CN117953977B - Recombinant mesenchymal stem cell culture control method and system - Google Patents
Recombinant mesenchymal stem cell culture control method and system Download PDFInfo
- Publication number
- CN117953977B CN117953977B CN202410352712.3A CN202410352712A CN117953977B CN 117953977 B CN117953977 B CN 117953977B CN 202410352712 A CN202410352712 A CN 202410352712A CN 117953977 B CN117953977 B CN 117953977B
- Authority
- CN
- China
- Prior art keywords
- culture
- data
- mesenchymal stem
- stem cell
- network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 210000002901 mesenchymal stem cell Anatomy 0.000 title claims abstract description 200
- 238000004113 cell culture Methods 0.000 title claims abstract description 192
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000011217 control strategy Methods 0.000 claims abstract description 107
- 230000000694 effects Effects 0.000 claims abstract description 42
- 238000012549 training Methods 0.000 claims description 33
- 239000013598 vector Substances 0.000 claims description 24
- 238000012795 verification Methods 0.000 claims description 18
- 238000002372 labelling Methods 0.000 claims description 10
- 238000005215 recombination Methods 0.000 claims description 6
- 230000006798 recombination Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 2
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 210000002894 multi-fate stem cell Anatomy 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 210000000130 stem cell Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B40/00—ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Bioethics (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- Epidemiology (AREA)
- Public Health (AREA)
- Biotechnology (AREA)
- General Health & Medical Sciences (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Image Analysis (AREA)
- Micro-Organisms Or Cultivation Processes Thereof (AREA)
Abstract
The invention provides a method and a system for controlling the culture of recombinant mesenchymal stem cells, which are characterized in that a control strategy decision is carried out on each priori culture result data based on a basic recombinant mesenchymal stem cell culture control network, decision control strategy data of each priori culture result data are respectively obtained, the decision control strategy data are judged based on culture effect data related to each priori culture result data, the culture control strategy of each priori culture result data is marked based on the judgment result, the recombinant mesenchymal stem cell culture control network is obtained by updating network weight parameters based on the marked priori culture result data and basic reference culture control learning data sequences, thereby the network weight parameters of the recombinant mesenchymal stem cell culture control network can be updated by utilizing the culture effect data, the marking workload is reduced, the recombinant mesenchymal stem cell culture control network can be trained with high efficiency, and the accuracy of culture control decisions is improved.
Description
Technical Field
The invention relates to the technical field of recombinant mesenchymal stem cell culture control systems, in particular to a recombinant mesenchymal stem cell culture control method and system.
Background
Recombinant mesenchymal stem cells are multipotent stem cells that share all the common properties of stem cells, namely self-renewal and multipotent differentiation. The clinical application is the greatest, along with the continuous development of the medical industry, the recombinant mesenchymal stem cell culture data needs to be controlled in real time in the recombinant mesenchymal stem cell culture process, for example, the recombinant mesenchymal stem cell culture control decision model according to the AI technology can be used for controlling, and the decision accuracy of the recombinant mesenchymal stem cell culture control decision model in the prior art is lower.
Disclosure of Invention
In view of the above, an object of the embodiments of the present invention is to provide a method and a system for controlling the culture of a recombinant mesenchymal stem cell, which are based on a basic recombinant mesenchymal stem cell culture control network to perform a control policy decision on each priori culture result data, respectively obtain decision control policy data of each priori culture result data, and based on culture effect data associated with each priori culture result data, determine the decision control policy data, label the culture control policy of each priori culture result data based on the determination result, and based on each calibrated priori culture result data and a basic reference culture control learning data sequence, update a network weight parameter to obtain a recombinant mesenchymal stem cell culture control network, thereby performing network weight parameter update on the recombinant mesenchymal stem cell culture control network by using the culture effect data, reducing the labeling workload, and performing high-efficiency training on the recombinant mesenchymal stem cell culture control network, and improving the accuracy of the culture control decision of the recombinant mesenchymal stem cell culture control network.
According to an aspect of an embodiment of the present invention, there is provided a recombinant mesenchymal stem cell culture control method, the method comprising:
obtaining recombinant mesenchymal stem cell culture state data;
extracting state feature vectors of the recombinant mesenchymal stem cell culture state data;
According to a training-completed recombinant mesenchymal stem cell culture control network, taking a state characteristic vector of the recombinant mesenchymal stem cell culture state data as network loading data to obtain culture control strategy data of the recombinant mesenchymal stem cell culture state data, wherein the recombinant mesenchymal stem cell culture control network is generated by updating network weight parameters based on calibrated prior culture result data and basic reference culture control learning data sequences, the calibrated prior culture result data are obtained by training and calibrating the culture control strategy data according to the basic recombinant mesenchymal stem cell culture control network and associated culture effect data, the basic recombinant mesenchymal stem cell culture control network is generated by updating network weight based on basic reference culture control learning data sequences, and the basic reference culture control learning data are reference recombinant mesenchymal stem cell culture state data with culture control strategy data training calibration.
In one possible embodiment, the training step of the recombinant mesenchymal stem cell culture control network comprises:
Acquiring each priori culture result data, and performing control strategy decision on each priori culture result data based on a basic recombination mesenchymal stem cell culture control network to respectively acquire decision control strategy data of each priori culture result data;
Acquiring culture effect data related to each priori culture result data, judging decision control strategy data of each priori culture result data based on the culture effect data, and labeling a culture control strategy of each priori culture result data based on a judging result, wherein the culture effect data comprises characteristic data of culture reliability observation data corresponding to the priori culture result data;
And updating the network weight parameters based on the calibrated prior culture result data and the basic reference culture control learning data sequence to obtain the recombinant mesenchymal stem cell culture control network.
In one possible implementation manner, the decision control strategy data of each priori culture result data is judged based on the culture effect data, and the culture control strategy of each priori culture result data is marked based on the judgment result, which specifically includes:
extracting control feature vectors associated with a culture control strategy from the culture effect data;
based on the extracted control feature vector, determining culture reliability observation data of each priori culture result data;
And matching the culture reliability observation data of each priori culture result data with decision control strategy data, if so, marking the culture control strategy of each priori culture result data as the decision control strategy data, and if not, marking the culture control strategy data training of each priori culture result data as strategy data represented by the culture reliability observation data.
In one possible implementation manner, based on the calibrated a priori culture result data and the basic reference culture control learning data sequence, the network weight parameter updating obtains a recombinant mesenchymal stem cell culture control network, which specifically comprises:
and retraining to obtain a recombinant mesenchymal stem cell culture control network based on the calibrated priori culture result data and the basic reference culture control learning data sequence.
In one possible implementation manner, based on the calibrated a priori culture result data and the basic reference culture control learning data sequence, the network weight parameter updating obtains a recombinant mesenchymal stem cell culture control network, which specifically comprises:
And updating and training the basic recombinant mesenchymal stem cell culture control network based on the calibrated prior culture result data and the basic reference culture control learning data sequence.
In one possible embodiment, after the network weight parameter update obtains the recombinant mesenchymal stem cell culture control network, further comprising:
acquiring a verification culture control learning data sequence;
Based on a recombinant mesenchymal stem cell culture control network with updated network weight parameters, carrying out culture control strategy decision on each piece of verification culture control learning data in the verification culture control learning data sequence, and based on decision results, determining network performance indexes of the recombinant mesenchymal stem cell culture control network with updated network weight parameters;
If the network performance index of the recombinant mesenchymal stem cell culture control network after the network weight parameter update is determined to be greater than the network performance index of the basic recombinant mesenchymal stem cell culture control network, merging the calibrated priori culture result data with the basic reference culture control learning data sequence, taking the merged data as the basic reference culture control learning data sequence for the next network weight parameter update, and taking the recombinant mesenchymal stem cell culture control network after the network weight parameter update as the basic recombinant mesenchymal stem cell culture control network for the next network weight parameter update;
If the network performance index of the recombinant mesenchymal stem cell culture control network after the network weight parameter update is not greater than the network performance index of the basic recombinant mesenchymal stem cell culture control network, the basic reference culture control learning data sequence is still used as the basic reference culture control learning data sequence for the next network weight parameter update, and the basic recombinant mesenchymal stem cell culture control network is still used as the basic recombinant mesenchymal stem cell culture control network for the next network weight parameter update.
According to another aspect of an embodiment of the present invention, there is provided a recombinant mesenchymal stem cell culture control system, comprising:
The acquisition unit is used for acquiring the culture state data of the recombinant mesenchymal stem cells;
the extraction unit is used for extracting the state characteristic vector of the recombinant mesenchymal stem cell culture state data;
The obtaining unit is used for obtaining culture control strategy data of the recombinant mesenchymal stem cell culture state data by taking a state characteristic vector of the recombinant mesenchymal stem cell culture state data as network loading data according to a trained recombinant mesenchymal stem cell culture control network, wherein the recombinant mesenchymal stem cell culture control network is generated by carrying out network weight parameter updating based on calibrated prior culture result data and basic reference culture control learning data sequences, the calibrated prior culture result data are obtained by carrying out culture control strategy data training calibration on the prior culture result data according to the basic recombinant mesenchymal stem cell culture control network and associated culture effect data, the basic recombinant mesenchymal stem cell culture control network is generated by carrying out network weight updating based on basic reference culture control learning data sequences, and the basic reference culture control learning data are reference recombinant mesenchymal stem cell culture state data with culture control strategy data training calibration.
In a possible implementation manner, the device further comprises a training unit, specifically configured to:
Acquiring each priori culture result data, and performing control strategy decision on each priori culture result data based on a basic recombination mesenchymal stem cell culture control network to respectively acquire decision control strategy data of each priori culture result data;
Acquiring culture effect data related to each priori culture result data, judging decision control strategy data of each priori culture result data based on the culture effect data, and labeling a culture control strategy of each priori culture result data based on a judging result, wherein the culture effect data comprises characteristic data of culture reliability observation data corresponding to the priori culture result data;
Based on the calibrated prior culture result data and the basic reference culture control learning data sequence, updating the network weight parameters to obtain a recombinant mesenchymal stem cell culture control network;
Judging decision control strategy data of each priori culture result data based on the culture effect data, and labeling the culture control strategy of each priori culture result data based on the judging result, wherein the decision control strategy comprises the following specific steps:
extracting control feature vectors associated with a culture control strategy from the culture effect data;
based on the extracted control feature vector, determining culture reliability observation data of each priori culture result data;
Matching the culture reliability observation data of each priori culture result data with decision control strategy data, if the culture reliability observation data is matched with the decision control strategy data, marking the culture control strategy of each priori culture result data as the decision control strategy data, and if the culture reliability observation data is not matched with the decision control strategy data, marking the culture control strategy data training of each priori culture result data as strategy data represented by the culture reliability observation data;
Based on the calibrated prior culture result data and the basic reference culture control learning data sequence, updating the network weight parameters to obtain a recombinant mesenchymal stem cell culture control network, which specifically comprises the following steps:
Retraining to obtain a recombinant mesenchymal stem cell culture control network based on the calibrated priori culture result data and the basic reference culture control learning data sequence;
Based on the calibrated prior culture result data and the basic reference culture control learning data sequence, updating the network weight parameters to obtain a recombinant mesenchymal stem cell culture control network, which specifically comprises the following steps:
updating and training the basic recombinant mesenchymal stem cell culture control network based on the calibrated priori culture result data and the basic reference culture control learning data sequence;
after the network weight parameter is updated to obtain the recombinant mesenchymal stem cell culture control network, the training unit is specifically further configured to:
acquiring a verification culture control learning data sequence;
Based on a recombinant mesenchymal stem cell culture control network with updated network weight parameters, carrying out culture control strategy decision on each piece of verification culture control learning data in the verification culture control learning data sequence, and based on decision results, determining network performance indexes of the recombinant mesenchymal stem cell culture control network with updated network weight parameters;
If the network performance index of the recombinant mesenchymal stem cell culture control network after the network weight parameter update is determined to be greater than the network performance index of the basic recombinant mesenchymal stem cell culture control network, merging the calibrated priori culture result data with the basic reference culture control learning data sequence, taking the merged data as the basic reference culture control learning data sequence for the next network weight parameter update, and taking the recombinant mesenchymal stem cell culture control network after the network weight parameter update as the basic recombinant mesenchymal stem cell culture control network for the next network weight parameter update;
If the network performance index of the recombinant mesenchymal stem cell culture control network after the network weight parameter update is not greater than the network performance index of the basic recombinant mesenchymal stem cell culture control network, the basic reference culture control learning data sequence is still used as the basic reference culture control learning data sequence for the next network weight parameter update, and the basic recombinant mesenchymal stem cell culture control network is still used as the basic recombinant mesenchymal stem cell culture control network for the next network weight parameter update.
According to another aspect of an embodiment of the present invention, there is provided an electronic device including a memory and a processor; the memory is used for storing programs; the processor is configured to execute the program to implement the steps of the recombinant mesenchymal stem cell culture control method described in any one of the above.
According to another aspect of an embodiment of the present invention, there is provided a readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the recombinant mesenchymal stem cell culture control method of any one of the above.
The foregoing objects, features and advantages of embodiments of the invention will be more readily apparent from the following detailed description of the embodiments taken in conjunction with the accompanying drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 shows a schematic diagram of components of a server provided by an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a method and a system for controlling the culture of recombinant mesenchymal stem cells according to an embodiment of the present invention;
fig. 3 is a functional block diagram of a recombinant mesenchymal stem cell culture control system according to an embodiment of the present invention.
Detailed Description
In order to enable those skilled in the art to better understand the present invention, a technical solution of the present embodiment of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiment of the present invention, and it is apparent that the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. All other embodiments, which can be made by those skilled in the art without the benefit of the teachings of this invention, are intended to fall within the scope of the invention.
The terms first, second, third and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented, for example, in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Fig. 1 shows an exemplary component diagram of a server 100. The server 100 may include one or more processors 104, such as one or more Central Processing Units (CPUs), each of which may implement one or more hardware threads. The server 100 may also include any storage medium 106 for storing any kind of information such as code, settings, data, etc. For example, and without limitation, storage medium 106 may include any one or more of the following combinations: any type of RAM, any type of ROM, flash memory devices, hard disks, optical disks, etc. More generally, any storage medium may store information using any technique. Further, any storage medium may provide volatile or non-volatile retention of information. Further, any storage medium may represent fixed or removable components of server 100. In one case, the server 100 may perform any of the operations of the associated instructions when the processor 104 executes the associated instructions stored in any storage medium or combination of storage media. The server 100 also includes one or more drive units 108, such as a hard disk drive unit, an optical disk drive unit, etc., for interacting with any storage media.
The server 100 also includes input/output 110 (I/O) for receiving various inputs (via input unit 112) and for providing various outputs (via output unit 114). One particular output mechanism may include a presentation device 116 and an associated Graphical User Interface (GUI) 118. The server 100 may also include one or more network interfaces 120 for exchanging data with other devices via one or more communication units 122. One or more communication buses 124 couple the components described above together.
The communication unit 122 may be implemented in any manner, for example, via a local area network, a wide area network (e.g., the internet), a point-to-point connection, etc., or any combination thereof. The communication unit 122 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers 100, etc., governed by any protocol or combination of protocols.
Fig. 2 is a schematic flow chart of a method and a system for controlling the culture of recombinant mesenchymal stem cells according to an embodiment of the present invention, which may be executed by the server 100 shown in fig. 1, and detailed steps of the method and the system for controlling the culture of recombinant mesenchymal stem cells are described below.
Step S110, obtaining recombinant mesenchymal stem cell culture state data;
step S120, extracting state feature vectors of the recombinant mesenchymal stem cell culture state data;
Step S130, according to a trained recombinant mesenchymal stem cell culture control network, taking a state characteristic vector of the recombinant mesenchymal stem cell culture state data as network loading data to obtain culture control strategy data of the recombinant mesenchymal stem cell culture state data, wherein the recombinant mesenchymal stem cell culture control network carries out network weight parameter updating based on calibrated prior culture result data and basic reference culture control learning data sequences to generate culture control strategy data, the calibrated prior culture result data are obtained after the culture control strategy data are trained and calibrated according to the basic recombinant mesenchymal stem cell culture control network and associated culture effect data, the basic recombinant mesenchymal stem cell culture control network is generated by carrying out network weight updating based on basic reference culture control learning data sequences, and the basic reference culture control learning data are reference recombinant mesenchymal stem cell culture state data with culture control strategy data training calibration.
Based on the above steps, the embodiment carries out control strategy decision on each priori culture result data based on the basic recombinant mesenchymal stem cell culture control network, respectively obtains decision control strategy data of each priori culture result data, discriminates the decision control strategy data based on culture effect data related to each priori culture result data, marks the culture control strategy of each priori culture result data based on the discrimination result, and obtains the recombinant mesenchymal stem cell culture control network based on each calibrated priori culture result data and basic reference culture control learning data sequence, thereby carrying out network weight parameter update on the recombinant mesenchymal stem cell culture control network by utilizing the culture effect data, reducing the marking workload, carrying out high-efficiency training on the recombinant mesenchymal stem cell culture control network, and improving the accuracy of culture control decision of the recombinant mesenchymal stem cell culture control network.
In one possible embodiment, the training step of the recombinant mesenchymal stem cell culture control network comprises:
Acquiring each priori culture result data, and performing control strategy decision on each priori culture result data based on a basic recombination mesenchymal stem cell culture control network to respectively acquire decision control strategy data of each priori culture result data;
Acquiring culture effect data related to each priori culture result data, judging decision control strategy data of each priori culture result data based on the culture effect data, and labeling a culture control strategy of each priori culture result data based on a judging result, wherein the culture effect data comprises characteristic data of culture reliability observation data corresponding to the priori culture result data;
And updating the network weight parameters based on the calibrated prior culture result data and the basic reference culture control learning data sequence to obtain the recombinant mesenchymal stem cell culture control network.
In one possible implementation manner, the decision control strategy data of each priori culture result data is judged based on the culture effect data, and the culture control strategy of each priori culture result data is marked based on the judgment result, which specifically includes:
extracting control feature vectors associated with a culture control strategy from the culture effect data;
based on the extracted control feature vector, determining culture reliability observation data of each priori culture result data;
And matching the culture reliability observation data of each priori culture result data with decision control strategy data, if so, marking the culture control strategy of each priori culture result data as the decision control strategy data, and if not, marking the culture control strategy data training of each priori culture result data as strategy data represented by the culture reliability observation data.
In one possible implementation manner, based on the calibrated a priori culture result data and the basic reference culture control learning data sequence, the network weight parameter updating obtains a recombinant mesenchymal stem cell culture control network, which specifically comprises:
and retraining to obtain a recombinant mesenchymal stem cell culture control network based on the calibrated priori culture result data and the basic reference culture control learning data sequence.
In one possible implementation manner, based on the calibrated a priori culture result data and the basic reference culture control learning data sequence, the network weight parameter updating obtains a recombinant mesenchymal stem cell culture control network, which specifically comprises:
And updating and training the basic recombinant mesenchymal stem cell culture control network based on the calibrated prior culture result data and the basic reference culture control learning data sequence.
In one possible embodiment, after the network weight parameter update obtains the recombinant mesenchymal stem cell culture control network, further comprising:
acquiring a verification culture control learning data sequence;
Based on a recombinant mesenchymal stem cell culture control network with updated network weight parameters, carrying out culture control strategy decision on each piece of verification culture control learning data in the verification culture control learning data sequence, and based on decision results, determining network performance indexes of the recombinant mesenchymal stem cell culture control network with updated network weight parameters;
If the network performance index of the recombinant mesenchymal stem cell culture control network after the network weight parameter update is determined to be greater than the network performance index of the basic recombinant mesenchymal stem cell culture control network, merging the calibrated priori culture result data with the basic reference culture control learning data sequence, taking the merged data as the basic reference culture control learning data sequence for the next network weight parameter update, and taking the recombinant mesenchymal stem cell culture control network after the network weight parameter update as the basic recombinant mesenchymal stem cell culture control network for the next network weight parameter update;
If the network performance index of the recombinant mesenchymal stem cell culture control network after the network weight parameter update is not greater than the network performance index of the basic recombinant mesenchymal stem cell culture control network, the basic reference culture control learning data sequence is still used as the basic reference culture control learning data sequence for the next network weight parameter update, and the basic recombinant mesenchymal stem cell culture control network is still used as the basic recombinant mesenchymal stem cell culture control network for the next network weight parameter update.
Fig. 3 is a functional block diagram of a recombinant mesenchymal stem cell culture control system 200 according to an embodiment of the present invention, where the functions implemented by the recombinant mesenchymal stem cell culture control system 200 may correspond to the steps executed by the above-described method. The recombinant mesenchymal stem cell culture control system 200 may be understood as the above-mentioned server 100, or a processor of the server 100, or may be understood as a component which is independent from the above-mentioned server 100 or processor and performs the functions of the present invention under the control of the server 100, as shown in fig. 3, and the functions of each functional module of the recombinant mesenchymal stem cell culture control system 200 will be described in detail.
An acquisition unit 210 for acquiring recombinant mesenchymal stem cell culture state data;
an extracting unit 220 for extracting a state feature vector of the recombinant mesenchymal stem cell culture state data;
The obtaining unit 230 is configured to obtain culture control policy data of the recombinant mesenchymal stem cell culture state data according to the trained recombinant mesenchymal stem cell culture control network by taking a state feature vector of the recombinant mesenchymal stem cell culture state data as network loading data, where the recombinant mesenchymal stem cell culture control network performs network weight parameter updating based on calibrated prior culture result data and a basic reference culture control learning data sequence, and generates culture control policy data, and the calibrated prior culture result data is obtained by performing culture control policy data training calibration on the prior culture result data according to the basic recombinant mesenchymal stem cell culture control network and associated culture effect data, and the basic recombinant mesenchymal stem cell culture control network is generated by performing network weight updating based on a basic reference culture control learning data sequence, where the basic reference culture control learning data is reference recombinant mesenchymal stem cell culture state data calibrated by the culture control policy data.
The recombinant mesenchymal stem cell culture control system further comprises a training unit, and the training unit is specifically used for:
Acquiring each priori culture result data, and performing control strategy decision on each priori culture result data based on a basic recombination mesenchymal stem cell culture control network to respectively acquire decision control strategy data of each priori culture result data;
Acquiring culture effect data related to each priori culture result data, judging decision control strategy data of each priori culture result data based on the culture effect data, and labeling a culture control strategy of each priori culture result data based on a judging result, wherein the culture effect data comprises characteristic data of culture reliability observation data corresponding to the priori culture result data;
Based on the calibrated prior culture result data and the basic reference culture control learning data sequence, updating the network weight parameters to obtain a recombinant mesenchymal stem cell culture control network;
Judging decision control strategy data of each priori culture result data based on the culture effect data, and labeling the culture control strategy of each priori culture result data based on the judging result, wherein the decision control strategy comprises the following specific steps:
extracting control feature vectors associated with a culture control strategy from the culture effect data;
based on the extracted control feature vector, determining culture reliability observation data of each priori culture result data;
Matching the culture reliability observation data of each priori culture result data with decision control strategy data, if the culture reliability observation data is matched with the decision control strategy data, marking the culture control strategy of each priori culture result data as the decision control strategy data, and if the culture reliability observation data is not matched with the decision control strategy data, marking the culture control strategy data training of each priori culture result data as strategy data represented by the culture reliability observation data;
Based on the calibrated prior culture result data and the basic reference culture control learning data sequence, updating the network weight parameters to obtain a recombinant mesenchymal stem cell culture control network, which specifically comprises the following steps:
Retraining to obtain a recombinant mesenchymal stem cell culture control network based on the calibrated priori culture result data and the basic reference culture control learning data sequence;
Based on the calibrated prior culture result data and the basic reference culture control learning data sequence, updating the network weight parameters to obtain a recombinant mesenchymal stem cell culture control network, which specifically comprises the following steps:
updating and training the basic recombinant mesenchymal stem cell culture control network based on the calibrated priori culture result data and the basic reference culture control learning data sequence;
after the network weight parameter is updated to obtain the recombinant mesenchymal stem cell culture control network, the training unit is specifically further configured to:
acquiring a verification culture control learning data sequence;
Based on a recombinant mesenchymal stem cell culture control network with updated network weight parameters, carrying out culture control strategy decision on each piece of verification culture control learning data in the verification culture control learning data sequence, and based on decision results, determining network performance indexes of the recombinant mesenchymal stem cell culture control network with updated network weight parameters;
If the network performance index of the recombinant mesenchymal stem cell culture control network after the network weight parameter update is determined to be greater than the network performance index of the basic recombinant mesenchymal stem cell culture control network, merging the calibrated priori culture result data with the basic reference culture control learning data sequence, taking the merged data as the basic reference culture control learning data sequence for the next network weight parameter update, and taking the recombinant mesenchymal stem cell culture control network after the network weight parameter update as the basic recombinant mesenchymal stem cell culture control network for the next network weight parameter update;
If the network performance index of the recombinant mesenchymal stem cell culture control network after the network weight parameter update is not greater than the network performance index of the basic recombinant mesenchymal stem cell culture control network, the basic reference culture control learning data sequence is still used as the basic reference culture control learning data sequence for the next network weight parameter update, and the basic recombinant mesenchymal stem cell culture control network is still used as the basic recombinant mesenchymal stem cell culture control network for the next network weight parameter update.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any accompanying drawings in the claims should not be taken as limiting the claim concerned.
Claims (7)
1. A recombinant mesenchymal stem cell culture control method, comprising:
obtaining recombinant mesenchymal stem cell culture state data;
extracting state feature vectors of the recombinant mesenchymal stem cell culture state data;
According to a training-completed recombinant mesenchymal stem cell culture control network, taking a state characteristic vector of the recombinant mesenchymal stem cell culture state data as network loading data to obtain culture control strategy data of the recombinant mesenchymal stem cell culture state data, wherein the recombinant mesenchymal stem cell culture control network carries out network weight parameter updating based on calibrated prior culture result data and basic reference culture control learning data sequences to generate culture control strategy data, the calibrated prior culture result data are obtained by training and calibrating the culture control strategy data according to the basic recombinant mesenchymal stem cell culture control network and associated culture effect data, the basic recombinant mesenchymal stem cell culture control network is generated by carrying out network weight updating based on basic reference culture control learning data sequences, and the basic reference culture control learning data are reference recombinant mesenchymal stem cell culture state data with culture control strategy data training calibration;
the training step of the recombinant mesenchymal stem cell culture control network comprises the following steps:
Acquiring each priori culture result data, and performing control strategy decision on each priori culture result data based on a basic recombination mesenchymal stem cell culture control network to respectively acquire decision control strategy data of each priori culture result data;
Acquiring culture effect data related to each priori culture result data, judging decision control strategy data of each priori culture result data based on the culture effect data, and labeling a culture control strategy of each priori culture result data based on a judging result, wherein the culture effect data comprises characteristic data of culture reliability observation data corresponding to the priori culture result data;
Based on the calibrated prior culture result data and the basic reference culture control learning data sequence, updating the network weight parameters to obtain a recombinant mesenchymal stem cell culture control network;
the method comprises the steps of obtaining the recombinant mesenchymal stem cell culture control network based on the calibration prior culture result data and the basic reference culture control learning data sequence, wherein the network weight parameter is updated, and the method specifically comprises the following steps:
and retraining to obtain a recombinant mesenchymal stem cell culture control network based on the calibrated priori culture result data and the basic reference culture control learning data sequence.
2. The method according to claim 1, wherein the decision control strategy data of each priori culture result data is determined based on the culture effect data, and the culture control strategy of each priori culture result data is labeled based on the determination result, and the method specifically comprises:
extracting control feature vectors associated with a culture control strategy from the culture effect data;
based on the extracted control feature vector, determining culture reliability observation data of each priori culture result data;
And matching the culture reliability observation data of each priori culture result data with decision control strategy data, if so, marking the culture control strategy of each priori culture result data as the decision control strategy data, and if not, marking the culture control strategy data training of each priori culture result data as strategy data represented by the culture reliability observation data.
3. The method according to claim 1, further comprising, after the network weight parameter is updated to obtain the recombinant mesenchymal stem cell culture control network:
acquiring a verification culture control learning data sequence;
Based on a recombinant mesenchymal stem cell culture control network with updated network weight parameters, carrying out culture control strategy decision on each piece of verification culture control learning data in the verification culture control learning data sequence, and based on decision results, determining network performance indexes of the recombinant mesenchymal stem cell culture control network with updated network weight parameters;
If the network performance index of the recombinant mesenchymal stem cell culture control network after the network weight parameter update is determined to be greater than the network performance index of the basic recombinant mesenchymal stem cell culture control network, merging the calibrated priori culture result data with the basic reference culture control learning data sequence, taking the merged data as the basic reference culture control learning data sequence for the next network weight parameter update, and taking the recombinant mesenchymal stem cell culture control network after the network weight parameter update as the basic recombinant mesenchymal stem cell culture control network for the next network weight parameter update;
If the network performance index of the recombinant mesenchymal stem cell culture control network after the network weight parameter update is not greater than the network performance index of the basic recombinant mesenchymal stem cell culture control network, the basic reference culture control learning data sequence is still used as the basic reference culture control learning data sequence for the next network weight parameter update, and the basic recombinant mesenchymal stem cell culture control network is still used as the basic recombinant mesenchymal stem cell culture control network for the next network weight parameter update.
4. A recombinant mesenchymal stem cell culture control system, comprising:
The acquisition unit is used for acquiring the culture state data of the recombinant mesenchymal stem cells;
the extraction unit is used for extracting the state characteristic vector of the recombinant mesenchymal stem cell culture state data;
The obtaining unit is used for obtaining culture control strategy data of the recombinant mesenchymal stem cell culture state data by taking a state characteristic vector of the recombinant mesenchymal stem cell culture state data as network loading data according to a trained recombinant mesenchymal stem cell culture control network, wherein the recombinant mesenchymal stem cell culture control network is generated by carrying out network weight parameter updating based on calibrated prior culture result data and basic reference culture control learning data sequences, and generates culture control strategy data, the calibrated prior culture result data are obtained by carrying out culture control strategy data training calibration on the prior culture result data according to the basic recombinant mesenchymal stem cell culture control network and associated culture effect data, and the basic recombinant mesenchymal stem cell culture control network is generated by carrying out network weight updating based on basic reference culture control learning data sequences, wherein the basic reference culture control learning data are reference recombinant mesenchymal stem cell culture state data with culture control strategy data training calibration;
The training unit is specifically used for:
Acquiring each priori culture result data, and performing control strategy decision on each priori culture result data based on a basic recombination mesenchymal stem cell culture control network to respectively acquire decision control strategy data of each priori culture result data;
Acquiring culture effect data related to each priori culture result data, judging decision control strategy data of each priori culture result data based on the culture effect data, and labeling a culture control strategy of each priori culture result data based on a judging result, wherein the culture effect data comprises characteristic data of culture reliability observation data corresponding to the priori culture result data;
Based on the calibrated prior culture result data and the basic reference culture control learning data sequence, updating the network weight parameters to obtain a recombinant mesenchymal stem cell culture control network;
Judging decision control strategy data of each priori culture result data based on the culture effect data, and labeling the culture control strategy of each priori culture result data based on the judging result, wherein the decision control strategy comprises the following specific steps:
extracting control feature vectors associated with a culture control strategy from the culture effect data;
based on the extracted control feature vector, determining culture reliability observation data of each priori culture result data;
Matching the culture reliability observation data of each priori culture result data with decision control strategy data, if the culture reliability observation data is matched with the decision control strategy data, marking the culture control strategy of each priori culture result data as the decision control strategy data, and if the culture reliability observation data is not matched with the decision control strategy data, marking the culture control strategy data training of each priori culture result data as strategy data represented by the culture reliability observation data;
Based on the calibrated prior culture result data and the basic reference culture control learning data sequence, updating the network weight parameters to obtain a recombinant mesenchymal stem cell culture control network, which specifically comprises the following steps:
Retraining to obtain a recombinant mesenchymal stem cell culture control network based on the calibrated priori culture result data and the basic reference culture control learning data sequence;
Based on the calibrated prior culture result data and the basic reference culture control learning data sequence, updating the network weight parameters to obtain a recombinant mesenchymal stem cell culture control network, which specifically comprises the following steps:
And updating and training the basic recombinant mesenchymal stem cell culture control network based on the calibrated prior culture result data and the basic reference culture control learning data sequence.
5. The recombinant mesenchymal stem cell culture control system of claim 4,
After the network weight parameter is updated to obtain the recombinant mesenchymal stem cell culture control network, the training unit is specifically further configured to:
acquiring a verification culture control learning data sequence;
Based on a recombinant mesenchymal stem cell culture control network with updated network weight parameters, carrying out culture control strategy decision on each piece of verification culture control learning data in the verification culture control learning data sequence, and based on decision results, determining network performance indexes of the recombinant mesenchymal stem cell culture control network with updated network weight parameters;
If the network performance index of the recombinant mesenchymal stem cell culture control network after the network weight parameter update is determined to be greater than the network performance index of the basic recombinant mesenchymal stem cell culture control network, merging the calibrated priori culture result data with the basic reference culture control learning data sequence, taking the merged data as the basic reference culture control learning data sequence for the next network weight parameter update, and taking the recombinant mesenchymal stem cell culture control network after the network weight parameter update as the basic recombinant mesenchymal stem cell culture control network for the next network weight parameter update;
If the network performance index of the recombinant mesenchymal stem cell culture control network after the network weight parameter update is not greater than the network performance index of the basic recombinant mesenchymal stem cell culture control network, the basic reference culture control learning data sequence is still used as the basic reference culture control learning data sequence for the next network weight parameter update, and the basic recombinant mesenchymal stem cell culture control network is still used as the basic recombinant mesenchymal stem cell culture control network for the next network weight parameter update.
6. An electronic device comprising a memory and a processor; the memory is used for storing programs; the processor for executing the program to realize the respective steps of the recombinant mesenchymal stem cell culture control method according to any one of claims 1 to 3.
7. A readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the respective steps of the recombinant mesenchymal stem cell culture control method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410352712.3A CN117953977B (en) | 2024-03-26 | 2024-03-26 | Recombinant mesenchymal stem cell culture control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410352712.3A CN117953977B (en) | 2024-03-26 | 2024-03-26 | Recombinant mesenchymal stem cell culture control method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117953977A CN117953977A (en) | 2024-04-30 |
| CN117953977B true CN117953977B (en) | 2024-06-11 |
Family
ID=90805515
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410352712.3A Active CN117953977B (en) | 2024-03-26 | 2024-03-26 | Recombinant mesenchymal stem cell culture control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117953977B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019178561A2 (en) * | 2018-03-16 | 2019-09-19 | The United States Of America, As Represented By The Secretary, Department Of Health & Human Services | Using machine learning and/or neural networks to validate stem cells and their derivatives for use in cell therapy, drug discovery, and diagnostics |
| CN112424822A (en) * | 2018-08-06 | 2021-02-26 | 株式会社岛津制作所 | Training label image correction method, learning-completed model generation method, and image analysis device |
| KR20210155927A (en) * | 2020-06-17 | 2021-12-24 | 한양디지텍 주식회사 | Integrated system of electro-stimulation for optimal differentiation of stem cells |
| KR20230059734A (en) * | 2021-10-25 | 2023-05-03 | 고려대학교 산학협력단 | Apparatus and method for distinguishing cells using artificial intelligence |
| JP2023121191A (en) * | 2022-02-21 | 2023-08-31 | 株式会社エビデント | System for evaluating formation of functional cell aggregate, method, and program |
| CN117402821A (en) * | 2023-10-26 | 2024-01-16 | 上海鲁一细胞生物技术有限公司 | Deep learning-based umbilical cord mesenchymal stem cell separation and culture method |
-
2024
- 2024-03-26 CN CN202410352712.3A patent/CN117953977B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019178561A2 (en) * | 2018-03-16 | 2019-09-19 | The United States Of America, As Represented By The Secretary, Department Of Health & Human Services | Using machine learning and/or neural networks to validate stem cells and their derivatives for use in cell therapy, drug discovery, and diagnostics |
| CN112424822A (en) * | 2018-08-06 | 2021-02-26 | 株式会社岛津制作所 | Training label image correction method, learning-completed model generation method, and image analysis device |
| KR20210155927A (en) * | 2020-06-17 | 2021-12-24 | 한양디지텍 주식회사 | Integrated system of electro-stimulation for optimal differentiation of stem cells |
| KR20230059734A (en) * | 2021-10-25 | 2023-05-03 | 고려대학교 산학협력단 | Apparatus and method for distinguishing cells using artificial intelligence |
| JP2023121191A (en) * | 2022-02-21 | 2023-08-31 | 株式会社エビデント | System for evaluating formation of functional cell aggregate, method, and program |
| CN117402821A (en) * | 2023-10-26 | 2024-01-16 | 上海鲁一细胞生物技术有限公司 | Deep learning-based umbilical cord mesenchymal stem cell separation and culture method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117953977A (en) | 2024-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20240185130A1 (en) | Normalizing text attributes for machine learning models | |
| CN109447156B (en) | Method and apparatus for generating a model | |
| CN108229591A (en) | Neural network adaptive training method and apparatus, equipment, program and storage medium | |
| CN109726763A (en) | A kind of information assets recognition methods, device, equipment and medium | |
| CN117953977B (en) | Recombinant mesenchymal stem cell culture control method and system | |
| CN113222554A (en) | Intelligent office cooperation method and system based on big data | |
| CN117033053A (en) | Data analysis method and system applied to automobile marketing management system software | |
| CN112308149A (en) | Optimization method and device for image information identification based on machine learning | |
| CN117729119A (en) | Equipment operation data processing method and system for edge computing gateway | |
| CN110046670B (en) | Feature vector dimension reduction method and device | |
| CN111368413A (en) | Tracking management method and system for clothing production plan | |
| CN113298622A (en) | Method and system for processing e-commerce business orders based on machine learning | |
| CN116926241B (en) | Immune cell culture control method and system | |
| CN117031421B (en) | Anomaly analysis method and system of radar signal simulation system | |
| CN111899060A (en) | Advertisement management method and system based on big data | |
| CN113904782A (en) | Online cloud platform management method and system | |
| CN113282482A (en) | Compatibility test method and system for software package | |
| CN117076221A (en) | Data center scanning processing method and system | |
| CN117033052B (en) | Object abnormality diagnosis method and system based on model identification | |
| CN116806814B (en) | Mesenchymal stem cell exosome preservation temperature control method and system | |
| CN116796174A (en) | Content identification method and system for micro-service | |
| CN113850565B (en) | Maturity model-based overall process consultation project management monitoring system and method | |
| CN112232068B (en) | Intention recognition method and device, electronic equipment and storage medium | |
| CN117325164A (en) | Massage robot control method and system based on artificial intelligence | |
| CN118133980A (en) | Transmission method, device and medium of isomorphic quantum circuit |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |