CN116403662A - Research and development process based on big data, process simulation method, system and platform - Google Patents
Research and development process based on big data, process simulation method, system and platform Download PDFInfo
- Publication number
- CN116403662A CN116403662A CN202310429357.0A CN202310429357A CN116403662A CN 116403662 A CN116403662 A CN 116403662A CN 202310429357 A CN202310429357 A CN 202310429357A CN 116403662 A CN116403662 A CN 116403662A
- Authority
- CN
- China
- Prior art keywords
- data
- model
- biopharmaceutical
- preparation
- experimental
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 112
- 230000008569 process Effects 0.000 title claims abstract description 78
- 238000012827 research and development Methods 0.000 title claims abstract description 45
- 238000004088 simulation Methods 0.000 title claims abstract description 34
- 229960000074 biopharmaceutical Drugs 0.000 claims abstract description 124
- 238000002360 preparation method Methods 0.000 claims abstract description 120
- 239000003814 drug Substances 0.000 claims abstract description 102
- 229940000406 drug candidate Drugs 0.000 claims abstract description 102
- 239000003777 experimental drug Substances 0.000 claims abstract description 102
- 238000012549 training Methods 0.000 claims abstract description 79
- 238000011156 evaluation Methods 0.000 claims abstract description 64
- 238000011161 development Methods 0.000 claims description 25
- 238000006243 chemical reaction Methods 0.000 claims description 14
- 238000012795 verification Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 12
- 238000003062 neural network model Methods 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000004519 manufacturing process Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 7
- 238000011160 research Methods 0.000 claims description 7
- 230000003993 interaction Effects 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 5
- 230000004044 response Effects 0.000 claims description 4
- 229940079593 drug Drugs 0.000 abstract description 55
- 239000002994 raw material Substances 0.000 abstract description 8
- 238000000227 grinding Methods 0.000 description 16
- 230000005540 biological transmission Effects 0.000 description 14
- 230000006870 function Effects 0.000 description 13
- 238000003860 storage Methods 0.000 description 9
- 238000002474 experimental method Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 238000009509 drug development Methods 0.000 description 5
- 239000004615 ingredient Substances 0.000 description 5
- 229940126585 therapeutic drug Drugs 0.000 description 4
- 230000001225 therapeutic effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000013523 data management Methods 0.000 description 2
- 235000008216 herbs Nutrition 0.000 description 2
- 230000002962 histologic effect Effects 0.000 description 2
- 238000002626 targeted therapy Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
- G06N3/0455—Auto-encoder networks; Encoder-decoder networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/10—Analysis or design of chemical reactions, syntheses or processes
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/90—Programming languages; Computing architectures; Database systems; Data warehousing
-
- 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
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The application provides a research and development process based on big data, a process simulation method, a system and a platform. According to the method, sample data of experimental medicines are obtained, and the sample data are converted into training data to unify the experimental data format of the medicines. And inputting the training data into a training network to obtain the biopharmaceutical model. And inputting the preparation parameters of the target experimental drug into a biopharmaceutical model to obtain the preparation evaluation value of the target experimental drug. And when the preparation evaluation value is greater than or equal to the evaluation threshold value, generating a sample report of the target experimental drug. The method and the device construct the biopharmaceutical model based on the data of the experimental drugs, and can predict the research and development results of the target experimental drugs by combining the preparation parameters of the target experimental drugs so as to solve the problems that a large amount of raw materials are consumed in the research and development process of the drugs and the time cost is high.
Description
Technical Field
The application relates to the technical field of biopharmaceuticals, in particular to a big data-based research and development process and process simulation method, system and platform.
Background
Drug development requires multiple experimental phases, each of which includes a large amount of experimental data. The data generated by drug research and development enterprises and scientific research institutions usually need secret processing, and the data and conclusions of each experimental stage cannot be easily communicated, so that the problems in the experimental stages are not solved.
In order to enable the drug research and development enterprises and scientific research institutions to realize data intercommunication, an application platform can be formed by a mode of intensively storing experimental data. However, the data recording modes of different drug research and development enterprises and scientific research institutions in the experimental stage may have inconsistent conditions due to experimental targets, experimental processes and other reasons. The data volume that produces in the medicine research and development experimental process is huge, if the format is inconsistent in the in-process of gathering, can reduce data acquisition's efficiency, has the risk of data loss simultaneously.
In addition, in the process of improving drug development according to experimental data, a large amount of drug raw materials are required to be consumed for experiments, so that the development cost is high, and the drug development is not facilitated.
Disclosure of Invention
The application provides a research and development process based on big data, a process simulation method, a process simulation system and a process simulation platform, which are used for solving the problems that in the process of drug research and development, a large number of drug raw materials are required to be consumed for experiments, so that research and development cost is high and drug research and development are not facilitated.
On the one hand, the application provides a research and development process based on big data and a process simulation method, comprising the following steps:
acquiring sample data of an experimental drug and converting the sample data into training data; the sample data comprises a plurality of groups of data in different experimental stages;
inputting the training data into a training network to obtain a biopharmaceutical model, wherein the biopharmaceutical model is an algorithm model constructed according to sample data of experimental drugs; the input of the neural network model comprises the training data, and the output of the neural network model comprises a sample report of the experimental drug;
inputting preparation parameters of a target experimental drug into the biopharmaceutical model to obtain a preparation evaluation value of the target experimental drug; the preparation parameters include pharmaceutical parameters and non-pharmaceutical parameters;
and if the preparation evaluation value is greater than or equal to an evaluation threshold value, generating a sample report of the target experimental drug according to the preparation parameter.
In some possible embodiments, the development process and process simulation method further comprises:
if the preparation evaluation value is smaller than the evaluation threshold value, calculating a difference value between the preparation evaluation value and the evaluation threshold value;
generating a preparation prompt report of the target experimental drug according to the difference value between the preparation evaluation value and the evaluation threshold value; the preparation prompt report comprises component adjustment suggestions and component content adjustment suggestions of the target experimental drug.
In some possible embodiments, the step of converting the sample data into training data comprises:
configuring a data acquisition strategy according to the data characteristics of the sample data; the configuration data acquisition strategy comprises a configuration data coding strategy and a data decoding strategy;
performing coding on the sample data according to the data coding strategy to obtain sample coding data;
and decoding the sample coded data according to the data decoding strategy to obtain the training data.
In some possible embodiments, the training data is input into a training network to obtain a biopharmaceutical model, further comprising:
acquiring the type of the experimental drug according to the training data; the experimental drug type information comprises the name of the experimental drug and the function of the experimental drug;
the training data and the biopharmaceutical model are stored in a database according to the experimental drug type.
In some possible embodiments, inputting the manufacturing parameters of the target test drug into the biopharmaceutical model includes:
according to the type of the target experimental drug, extracting experimental data in the same category as the target experimental drug from the database, wherein the experimental data comprises the training data and the biopharmaceutical model;
filtering redundant parameters in the preparation parameters according to training data in the database;
and inputting the preparation parameters subjected to redundant parameter filtering into the biopharmaceutical model.
In some possible embodiments, inputting the manufacturing parameters of the target experimental drug into the biopharmaceutical model comprises:
extracting the biopharmaceutical model from the database in response to user entered instructions for selecting the biopharmaceutical model;
and inputting the preparation parameters of the target experimental drug to the input end of the biopharmaceutical model.
In some possible embodiments, the development process and process simulation method further comprises:
detecting an event of inputting preparation parameters of a target experimental drug by a user, and extracting the biopharmaceutical model from the database;
and inputting the preparation parameters of the target experimental drug to the input end of the biopharmaceutical model.
In some possible embodiments, the development process and process simulation method further comprises:
responding to an instruction input by a user for selecting a biopharmaceutical model and/or detecting an event of inputting preparation parameters of a target experimental drug by the user, and displaying a verification interface;
and if the verification information input by the user through the verification interface passes the verification, executing the step of extracting the biopharmaceutical model from the database.
In another aspect, the present application provides a development process and process simulation system based on big data, including: the system comprises a data acquisition module, a data processing module and a data decision module;
the data acquisition module is used for acquiring sample data of the experimental medicine and converting the sample data into training data; the sample data comprises a plurality of groups of data in different experimental stages;
the data processing module is used for inputting the training data into a training network to obtain a biopharmaceutical model, and the biopharmaceutical model is an algorithm model constructed according to sample data of experimental drugs; the input of the neural network model comprises the training data, and the output of the neural network model comprises a sample report of the experimental drug;
the data processing module is also used for inputting preparation parameters of the target experimental drug into the biopharmaceutical model to obtain a preparation evaluation value of the target experimental drug; the preparation parameters include pharmaceutical parameters and non-pharmaceutical parameters;
and the data decision module generates a sample report of the target experimental drug according to the preparation parameter when the preparation evaluation value is greater than or equal to an evaluation threshold value.
In some possible embodiments, the development process and process simulation system further comprises:
the data decision module generates a preparation prompt report of the target experiment drug when the preparation evaluation value is smaller than an evaluation threshold value; the preparation prompt report comprises component adjustment suggestions for the target experimental drug and component content adjustment suggestions.
On the other hand, the application provides a research and development process and process simulation platform based on big data, which comprises the research and development process and process simulation system based on big data and a man-machine interaction system, wherein the research and development process and process simulation system based on big data is mentioned in the technical scheme; and the platform receives the preparation parameters input by the man-machine interaction system into the target experimental medicament, and obtains the research, development and test results of the target experimental medicament according to the simulation system and the preparation parameters.
As can be seen from the above technical content, the present application provides a development process based on big data, and a process simulation method, system and platform thereof. According to the method, sample data of experimental medicines are obtained, and the sample data are converted into training data to unify the experimental data format of the medicines. And inputting the training data into a training network to obtain the biopharmaceutical model. And inputting the preparation parameters of the target experimental drug into a biopharmaceutical model to obtain the preparation evaluation value of the target experimental drug. And if the dominant evaluation value is greater than or equal to the evaluation threshold, generating a sample report of the target experimental drug. The method and the device construct the biopharmaceutical model based on the data of the experimental drugs, and can predict the research and development of the target experimental drugs by combining the preparation parameters of the target experimental drugs so as to solve the problems that a large amount of raw materials are needed for the research and development of the drugs and the cost is high.
Drawings
In order to more clearly illustrate the technical solutions of the present application, the drawings that are needed in the embodiments will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.
FIG. 1 is a schematic diagram of a development process and process simulation provided in an embodiment of the present application;
FIG. 2 is a schematic diagram of database call provided in an embodiment of the present application;
FIG. 3 is a schematic diagram of a selected biopharmaceutical model provided in an embodiment of the present application;
FIG. 4 is a flowchart of a development process and process simulation provided in an embodiment of the present application;
FIG. 5 is a flowchart of a development process and process simulation provided in an embodiment of the present application.
Detailed Description
Reference will now be made in detail to the embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The embodiments described in the examples below do not represent all embodiments consistent with the present application. Merely as examples of systems and methods consistent with some aspects of the present application as detailed in the claims.
The process of drug development includes several experimental stages, with a large amount of experimental data generated in each experimental stage. When the research and development process and the result are analyzed according to the experimental data, the problems in the research and development process are improved, and then the experiment is repeated according to the improved result, so that a sample of the target drug is finally prepared.
In the experimental and improvement process, in order to verify whether the improvement is effective through experimental data, a large amount of raw materials need to be repeatedly input, which results in an increase in research and development costs. In view of the foregoing, as shown in fig. 1, 4 and 5, some embodiments of the present application provide a development process and a process simulation method based on big data, including:
s100: acquiring sample data of an experimental drug and converting the sample data into training data;
the sample data includes several sets of data for different experimental phases. The data of the experimental medicine in different stages of research and development can be stored as sample data in a unified storage space. The storage space can be a simple local memory, a cloud memory or an operation platform capable of calling the local memory and the cloud memory.
The composition of the medicine itself is different, so that the data generated in the medicine experiment stage may have a certain difference, and therefore, the adopted data format may also have a certain difference when the experimental data are acquired and recorded. When data with different formats are input into a unified operation platform, the transmission of the data is not facilitated, and meanwhile, the user is not facilitated to call the data on the operation platform.
Thus, in the embodiment of the present application, the sample data is unified into training data. By unifying the data formats, the need of adjusting the data formats each time when the data is called is avoided, and the efficiency of data calling is improved. The unification of the data formats can also reduce the difficulty of the configuration of the data transmission interface, and the data transmission interface is not required to be configured repeatedly so as to adapt to various data formats.
S200: inputting the training data into a training network to obtain a biopharmaceutical model;
the biopharmaceutical model is an algorithm model constructed according to sample data of experimental drugs, and the algorithm model can be a neural network model; the input of the neural network model comprises the training data, and the output of the neural network model comprises a sample report of the experimental drug; the training data includes various types of data for the experimental stage, such as the manufacturing parameters of the experimental drug. The preparation parameters include, but are not limited to, various parameters such as component names, component contents, reaction time, reaction temperature, reaction humidity and the like of experimental medicines.
Based on training data of some experimental drugs and a proper training network, a biopharmaceutical model constructed based on a neural network model can be obtained. The types of biopharmaceutical models are not unique, each biopharmaceutical model may correspond to a class of drugs, which may include multiple drugs. Common to multiple drugs may include various parameters of composition, content of composition, function, etc.
In developing a drug, information such as components and component contents of the drug may be input into the biopharmaceutical model. Because the biopharmaceutical model is trained by a large number of historical training data of experimental drugs, the preparation result of the drugs is easy to predict according to input values for drug research and development.
After the training data of the experimental medicine is input into the biopharmaceutical model, a sample report of the experimental medicine can be obtained. The sample report can include various information such as success rate, failure rate, improvement point and the like of the experimental drugs. It will be appreciated that the biopharmaceutical model may be used for outcome prediction at a stage of experimental drug, and may also be used for outcome prediction throughout the development stage of experimental drug. In some embodiments, the biopharmaceutical model may be invoked for an experimental stage with a large amount of drug materials, so as to achieve the purposes of saving experimental materials and reducing experimental costs.
S300: inputting preparation parameters of a target experimental drug into the biopharmaceutical model to obtain a preparation evaluation value of the target experimental drug;
the preparation parameters include pharmaceutical parameters and non-pharmaceutical parameters. The drug parameters include, but are not limited to, drug function, drug ingredient, ingredient content, and the non-drug parameters include, but are not limited to, reaction duration, reaction temperature, and reaction humidity. The target experimental medicine comprises simulated medicine and original grinding medicine, and the composition of the original grinding medicine is obviously different from that of the existing medicine in the research and development process, so that the research process of the original grinding medicine is difficult, a large amount of raw materials are required to be repeatedly tested, the development period is long, and the cost is high.
However, the original herbs have certain functions, and some ingredients usually overlap with the existing herbs, and chemical reactions and other processes occurring in the experimental process can be properly classified. Therefore, when the training data of the original grinding medicine is input into the biopharmaceutical model, the biopharmaceutical model can predict the research and development process of the original grinding medicine according to the association degree between the functions, components and chemical reactions of the original grinding medicine and the training data of the existing medicine. Adjustment suggestions may also be made for different experimental stages.
S400: and if the preparation evaluation value is greater than or equal to an evaluation threshold value, generating a sample report of the target experimental drug according to the preparation parameter.
The evaluation threshold may be adjusted according to the type of the target experimental drug. For example, when the target experimental drug is a simulated drug, parameters such as a manufacturing process, raw materials and the like are familiar, so that the evaluation threshold can be set to a higher value to ensure the quality of the simulated drug. When the target experimental medicine is an original medicine, parameters such as a manufacturing process, component content and the like are all in an experimental stage, so that an evaluation threshold can be flexibly adjusted to ensure the progress of experimental research and development.
The biopharmaceutical model can score the association degree of functions and components of the original ground drug, calculate the score according to the efficacy of the components, and calculate the score according to the association degree between the preparation parameters of the original ground drug and the existing drug. The biopharmaceutical model can calculate the scores of the preparation process and results of the original grinding medicine according to the functions of the existing medicine and the parameters of the related components in the experimental process. It is understood that the score calculation may include a step of weighting according to the importance degree of the calculation item to obtain the preparation evaluation value.
The preparation evaluation value and the evaluation threshold value can be compared, and under the condition that the preparation evaluation value is larger than or equal to the evaluation threshold value, the preparation evaluation value is equivalent to the feasibility of the original grinding medicine in the current experimental stage or the complete experimental stage. Furthermore, according to the preparation parameters of the original grinding medicine, a sample report comprising various contents such as experimental process, result prediction and the like can be generated.
In other embodiments, where the evaluation value is less than the evaluation threshold, the biopharmaceutical model may also generate adjustment recommendations based on training data for existing drugs that are more relevant to the original drug. The method comprises the following steps:
if the preparation evaluation value is smaller than the evaluation threshold value, calculating a difference value between the preparation evaluation value and the evaluation threshold value;
generating a preparation prompt report of the target experimental drug according to the difference value between the preparation evaluation value and the evaluation threshold value; the preparation prompt report comprises component adjustment suggestions and component content adjustment suggestions of the target experimental drug.
In some embodiments, the biopharmaceutical model predicts the results of the experimental stage to yield the preparation evaluation value of the experimental stage. Under the condition that the preparation evaluation value is smaller than the evaluation threshold value, the biopharmaceutical model can provide adjustment suggestions for components and component contents of the original ground medicament according to the preparation parameters and the relevance scores calculated according to the preparation parameters. So that the user can improve the original drug grinding experiment according to the calculation result of the biopharmaceutical model.
It can be understood that the results of multiple experimental stages are predicted, and adjustment suggestions can be generated for the preparation parameters of the raw medicine components, the component content, the temperature, the humidity, the reaction duration and the like of the multiple experimental stages.
As shown in fig. 4, in some embodiments, the sample data used to create the biopharmaceutical model may include successful development data for various types of drugs, may include data related to various types of drug development failures, and may further include empirical data refined from the successful development data and the failed development data. The successful development data can be used as a basic direction reference for the research and development of the original medicine, and the failed development data can be used as a reference for correcting errors and correction parameters when problems occur in the research and development process. Through the multidimensional data, the accuracy and the applicability of the biopharmaceutical model can be improved.
In some embodiments, as shown in fig. 5, the preparation parameters of the drug in question may also be predicted in connection with the therapeutic objectives of the drug in question. Taking a targeted therapeutic drug as an example, pathological data of a therapeutic target is combined with biomedical data, empirical data and histologic data for targeted therapy are input into a biopharmaceutical model to simulate and predict preparation parameters of the targeted therapeutic drug. Various data can be subjected to data screening to a certain degree before entering the model so as to filter out parameters with low association degree with the targeted therapeutic drug. And (3) repeatedly iterating the simulation result of the preparation parameters output by the biopharmaceutical model in the simulation process to reach an expected value, and outputting the preparation parameters of the current biopharmaceutical model and the targeted therapeutic drug when the simulation result reaches the expected value.
The biopharmaceutical model may be trained based on methods such as trial and error algorithms, ordinary differential algorithms, and the like based on data related to biomedical data, empirical data, and histologic data for targeted therapy. The biopharmaceutical model provided by the embodiment of the application can input the preparation parameters of the target experimental drug through the input end, and test, check and correct the preparation parameters through the model. The therapeutic target and related data may also be entered via an input, drug preparation parameters for the therapeutic target and the biopharmaceutical model may be obtained from the model and stored in a memory device for use as reference data in a subsequent development process. The biopharmaceutical model capable of receiving various data is beneficial to reducing the time cost of research and development of original drugs and saving experimental materials.
When the training data are data with uniform formats, the efficiency of data calling can be improved. In some embodiments, sample data is collected by custom encoding and decoding and converted into training data. The method comprises the following steps:
configuring a data acquisition strategy according to the data characteristics of the sample data;
performing coding on the sample data according to the data coding strategy to obtain sample coding data;
and decoding the sample coded data according to the data decoding strategy to obtain the training data.
Taking the original research and development of the original medicine as an example, the research and development of the original medicine comprises a plurality of experimental stages, so that corresponding experimental data can be stored in a group form. Meanwhile, experimental data at different stages are different in storage units in the storage process. Therefore, when data transmission is performed, data of a plurality of parallel storage units may be transmitted in a multi-path parallel manner, and data of storage units with a certain order may be transmitted in a serial manner, so as to facilitate data management after transmission. Therefore, the transmission mode needs to be specified according to the data characteristics of the sample data, that is, the data storage characteristics.
The configuration data acquisition strategy comprises a configuration data coding strategy and the data decoding strategy. The experimental data are stored in different modes, and it is understood that the storage formats of various data may be different, so that the phenomenon of data loss easily occurs in the process of data transmission.
In order to improve the transmission efficiency of data, as well as the transmission stability, in some embodiments, a way of arranging an "encode-decode" strategy during transmission is used. Before the sample data is transmitted, the sample data is encoded to ensure the stability of data transmission in a unified data format. After receiving the encoded sample data, the encoded sample data can be decoded according to a decoding strategy to obtain sample data with uniform data format, namely training data.
When the data formats are unified and transmitted, the configuration difficulty of the transmission interface is reduced, and the data formats are not required to be changed according to the data characteristics, so that the efficiency of data transmission is improved. And facilitates data management after transmission.
The training data can be used as the basis for the prediction of the biopharmaceutical model and also can be used as the training data for training the biopharmaceutical model. Thus, training data and biopharmaceutical models need to be stored in a database for recall. As shown in fig. 2, the steps include:
acquiring the type of the experimental drug according to the training data; the experimental drug type information comprises the name of the experimental drug and the function of the experimental drug;
the training data and the biopharmaceutical model are stored in a database according to the experimental drug type.
In some embodiments, the training data includes components, i.e., component content, of the original drug, so that information such as the functional type of the original drug can be obtained through the training data. According to the information such as the function type of the original grinding medicine, a storage unit for storing the original grinding medicine data can be established in the database, and the training data of the original grinding medicine can be stored by searching the storage units of similar types in the database.
The training data of the original medicine, the biopharmaceutical model, the information such as functions, names and the like are stored in groups, so that the data calling and the later maintenance are facilitated. For example, when the biopharmaceutical model is called, the biopharmaceutical model can be found through information such as training data, functions, names and the like, and the training data, the corresponding functions and the like can be found according to the biopharmaceutical model and the drug names, so that the data utilization rate is improved.
In the process of simulating the development process of the original grinding medicine, the biopharmaceutical model needs to perform a large amount of calculation, and the relevant parameters used for calculation are the preparation parameters of the original grinding medicine. The more parameters that the preparation parameters include, the less computationally efficient, and therefore the preparation parameters are optimized prior to inputting the preparation parameters into the biopharmaceutical model. The method comprises the following steps:
according to the type of the target experimental drug, extracting experimental data in the same category as the target experimental drug from the database, wherein the experimental data comprises the training data and the biopharmaceutical model;
filtering redundant parameters in the preparation parameters according to training data in the database;
and inputting the preparation parameters subjected to redundant parameter filtering into the biopharmaceutical model.
In some embodiments, the ingredients of the original drug and the preparation parameters such as ingredient content, reaction duration, reaction temperature, etc. are different from those of the existing drug. However, the chemical reaction involved in the preparation process of the original grinding medicine, the action of the components in the reaction, and the efficacy provided by each component for the sample have correlation with the training data and the biopharmaceutical model of the existing medicine. Therefore, the biopharmaceutical model of the original drug can calculate the preparation evaluation value of the original drug according to the association degree.
The preparation parameters to be entered into the biopharmaceutical model may be screened in combination with training data in the database, drug names, drug functions, prior to entering the biopharmaceutical model. For optional preparation parameters, such as redundant components or redundant reaction conditions, filtering can be performed to optimize the input parameters. After the redundant parameters are removed, the calculation efficiency of the biopharmaceutical model can be improved, and the research and development process is further quickened.
As shown in fig. 3, when the biopharmaceutical model is invoked, a user may actively find a desired model, which includes the steps of:
extracting the biopharmaceutical model from the database in response to user entered instructions for selecting the biopharmaceutical model;
and inputting the preparation parameters of the target experimental drug to the input end of the biopharmaceutical model.
When a user invokes the biopharmaceutical model from the database using a tool similar to an operating platform, the biopharmaceutical model may be actively searched according to development requirements. After the biopharmaceutical model is obtained, the manufacturing parameters may be input to the biopharmaceutical model.
In response to a user's instructions, the way in which the biopharmaceutical model is extracted provides a biopharmaceutical model that is more accurate and more consistent with the user's needs. When searching the biopharmaceutical model according to the instruction of the user, a fuzzy search mode can be used as an auxiliary search mode to improve the utilization rate of the biopharmaceutical model in the database.
As shown in fig. 3, when the biopharmaceutical model is invoked, a desired model may be actively provided to a user according to preparation parameters input by the user, which includes the steps of:
detecting an event of inputting preparation parameters of a target experimental drug by a user, and extracting the biopharmaceutical model from the database;
and inputting the preparation parameters of the target experimental drug to the input end of the biopharmaceutical model.
Taking an operation platform as an example, the user can also directly input the preparation parameters. The operating platform can search the biopharmaceutical model meeting the conditions from the database according to the preparation parameters.
The variety and the number of the provided biopharmaceutical models are more by the way of searching the biopharmaceutical models through the preparation parameters. For the research and development of the original medicine, a multidirectional biopharmaceutical model is provided, the analysis of the components and the component combination of the original medicine is facilitated, and a plurality of biopharmaceutical model prediction results also provide more reference values, so that the theoretical basis of the research and development of the original medicine is more sufficient, and the research and development success rate is improved.
Because of the secrecy of experimental data, when the database is called, the training data and the biopharmaceutical model in the database can be called only through verification, and the method comprises the following steps:
responding to an instruction input by a user for selecting a biopharmaceutical model and/or detecting an event of inputting preparation parameters of a target experimental drug by the user, and displaying a verification interface;
and if the verification information input by the user through the verification interface passes the verification, executing the step of extracting the biopharmaceutical model from the database.
The training data and the biopharmaceutical model stored in the database are all more secret data, so encryption processing is needed. And, the operation can be continued only by verification when the training data and the biopharmaceutical model are searched in the database. It should be noted that, when responding to the selection instruction input by the user or detecting the preparation parameter input by the user, the user authority is verified first, and then the operation of searching the biopharmaceutical model is executed. Under the condition that the user does not have access rights, processing steps can be saved, and occupation of resources is reduced.
Some embodiments of the present application also provide a big data based biopharmaceutical system comprising: the system comprises a data acquisition module, a data processing module and a data decision module.
The data acquisition module is used for acquiring sample data of the experimental medicine and converting the sample data into training data; the sample data comprises a plurality of groups of data in different experimental stages;
the data processing module is used for inputting the training data into a training network to obtain a biopharmaceutical model, and the biopharmaceutical model is an algorithm model constructed according to sample data of experimental drugs; the input of the neural network model comprises the training data, and the output of the neural network model comprises a sample report of the experimental drug;
the data processing module is also used for inputting preparation parameters of the target experimental drug into the biopharmaceutical model to obtain a preparation evaluation value of the target experimental drug; the preparation parameters include pharmaceutical parameters and non-pharmaceutical parameters;
and the data decision module generates a sample report of the target experimental drug according to the preparation parameter when the preparation evaluation value is greater than or equal to an evaluation threshold value.
The data decision module generates a preparation prompt report of the target experiment drug when the preparation evaluation value is smaller than an evaluation threshold value; the preparation prompt report comprises component adjustment suggestions for the target experimental drug and component content adjustment suggestions.
Some embodiments of the present application further provide a research and development process and process simulation platform based on big data, which is characterized by comprising the research and development process and process simulation system based on big data and a man-machine interaction system described in the above technical scheme; and the platform receives the preparation parameters input by the man-machine interaction system into the target experimental medicament, and obtains the research, development and test results of the target experimental medicament according to the simulation system and the preparation parameters.
As can be seen from the technical content, the application provides a research and development process based on big data, a process simulation method, a system and a platform. According to the method, sample data of experimental medicines are obtained, and the sample data are converted into training data to unify the experimental data format of the medicines. And inputting the training data into a training network to obtain the biopharmaceutical model. And inputting the preparation parameters of the target experimental drug into a biopharmaceutical model to obtain the preparation evaluation value of the target experimental drug. And (5) preparing a sample report of the target experimental drug if the evaluation value is greater than or equal to the evaluation threshold value. The method and the device construct the biopharmaceutical model based on the data of the experimental drugs, and can predict the research and development of the target experimental drugs by combining the preparation parameters of the target experimental drugs so as to relieve the problems that a large amount of raw materials are needed for drug research and development and the cost is high.
The foregoing detailed description of the embodiments is merely illustrative of the general principles of the present application and should not be taken in any way as limiting the scope of the invention. Any other embodiments developed in accordance with the present application without inventive effort are within the scope of the present application for those skilled in the art.
Claims (10)
1. A research and development process and process simulation method based on big data is characterized by comprising the following steps:
acquiring sample data of an experimental drug and converting the sample data into training data; the sample data comprises a plurality of groups of data in different experimental stages;
inputting the training data into a training network to obtain a biopharmaceutical model, wherein the biopharmaceutical model is an algorithm model constructed according to sample data of experimental drugs;
combining preparation parameters of the target experimental drug with the biopharmaceutical model, and obtaining a preparation evaluation value of the target experimental drug through a platform; the preparation parameters include pharmaceutical parameters and non-pharmaceutical parameters;
and if the preparation evaluation value is greater than or equal to an evaluation threshold value, generating a sample report of the target experimental drug according to the preparation parameter.
2. The method as recited in claim 1, further comprising:
if the preparation evaluation value is smaller than the evaluation threshold value, calculating a difference value between the preparation evaluation value and the evaluation threshold value;
generating a preparation prompt report of the target experimental drug according to the difference value between the preparation evaluation value and the evaluation threshold value; the preparation prompt report comprises component adjustment suggestions and component content adjustment suggestions of the target experimental drug.
3. The method of claim 1, wherein the step of performing conversion of the sample data into training data comprises:
configuring a data acquisition strategy according to the data characteristics of the sample data; the configuration data acquisition strategy comprises a configuration data coding strategy and a data decoding strategy;
performing coding on the sample data according to the data coding strategy to obtain sample coding data;
and decoding the sample coded data according to the data decoding strategy to obtain the training data.
4. The method of claim 1, wherein inputting the training data into a training network results in a biopharmaceutical model, further comprising:
acquiring the type of the experimental drug according to the training data; the experimental drug type information comprises the name of the experimental drug and the function of the experimental drug;
the training data and the biopharmaceutical model are stored in a database according to the experimental drug type.
5. The method of claim 1, wherein said inputting the manufacturing parameters of the subject experimental drug into the biopharmaceutical model comprises:
according to the type of the target experimental drug, extracting experimental data in the same category as the target experimental drug from the database, wherein the experimental data comprises the training data and the biopharmaceutical model;
filtering redundant parameters in the preparation parameters according to training data in the database;
and inputting the preparation parameters subjected to redundant parameter filtering into the biopharmaceutical model.
6. The method of claim 4, wherein inputting the manufacturing parameters of the target experimental drug into the biopharmaceutical model comprises:
extracting the biopharmaceutical model from the database in response to user entered instructions for selecting the biopharmaceutical model;
and inputting the preparation parameters of the target experimental drug to the input end of the biopharmaceutical model.
7. The method of claim 6, wherein the input form further comprises:
detecting an event of inputting preparation parameters of a target experimental drug by a user, and extracting the biopharmaceutical model from the database;
and inputting the preparation parameters of the target experimental drug to the input end of the biopharmaceutical model.
8. The method of claim 7, wherein the method further comprises:
responding to an instruction input by a user for selecting a biopharmaceutical model and/or detecting an event of inputting preparation parameters of a target experimental drug by the user, and displaying a verification interface;
and if the verification information input by the user through the verification interface passes the verification, executing the step of extracting the biopharmaceutical model from the database.
9. A big data based development process and process simulation system, comprising: the system comprises a data acquisition module, a data processing module and a data decision module;
the data acquisition module is used for acquiring sample data of the experimental medicine and converting the sample data into training data; the sample data comprises a plurality of groups of data in different experimental stages;
the data processing module is used for inputting the training data into a training network to obtain a biopharmaceutical model, wherein the biopharmaceutical model is a neural network model constructed according to sample data of experimental drugs;
the data processing module is also used for inputting preparation parameters of the target experimental drug into the biopharmaceutical model to obtain a preparation evaluation value of the target experimental drug; the preparation parameters include pharmaceutical parameters and non-pharmaceutical parameters;
and the data decision module generates a sample report of the target experimental drug according to the preparation parameter when the preparation evaluation value is greater than or equal to an evaluation threshold value.
10. A research and development process and process simulation platform based on big data, which is characterized by comprising a research and development process and process simulation system based on big data and a man-machine interaction system as claimed in claim 9; and the platform receives the preparation parameters input by the man-machine interaction system into the target experimental medicament, and obtains the research, development and test results of the target experimental medicament according to the simulation system and the preparation parameters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310429357.0A CN116403662A (en) | 2023-04-20 | 2023-04-20 | Research and development process based on big data, process simulation method, system and platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310429357.0A CN116403662A (en) | 2023-04-20 | 2023-04-20 | Research and development process based on big data, process simulation method, system and platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116403662A true CN116403662A (en) | 2023-07-07 |
Family
ID=87017811
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310429357.0A Pending CN116403662A (en) | 2023-04-20 | 2023-04-20 | Research and development process based on big data, process simulation method, system and platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116403662A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117250923A (en) * | 2023-09-25 | 2023-12-19 | 浙江迦楠智药科技有限公司 | Process, production and equipment operation linkage control method for pharmaceutical production line |
-
2023
- 2023-04-20 CN CN202310429357.0A patent/CN116403662A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117250923A (en) * | 2023-09-25 | 2023-12-19 | 浙江迦楠智药科技有限公司 | Process, production and equipment operation linkage control method for pharmaceutical production line |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110111886A (en) | A kind of intelligent interrogation system and method based on XGBoost disease forecasting | |
| CN109741826B (en) | Anesthesia evaluation decision tree construction method and equipment | |
| CN116403662A (en) | Research and development process based on big data, process simulation method, system and platform | |
| WO2006026383A2 (en) | Sytem for optimizing treatment strategies using a patient-specific rating system | |
| CN112017785B (en) | Disease risk prediction system, method, device, equipment and medium | |
| CN113707253B (en) | Medical scheme recommendation method, device, equipment and medium | |
| CN111933284B (en) | Complication risk prediction system, method, device, equipment and medium | |
| CN112037922A (en) | Pathological data analysis method and device, computer equipment and storage medium | |
| CN113470741B (en) | Drug target relation prediction method, device, computer equipment and storage medium | |
| WO2020172607A1 (en) | Systems and methods for using deep learning to generate acuity scores for critically ill or injured patients | |
| CN109377388B (en) | Medical insurance application method, medical insurance application device, computer equipment and storage medium | |
| CN110379475A (en) | The method, apparatus and storage medium of clinical guidelines are improved based on electronic health record | |
| CN116113356A (en) | Method and device for determining user dementia degree | |
| CN111881193A (en) | Performance scheme measuring and calculating system, device and medium based on machine learning | |
| CN113345564B (en) | Early prediction method and device for patient hospitalization duration based on graph neural network | |
| Voldal et al. | Model misspecification in stepped wedge trials: Random effects for time or treatment | |
| CN114822863B (en) | Medical data analysis method, equipment and storage medium based on federal learning system | |
| CN115938600A (en) | Mental health state prediction method and system based on correlation analysis | |
| CN113704697B (en) | Medical data missing processing method, device and equipment based on multiple regression model | |
| CN108288491B (en) | Control method, control system and storage device for automatically processing medical record data | |
| Mould | Defining covariate distribution models for clinical trial simulation | |
| WO2023178789A1 (en) | Disease risk estimation network optimization method and apparatus, medium, and device | |
| Wang et al. | Using SCDL for integrating tools and data for complex biomedical applications | |
| CN114724675A (en) | Method and device for selecting treatment strategy, computer equipment and storage medium | |
| CN117174285A (en) | Second diagnosis and treatment opinion generation system and method based on evidence-based medicine |
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 |