Biosynthesis method and system

Abstract

The invention provides a biosynthesis method and system. The method comprises the following steps: acquiring sequence data of a synthetic organism; generating an initial experiment task according to the sequence data and experiment data input by a user; detecting the initial experiment task; calling an intelligent production scheduling algorithm to generate a target production scheduling plan according to the target experiment task which is detected to be qualified; generating a scheduling instruction set corresponding to the target experiment task according to the target production scheduling plan; and generating a driving instruction corresponding to the scheduling instruction set, sending the driving instruction to experimental equipment, and controlling the experimental equipment to execute the target experimental task to obtain the synthetic organism and experimental result data of the synthetic organism. By utilizing the method, the biosynthesis efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the field of biosynthesis technology, and in particular to a biosynthesis method and system. Background Art

[0002] At present, the field of biosynthesis mainly uses semi-automated artificial biological synthesis methods. However, semi-automated artificial biological synthesis methods have certain limitations in the field of biosynthesis. For example, there are problems such as low operating efficiency, poor operational standardization, and low synthesis accuracy.

[0003] In addition, in this method, only a single device is automated or a few devices are semi-automated, which limits its scalability and adaptability. The unsatisfactory automation effect of the equipment and the poor flexibility between the equipment make it difficult to achieve large-scale execution of throughput and meet various production needs, resulting in poor efficiency of biosynthesis. Summary of the invention

[0004] In view of the above, it is necessary to provide a biosynthesis method and system that can solve the technical problem of poor biosynthesis efficiency due to unsatisfactory automation effect of equipment and poor flexibility between equipment.

[0005] On the one hand, the present application provides a biological synthesis method, which includes: obtaining sequence data of a synthetic organism, generating an initial experimental task based on the sequence data and experimental data input by a user, testing the initial experimental task, and calling an intelligent production scheduling algorithm to generate a target production scheduling plan based on a target experimental task that has passed the test, generating a scheduling instruction set corresponding to the target experimental task based on the target production scheduling plan, generating a driving instruction corresponding to the scheduling instruction set, and sending the driving instruction to an experimental device, controlling the experimental device to execute the target experimental task, and obtaining the synthetic organism and experimental result data of the synthetic organism.

[0006] In some embodiments of the present application, if there are multiple synthetic organisms, the method further includes: constructing a deep learning model, and using the deep learning model to train the sequence data and experimental result data of multiple synthetic organisms to obtain target sequence data.

[0007] In some embodiments of the present application, the deep learning model is used to train the sequence data and experimental result data of multiple synthetic organisms to obtain target sequence data, including: evaluating the multiple synthetic organisms based on the experimental result data of the multiple synthetic organisms to obtain evaluation results, screening a target synthetic organism from the multiple synthetic organisms based on the evaluation results, and determining the sequence data of the target synthetic organism as first target sequence data, and generating second target sequence data based on the first target sequence data.

[0008] In some embodiments of the present application, generating the second target sequence data according to the first target sequence data includes: modifying the first target sequence data or introducing a mutation into the first target sequence data to obtain the second target sequence data.

[0009] In some embodiments of the present application, if there are multiple target experimental tasks, each target experimental task has a corresponding priority, the intelligent production scheduling algorithm is called to generate a target production scheduling plan based on the multiple target experimental tasks, the priorities of the multiple target experimental tasks, and the equipment status of the experimental equipment involved in the multiple target experimental tasks.

[0010] In some embodiments of the present application, calling the intelligent production scheduling algorithm to generate a target production scheduling plan based on multiple target experimental tasks, the priorities of the multiple target experimental tasks, and the equipment status of the experimental equipment involved in the multiple target experimental tasks includes: determining the experimental sequence of the multiple target experimental tasks according to the priorities of the multiple target experimental tasks, decomposing each target experimental task according to the experimental sequence to obtain the experimental steps in each target experimental task, the number of equipment for the experimental steps, and the experimental duration, modeling the number of equipment, the equipment status, and the experimental duration to obtain a production scheduling model, and constructing a constraint condition function, optimizing the production scheduling model and the constraint condition function to obtain the target production scheduling plan.

[0011] In some embodiments of the present application, generating a scheduling instruction set corresponding to the target experimental task according to the target production schedule includes: adding the target production schedule and the multiple target experimental tasks to a scheduling queue, determining the experimental operation of each experimental step in each target experimental task and each experimental equipment corresponding to each experimental operation, generating a scheduling instruction for each experimental operation of each experimental equipment, and obtaining a scheduling instruction set for each target experimental task based on the scheduling instructions of all experimental steps of each target experimental task.

[0012] In some embodiments of the present application, before sending the driving instruction to the experimental device, the method further includes: acquiring a device state of the experimental device, and detecting whether the scheduling instruction set matches the device state.

[0013] On the other hand, the present application provides a biosynthesis system for implementing the biosynthesis method, the biosynthesis system comprising: a protein sequence design platform, a data platform subsystem, a cloud laboratory subsystem, an intelligent production scheduling subsystem, a scheduling center subsystem, an equipment control subsystem and experimental equipment, wherein:

[0014] The protein sequence design platform is used to obtain sequence data of synthetic organisms and send the sequence data to the data platform subsystem;

[0015] The data platform subsystem is used to send the received sequence data to the cloud laboratory subsystem;

[0016] The cloud laboratory subsystem is used to generate an initial experimental task according to the sequence data and the experimental data input by the user, and send the initial experimental task to the intelligent production scheduling subsystem;

[0017] The intelligent production scheduling subsystem is used to detect the initial experimental tasks, call the intelligent production scheduling algorithm to generate a target production scheduling plan based on the qualified target experimental tasks, and send the target production scheduling plan and the target experimental tasks to the scheduling center subsystem;

[0018] The dispatch center subsystem is used to generate a dispatch instruction set corresponding to the target experimental task according to the target production scheduling plan, and send the dispatch instruction set to the equipment control subsystem;

[0019] The device control subsystem is used to generate driving instructions corresponding to the scheduling instruction set, and send the driving instructions to the experimental equipment, control the experimental equipment to perform the target experimental task, and obtain the synthetic organism and the experimental result data of the synthetic organism.

[0020] In some embodiments of the present application, the data platform subsystem receives data from the protein sequence design platform, the cloud laboratory subsystem, the intelligent scheduling subsystem, the equipment control subsystem, and the experimental equipment, and analyzes and visualizes the received data.

[0021] The biosynthetic method in the embodiment of the present application is applied to the biosynthetic system, and each system and platform between the biosynthetic system can carry out data transmission, realizing the sharing and communication between information. The biosynthetic system can generate the initial experimental task according to the experimental data input by the user, has flexibility, and can meet the requirements of different experimental tasks. The high-throughput, high-flexibility, automated biosynthetic system can carry out multiple experiments at the same time, and has high-throughput experimental capabilities. The biosynthetic system can automatically perform experimental tasks, ensure the stability and repeatability of the experiment, and therefore can improve the efficiency of biosynthesis. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 Schematic diagram of a biosynthesis system provided in one embodiment of the present application.

[0023] Figure 2 1 is a flow chart of a biosynthetic method provided in one embodiment of the present application.

[0024] Figure 3 It is a functional module diagram of a cloud laboratory subsystem provided in an embodiment of the present application.

[0025] Figure 4 It is a functional module diagram of a dispatch center subsystem provided in one embodiment of the present application.

[0026] Figure 5 It is a functional module diagram of a device control subsystem provided in one embodiment of the present application.

[0027] Figure 6 It is a flowchart of a method for generating a target production scheduling plan provided in an embodiment of the present application.

[0028] Figure 7 This is a flowchart of a method for generating a scheduling instruction set provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] In order to more clearly understand the above-mentioned purposes, features and advantages of the present application, the present application is described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0030] In the following description, many specific details are set forth to facilitate a full understanding of the present application. The embodiments described are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0031] 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 in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0032] It should be noted that in this application, "at least one" means one or more, and "more than one" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The terms "first", "second", "third", "fourth", etc. (if any) in the specification, claims and drawings of this application are used to distinguish similar objects, rather than to describe a specific order or sequence.

[0033] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as having priority or advantage over other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way. The following embodiments and features in the embodiments may be combined with each other without conflict.

[0034] At present, the field of biosynthesis mainly uses semi-automated artificial synthetic biology methods. However, semi-automated artificial synthetic biology methods have certain limitations in the field of biosynthesis. For example, there are problems such as low operating efficiency, poor operational standardization, and low synthesis accuracy. For example, researchers not only need to design the synthesis path of synthetic organisms, but also need to operate them personally according to the steps, which leads to low work efficiency. In the biosynthesis process, the culture time of synthetic organisms in each experimental device is fixed, and they must be transferred on time after the culture time is over. It is difficult for manual operation to accurately grasp each transfer node, and it is easy to cause synthesis failure due to transfer timeout. In addition, the various experimental processes of biosynthesis are highly similar and easy to confuse, which leads to a high rate of operational errors.

[0035] In addition, in this method, only a single device is automated or a few devices are semi-automated, which limits its scalability and adaptability. The unsatisfactory automation effect of the equipment and the poor flexibility between the equipment make it difficult to achieve large-scale execution of throughput and meet various production needs, resulting in poor efficiency of biosynthesis.

[0036] In order to solve the above problems, the embodiments of the present application provide a biosynthesis method and system, which will be introduced below in conjunction with relevant drawings.

[0037] like Figure 1 Shown is a schematic diagram of a biosynthesis system provided in one embodiment of the present application. Figure 1 The biosynthesis system 1 in the embodiment includes a software system 11 and a hardware system 12. The software system 11 includes a protein sequence design platform 111, a data platform subsystem 112, a cloud laboratory subsystem 113, an intelligent production scheduling subsystem 114, a dispatch center subsystem 115, and an equipment control subsystem 116. The hardware system 12 includes a plurality of experimental devices 122.

[0038] The protein sequence design platform 111 is used to obtain sequence data of synthetic organisms and send the sequence data to the data platform subsystem.

[0039] In some embodiments of the present application, the protein sequence design platform 111 communicates with the data platform subsystem 112 and receives the experimental result data sent from the data platform subsystem 112 .

[0040] The data platform subsystem 112 is used to send the received sequence data to the cloud laboratory subsystem 113.

[0041] The cloud laboratory subsystem 113 is used to generate an initial experimental task according to the sequence data and the experimental data input by the user, and send the initial experimental task to the intelligent production scheduling subsystem 114.

[0042] The intelligent production scheduling subsystem 114 is used to detect the initial experimental tasks, call the intelligent production scheduling algorithm to generate a target production scheduling plan based on the target experimental tasks that have passed the detection, and send the target production scheduling plan and the target experimental tasks to the scheduling center subsystem 115.

[0043] The dispatch center subsystem 115 is used to generate a dispatch instruction set corresponding to the target experimental task according to the target production scheduling plan, and send the dispatch instruction set to the equipment control subsystem 116.

[0044] The device control subsystem 116 is used to generate driving instructions corresponding to the scheduling instruction set, and send the driving instructions to the multiple experimental devices 122 to control the experimental devices to perform the target experimental tasks and obtain the synthetic organism and the experimental result data of the synthetic organism.

[0045] In some embodiments of the present application, the plurality of experimental equipment 122 include, but are not limited to: biosynthesis equipment, transfer equipment, storage equipment, sterile maintenance equipment, monitoring equipment, and detection equipment. The biosynthesis equipment is used to synthesize organisms (such as bacteria and yeast), and the biosynthesis equipment includes, but is not limited to: fermentation tanks, separation equipment, and purification devices. The transfer equipment is used to transfer experimental materials (such as test kits, culture media, and culture dishes), and the transfer equipment includes, but is not limited to: syringes, pipettes, and samplers. The storage equipment is used to store experimental materials, and the storage equipment includes, but is not limited to: refrigerators, freezers, and liquid nitrogen tanks. The sterile maintenance equipment is used to maintain the sterile environment of the laboratory, and the sterile maintenance equipment includes, but is not limited to: biological safety cabinets, sterile operating tables, and autoclaves. The monitoring equipment is used to monitor the laboratory environment, and the monitoring equipment includes, but is not limited to: temperature sensors, humidity sensors, and video monitoring equipment. The detection equipment includes, but is not limited to: microplate readers and PCR instruments.

[0046] In this embodiment, the intelligent production scheduling subsystem 114 can be integrated into the cloud laboratory subsystem 113, the protein sequence design platform 111, the data platform subsystem 112 and the scheduling center subsystem 115 can be integrated into a server (Server), and the equipment control subsystem 116 is a client (Client) that communicates with the server.

[0047] In other embodiments of the present application, the biosynthesis system 1 supports expansion and integration of other experimental equipment to meet future changes in production needs. For example, currently, driving most experimental equipment requires additional manual programming of experimental tasks (protocols), which can be subsequently automatically parsed and generated according to experimental requirements through deep learning to drive the experimental equipment. Alternatively, the biosynthesis system 1 can also integrate voice functions, and the experimenter can control the experimental equipment in the laboratory through voice control to perform corresponding operations, rather than relying on manual click operations on the software platform for control.

[0048] This application realizes automatic control of experimental equipment through the integration of protein sequence design platform, cloud laboratory subsystem and equipment control subsystem, which can reduce manual intervention in the experimental process and improve the reliability and accuracy of the experiment. Through the deployment of the cloud laboratory subsystem, the rapid generation and efficient execution of experimental tasks are realized. Through the collaborative work of the intelligent production scheduling subsystem and the scheduling center subsystem, flexible control of target production scheduling planning and scheduling is realized, so that the biosynthesis system can adapt to different experimental needs, including the execution of multiple experimental tasks and large-scale operation of throughput, thereby improving the efficiency of biosynthesis. The data platform subsystem provides a comprehensive data analysis and decision support platform to optimize the experimental process and perform data analysis of experimental results. In addition, the biosynthesis system in the embodiment of the present application supports the expansion and integration of other experimental equipment to meet changes in future production needs.

[0049] like Figure 2 , which is a flow chart of a biosynthesis method provided in one embodiment of the present application. The execution subject of the method is a biosynthesis system, such as Figure 1 The biosynthetic system shown is 1. According to different needs, the order of each step in the flow chart can be adjusted according to actual requirements, and some steps can be omitted.

[0050] In some embodiments, the biosynthesis system includes a protein sequence design platform, a data platform subsystem, a cloud laboratory subsystem, an intelligent production scheduling subsystem, a dispatch center subsystem, an equipment control subsystem, and experimental equipment.

[0051] S11, the protein sequence design platform obtains sequence data of a synthetic organism.

[0052] In some embodiments of the present application, the synthetic organisms include, but are not limited to: bacterial strains, fungi (yeast) and protein mutants, etc. The synthetic organisms used for the sequence data may be gene sequences, deoxyribonucleic acid sequences (DNA) or protein sequences and other data.

[0053] The protein sequence design platform can modify the original gene sequence, original DNA sequence or original protein sequence of the synthetic organism or introduce mutations into the original gene sequence, original DNA sequence or original protein sequence to obtain the sequence data.

[0054] Among them, the sequence data can be modified in a targeted manner according to actual needs. For example, if you want to synthesize a bacterium that produces enzymes (DNA polymerases and DNA ligases), antibiotics, proteins with catalytic activity, vitamins or fuels, you can modify the original gene sequence of the bacterium in a targeted manner or introduce mutations in the original gene sequence of the bacterium to obtain the sequence data; or, if you want to synthesize a fungus (such as yeast) that produces alcohol, beer, wine or medicine, you can modify the original gene sequence of the fungus in a targeted manner or introduce mutations in the original gene sequence of the fungus to obtain the sequence data; or, if you want to synthesize a mutant (protein variant) of a protein with catalytic activity, you can modify the sequence of the original protein in a targeted manner or introduce mutations in the sequence of the original protein to obtain the sequence data.

[0055] The original gene sequence, the original DNA sequence or the original protein sequence can be imported or inputted by a user on the protein sequence design platform. There can be multiple synthetic organisms, so the sequence data can be multiple copies.

[0056] In other embodiments of the present application, the sequence data may also be generated by other methods, and the present application does not limit the method for generating the sequence data.

[0057] In some embodiments of the present application, after receiving the sequence data, the data platform subsystem sends the received sequence data to the cloud laboratory subsystem.

[0058] In some embodiments of the present application, the data platform subsystem receives data from the protein sequence design platform, the cloud laboratory subsystem, the intelligent scheduling subsystem, the equipment control subsystem, and the experimental equipment, and analyzes and visualizes the received data.

[0059] In some embodiments of the present application, the data platform subsystem may perform hierarchical management and generate a database based on the received data.

[0060] For example, the data from the experimental equipment may be equipment resource data and experimental result data. The equipment resource data includes, but is not limited to: equipment quantity, equipment status, equipment name, and equipment identification, etc. The experimental result data will be described in detail below. The data from the intelligent production scheduling subsystem may be experimental cost data, such as cost data of reagents and consumables. The data platform subsystem generates a Gantt chart based on the equipment resource data, generates a two-dimensional curve based on the experimental result data, and generates a pie chart based on the experimental cost data, and visualizes the Gantt chart, the pie chart, and the two-dimensional curve.

[0061] S12, the cloud laboratory subsystem generates an initial experimental task according to the sequence data and the experimental data input by the user, and sends the initial experimental task to the intelligent production scheduling subsystem.

[0062] In some embodiments of the present application, the experimental data includes the experimental process, experimental steps, reagents, consumables and experimental parameters involved in each experimental step, etc. of each initial experimental task. Since there can be multiple synthetic organisms, there can also be multiple initial experimental tasks, and each initial experimental task can be generated by the sequence data of each synthetic organism.

[0063] like Figure 3 As shown, it is a functional module diagram of the cloud laboratory subsystem provided by an embodiment of the present application. In the figure, the cloud laboratory subsystem 113 includes a registration and login module, a design tool set module, an experimental design module, an experimental process management module, a task management module, a warehouse management module, an equipment management module and a permission management module. The registration and login module is used to provide users with registration and login functions, and match corresponding permissions for users. For example, production line managers and production line experimenters can register and log in to the cloud laboratory subsystem by entering information such as mobile phone numbers, email addresses and account numbers on the login module. The design tool set module is an integrated tool module, such as Geneious and SnapGene, etc. The design tool set module can be used to design DNAassembly and assemble sequence data to obtain assembled sequence data. The experimental design module can be used to receive information such as experimental processes and experimental steps input by users (such as production line experimenters), and combine with the assembled sequence data to generate initial experimental tasks. The experimental design module can also be used to modify the unqualified initial experimental tasks returned by the intelligent production scheduling subsystem. The experimental process management module records the parameters of each experimental operation and the experimental equipment corresponding to each experimental operation. The task management module is used to receive modification information of the generated initial experimental task by the user (such as the production line manager) and configuration information of the priority of the generated initial experimental task, etc. The warehouse management module is used to manage all reagents and consumables in the experiment, and the equipment management module records the use, failure and maintenance history of the experimental equipment.

[0064] S13, the intelligent production scheduling subsystem detects the initial experimental task.

[0065] In some embodiments, the intelligent production scheduling subsystem can detect whether the core parameters are set in each initial experimental task, whether the core parameters are set normally, and whether the time of the experimental steps is normal. The time of the experimental step can be used to indicate the time required to complete an experimental step.

[0066] For example, if the time of an experimental step in an initial experimental task is greater than a preset time threshold, or a core parameter is missing, the intelligent production scheduling subsystem determines that the initial experimental task is abnormal, and returns the initial experimental task to the cloud laboratory subsystem for modification. Among them, the core parameters may include experimental operations and experimental equipment, etc., and the preset time threshold may be a duration, which can be set by the user according to the experimental requirements, and the embodiment of the present application does not limit this. If the intelligent production scheduling subsystem determines that the initial experimental task is qualified, the qualified initial experimental task is determined as the target experimental task. The target experimental task can be one or more.

[0067] S14, the intelligent production scheduling subsystem calls the intelligent production scheduling algorithm to generate a target production scheduling plan based on the qualified target experimental tasks.

[0068] In some embodiments of the present application, if there are multiple target experimental tasks, each of which has a corresponding priority, the intelligent production scheduling subsystem calls the intelligent production scheduling algorithm to generate a target production scheduling plan based on the multiple target experimental tasks, the priorities of the multiple target experimental tasks, and the equipment status of the experimental equipment involved in the multiple target experimental tasks.

[0069] In some embodiments of the present application, the intelligent production scheduling algorithm includes, but is not limited to: shortest delivery time algorithm, shortest process algorithm, neural network, simulated annealing algorithm, genetic algorithm, taboo search algorithm and artificial bee colony algorithm. For example, the electronic device can use the artificial bee colony algorithm to model the experimental parameters such as the experimental steps, experimental duration and number of equipment of each target experimental task, and construct a constraint condition function to generate the target production scheduling plan. For the specific detailed process, please refer to steps S141-S144 below.

[0070] When there are multiple target experimental tasks, the target production scheduling plan is a plan corresponding to multiple target experimental tasks. The target production scheduling plan includes, but is not limited to: the experimental sequence between multiple target experimental tasks, the experimental equipment involved in each experimental step in each target experimental task, the reagents required for each experimental step in each target experimental task, the usage and cost of consumables, and other data.

[0071] In some embodiments of the present application, the intelligent scheduling subsystem calls the intelligent scheduling algorithm to intelligently sort multiple target experimental tasks based on constraints such as improving equipment utilization, maximizing efficiency, and reducing costs, thereby obtaining the target scheduling plan, and uses the target scheduling plan to be visualized to obtain a Gantt chart of the arrangement of multiple target experimental tasks, a Gantt chart corresponding to equipment resource data, and a pie chart corresponding to reagent and consumable usage and experimental cost data.

[0072] In some embodiments of the present application, the dispatch center subsystem can also detect the target experimental task and return the target experimental task that fails the detection to the intelligent production scheduling subsystem. The process of the dispatch center subsystem detecting the target experimental task is basically the same as the process of the intelligent production scheduling subsystem detecting the initial experimental task, so it will not be repeated here.

[0073] S15, the dispatch center subsystem generates a dispatch instruction set corresponding to the target experimental task according to the target production scheduling plan.

[0074] In some embodiments of the present application, the scheduling center subsystem can output a scheduling instruction set for each target experimental task according to the target production scheduling plan. The scheduling instruction set is used to describe the arrangement and sequence of the experimental tasks. Each scheduling instruction set may include one or more scheduling instructions, and each scheduling instruction includes information such as the execution time, end time, and priority of each experimental step or experimental operation. By generating the scheduling instruction set, the experimental tasks can be reasonably scheduled and allocated on the experimental equipment.

[0075] like Figure 4 , which is a functional module diagram of the dispatch center subsystem provided by an embodiment of the present application. Figure 4 In the scheduling center subsystem 115, the scheduling instruction set module and the exception mechanism module are included. The scheduling instruction set module integrates the scheduling instruction sets of all experimental equipment, and the scheduling instruction set is used to generate drive instructions to control the corresponding experimental equipment to perform corresponding operations. The exception mechanism module includes a variety of exception handling mechanisms. For example, in the bacterial strain cultivation link, when it is detected that the growth concentration of the bacterial strain is insufficient, the exception mechanism module can control the corresponding experimental equipment through the scheduling instruction set to return the bacterial strain to the incubator for cultivation until the growth concentration of the bacterial strain meets the requirements. Alternatively, if an experimental equipment is abnormal, the exception mechanism module can generate a prompt message on whether to skip the step of the experimental equipment to remind the user; or, if an experimental step of an experimental task is abnormal, the exception mechanism module can generate a prompt message on whether to skip the experimental step or experimental task to remind the user.

[0076] S16, the device control subsystem generates a driving instruction corresponding to the scheduling instruction set, and sends the driving instruction to the experimental equipment, controls the experimental equipment to execute the target experimental task, and obtains the synthetic organism and the experimental result data of the synthetic organism.

[0077] In some embodiments of the present application, before sending the driving instruction to the experimental equipment, the equipment control subsystem obtains the equipment status of each experimental equipment and detects whether the scheduling instruction corresponding to each experimental equipment matches the equipment status. If the equipment status of an experimental equipment does not match the corresponding scheduling instruction, the equipment control subsystem stops controlling the experimental equipment to perform the corresponding operation through the scheduling instruction. For example, the scheduling instruction of an experimental equipment is to transfer the bacterial strain to an incubator for cultivation, but the equipment control subsystem detects that there is no extra space in the incubator to store the bacterial strain, and the equipment control subsystem temporarily stops controlling the experimental equipment to perform the transfer operation through the scheduling instruction.

[0078] like Figure 5 , which is a functional module diagram of a device control subsystem provided by an embodiment of the present application. Figure 5 In the embodiment, the equipment control subsystem 116 includes a driving instruction set module, an experimental equipment monitoring module and an acquisition module. The driving instruction set module integrates the driving instructions for controlling each experimental operation of all experimental equipment, and can directly control the experimental equipment to perform corresponding operations according to the driving instructions. The experimental equipment monitoring module is used to monitor the usage and working conditions of all experimental equipment, such as abnormalities, temperature, humidity, pressure and other signals. The acquisition module is used to collect the experimental result data of all experimental equipment and the working conditions of the experimental equipment. The experimental result data includes, but is not limited to: the absorbance detection results of the microplate reader, the fluorescence value detection results, etc. The working conditions of the experimental equipment include, but are not limited to: temperature, humidity, pressure and other signals.

[0079] In some embodiments of the present application, the experimental equipment includes, but is not limited to: an autoclave, an ultraviolet lamp, a freezer, and an ELISA instrument. The experimental equipment may be, for example, Figure 1 A plurality of experimental devices 122 are shown.

[0080] In some embodiments of the present application, the driving instructions are used to control the specific operations of the experimental equipment. The equipment control subsystem parses each scheduling instruction set and generates driving instructions for controlling the start, execution of corresponding operations, and stop of the experimental equipment in combination with the equipment status and equipment identification of the experimental equipment, or determines the driving instructions for controlling the start, execution of corresponding operations, and stop of the experimental equipment in the driving instruction set module.

[0081] In other embodiments of the present application, the equipment control subsystem collects the execution results of the experimental equipment on the driving instructions and the experimental result data, returns the execution results to the dispatch center subsystem, and sends the experimental result data to the data platform subsystem. The execution results include, but are not limited to: the execution status of the experimental equipment (abnormal or normal, etc.), temperature, humidity, and execution progress, etc.

[0082] After the experimental equipment performs multiple target experimental tasks, one or more synthetic organisms can be obtained. Since one or more synthetic organisms can produce substances, the substances produced by the synthetic organisms are detected by the experimental equipment to obtain the experimental result data. For example, if the synthetic organism is a plurality of bacterial strains producing proteins with catalytic activity, the concentration of the protein produced by each bacterial strain can be detected by an ELISA instrument to obtain data such as the absorbance and fluorescence value of each bacterial strain on the ELISA instrument. The absorbance of the ELISA instrument can reflect the growth concentration of the bacterial strain, and the fluorescence value of the ELISA instrument can reflect the concentration (expression amount of the protein) of the product generated after the protein produced by each bacterial strain reacts with the substrate. Among them, the product generated after the protein reacts with the substrate will produce a fluorescent signal (luminescent signal), and the ELISA instrument can detect the intensity of the fluorescent signal (luminescent signal) to obtain the fluorescence value of the ELISA instrument, and the fluorescence value of the ELISA instrument can also reflect the catalytic activity of the protein. For example, the substrate can be substances such as 4-methylhydrazine, p-aminobenzoate and Resorufin, and this application is not limited to this.

[0083] In other embodiments of the present application, the biosynthesis system also supports the expansion and integration of other experimental equipment to meet future changes in production needs. For example, currently, driving most experimental equipment requires additional manual programming of experimental tasks (protocols), which can be subsequently driven by deep learning to automatically parse and generate experimental tasks according to experimental requirements. Alternatively, the biosynthesis system can also integrate voice functions, and the experimenter can perform corresponding operations in the laboratory by voice control of the experimental equipment without relying on manual click operations on the software platform for control.

[0084] The biosynthetic method in the embodiment of the present application is applied to the biosynthetic system, and each system and platform between the biosynthetic system can carry out data transmission, realizing the sharing and communication between information. The biosynthetic system can generate the initial experimental task according to the experimental data input by the user, has flexibility, and can meet the requirements of different experimental tasks. The high-throughput, high-flexibility, automated biosynthetic system can carry out multiple experiments at the same time, and has high-throughput experimental capabilities. The biosynthetic system can automatically perform experimental tasks, ensure the stability and repeatability of the experiment, and therefore can improve the efficiency of biosynthesis.

[0085] In some embodiments of the present application, after obtaining the synthetic organism and the experimental result data of the synthetic organism, the device control subsystem sends the experimental result data to the data platform subsystem, and then the data platform subsystem sends the experimental result data to the protein sequence design platform.

[0086] If there are multiple synthetic organisms, the protein sequence design platform constructs a deep learning model, and uses the deep learning model to train the sequence data of multiple synthetic organisms and experimental result data to obtain target sequence data.

[0087] Specifically, the protein sequence design platform uses the deep learning model to train the sequence data and experimental result data of multiple synthetic organisms to obtain target sequence data, including: the protein sequence design platform evaluates the multiple synthetic organisms based on the experimental result data of the multiple synthetic organisms to obtain evaluation results, and based on the evaluation results, screens the target synthetic organism from the multiple synthetic organisms, and determines the sequence data of the target synthetic organism as the first target sequence data, and the protein sequence design platform generates second target sequence data based on the first target sequence data.

[0088] For example, following the above embodiment, if the synthetic organism is a plurality of bacterial strains that produce proteins with catalytic activity, the protein sequence design platform obtains the experimental result data such as the absorbance and fluorescence value of each bacterial strain in the microplate reader, and sorts the performance of the plurality of bacterial strains according to the experimental result data such as the absorbance of the microplate reader and the fluorescence value of the microplate reader, and obtains the evaluation result, and selects a preset number of bacterial strains with the best performance as the target bacterial strain in the evaluation result, and determines the sequence data of the target bacterial strain as the first target sequence data, modifies the first target sequence data or introduces mutations in the first target sequence data, and obtains the second target sequence data. Among them, the preset number can be set by itself, and this application does not limit this. Since the fluorescence value of the microplate reader can reflect the catalytic activity of the protein, the performance evaluation and sorting of the plurality of bacterial strains using the fluorescence value of the microplate reader can improve the accuracy of the evaluation result.

[0089] In other embodiments of the present application, if the synthetic organism is a mutant (protein variant) with catalytic activity, the deep learning model may be an EvoPlay model constructed by placing amino acid residues in space.

[0090] After obtaining the second target sequence data, the protein sequence design platform can send the second target sequence data to the data platform subsystem, and then the data platform subsystem sends the second target sequence data to the cloud laboratory subsystem for the next round of biosynthesis (biological experiment).

[0091] In other embodiments of the present application, the biosynthesis system can also be used to synthesize and test mutants. For example, if the synthetic organism is a mutant of a protein, assuming that 1 protein contains 300 sites, and only one site is mutated, each site has 20 mutation possibilities, then a total of 20*300=6000 mutants need to be synthesized. If the time for testing a mutant is half an hour, it takes about half a year to complete the synthesis and performance test of 6000 mutants. Practice has proved that the time for the synthesis and performance test of 6000 mutants using the biosynthesis system of the present application embodiment is much less than half a year, so efficiency can be improved.

[0092] For example, if a protein mutates 4 sites, it is necessary to synthesize 20^4=160K mutants. It takes a lot of time to synthesize and perform performance tests on 160K mutants. In order to solve the above technical problems, an experimental task of calculating the information volume of sequence data of each mutant can be generated on the protein sequence design platform, so that the protein sequence design platform can screen the sequence data according to the amount of information, thereby recommending a batch of sequence data with a large amount of information. Mutants are synthesized according to the sequence data recommended by the protein sequence design platform, and the synthesized mutants are tested for performance. Experiments show that for the original 160K mutants, only the first 384 mutants with the largest amount of information need to be synthesized and tested in each round. After 5 rounds of synthesis and testing (only 384*5=1920 (1920 / 160K=1.2%) mutants need to be synthesized and tested), the required target mutants and their sequence data can be found. The synthesis and performance testing of invalid mutants can be greatly reduced through screening, thereby improving the efficiency of biosynthesis.

[0093] In this embodiment, a loop of recommending sequence data to the cloud laboratory subsystem is constructed based on deep learning, and then a dry (deep learning) and wet (biological experiment) experimental closed loop is constructed to achieve rapid verification of dry experiment data through wet experiments, thereby greatly improving screening efficiency and quality.

[0094] In some embodiments of the present application, if there are multiple target experimental tasks, each of which has a corresponding priority, the intelligent production scheduling subsystem calls the intelligent production scheduling algorithm to generate a target production scheduling plan based on the multiple target experimental tasks, the priorities of the multiple target experimental tasks, and the equipment status of the experimental equipment involved in the multiple target experimental tasks. Figure 6 FIG. 1 is a flow chart of a method for generating a target production schedule provided by an embodiment of the present application. Specifically, the following steps are included:

[0095] S141, the intelligent production scheduling subsystem determines the experiment sequence of the multiple target experiment tasks according to the priorities of the multiple target experiment tasks.

[0096] In some embodiments, the intelligent scheduling subsystem may set the experimental order of the target experimental tasks corresponding to higher priorities to the front, and the target experimental tasks corresponding to lower priorities to the back, so as to determine the experimental order of the multiple target experimental tasks.

[0097] In other embodiments of the present application, the intelligent scheduling subsystem may set the experimental order of the target experimental tasks corresponding to higher priorities to a later stage, and set the target experimental tasks corresponding to lower priorities to an earlier stage. The present application may flexibly set the experimental order of multiple target experimental tasks according to the priorities of the multiple target experimental tasks.

[0098] S142, the intelligent production scheduling subsystem disassembles each target experimental task according to the experimental sequence to obtain the experimental steps in each target experimental task, the number of equipment for the experimental steps, and the experimental duration.

[0099] In some embodiments, each target experimental task may be broken down into one or more experimental steps, each experimental step may include one or more experimental operations, and each experimental operation may involve one or more experimental equipment.

[0100] S143, the intelligent production scheduling subsystem models the equipment quantity, the equipment status and the experiment duration to obtain a production scheduling model and construct a constraint condition function.

[0101] In some embodiments, the intelligent production scheduling subsystem can improve equipment utilization, maximize efficiency, and reduce costs to construct the constraint function, and the equipment state can be an idle state.

[0102] S144, the intelligent production scheduling subsystem optimizes the production scheduling model and the constraint condition function to obtain the target production scheduling plan.

[0103] The production scheduling model and the constraint condition function are optimized to obtain the target production scheduling plan, and reference may be made to relevant technologies.

[0104] In this embodiment, the constraint condition function is constructed to improve equipment utilization, maximize efficiency and reduce cost, which can improve the utilization of experimental equipment, maximize efficiency and reduce cost. The production scheduling model and the constraint condition function are optimized to ensure the accuracy and reliability of the target production scheduling plan.

[0105] like Figure 7FIG. 1 is a flow chart of a method for generating a scheduling instruction set provided in an embodiment of the present application. Specifically, the following steps are included:

[0106] S151, the scheduling center subsystem adds the target production schedule and the multiple target experimental tasks to the scheduling queue.

[0107] In this embodiment, by adding the target production scheduling and experimental tasks to the scheduling queue, the scheduling center subsystem can perform intelligent scheduling based on the priority of the target experimental tasks and the availability of resources such as experimental equipment, thereby ensuring the on-time completion of the target experimental tasks and maximizing production efficiency.

[0108] S152, the scheduling center subsystem determines the experimental operation of each experimental step in each target experimental task and each experimental device corresponding to each experimental operation, and generates a scheduling instruction for each experimental operation of each experimental device.

[0109] In some embodiments, the scheduling center subsystem can generate scheduling instructions corresponding to each experimental operation of each experimental device based on each experimental operation and the device identification of the experimental device corresponding to the experimental operation, or determine the scheduling instructions corresponding to each experimental operation of each experimental device in the scheduling instruction set module.

[0110] S153, the scheduling center subsystem obtains a scheduling instruction set for each target experimental task based on the scheduling instructions of all experimental steps of each target experimental task.

[0111] In some embodiments of the present application, the scheduling center subsystem combines the scheduling instructions of all experimental steps of each target experimental task according to the experimental sequence to obtain a scheduling instruction set for each target experimental task.

[0112] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules is only a logical function division, and there may be other division methods in actual implementation.

[0113] The modules described as separate components may or may not be physically separated, and the components shown as modules 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 modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0114] In addition, each functional module in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0115] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present application is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present application. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0116] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in this application can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0117] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical solution of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present application.

Claims

1. A biosynthetic method, characterized in that: The method comprises: Obtaining sequence data for synthetic organisms; Generate an initial experimental task according to the sequence data and the experimental data input by the user; Testing the initial experimental task; Based on the qualified target experimental tasks, the intelligent production scheduling algorithm is called to generate the target production scheduling plan; Generate a scheduling instruction set corresponding to the target experimental task according to the target production scheduling plan; Generate a driving instruction corresponding to the scheduling instruction set, and send the driving instruction to the experimental equipment, control the experimental equipment to execute the target experimental task, and obtain the synthetic organism and the experimental result data of the synthetic organism.

2. The biosynthesis method according to claim 1, characterized in that If there are multiple synthetic organisms, the method further comprises: A deep learning model is constructed, and the deep learning model is used to train sequence data of multiple synthetic organisms and experimental result data to obtain target sequence data.

3. The biosynthesis method according to claim 2, characterized in that The deep learning model is used to train the sequence data of multiple synthetic organisms and the experimental result data to obtain the target sequence data, including: evaluating the plurality of synthetic organisms based on the experimental result data of the plurality of synthetic organisms to obtain evaluation results; According to the evaluation result, a target synthetic organism is screened from the multiple synthetic organisms, and sequence data of the target synthetic organism is determined as first target sequence data; Generate second target sequence data based on the first target sequence data.

4. The biosynthesis method according to claim 3, characterized in that Generating second target sequence data according to the first target sequence data comprises: The first target sequence data is modified or a mutation is introduced into the first target sequence data to obtain the second target sequence data.

5. The biosynthesis method according to claim 1, characterized in that If there are multiple target experimental tasks, each of which has a corresponding priority, the intelligent production scheduling algorithm is called to generate a target production scheduling plan based on the multiple target experimental tasks, the priorities of the multiple target experimental tasks, and the equipment status of the experimental equipment involved in the multiple target experimental tasks.

6. The biosynthesis method according to claim 5, characterized in that The step of calling the intelligent production scheduling algorithm to generate a target production scheduling plan according to the multiple target experimental tasks, the priorities of the multiple target experimental tasks, and the equipment states of the experimental equipment involved in the multiple target experimental tasks includes: Determine the experiment order of the multiple target experiment tasks according to the priorities of the multiple target experiment tasks; Disassemble each target experimental task according to the experimental sequence to obtain the experimental steps in each target experimental task, the number of devices for the experimental steps, and the experimental duration; Modeling the number of devices, the device status, and the experiment duration to obtain a production scheduling model, and constructing a constraint condition function; The production scheduling model and the constraint condition function are optimized to obtain the target production scheduling plan.

7. The biosynthesis method according to claim 6, characterized in that The generating of the scheduling instruction set corresponding to the target experimental task according to the target production scheduling plan includes: Adding the target production schedule and the multiple target experimental tasks to a scheduling queue; Determine the experimental operation of each experimental step in each target experimental task and each experimental device corresponding to each experimental operation, and generate a scheduling instruction for each experimental operation of each experimental device; Based on the scheduling instructions of all experimental steps of each target experimental task, a scheduling instruction set of each target experimental task is obtained.

8. The biosynthesis method according to claim 1, characterized in that Before sending the driving instruction to the experimental device, the method further includes: The device status of the experimental device is obtained, and whether the scheduling instruction set matches the device status is detected.

9. A biosynthetic system for implementing the biosynthetic method according to any one of claims 1 to 8, characterized in that: The biosynthesis system includes: a protein sequence design platform, a data platform subsystem, a cloud laboratory subsystem, an intelligent production scheduling subsystem, a dispatch center subsystem, an equipment control subsystem and experimental equipment, wherein: The protein sequence design platform is used to obtain sequence data of synthetic organisms and send the sequence data to the data platform subsystem; The data platform subsystem is used to send the received sequence data to the cloud laboratory subsystem; The cloud laboratory subsystem is used to generate an initial experimental task according to the sequence data and the experimental data input by the user, and send the initial experimental task to the intelligent production scheduling subsystem; The intelligent production scheduling subsystem is used to detect the initial experimental tasks, call the intelligent production scheduling algorithm to generate a target production scheduling plan based on the qualified target experimental tasks, and send the target production scheduling plan and the target experimental tasks to the scheduling center subsystem; The dispatch center subsystem is used to generate a dispatch instruction set corresponding to the target experimental task according to the target production scheduling plan, and send the dispatch instruction set to the equipment control subsystem; The device control subsystem is used to generate driving instructions corresponding to the scheduling instruction set, and send the driving instructions to the experimental equipment, control the experimental equipment to perform the target experimental task, and obtain the synthetic organism and the experimental result data of the synthetic organism.

10. The biosynthesis system according to claim 9, characterized in that The data platform subsystem receives data from the protein sequence design platform, the cloud laboratory subsystem, the intelligent production scheduling subsystem, the equipment control subsystem and the experimental equipment, and analyzes and visualizes the received data.

Images