid extraction and library preparation through the target parsing model;

[0008] Generate target process flow and target material information from the process card information to be analyzed through the process card prediction information;

[0009] Encapsulating the target process flow in a segment program to generate a segment program combination file, and transmitting the segment program combination file to the target module via a bus;

[0010] The target module is controlled according to the segment program combination file to automatically perform nucleic acid extraction operation or library preparation operation.

[0011] In some embodiments, obtaining the process card information to be parsed includes:

[0012] Obtain the process card information uploaded by the experimenter's terminal device;

[0013] Processing the process card information uploaded by the laboratory technician terminal device to obtain the process card information to be parsed;

[0014] The process card information to be analyzed includes: operation method, sample quantity and sample type.

[0015] In some embodiments, the predicting of the process card prediction information corresponding to the nucleic acid extraction and library preparation by the analytical model includes:

[0016] Obtaining the industrial customized process of nucleic acid extraction and library preparation;

[0017] Updating the first historical operation process corresponding to the nucleic acid extraction and library preparation according to the industrial customized process to obtain a second historical operation process;

[0018] The current real-time analytical model is trained by the second historical operation process to obtain a target analytical model;

[0019] The target parsing model is used to predict the process card prediction information corresponding to the nucleic acid extraction and library preparation.

[0020] In some embodiments, the step of generating target process flow and target material information from the process card information to be parsed using the process card prediction information includes:

[0021] Obtaining the standard process of nucleic acid extraction and library preparation according to the process card prediction information;

[0022] Acquire the target process flow according to the standard process and the process card information to be analyzed;

[0023] Acquire target module information and target module position information through the target process flow;

[0024] Integrate the target module information and the target module position information to obtain the material position;

[0025] Determine the type and amount of materials through the target process flow;

[0026] The material position is combined with the material type and usage to obtain the target material information.

[0027] In some embodiments, encapsulating the target process flow into a segment program to generate a segment program combination file includes:

[0028] Splitting the target process flow into target process steps;

[0029] Determining macro variable parameters according to the target process step;

[0030] Generate a preset code instruction through the target process step and the macro variable parameter;

[0031] Generate a segment program corresponding to each target process step according to the preset code instruction;

[0032] The segment program combination file is generated according to all the segment programs.

[0033] In some embodiments, the target module includes: a thermal vibration module, a liquid handling module, a centrifugation module, a magnetic bead or silica bead extraction module, a constant temperature oscillation module, a PMT module, a thermal cycle module, a real-time fluorescence quantitative PCR module, a multifunctional head module, a consumable transfer stacking module or a tip box stacking module.

[0034] In some embodiments, the target material information is displayed through a graphical user interface; the target process flow is displayed through an automated flow chart.

[0035] To achieve the above-mentioned purpose, another aspect of the present application provides an automated control device for nucleic acid extraction and library preparation, the device comprising:

[0036] The first module is used to obtain the process card information to be analyzed;

[0037] The second module is used to predict the process card prediction information corresponding to the nucleic acid extraction and library preparation through the target analysis model;

[0038] The third module is used to generate target process flow and target material information from the process card information to be analyzed through the process card prediction information;

[0039] A fourth module is used to encapsulate the target process flow into a segment program to generate a segment program combination file, and transmit the segment program combination file to the target module through a bus;

[0040] The fifth module is used to control the target module to automatically perform nucleic acid extraction operation or library preparation operation according to the segment program combination file.

[0041] To achieve the above objective, another aspect of the present application provides a computer device, including:

[0042] at least one processor;

[0043] at least one memory for storing at least one program;

[0044] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.

[0045] To achieve the above objective, another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0046] The embodiments of the present application include at least the following beneficial effects: The present application provides an automated control method, device and storage medium for nucleic acid extraction and library preparation. The scheme predicts process card prediction information through a target analysis model, generates target process flow and target material information from the process card information to be analyzed, simplifies the workflow of the experimenter, obtains accurate process flow of nucleic acid extraction and library preparation based on the target analysis model, and improves interpretability and computational efficiency. The target process flow is encapsulated in a segment program to generate a segment program combination file and transmit it to the target module, which ensures the accuracy and consistency of the operation and improves the accuracy of nucleic acid extraction and library preparation in automated control. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a flow chart of the automated control method for nucleic acid extraction and library preparation provided in the embodiments of the present application;

[0048] Figure 2 yes Figure 1 Flow chart of step S102 in FIG.

[0049] Figure 3 yes Figure 1 Flow chart of step S103 in FIG.

[0050] Figure 4 yes Figure 1 Flow chart of step S104 in FIG.

[0051] Figure 5 It is a schematic diagram of industrial customization process for four different purposes provided in the embodiments of the present application;

[0052] Figure 6 It is a flow chart of the target prediction model for nucleic acid extraction and library preparation provided in the embodiments of the present application;

[0053] Figure 7 It is a schematic diagram of transmitting parameter configuration and specification information to a segment program file provided in an embodiment of the present application;

[0054] Figure 8 It is a schematic diagram of the implementation of the automated control method for nucleic acid extraction and library preparation provided in the embodiments of the present application;

[0055] Fig. 9 It is a schematic diagram of target material information processing provided by an embodiment of the present application;

[0056] Fig.10is a schematic diagram of an automated control device for nucleic acid extraction and library preparation provided in an embodiment of the present application;

[0057] Fig.11 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application, they are only examples of devices and methods consistent with some aspects of the embodiments of the present application.

[0059] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0060] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0061] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0062] Before describing the embodiments of the present application in detail, some nouns and terms involved in the embodiments of the present application are first described. The nouns and terms involved in the embodiments of the present application are subject to the following explanations.

[0063] Decision Tree (DT): A decision tree is a supervised learning model in machine learning. It is like an inverted tree consisting of a root node, internal nodes, and leaf nodes. By learning from the training data, the decision tree can make judgments step by step along the branches of the tree according to the input features and finally give a prediction result.

[0064] Nucleic Acid Extraction (NAE): Nucleic acid extraction is a key step in molecular biology experiments. It is the process of separating and purifying nucleic acids (including DNA and RNA) from biological samples (such as blood, tissues, cells, etc.). This process is mainly to obtain pure nucleic acids for subsequent experimental research.

[0065] Library preparation (LP): Library preparation is an important step after nucleic acid extraction, referred to as LP. It is the process of constructing the extracted nucleic acid into a nucleic acid library suitable for specific high-throughput sequencing technology or other molecular biology research. The library preparation process includes steps such as nucleic acid fragmentation, end repair, A-tailing (for DNA), adapter ligation and library amplification. The purpose is to enable nucleic acids to be effectively identified and sequenced on the sequencing platform, and to cover enough gene regions to provide rich information for subsequent gene analysis.

[0066] Segment Program (SP): Segment Program is a program organization method, referred to as SP. It decomposes a complex program or process into multiple relatively independent program segments.

[0067] G' code (G-prime Code): G' code is an instruction code used to control the operation of a device or system. It is written in a specific grammatical rule. Each G' code instruction corresponds to a specific operation action.

[0068] Process Card (PC): A process card is a card that records information related to product manufacturing or experimental processes, referred to as PC. It is a guide for the entire operation process. Workers can plan experiments, prepare equipment, and perform operations based on the information provided by the process card. At the same time, the content of the process card can also be used as data input to predict the best operation process through models such as decision trees.

[0069] Computer Numerical Control Machine Tools (CNC): Computer Numerical Control Machine Tools is an automated machine tool equipped with a program control system, referred to as CNC. It combines computer technology with traditional machine tool processing technology to control the movement and processing operations of the machine tool through pre-written numerical control programs.

[0070] PCR (Polymerase Chain Reaction): A technique used to amplify specific DNA fragments in vitro, which plays a key role in the library preparation process after nucleic acid extraction. It enables the target DNA fragment to be amplified in large quantities in a short period of time. In library preparation, PCR is used to increase the number of nucleic acid fragments in the library to meet the requirements of subsequent high-throughput sequencing or other analytical methods for the amount of nucleic acid.

[0071] PMT (Photomultiplier Tube): In the process of nucleic acid extraction and library preparation, photomultiplier tube detection (PMT) is mainly used to detect optical signals of nucleic acid-related substances. Photomultiplier tube is an extremely sensitive light detector that can convert weak light signals into electrical signals and amplify them. The fluorescent signals detected by PMT are used to quantitatively analyze or evaluate the quality of nucleic acids.

[0072] AGV (Automated Guided Vehicle): AGV transport is the use of automated guided vehicles to transport materials, products or equipment. AGV is a type of transport equipment that can automatically travel along a preset path and usually does not require manual driving.

[0073] The automated control method for nucleic acid extraction and library preparation provided in the embodiment of the present application relates to the field of biological extraction technology. The automated control method for nucleic acid extraction and library preparation provided in the embodiment of the present application can be applied to a terminal, can also be applied to a server, and can also be software running in a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and a car terminal, etc., but is not limited to this; the server side can be configured as an independent physical server, or it can be configured as a server cluster or a distributed system composed of multiple physical servers, and can also be configured to provide cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms and other basic cloud computing services. The cloud server, the server can also be a node server in a blockchain network; the software can be an application of an automated control method for nucleic acid extraction and library preparation, etc., but is not limited to the above form.

[0074] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application 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 present application can also be practiced in distributed computing environments, in which 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.

[0075] Figure 1 is an optional flow chart of the automated control method for nucleic acid extraction and library preparation provided in the embodiments of the present application. Figure 1 The method may include but is not limited to steps S101 to S105:

[0076] Step S101: Obtain process card information to be analyzed;

[0077] Step S102: predicting process card prediction information corresponding to nucleic acid extraction and library preparation through the target analysis model;

[0078] Step S103: Generate target process flow and target material information from the process card information to be parsed through the process card prediction information;

[0079] Step S104: Encapsulate the target process flow into a segment program to generate a segment program combination file, and transmit the segment program combination file to the target module via a bus;

[0080] Step S105: Control the target module to automatically perform nucleic acid extraction operation or library preparation operation according to the segment program combination file.

[0081] In some embodiments, Figure 1As shown, after the experimenter fills in the process card information and uploads it, the information involved in the process card is preprocessed, and the preprocessed process card information is transmitted to the target parsing model for prediction to obtain the target process flow and target material information. The target material information is used to know the amount and placement of reagents and consumables required for the target module. The experimenter places the corresponding reagents and consumables in the corresponding positions according to the target material information, and prepares in advance for the nucleic acid extraction operation or library preparation operation. The target process flow is encapsulated in a segment program combination file and transmitted to the target module through the bus, so that the target module can know the corresponding process flow content in the nucleic acid extraction operation or library preparation operation, and each module is executed one by one in sequence according to the process flow content, so that the target module can accurately operate according to the target process flow.

[0082] In some embodiments, in step S101, the experimenter fills in the information about the operation method, sample quantity and sample type on the terminal device according to the experimental requirements of nucleic acid extraction and library preparation, and this information is collected into process card information and uploaded to the system. According to the process card information filled in by the experimenter, the process card information is preprocessed, and the preprocessing includes data extraction, format unification, error checking, missing value processing and noise data processing, and classified storage and association analysis integration are performed. Specifically, the error check is to check whether there are errors in the extracted process card information, which may include data entry errors or logical contradictions; for example, the sample size is negative, and the upper limit of the library fragment size is less than the lower limit, which is a logical contradiction. Missing value processing is that some process cards may not fully fill in all information, such as lack of sample source, equipment model, etc. For these missing values, default values ​​can be used to fill, fill according to other relevant information, or mark as missing state and wait for manual supplementation. Noise data processing is to remove or correct the noise data in the process card information. The noise data may be caused by interference or inaccurate records during the data acquisition process. These noise data can be processed by data smoothing technology or methods such as statistical distribution of data. By preprocessing the process card information uploaded by the experimenter's terminal device, the process card information to be parsed is obtained, which ensures the stability of the data in subsequent data processing.

[0083] Figure 2 yes Figure 1 Flowchart of step S102 in FIG. Figure 1 Step S102 includes but is not limited to steps S201 to S204:

[0084] Step S201: obtaining an industrial customized process for nucleic acid extraction and library preparation;

[0085] Step S202: updating the first historical operation process corresponding to nucleic acid extraction and library preparation according to the industrial customized process to obtain a second historical operation process;

[0086] Step S203: training the current real-time parsing model through the second historical operation process to obtain a target parsing model;

[0087] Step S204: predicting process card prediction information corresponding to nucleic acid extraction and library preparation through the target analysis model.

[0088] In some embodiments, industrial customized processes for nucleic acid extraction and library preparation are collected through historical materials, and the operating processes of the target analysis model are updated in real time according to the updates of the industrial customized processes, so as to avoid the process flow predicted by the target analysis model being outdated and unable to complete the process requirements of nucleic acid extraction and library preparation as required. The updated target analysis model is used to predict the process card to be analyzed to obtain the process card prediction information corresponding to nucleic acid extraction and library preparation.

[0089] It is understandable that in obtaining industrial customized processes, through market demand and a comprehensive evaluation of various technologies and process methods involved in current nucleic acid extraction and library preparation, the advantages and disadvantages of different nucleic acid extraction technologies on different sample types, as well as the different reagents, equipment and performance available in each link of library preparation, are analyzed. Combined with the latest research results and technological development trends in the industry, the optimization space of technology and process is determined to meet the requirements of industrial large-scale production. According to the analysis results of the requirements, the industrial customized process framework of nucleic acid extraction and library preparation is constructed, the main stages and sequence of the overall process are determined, and the connection relationship between the stages, the flow of data and samples are clarified. The key links of each main stage are optimized and customized, and according to the needs of the customized process, appropriate industrial equipment and supporting resources are selected to ensure that the entire industrial customized process can run stably and efficiently.

[0090] For example, Figure 5 As shown, there are four industrial customized processes for different purposes. Specifically, when the magnetic bead method is used for trace nucleic acid extraction, the steps of thermal lysis, magnetic bead purification, concentration detection and PCR amplification are completed in sequence; when the magnetic bead method is used for plasmid structure extraction, the steps of thermal lysis, magnetic bead purification, concentration detection and PCR amplification are also completed in sequence; when mRNA library preparation is performed, the steps of thermal lysis, PCR amplification, PCR amplification, magnetic bead purification, concentration and fragment analysis, PCR amplification, PCR amplification, magnetic bead purification, and concentration and fragment analysis are completed in sequence; when target capture sequencing library preparation is performed, the steps of heated incubation, PCR amplification, magnetic bead purification, concentration and fragment analysis, heated incubation, magnetic bead capture probe, PCR amplification, magnetic bead purification, and concentration and fragment analysis are completed in sequence.

[0091] In some embodiments, in step S202, by collecting the first historical operation process records of nucleic acid extraction and library preparation in the past, the first historical operation process records contain detailed information such as actual operation processes, parameter settings, equipment used, and reagents at different stages from manual operation to small-scale automation attempts, and these information are sorted out to form a clear first historical operation process document. The industrial customized process is compared with the first historical operation process link by link, and the differences in all process sequences, operation parameters, equipment use, etc. are recorded, and these differences are analyzed based on the application of new technologies or efficiency improvement needs or quality improvement considerations. According to the results of the difference analysis, the first historical operation process is updated, and the parts that do not conform to the industrial customized process are replaced. At the same time, the overall process sequence is sorted out, and the operation steps are rearranged according to the logic of the customized process to ensure that the connection between the links meets the requirements of industrial production. The updated contents of each link are integrated to form a complete second historical operation process document, and the operation method of each step, the equipment and reagents involved, the expected results, and the key points of quality control are described in detail in the document, so that the second historical operation process can accurately reflect the operation mode of nucleic acid extraction and library preparation based on the industrial customized process.

[0092] In some embodiments, in step S203, the current real-time analytical model is trained through the second historical operation process to obtain a target analytical model. Specifically, the data related to the second historical operation process is sorted so that it can be used as a data set for training the analytical model. Features valuable for model training are extracted from the sorted data. For example, for operating parameters, key parameters such as lysis temperature in nucleic acid extraction and number of PCR cycles in library preparation are selected; for product quality indicators, indicators that can measure the quality of the final result are selected as output label features, and the original data is converted into a feature vector form suitable for model training through feature selection, feature encoding and other technologies. The prepared feature vector data is divided into training set, validation set and test set. It can be understood that by inputting the training set data into the selected model, the model parameters are adjusted to make the model learn the mapping relationship between the input features and the output labels, and minimize the error between the predicted results and the actual results; during the training process, the performance of the model is monitored through the validation set data to prevent overfitting and continuously optimize the model until satisfactory performance is achieved; the test set data is used to conduct a final evaluation of the trained multiple models, and their performance in evaluation indicators such as prediction accuracy, recall rate, F1 value or mean square error, mean absolute error, etc. is compared. The model with the best performance is selected as the target parsing model to ensure that it can accurately predict the key process information corresponding to nucleic acid extraction and library preparation based on the input process card-related feature information.

[0093] In some embodiments, the parsing model includes a DecisionTreeClassifier of the sklearn.tree library in a decision tree, and may also be a model such as a random forest or a support vector machine.

[0094] In some embodiments, in step S204, the process card prediction information corresponding to nucleic acid extraction and library preparation is predicted by the target parsing model. Specifically, the nucleic acid extraction and library preparation process card information to be predicted is obtained, and the information content corresponding to the features used in model training is extracted therefrom, including operation methods, sample quantity, and sample type. Ensure that the input feature information is complete and accurate, and matches the input requirements of the model so that the model can make effective predictions based on these features. The extracted feature information may require some necessary preprocessing to map the feature values ​​of different magnitudes to a unified interval to avoid affecting the prediction effect of the model due to excessive differences in feature scales. The preprocessed feature vector is input into the target parsing model, and the model predicts the process information related to nucleic acid extraction and library preparation corresponding to the process card based on the mapping relationship learned internally. After the model outputs the prediction result, it is converted into a format that is easy to understand and apply.

[0095] Figure 3 yes Figure 1 The flowchart of step S103 in FIG. Figure 1 Step S103 includes but is not limited to steps S301 to S306:

[0096] Step S301: Obtaining the standard process of nucleic acid extraction and library preparation according to the prediction information of the process card;

[0097] Step S302: Obtain the target process flow according to the standard process and the process card information to be analyzed;

[0098] Step S303: obtaining target module information and target module position information through the target process flow;

[0099] Step S304: Integrate the target module information and the target module position information to obtain the material position;

[0100] Step S305: Determine the type and amount of materials through the target process flow;

[0101] Step S306: Combine the material location with the material type and usage to obtain target material information.

[0102] In some embodiments, the target parsing model is used to obtain the standard process of nucleic acid extraction and library preparation according to the process card prediction information. The target process flow is obtained through the target parsing model according to the standard process and the process card information to be parsed. The target process flow is the total target process flow of all target modules for nucleic acid extraction and library preparation. The target process flow determines the target module information to be used according to the information of the process card to be parsed. The target module refers to the functions and corresponding equipment used to complete nucleic acid extraction and library preparation. The target module position information can be obtained according to the target module information. The specific location information of the material placed in the target module, that is, the material position, is further obtained according to the target module information and the target module position information. After the material type and amount determined in the target process flow and the material position are determined, the target material information is obtained.

[0103] It is understandable that the content of the process card prediction information includes the predicted results of sample characteristics, target product requirements, and special conditions that may be involved. According to the internally established knowledge base related to nucleic acid extraction and library preparation, the knowledge base includes a large number of successful experimental processes in the past, industry-wide best practices, and standard operating specifications under different sample types and target requirements. Combined with the process card prediction information, the standard process framework for nucleic acid extraction and library preparation is determined. For each step in the standard process framework, its operational details are further refined. In the cell lysis step, the specific formula of the lysis solution, the amount of magnetic beads, the temperature and time settings of the lysis, and other parameters are clarified; for the library amplification step, the PCR reaction system, the number of PCR cycles, the temperature settings of each stage, etc. are refined to make the standard process operational and have clear quality control requirements.

[0104] In some embodiments, in step S302, the target process flow is obtained according to the standard process and the process card information to be analyzed. Specifically, by conducting an in-depth analysis of the process card information to be analyzed, the differences from the general situation on which the standard process is based are obtained, and the special requirements proposed in the process card information to be analyzed are identified. For example, if the completion time of the entire process is limited, it is necessary to evaluate the time consumption of each step in the standard process, and consider whether the time requirements can be met by optimizing the operation. According to the analyzed differences and special requirements, the standard process is adjusted and optimized in a targeted manner. If it is necessary to increase sample quality assessment and repair operations, the corresponding detection methods and repair procedures are inserted into the sample pretreatment steps. By adjusting each step one by one, the standard process is converted into a target process flow that meets the specific requirements of the process card to be analyzed, ensuring that the process not only follows the basic scientific principles and specifications of nucleic acid extraction and library preparation, but also meets the personalized conditions proposed by the current process card.

[0105] In some embodiments, in step S303, the target module information and the target module position information are obtained through the target process flow. Specifically, according to the various steps of the target process flow, the equipment support and corresponding functional requirements required for each step are sorted out. It can be understood that in the cell lysis step of nucleic acid extraction, if the lysis is achieved by heating and stirring, a heating and stirring device that can accurately control the temperature and stirring speed is required; in the library amplification step, a PCR instrument with precise temperature control and cycle program setting functions must be used, and the functional requirements of each step are analyzed at the same time. Determine the physical location of each equipment module based on the actual laboratory layout, production workshop setting or automated production line planning.

[0106] In some embodiments, in step S304, the target module information and the target module position information are integrated to obtain the material position. Specifically, the target module information and the target module position information are integrated according to the sequence of the process flow and the collaborative relationship between the equipment and the function, and the specific position of the material is further determined according to factors such as the frequency of use, stability, and safety requirements of the material. The required material information is determined according to the execution items of the execution equipment, and the location where the material should be stored during the experiment is determined according to the location of the target module. The materials include consumables and reagents. It is understandable that there may be material transfer, signal interaction, etc. between the devices, and the material position is only a fixed position where the material corresponding to the target module is placed before the nucleic acid extraction and library preparation operations are started.

[0107] In some embodiments, the target process flow is displayed through an automated flow chart. Specifically, by drawing a layout diagram, establishing a position relationship matrix, or using digital factory layout software, the position information of each target module and the target module is visually integrated, and the specific position of each module, the connection path between modules, and the relative distance and other information are clearly marked on the layout diagram to form complete material location information, intuitively display the spatial distribution of each module in the entire nucleic acid extraction and library preparation process, and facilitate the subsequent material distribution, operation management, and automation control planning.

[0108] In some embodiments, in step S305, the type and amount of materials are determined by the target process flow. Specifically, each step in the target process flow is analyzed in detail to determine the materials required for each step. In the sample pretreatment step of nucleic acid extraction, materials such as anticoagulants, blood collection tubes, and sample storage solutions may be required; the cell lysis step requires specific lysis solutions, magnetic beads, etc.; in the nucleic acid fragmentation step of library preparation, subsequent end repair, A-tailing, linker addition, or library amplification steps correspond to the enzyme reagents, linker sequences, PCR reaction reagents, etc. required for each step. The materials required for each step are comprehensively sorted out to form a draft of the bill of materials, clarify the use position and role of different types of materials in the entire process flow, and calculate the amount of materials according to factors such as the sample size, reaction scale, and operating parameters of each step in the target process flow. For PCR reaction reagents, the amount of primers, etc. is determined based on the volume size and number of cycles of the PCR reaction system, so as to accurately calculate the specific quantity required for each material in the entire process, improve the bill of materials, and obtain accurate information on the type and amount of materials.

[0109] In some embodiments, in step S306, the material type and amount are combined with the material location to obtain target material information. Specifically, the material type and amount information are integrated with the material location information, and the integrated target material information is reviewed and improved to check whether there are any omissions, errors or unreasonable information, to ensure that the target material information is accurate and can provide reliable material guarantee for nucleic acid extraction and library preparation. Material information includes loading consumables and required reagents.

[0110] In some embodiments, the target material information is displayed through a graphical user interface. Specifically, based on the obtained material information, that is, the loading consumables and required reagents are displayed in the graphical user interface, and the experimenter places the corresponding consumables and reagents in the corresponding positions as required according to the types, positions and amounts displayed on the interface, in preparation for the subsequent automated nucleic acid extraction and library preparation.

[0111] In some embodiments, Figure 6As shown, in the industrialization process of nucleic acid extraction and library preparation, a machine learning decision tree algorithm is used as a model. Specifically, the algorithm is imported into the machine learning library, and the feature data set X and the corresponding result Y are obtained from the process card filled in by the experimenter. Then, the feature matrix is ​​converted into a numerical feature, and different models are created according to actual needs. The prediction of the operation type and output parameters in the new process card is finally obtained through model training. Exemplarily, taking X=[magnetic bead method, 48, molecular forensics] as an example, after completing the model training, the process card data set X is stored, processed by the conversion function encoder, converted into a numerical feature matrix and stored, and the numerical feature matrix is ​​input through model prediction to obtain the predicted output parameter predicted_Y, wherein the first member variable Procedure[S] of predicted_Y represents S segment program files, and the second member variable two-dimensional array Para[m][n] represents the parameters closely related to the S segment program files and the amount of reagents and consumables. When input new_X = [magnetic bead method, 48, molecular forensics], after conversion new_X = {1, 48, 1}, the new process card is predicted, and the output is as follows: predicted_Y.Procedure[S] = {0, 1, 2, 3, 3, 3, 4, 5, 9, ...}, where: 0 represents lysis, 1 represents centrifugation, 2 represents binding, 3 represents washing, 4 represents elution, 5 represents concentration determination, 6 represents constant temperature incubation, 7 represents magnetic bead capture, 8 represents concentration determination and fragment analysis, 9 represents PCR, 10 represents liquid addition, 11 represents automated consumables transfer and stacking Station, 12 automated tip box stacking stations, output parameters: predicted_Y.Para[0] = {420, 56, 1000, 20, 95, 500, 20, 2, 52, ...}, where para[0] represents all parameters related to the lysis process, lysis solution volume 420uL, lysis temperature 56°C, lysis speed 1000rpm, lysis time 20min, inactivation temperature 95°C, inactivation speed 500rpm, inactivation time 20min, 2 24-well lysis plates, and 52 1mL tips consumed.

[0112] Figure 4 yes Figure 1 The flowchart of step S104 in FIG. Figure 1 Step S104 includes but is not limited to steps S401 to S405:

[0113] Step S401: split the target process flow into target process steps;

[0114] Step S402: determining macro variable parameters according to the target process step;

[0115] Step S403: Generate preset code instructions through target process steps and macro variable parameters;

[0116] Step S404: Generate a segment program corresponding to each target process step according to the preset code instruction;

[0117] Step S405: Generate a segment program combination file according to all segment programs.

[0118] In some embodiments, to facilitate segment program encapsulation, the target process flow is split, the macro variable parameters of the split target process flow are determined, and then the split target process flow and the macro variable parameters are combined to generate preset code instructions, each preset code instruction is separately encapsulated into a segment program, and the segment programs are combined to generate a segment program combination file, which can ensure that the various operation steps of nucleic acid extraction and library preparation are carried out smoothly in sequence and ensure the complete transmission of data.

[0119] It is understandable that, taking nucleic acid extraction as an example, it can be divided into fine steps such as sample pretreatment, cell lysis, nucleic acid adsorption, impurity washing, nucleic acid elution, etc.; library preparation includes nucleic acid fragmentation, end repair, A-tailing, linker addition, library amplification, etc. According to the reaction principle, sequence and equipment operation logic. For example, cell lysis requires the preparation of appropriate lysis solution and setting temperature to effectively release nucleic acids. Only by clarifying these details can accurate splitting be ensured to ensure that each step has a clear starting and ending point and operation purpose, laying the foundation for subsequent programming.

[0120] In some embodiments, in step S402, macro variable parameters are determined according to the target process steps. Specifically, key variable factors are found for the split steps. For example, in the cell lysis step, the amount of lysate, temperature, and time are key. These parameters will be adjusted according to sample differences and set as macro variables. When amplifying the library, the number of PCR cycles, denaturation temperature, etc. are also set as macro variables, which facilitates the subsequent code to flexibly control the process and adapt to different process requirements, making the program more versatile.

[0121] In some embodiments, in step S403, preset code instructions are generated through target process steps and macro variable parameters, and codes are written using specific programming rules according to step operation requirements and macro variables to ensure that the instructions can accurately direct the equipment to act according to process requirements and can be flexibly adjusted as macro variables change, such as automatically adapting when the amount of lysis solution is changed.

[0122] In some embodiments, the preset code instructions may be implemented as G' code instructions for a computer numerical control machine tool.

[0123] In some embodiments, in step S404, a segment program corresponding to each target process step is generated according to preset code instructions, and the code instructions of each step are encapsulated into independent program segments. It is understandable that in addition to the core instructions, preparatory work should be added, such as initializing the equipment to ensure that it is in a normal state; post-processing should also be added, such as checking whether the results meet the standards and handling abnormal situations. In addition, comments are added to improve the readability of the program to facilitate subsequent maintenance work.

[0124] In some embodiments, in step S405, a segment program combination file is generated based on all segment programs, and segment programs are combined according to the process flow logic to ensure smooth data transmission, such as the results of the nucleic acid extraction and elution steps are accurately input into the start of library preparation to avoid data loss and logic conflicts. Framework codes such as global variable declarations and function entries are added, necessary library files are introduced to support operation, overall test optimization is performed, and simulation operations are performed to check connection loopholes and resource conflicts, so as to ensure that the segment program combination file is complete and accurate to achieve process automation.

[0125] In some embodiments, Figure 7 As shown, it is the process of transferring parameter configuration and specification information to the segment program file. For example, the centrifugation process is taken as an example to show the process of transferring centrifugation parameters to the corresponding centrifugation segment program file through macro definition packaging. (A) Machine learning analyzes the parameters generated by the process card (such as centrifugation time, centrifugation speed, etc.), (B) Parameter packaging (Centrifugation (SPEED = 3500, TIME = 5, ...)), (C) Transfer to the segment program file (Centrifugation.NC), (D) Detailed G' code instruction set of the segment program file (G201 D3 R#CEN_SPEED#H#CEN_TIME#).

[0126] In some embodiments, Figure 8As shown, part (A): fill in the process card. Usually, you only need to fill in the method, sample quantity and sample type used for nucleic acid extraction on the process card. The method includes magnetic bead method or silica bead method. For example, the information filled in is ["magnetic bead method, sample quantity: 48, application: molecular forensics"]. Part (B): The system automatically analyzes the biological process with the help of machine learning decision tree algorithm, which mainly includes the following key steps. First, the automatic process protocol generation is realized. Specifically, based on the input process card information, an abstract automatic flow chart is generated. For example, the generated flow chart is ["temperature-controlled vibration lysis, magnetic bead-based purification, concentration detection, PCR amplification"], and the corresponding machine operation process Procedure is ["lysis, centrifugation, binding, wash 1, wash 2, wash 3, elution, PMT fluorescence quantification, PCR"]. This Procedure clearly shows the order of each link when the machine is actually running from top to bottom. Then complete the automation module settings. Specifically, according to the automation flow chart and related biological process characteristics, generate the parameters involved in each process, including a series of key parameters such as lysis buffer volume, oscillation temperature, oscillation speed, oscillation time, centrifugation speed and time, etc. These parameters provide a specific quantitative basis for subsequent precise operations. Finally, based on the previously generated process parameters, more specifically, realize the automated reagent and consumable calculation, and calculate in detail the number of plates for lysis buffer, the number of plates for magnetic beads, the number of plates for nucleic acid binding, the number of plates for washing buffer, and the volume of lysis buffer, binding buffer, washing buffer, etc. A series of reagents and consumables are accurately used, thereby providing comprehensive and detailed material preparation support for the smooth implementation of the entire nucleic acid extraction and library preparation process.

[0127] In some embodiments, Fig. 9 As shown, the machine learning decision tree algorithm analysis will automatically generate a reagent and consumables calculation table, and then guide the placement of the target material information through the GUI interface to the corresponding station, and the corresponding material is placed at the corresponding station by the experimenter, wherein the station in the reagent and consumables calculation table refers to the specific location of the material in the target module. For example, for a 48-channel experiment, two 24-well lysis plates are required, and the interface guides the placement of them at the L1 and L2 stations. The lysis solution is in the first small compartment of the liquid tank plate, and the liquid tank plate is placed at the Y1 station. The 1mL gun tip box is placed at the T1 and T3 stations.

[0128] In some embodiments, the machine learning decision tree algorithm analysis will automatically generate a reagent and consumables calculation table, and then display the corresponding workstation of the material through the GUI interface according to the target material information, and place the materials in the automated consumables transfer stacking station and the automated tip box stacking station in advance through the AGV, and then transfer the materials from the automated consumables transfer stacking station and the automated tip box stacking station to the corresponding workstations through the gripper of the multi-function head, completing the material stacking task in an entirely automated manner.

[0129] In some embodiments, Fig.10 As shown, another aspect of the embodiment of the present application provides an automated control device for nucleic acid extraction and library preparation, the device comprising:

[0130] The first module is used to obtain the process card information to be analyzed;

[0131] The second module is used to predict the process card prediction information corresponding to nucleic acid extraction and library preparation through the target analysis model;

[0132] The third module is used to generate target process flow and target material information from the process card information to be parsed through the process card prediction information;

[0133] The fourth module is used for encapsulating the target process flow into the segment program to generate a segment program combination file, and transmitting the segment program combination file to the target module through the bus;

[0134] The fifth module is used to control the target module to automatically perform nucleic acid extraction operation or library preparation operation according to the segment program combination file.

[0135] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0136] See also Fig.11 , Fig.11 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0137] The processor 410 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0138] The memory 420 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 420 can store an operating system and other application programs. When the technical solution provided in the embodiments of this specification is implemented by software or firmware, the relevant program code is stored in the memory 420, and the processor 410 is called to execute the automated control method for nucleic acid extraction and library preparation of the embodiments of this application;

[0139] Input / output interface 430, used to implement information input and output;

[0140] Communication interface 440, used to realize communication interaction between the device and other devices, which can be realized through wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0141] bus 450 , which transmits information between the various components of the device (e.g., processor 410 , memory 420 , input / output interface 430 , and communication interface 440 );

[0142] The processor 410 , the memory 420 , the input / output interface 430 , and the communication interface 440 are connected to each other in communication within the device via the bus 450 .

[0143] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, an automated control method for nucleic acid extraction and library preparation is implemented.

[0144] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0145] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0146] The automated control method, device and storage medium for nucleic acid extraction and library preparation provided in the embodiments of the present application predict the process card information through a target parsing model, obtain the target process flow and target material information, convert the target process flow into a segment program combination file and transmit it to the target module through a bus for automated control operations, thereby simplifying the workflow of the experimenter, improving the interpretability and computing efficiency, and also improving the degree of automation and work efficiency.

[0147] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0148] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0149] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0150] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0151] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0152] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0153] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0154] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0155] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0156] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it 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 all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes multiple instructions for 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 methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store programs.

[0157] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. An automated control method for nucleic acid extraction and library preparation, characterized in that: The method comprises the following steps: Get the process card information to be parsed; Predicting the process card prediction information corresponding to the nucleic acid extraction and library preparation through the target parsing model; Generate target process flow and target material information from the process card information to be analyzed through the process card prediction information; Encapsulating the target process flow in a segment program to generate a segment program combination file, and transmitting the segment program combination file to the target module via a bus; The target module is controlled according to the segment program combination file to automatically perform nucleic acid extraction operation or library preparation operation.

2. The method according to claim 1, characterized in that The obtaining of the process card information to be parsed includes: Obtain the process card information uploaded by the experimenter's terminal device; Processing the process card information uploaded by the laboratory technician terminal device to obtain the process card information to be parsed; The process card information to be analyzed includes: operation method, sample quantity and sample type.

3. The method according to claim 1, characterized in that The process card prediction information corresponding to the nucleic acid extraction and library preparation is predicted by the target parsing model, including: Obtaining the industrial customized process of nucleic acid extraction and library preparation; Updating the first historical operation process corresponding to the nucleic acid extraction and library preparation according to the industrial customized process to obtain a second historical operation process; Training the current real-time parsing model through the second historical operation process to obtain the target parsing model; The target parsing model is used to predict the process card prediction information corresponding to the nucleic acid extraction and library preparation.

4. The method according to claim 1, characterized in that: The step of generating target process flow and target material information from the process card information to be parsed by using the process card prediction information includes: Obtaining the standard process of nucleic acid extraction and library preparation according to the process card prediction information; Acquire the target process flow according to the standard process and the process card information to be analyzed; Acquire target module information and target module position information through the target process flow; Integrate the target module information and the target module position information to obtain the material position; Determine the type and amount of materials through the target process flow; The material position is combined with the material type and usage to obtain the target material information.

5. The method according to claim 1, characterized in that The step of encapsulating the target process flow into a segment program to generate a segment program combination file includes: Splitting the target process flow into target process steps; Determining macro variable parameters according to the target process step; Generate a preset code instruction through the target process step and the macro variable parameter; Generate a segment program corresponding to each target process step according to the preset code instruction; The segment program combination file is generated according to all the segment programs.

6. The method according to claim 1, characterized in that The target module includes: a thermal vibration module, a liquid processing module, a centrifugation module, a magnetic bead or silica bead extraction module, a constant temperature oscillation module, a PMT module, a thermal cycle module, a real-time fluorescence quantitative PCR module, a multifunctional head module, a consumable transfer stacking module or a tip box stacking module.

7. The method according to claim 1, characterized in that The target material information is displayed through a graphical user interface; the target process flow is displayed through an automated flow chart.

8. An automated control device for nucleic acid extraction and library preparation, characterized in that: The device comprises: The first module is used to obtain the process card information to be analyzed; The second module is used to predict the process card prediction information corresponding to the nucleic acid extraction and library preparation through the target analysis model; The third module is used to generate target process flow and target material information from the process card information to be analyzed through the process card prediction information; A fourth module is used to encapsulate the target process flow into a segment program to generate a segment program combination file, and transmit the segment program combination file to the target module through a bus; The fifth module is used to control the target module to automatically perform nucleic acid extraction operation or library preparation operation according to the segment program combination file.

9. A computer device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images