Method and device for generating bioavailability prediction model, equipment and medium

Abstract

The invention discloses a bioavailability prediction model generation method and device, equipment and a medium. The method comprises the following steps: determining a plurality of training samples; determining a target pharmacokinetic prediction sub-model based on the plurality of training samples and a to-be-trained pharmacokinetic prediction sub-model; and determining a bioavailability prediction model based on the target pharmacokinetic prediction sub-model and a predetermined target physiological pharmacokinetic sub-model, so as to predict the bioavailability of the to-be-detected drug corresponding to different doses based on the bioavailability prediction model. According to the technical scheme provided by the embodiment of the invention, the effect of accurately predicting the bioavailability of the drug acting on the administration individual on the basis of reducing the cost is realized, and further, the research and development success rate of the oral soluble film preparation drug is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical industry, and in particular to a method, device, equipment and medium for generating a bioavailability prediction model. Background Art

[0002] In the research and development stage of improved drug dosage forms, predicting the bioavailability of the dosage form is a key step. In the related art, the method for determining the bioavailability of orodispersible films usually uses non-rodent mammal models to conduct drug experiments. Then, the bioavailability of the orodispersible film of the corresponding drug is determined based on the experimental data.

[0003] However, the above method is time-consuming and expensive. In addition, this method cannot take into account the significant interspecies differences in metabolic pathways between individuals, which in turn leads to a low accuracy rate of bioavailability of the object. Summary of the invention

[0004] The present invention provides a method, device, equipment and medium for generating a bioavailability prediction model, so as to achieve the effect of accurately predicting the bioavailability of a drug on a drug-administered individual on the basis of reducing costs, thereby improving the success rate of research and development of orodispersible film preparations.

[0005] According to one aspect of the present invention, a method for generating a bioavailability prediction model is provided, the method comprising:

[0006] Determine a plurality of training samples; wherein the training samples include drug physicochemical property parameters corresponding to an orodispersible film preparation drug, pharmacokinetic parameters corresponding to a plurality of drug doses of the orodispersible film preparation drug, oral physiological parameters and oral mucosal characteristic parameters corresponding to a drug administration individual, and a plurality of true physiological pharmacokinetic parameters corresponding to the drug doses; the true physiological pharmacokinetic parameters include at least one of an unbound fraction, an oral mucosal diffusion rate, and a clearance rate;

[0007] Determining a target pharmacokinetic prediction sub-model based on the multiple training samples and a predetermined pharmacokinetic prediction sub-model;

[0008] Based on the target pharmacokinetics prediction sub-model and a predetermined target physiological pharmacokinetics sub-model, a bioavailability prediction model is determined to predict the bioavailability of the drug to be tested at different drug doses based on the bioavailability prediction model.

[0009] According to another aspect of the present invention, there is provided a device for generating a bioavailability prediction model, the device comprising:

[0010] A training sample determination module, used to determine a plurality of training samples; wherein the training samples include drug physicochemical property parameters corresponding to an orodispersible film preparation drug, pharmacokinetic parameters corresponding to a plurality of drug doses of the orodispersible film preparation drug, oral physiological parameters and oral mucosal characteristic parameters corresponding to a drug administration individual, and real physiological pharmacokinetic parameters corresponding to a plurality of the drug doses; the real physiological pharmacokinetic parameters include at least one of an unbound fraction, an oral mucosal diffusion rate, and a clearance rate;

[0011] A sub-model determination module, used to determine a target pharmacokinetic prediction sub-model based on the multiple training samples and a predetermined pharmacokinetic prediction sub-model;

[0012] The prediction model determination module is used to determine the bioavailability prediction model based on the target pharmacokinetics prediction sub-model and the predetermined target physiological pharmacokinetics sub-model, so as to predict the bioavailability of the drug to be tested corresponding to different drug doses based on the bioavailability prediction model.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for generating a bioavailability prediction model described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for generating a bioavailability prediction model described in any embodiment of the present invention when executed.

[0018] The technical solution of the embodiment of the present invention determines multiple training samples, and then determines a target pharmacokinetics prediction submodel based on the multiple training samples and the pharmacokinetic prediction submodel to be trained. Further, based on the target pharmacokinetic prediction submodel and a predetermined target physiological pharmacokinetic submodel, a bioavailability prediction model is determined to predict the bioavailability of the test drug corresponding to different drug doses based on the bioavailability prediction model. This solves the problems that the bioavailability determination method in the related art is time-consuming and expensive, and that the significant interspecies differences in metabolic pathways between individuals cannot be considered, thereby resulting in a low accuracy rate of bioavailability. This achieves the effect of accurately predicting the bioavailability of the drug on the individual receiving the drug while reducing costs, thereby improving the success rate of research and development of orodispersible film preparations.

[0019] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0021] Figure 1 is a flow chart of a method for generating a bioavailability prediction model provided in Example 1 of the present invention;

[0022] Figure 2 is a flow chart of a method for generating a bioavailability prediction model provided in Example 2 of the present invention;

[0023] Figure 3 is a schematic diagram of the structure of a bioavailability prediction model generation device provided in Example 3 of the present invention;

[0024] Figure 4 It is a schematic diagram of the structure of an electronic device for implementing the method for generating a bioavailability prediction model according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] Embodiment 1

[0028] Figure 1 This is a flow chart of a method for generating a bioavailability prediction model provided by the first embodiment of the present invention. This embodiment is applicable to the case of predicting the bioavailability of orally dissolving film preparation drugs. The method can be executed by a bioavailability prediction model generating device. The bioavailability prediction model generating device can be implemented in the form of hardware and / or software. The bioavailability prediction model generating device can be configured in a terminal and / or a server. Figure 1 As shown, the method includes:

[0029] S110: Determine a plurality of training samples.

[0030] Among them, the training samples include the physicochemical property parameters corresponding to the orodispersible film preparation drugs, the pharmacokinetic parameters corresponding to multiple drug doses of the orodispersible film preparation drugs, the oral physiological parameters and oral mucosal characteristic parameters corresponding to the drug-administered individuals, and the real physiological pharmacokinetic parameters corresponding to multiple drug doses; the real physiological pharmacokinetic parameters include at least one of the unbound fraction, oral mucosal diffusion rate and clearance rate.

[0031] Among them, the oral dissolving film preparation drug can be a drug whose dosage form includes an oral dissolving film. The oral dissolving film is an ultra-thin film using a hydrophilic polymer, which is only the size of a stamp and is composed of active pharmaceutical ingredients, film formers, plasticizers, sweeteners, salivary stimulants, surfactants and flavor pigments. After contacting with saliva, it dissolves or decomposes rapidly (within a few seconds) in the oral cavity, and forms a solution or suspension that is easy to swallow, which is absorbed by the systemic circulation through the gastrointestinal tract. Exemplarily, oral dissolving film preparation drugs can include ferofibrate oral dissolving film and olatolla oral dissolving film. Physicochemical property parameters can be understood as indicators that measure the physical and chemical properties of the corresponding drugs. Optionally, physicochemical property parameters can include molecular weight, chemical structure, fat solubility, free fraction, solubility, and lipid-water partition coefficient. The drug dose is the volume or quantity of the corresponding drug acting on the individual being administered in a single administration phase. Pharmacokinetic parameters can be understood as parameters that characterize the absorption, distribution, metabolism and excretion process of the corresponding drug in the organism. For different drug doses, pharmacokinetic parameters correspond to different parameter values, that is, the parameter values ​​of pharmacokinetic parameters corresponding to different drug doses are different. Optionally, pharmacokinetic parameters may include drug absorption parameters (such as permeability, absorption rate, etc.), drug distribution parameters (such as plasma protein binding rate, etc.), drug metabolism parameters (such as drug plasma concentration, etc.), drug excretion parameters, area under the plasma concentration-time curve (AUC), dosage form dissolution time and dissolution rate, etc.

[0032] Among them, the dosing individual can be understood as an object receiving the drug. The dosing individual can be any kind of organism. Optionally, the types of dosing individuals can include but are not limited to rodents, dogs, rabbits and fish. Oral physiological parameters can be parameters that characterize the oral physiological characteristics of the corresponding dosing individual. Optionally, oral physiological parameters can include but are not limited to oral pH and salivary flow rate. Oral mucosal properties can be parameters that characterize the oral mucosal characteristics of the corresponding dosing individual. Optionally, oral mucosal properties can include but are not limited to oral mucosal surface area and oral mucosal permeability. It should be noted that for different dosing individuals, different oral physiological parameters and oral mucosal properties are corresponding. The real physiological pharmacokinetic parameters can be actual parameters that characterize the physiological pharmacokinetic characteristics of the corresponding oral dissolving film preparation drug. Optionally, the real physiological pharmacokinetic parameters can include at least one of the real physiological pharmacokinetic parameters including unbound fraction, oral mucosal diffusion rate and clearance rate. It can be understood in the art that the unbound fraction (Fu-t) can be the ratio of the unbound drug to the total drug concentration in tissues outside the plasma. The oral mucosal diffusion rate (Diff-t) can be the ratio between the diffusion area of ​​the drug on the oral mucosa and the total area of ​​the oral mucosa.

[0033] In this embodiment, multiple oral mucosal preparation drugs and at least one individual to whom the drug is administered may be determined. Furthermore, for each oral dissolving film preparation drug, drug characteristic parameters corresponding to the oral dissolving film preparation drug and oral characteristic parameters corresponding to the individual to whom the drug is administered may be obtained, and training samples may be constructed based on the obtained parameters. It should be noted that before constructing the training samples, in order to better utilize the data for subsequent analysis and model processing, the obtained parameters may be processed, and training samples may be constructed based on the processed parameters.

[0034] Optionally, multiple training samples are determined, including: obtaining initial physicochemical property parameters corresponding to multiple orodispersible film preparation drugs, initial pharmacokinetic parameters and true physiological pharmacokinetic parameters at multiple drug doses, and oral physiological parameters and oral mucosal characteristic parameters corresponding to the drug-administered individuals; for each orodispersible film preparation drug, processing the initial physicochemical property parameters and initial pharmacokinetic parameters at multiple drug doses corresponding to the orodispersible film preparation drug according to a preset data processing method to obtain the physicochemical property parameters and pharmacokinetic parameters at multiple drug doses corresponding to the orodispersible film preparation drug; based on the physicochemical property parameters and pharmacokinetic parameters at multiple drug doses corresponding to the orodispersible film preparation drug, the oral physiological parameters and oral mucosal characteristic parameters corresponding to the drug-administered individuals, and true physiological pharmacokinetic parameters at multiple drug doses, constructing training samples corresponding to the orodispersible film preparation drug.

[0035] Among them, the initial physicochemical property parameters can be the physicochemical property parameters of the drug without data processing. Similarly, the initial pharmacokinetic parameters can be the pharmacokinetic parameters without data processing. The preset data processing method can include at least one of data cleaning, data encoding, data transformation and data normalization. Among them, data encoding can be understood as a method of encoding the molecular structure included in the data into a vector. Data transformation can be understood as a method of transforming data into characteristic parameters that can be better recognized by a computer based on a preset data processing model. Data normalization can be understood as a method of mapping data to a specified range to remove the dimensions and dimensional units of data of different dimensions.

[0036] It should be noted that the oral physiological parameters and oral mucosal characteristic parameters corresponding to the individual being administered can be average values. For example, for the oral physiological parameters, the initial oral physiological parameters corresponding to multiple individuals being administered can be obtained. Afterwards, the multiple initial oral physiological parameters can be summed to obtain the total oral physiological parameters corresponding to the multiple individuals being administered. Afterwards, the ratio between the total oral physiological parameters and the number of individuals being administered can be determined, and the obtained ratio can be used as the oral physiological parameters corresponding to the individual being administered. Alternatively, the oral physiological parameters and oral mucosal characteristic parameters corresponding to the individual being administered obtained are the initial oral physiological parameters and initial oral mucosal characteristic parameters corresponding to a preset number of individuals being administered. For example, for the oral physiological parameters, the initial oral physiological parameters corresponding to a preset number of individuals being administered can be obtained, and the obtained initial oral physiological parameters can be used as the oral physiological parameters corresponding to the individual being administered.

[0037] In this embodiment, the acquisition methods of initial physicochemical property parameters, initial pharmacokinetic parameters, true physiological pharmacokinetic parameters, oral physiological parameters and oral mucosal characteristic parameters may include multiple methods. Optionally, when multiple oral dissolving film preparation drugs and at least one individual are determined, for each oral dissolving film preparation drug and each individual, the initial physicochemical property parameters, initial pharmacokinetic parameters and true physiological pharmacokinetic parameters corresponding to the oral dissolving film preparation drug, as well as the oral physiological parameters and oral mucosal characteristic parameters corresponding to the individual can be retrieved from a pre-constructed database. Furthermore, the initial physicochemical property parameters, initial pharmacokinetic parameters and true physiological pharmacokinetic parameters corresponding to multiple oral dissolving film preparation drugs, as well as the oral physiological parameters and oral mucosal characteristic parameters corresponding to the individual can be obtained. Alternatively, the initial physicochemical property parameters, initial pharmacokinetic parameters and true physiological pharmacokinetic parameters corresponding to multiple oral dissolving film preparation drugs, as well as the oral physiological parameters and oral mucosal characteristic parameters corresponding to the individual can be obtained based on other data acquisition methods, and this embodiment does not specifically limit this.

[0038] In a specific implementation, the initial physicochemical property parameters corresponding to a plurality of orodispersible film preparation drugs, the initial pharmacokinetic parameters at a plurality of drug doses, and the real physiological pharmacokinetic parameters can be obtained, and the oral physiological parameters and oral mucosal characteristic parameters corresponding to the drug-administered individual can be obtained. Furthermore, in order to facilitate the better use of data for subsequent analysis and modeling, for each orodispersible film preparation drug, the initial physicochemical property parameters and initial pharmacokinetic parameters corresponding to the orodispersible film preparation drug can be processed according to a preset data processing method, and the data obtained after the processing is completed are used as the physicochemical property parameters and pharmacokinetic parameters corresponding to the orodispersible film preparation drug.

[0039] Exemplarily, for the initial physicochemical property parameters, the initial physicochemical property parameters can be processed according to data cleaning and / or data encoding. For example, for the molecular weight in the initial physicochemical property parameters, compounds with a molecular weight between 0 and 1000 Daltons (Da) can be included, and compounds with less than 3 atoms and hexapeptides can be excluded. For the chemical structure in the initial physicochemical property parameters, in order to make the comparison of molecular chemical structures easier in calculation, the drug chemical structure can be simplified or abstracted, the molecular structure characteristics can be extracted, and the molecules can be encoded into a series of bit vectors, and the molecular chemical structures can be compared by comparing the simplified bit vectors.

[0040] Exemplarily, for the initial pharmacokinetic parameters, the initial pharmacokinetic parameters can be processed according to data conversion and / or data normalization. For example, for the dissolution data in the initial pharmacokinetic parameters (such as dosage form dissolution time and dissolution rate), time and dissolution percentage are usually taken for recording, so the time variable is crucial for representing the entire dissolution probability. For immediate release preparations, the dissolution is faster, and the dissolution is basically complete in 5 minutes. Therefore, when comparing the dissolution characteristics, sampling time points of 0.5 minutes, 1 minute, 1.5 minutes, 2 minutes, 3 minutes, 5 minutes and 10 minutes are used to make the recorded dissolution data more complete. In order to make the dissolution data better recognized by the computer, the dissolution data can be converted according to the preset data conversion algorithm, and the z value used to describe the release process of the drug in the dissolution medium is calculated from the dissolution data, and the z value is used as the drug dissolution data in the pharmacokinetic parameters.

[0041] Furthermore, for each oral dissolving film preparation drug, after obtaining the corresponding physicochemical property parameters and pharmacokinetic parameters at multiple drug doses, training samples corresponding to the oral dissolving film preparation drug can be constructed based on the corresponding physicochemical property parameters, pharmacokinetic parameters, oral physiological parameters and oral mucosal characteristic parameters corresponding to the drug-administered individual, and real physiological pharmacokinetic parameters. Furthermore, training samples corresponding to multiple oral dissolving film preparation drugs can be obtained.

[0042] S120. Determine a target pharmacokinetic prediction sub-model based on multiple training samples and the pharmacokinetic prediction sub-model to be trained.

[0043] Among them, the pharmacokinetics prediction submodel can be a neural network model that can realize the prediction of pharmacokinetic parameters, and the model parameters are initial values ​​or default values. The pharmacokinetics prediction submodel can be a neural network model of any model structure. Optionally, the pharmacokinetics prediction submodel can be a support vector machine (SVM), a random forest (RF) model, a gradient boosting machine (GBM) model, and a deep neural network (DNN) model. The target pharmacokinetics prediction submodel can be a trained neural network model that takes the physicochemical property parameters, pharmacokinetic parameters, oral physiological parameters and oral mucosal characteristic parameters of the drug to be predicted as input objects, so as to predict the physiological pharmacokinetic parameters of the drug to be predicted for the individual based on the input object.

[0044] In this embodiment, after obtaining a plurality of training samples, the pharmacokinetic prediction sub-model to be trained can be trained based on the plurality of training samples, and then a trained target pharmacokinetic prediction sub-model can be obtained.

[0045] Optionally, based on multiple training samples and pharmacokinetic prediction sub-models to be trained, a target pharmacokinetic prediction sub-model is determined, including: for each training sample, the physicochemical property parameters, pharmacokinetic parameters at multiple drug doses, oral physiological parameters and oral mucosal characteristic parameters in the training sample are input into the pharmacokinetic prediction sub-model to obtain predicted physiological pharmacokinetic parameters corresponding to the training sample; the predicted physiological pharmacokinetic parameters and the actual physiological pharmacokinetic parameters in the training sample are processed according to at least one preset evaluation indicator to obtain evaluation results corresponding to each preset evaluation indicator; and the model parameters in the pharmacokinetic prediction sub-model are corrected based on at least one of the evaluation results until the preset training goal is reached and the target pharmacokinetic prediction sub-model is obtained.

[0046] Wherein, the predicted physiological pharmacokinetic parameters can be physiological pharmacokinetic parameters predicted based on the pharmacokinetic prediction submodel. Wherein, the preset evaluation index is used to evaluate the model prediction performance of the pharmacokinetic prediction submodel. Optionally, the preset evaluation index may include prediction deviation, prediction accuracy, and prediction correlation, etc. Wherein, the prediction deviation can be characterized by average folding error (Average Folding Error, AFE). AFE is a commonly used indicator for evaluating the accuracy of protein structure prediction models, which represents the average value of the folding error between the protein structure predicted by the model and the actual protein structure. Generally, the lower the AFE, the higher the accuracy of the prediction model. The prediction accuracy can be characterized by absolute average folding error (Absolute Average Folding Error, AAFE), folding error percentage, residual mean square error (Residual Mean-Square Error, RMSE) or root mean square logarithmic error (Root Mean Squared Logarithmic Error, RMSLE). Prediction correlation can be used to indicate the correlation between the true value and the predicted value. Prediction correlation can be expressed by Pearson correlation coefficient (R), Pearson determination coefficient (R 2 ) and the consistency correlation coefficient (Concordance Correlation Coefficient, CCC). For each preset evaluation indicator, the evaluation result corresponding to the preset evaluation indicator may be the indicator value corresponding to the corresponding preset evaluation indicator. The preset training target may be a preset target for the end of the model training process. Optionally, the preset training target may be that the training error is less than the preset error, the error change trend tends to be stable, or the current number of training iterations reaches a preset number, etc.

[0047] In a specific implementation, for each training sample, the physicochemical property parameters, pharmacokinetic parameters at multiple drug doses, oral physiological parameters, and oral mucosal characteristic parameters in the training sample can be input into the pharmacokinetic prediction submodel to predict physiological pharmacokinetic parameters. Then, the predicted physiological pharmacokinetic parameters corresponding to the training sample can be obtained. Further, the predicted physiological pharmacokinetic parameters and the real pharmacokinetic parameters in the training sample can be processed according to at least one preset evaluation index, and an evaluation result corresponding to each preset evaluation index can be obtained. Then, the model parameters in the pharmacokinetic prediction submodel can be corrected according to the evaluation result. Afterwards, the training error of the loss function in the pharmacokinetic prediction submodel, that is, the loss parameter, can be used as a condition for detecting whether the current loss function converges, for example, whether the training error is less than the preset error or whether the error change trend tends to be stable, or whether the current model iteration number is equal to the preset number of times, etc. If the detection reaches the preset training target, for example, the training error of the loss function is less than the preset error or the error change tends to be stable, it indicates that the training of the pharmacokinetic prediction submodel is completed, and at this time, the iterative training can be stopped. If it is detected that the preset training target is not reached at present, other training samples can be further obtained to train the pharmacokinetic prediction sub-model until the training error of the loss function is within the preset range. When the training error of the loss function reaches convergence, the trained pharmacokinetic prediction sub-model can be obtained, and the obtained pharmacokinetic prediction sub-model can be used as the target pharmacokinetic prediction sub-model.

[0048] S130, determining a bioavailability prediction model based on the target pharmacokinetics prediction sub-model and a predetermined target physiological pharmacokinetics sub-model, and predicting the bioavailability of the test drug at different drug doses based on the bioavailability prediction model.

[0049] Among them, the target physiological pharmacokinetic submodel can be a model that uses the physiological pharmacokinetic parameters of the drug to be tested for the individual being administered as an input object to predict the pharmacodynamic parameters such as the bioavailability, maximum concentration or distribution volume of the drug to be tested. The target physiological pharmacokinetic submodel can be used to predict the absorption of the drug by the oral cavity. The target physiological pharmacokinetic submodel is a model of a mathematical function structure, that is, a model constructed based on a data function relationship. In this embodiment, the physiological pharmacokinetic parameters and pharmacodynamic parameters corresponding to a variety of oral dissolving film preparation drugs can be obtained in advance. Afterwards, the physiological pharmacokinetic parameters and pharmacodynamic parameters can be used as a set of data, and multiple sets of data can be obtained. Afterwards, data analysis can be performed on the multiple sets of data to determine the mapping relationship between the physiological pharmacokinetic parameters and the pharmacodynamic parameters according to the data analysis results. Furthermore, a model can be constructed based on the mapping relationship, and the constructed model can be used as the target physiological pharmacokinetic submodel. The target physiological pharmacokinetic submodel can be a model obtained by associating the oral mucosal absorption and transport (OCCAT) model with the advanced chamber absorption and transport (ACAT) model. The bioavailability prediction model can be a neural network model that takes the physicochemical property parameters and pharmacokinetic parameters of the drug to be tested at a specific dose, as well as the oral physiological parameters and oral mucosal characteristic parameters of the individual to be administered as input objects to predict the bioavailability and other pharmacodynamic parameters of the drug to be tested at a specific dose. Bioavailability refers to the relative amount of a drug absorbed into the systemic blood circulation after administration via an extravascular route. Bioavailability is an indicator used to evaluate the degree of absorption of a preparation. The drug to be tested can be an orodispersible film preparation drug to be predicted.

[0050] It should be noted that in addition to predicting the bioavailability of the drug to be tested, the bioavailability prediction model can also predict other pharmacodynamic parameters of the drug to be tested based on the physicochemical properties of the drug to be tested and the pharmacokinetic parameters at a specific dose, as well as the oral physiological parameters and oral mucosal characteristic parameters of the drug-administered individual.

[0051] In this embodiment, after obtaining the target pharmacokinetics prediction sub-model, the bioavailability prediction model can be determined based on the target pharmacokinetics prediction sub-model and the target physiological pharmacokinetics sub-model.

[0052] Optionally, based on the target pharmacokinetics prediction sub-model and a predetermined target physiological pharmacokinetics sub-model, a bioavailability prediction model is determined, including: splicing the target pharmacokinetics prediction sub-model with the target physiological pharmacokinetics sub-model, using the model output of the target pharmacokinetics prediction sub-model as the model input of the target physiological pharmacokinetics sub-model, and using the model obtained after splicing as the bioavailability prediction model.

[0053] In a specific implementation, after obtaining the target pharmacokinetics prediction sub-model, the target pharmacokinetics prediction sub-model and the target physiological pharmacokinetics sub-model can be spliced ​​together, and the model output of the target pharmacokinetics prediction sub-model is used as the model input of the target physiological pharmacokinetics sub-model. Furthermore, the spliced ​​model can be used as a bioavailability prediction model.

[0054] The technical solution of the embodiment of the present invention determines multiple training samples, and then determines a target pharmacokinetics prediction submodel based on the multiple training samples and the pharmacokinetic prediction submodel to be trained. Further, based on the target pharmacokinetic prediction submodel and a predetermined target physiological pharmacokinetic submodel, a bioavailability prediction model is determined to predict the bioavailability of the test drug corresponding to different drug doses based on the bioavailability prediction model. This solves the problems that the bioavailability determination method in the related art is time-consuming and expensive, and that the significant interspecies differences in metabolic pathways between individuals cannot be considered, thereby resulting in a low accuracy rate of bioavailability. This achieves the effect of accurately predicting the bioavailability of the drug on the individual receiving the drug while reducing costs, thereby improving the success rate of research and development of orodispersible film preparations.

[0055] Embodiment 2

[0056] Figure 2 It is a flow chart of a method for generating a bioavailability prediction model provided in the second embodiment of the present invention. On the basis of the above-mentioned embodiment, after obtaining the bioavailability prediction model, the drug physicochemical property parameters corresponding to the drug to be tested, the pharmacokinetic parameters corresponding to the drug to be tested at the drug dose to be tested, the oral physiological parameters and oral mucosal characteristic parameters corresponding to the individual to be tested can be obtained. Furthermore, based on the bioavailability prediction model and the obtained parameters, the bioavailability of the drug to be tested corresponding to the individual to be tested at the drug dose to be tested can be determined. The specific implementation method can refer to the technical solution of this embodiment. Among them, the technical terms that are the same or similar to those in the above-mentioned embodiments are not repeated here.

[0057] like Figure 2 As shown, the method includes:

[0058] S210: Determine a plurality of training samples.

[0059] S220: Determine a target pharmacokinetic prediction sub-model based on multiple training samples and the pharmacokinetic prediction sub-model to be trained.

[0060] S230, determining a bioavailability prediction model based on the target pharmacokinetics prediction sub-model and a predetermined target physiological pharmacokinetics sub-model, and predicting the bioavailability of the test drug at different drug doses based on the bioavailability prediction model.

[0061] S240, obtaining the physicochemical property parameters corresponding to the drug to be tested, the pharmacokinetic parameters corresponding to the drug to be tested at at least one dose of the drug to be tested, and the oral physiological parameters and oral mucosal characteristic parameters corresponding to the individual to be tested.

[0062] Wherein, the drug to be tested may be an orally dissolving film preparation drug for which bioavailability prediction is to be performed. The physicochemical property parameters corresponding to the drug to be tested may be parameters for characterizing the physical and chemical properties of the drug to be tested. Optionally, the physicochemical property parameters may include molecular weight, chemical structure, lipid solubility, free fraction, solubility, and lipid-water partition coefficient, etc. The dose of the drug to be tested may be any drug dose. Pharmacokinetic parameters may be parameters characterizing drug metabolism, absorption, distribution, and excretion of the drug to be tested at the dose of the drug to be tested. The individual to be administered may be an object to which the drug to be tested is to be applied. The individual to be administered may be any type of organism. Optionally, the types of the individual to be administered may include, but are not limited to, rodents, dogs, rabbits, and fish, etc. Oral physiological parameters are parameters characterizing the oral physiological characteristics of the individual to be administered. Oral mucosal characteristic parameters may be parameters characterizing the oral mucosal characteristics of the individual to be administered.

[0063] It should be noted that there are multiple ways to obtain the physicochemical property parameters and pharmacokinetic parameters corresponding to the drug to be tested. Optionally, when the drug to be tested is determined, the drug identification of the drug to be tested can be obtained, and then, the corresponding physicochemical property parameters and pharmacokinetic parameters can be retrieved from a pre-constructed database according to the drug identification. Thus, the physicochemical property parameters and pharmacokinetic parameters corresponding to the drug to be tested can be obtained. Alternatively, when the drug to be tested is determined, the drug to be tested can be tested. Thus, the physicochemical property parameters and pharmacokinetic parameters corresponding to the drug to be tested can be obtained. Alternatively, the physicochemical property parameters and pharmacokinetic parameters corresponding to the drug to be tested can also be obtained by other means, which is not specifically limited in this embodiment.

[0064] It should also be noted that the acquisition methods of the oral physiological parameters and oral mucosal characteristic parameters corresponding to the individual to be tested for drug administration may include multiple methods. Optionally, when the individual to be tested for drug administration is determined, the individual identification corresponding to the individual to be tested for drug administration may be obtained. Furthermore, the corresponding oral physiological parameters and oral mucosal characteristic parameters may be retrieved from a pre-constructed database according to the individual identification. Furthermore, the oral physiological parameters and oral mucosal characteristic parameters corresponding to the individual to be tested for drug administration may be obtained. Alternatively, when the individual to be tested for drug administration is obtained, the individual to be tested for drug administration may be tested in real time. Furthermore, the oral physiological parameters and oral mucosal characteristic parameters corresponding to the individual to be tested for drug administration may be determined based on the test results. Alternatively, the oral physiological parameters and oral mucosal characteristic parameters corresponding to the individual to be tested for drug administration may also be obtained by other methods, and this embodiment does not specifically limit this.

[0065] In a specific implementation, the drug to be tested, at least one dose of the drug to be tested, and the individual to be administered can be determined first. Further, the physicochemical property parameters corresponding to the drug to be tested, the pharmacokinetic parameters corresponding to the drug to be tested at at least one dose of the drug to be tested, and the oral physiological parameters and oral mucosal characteristic parameters corresponding to the individual to be administered can be obtained. Furthermore, the subsequent process can be continued based on the acquired physicochemical property parameters, pharmacokinetic parameters, oral physiological parameters, and oral mucosal characteristic parameters.

[0066] S250. For each dose of the drug to be tested, the physicochemical property parameters, the pharmacokinetic parameters of the drug to be tested at the dose of the drug to be tested, the oral physiological parameters and the oral mucosal characteristic parameters are processed based on the bioavailability prediction model to obtain the bioavailability of the drug to be tested at the dose of the drug to be tested and corresponding to the individual to be administered the drug.

[0067] In this embodiment, after obtaining the physicochemical property parameters corresponding to the drug to be tested, the pharmacokinetic parameters corresponding to the drug to be tested at at least one dose of the drug to be tested, and the oral physiological parameters and oral mucosal characteristic parameters corresponding to the individual to be tested, for each dose of the drug to be tested, the physicochemical property parameters, the pharmacokinetic parameters corresponding to the drug to be tested at the dose of the drug to be tested, and the oral physiological parameters and oral mucosal characteristic parameters corresponding to the individual to be tested can be input into the bioavailability prediction model. Furthermore, the bioavailability of the drug to be tested corresponding to the individual to be tested at the dose of the drug to be tested can be predicted based on the bioavailability prediction model.

[0068] Optionally, the physicochemical property parameters, pharmacokinetic parameters corresponding to the test drug at the test drug dose, oral physiological parameters and oral mucosal characteristic parameters are processed based on the bioavailability prediction model to obtain the bioavailability of the test drug at the test drug dose corresponding to the test administration individual, including: processing the physicochemical property parameters, pharmacokinetic parameters, oral physiological parameters and oral mucosal characteristic parameters based on the target pharmacokinetics prediction sub-model in the bioavailability prediction model to obtain the predicted values ​​of physiological pharmacokinetic parameters corresponding to the test drug at the test drug dose and the test administration individual; processing the predicted values ​​of physiological pharmacokinetic parameters based on the target physiological pharmacokinetics sub-model in the bioavailability prediction model to obtain the bioavailability of the test drug at the test drug dose corresponding to the test administration individual.

[0069] The predicted value of the physiological pharmacokinetic parameter may be a value of the physiological pharmacokinetic parameter predicted based on the model. Optionally, the predicted value of the physiological pharmacokinetic parameter may include at least one of the unbound fraction, oral mucosal diffusion rate and clearance rate.

[0070] In a specific implementation, for each dose of the drug to be tested, the physicochemical property parameters corresponding to the drug to be tested, the pharmacokinetic parameters corresponding to the drug to be tested at the dose of the drug to be tested, the oral physiological parameters and oral mucosal characteristic parameters corresponding to the individual to be tested can be input into the bioavailability prediction model. Furthermore, the physiological pharmacokinetic parameters of the drug to be tested can be predicted based on the physicochemical property parameters, pharmacokinetic parameters, oral physiological parameters and oral mucosal characteristic parameters by the target pharmacokinetics prediction submodel in the bioavailability prediction model, and the physiological pharmacokinetic parameter prediction value corresponding to the individual to be tested at the dose of the drug to be tested can be obtained. Further, the obtained physiological pharmacokinetic parameter prediction value can be input into the target physiological pharmacokinetics submodel in the bioavailability prediction model. Furthermore, the bioavailability of the drug to be tested corresponding to the individual to be tested at the dose of the drug to be tested can be obtained.

[0071] It should be noted that after obtaining the bioavailability of the test drug at at least one test drug dose, the orodispersible film design process of the test drug can be assisted based on the predicted bioavailability.

[0072] Based on this, on the basis of the above-mentioned technical solutions, it also includes: determining the target bioavailability from at least one bioavailability according to a preset design standard; determining the orodispersible film design corresponding to the drug to be tested based on the target bioavailability and the dose of the drug to be tested corresponding to the target bioavailability.

[0073] The preset design standard may be the design standard used by the oral dissolving film dosage form drug when designing the oral dissolving film. The target bioavailability may be the bioavailability that meets the preset design standard. The oral dissolving film design scheme may include at least parameters associated with the design, such as the shape of the oral dissolving film and the size of the oral dissolving film (including at least one of the length, width or thickness).

[0074] In a specific implementation, after obtaining at least one bioavailability, at least one bioavailability can be screened according to a preset design standard. Then, a target bioavailability can be obtained. Further, a dose of the drug to be tested corresponding to the target bioavailability can be determined, and the target bioavailability and the corresponding dose of the drug to be tested can be analyzed. Then, a design scheme of an orally dissolving film corresponding to the drug to be tested can be determined based on the analysis results, so that the orally dissolving film dosage form corresponding to the drug to be tested, which is designed based on the orally dissolving film design scheme, can maximize the efficacy of the drug.

[0075] It should be noted that the bioavailability prediction model provided in this embodiment can also achieve the following effects:

[0076] Optimize the therapeutic effect and safety of orodispersible films: The bioavailability prediction model can be used to predict drug dose-effect and drug-pharmacodynamic relationships, helping to design orodispersible films to achieve better adjuvant therapeutic effects. In addition, the model can also evaluate the safety of orodispersible films for individuals receiving the drug, such as changes in blood drug concentrations at different doses.

[0077] Virtual screening and design of new drugs: The bioavailability model can be used to conduct virtual screening and design of drugs to be tested. By inputting the physicochemical properties of the drug to be tested, the model can predict its oral absorption performance, helping drug designers to eliminate inappropriate orodispersible film drug candidates at an early stage.

[0078] The technical solution of the embodiment of the present invention determines a plurality of training samples, and then determines a target pharmacokinetics prediction submodel based on the plurality of training samples and the pharmacokinetic prediction submodel to be trained. Further, a bioavailability prediction model is determined based on the target pharmacokinetic prediction submodel and a predetermined target physiological pharmacokinetic submodel, so as to predict the bioavailability of the drug to be tested corresponding to different drug doses based on the bioavailability prediction model. Further, the physicochemical property parameters corresponding to the drug to be tested, the pharmacokinetic parameters corresponding to the drug to be tested at at least one drug dose to be tested, and the oral physiological parameters and oral mucosal characteristic parameters corresponding to the individual to be tested are obtained. Then, for each drug dose to be tested, the physicochemical property parameters, the pharmacokinetic parameters corresponding to the drug to be tested at the drug dose to be tested, the oral physiological parameters and the oral mucosal characteristic parameters are processed based on the bioavailability prediction model to obtain the bioavailability of the drug to be tested corresponding to the individual to be tested at the drug dose to be tested, thereby achieving the effect of accurately predicting the bioavailability of the drug on the individual to be tested on the basis of reducing costs, thereby improving the success rate of research and development of orodispersible film preparations.

[0079] Embodiment 3

[0080] Figure 3 Schematic diagram of the structure of a bioavailability prediction model generation device provided in Example 3 of the present invention. Figure 3 As shown, the device includes: a training sample determination module 310, a sub-model determination module 320 and a prediction model determination module 330.

[0081] Among them, the training sample determination module 310 is used to determine multiple training samples; wherein the training samples include drug physicochemical property parameters corresponding to the orodispersible film preparation drug, pharmacokinetic parameters corresponding to the orodispersible film preparation drug at multiple drug doses, oral physiological parameters and oral mucosal characteristic parameters corresponding to the drug administration individual, and multiple real physiological pharmacokinetic parameters corresponding to the drug doses; the real physiological pharmacokinetic parameters include at least one of the unbound fraction, oral mucosal diffusion rate and clearance rate; the sub-model determination module 320 is used to determine the target pharmacokinetic prediction sub-model based on the multiple training samples and a predetermined pharmacokinetic prediction sub-model; the prediction model determination module 330 is used to determine the bioavailability prediction model based on the target pharmacokinetic prediction sub-model and a predetermined target physiological pharmacokinetic sub-model, so as to predict the bioavailability of the test drug corresponding to different doses based on the bioavailability prediction model.

[0082] The technical solution of the embodiment of the present invention determines multiple training samples, and then determines a target pharmacokinetics prediction submodel based on the multiple training samples and the pharmacokinetic prediction submodel to be trained. Further, based on the target pharmacokinetic prediction submodel and a predetermined target physiological pharmacokinetic submodel, a bioavailability prediction model is determined to predict the bioavailability of the drug to be tested at different doses based on the bioavailability prediction model. This solves the problems that the bioavailability determination method in the related art is time-consuming and expensive, and that the significant interspecies differences in metabolic pathways between individuals cannot be considered, thereby resulting in a low accuracy rate of bioavailability. This achieves the effect of accurately predicting the bioavailability of the drug on the individual receiving the drug while reducing costs, thereby improving the success rate of research and development of orodispersible film preparations.

[0083] Optionally, the training sample determination module 310 includes: a parameter acquisition unit, a data processing unit and a training sample determination unit.

[0084] A parameter acquisition unit, used to acquire initial physicochemical property parameters corresponding to a plurality of orodispersible film preparation drugs, initial pharmacokinetic parameters and true physiological pharmacokinetic parameters at a plurality of drug doses, and oral physiological parameters and oral mucosal characteristic parameters corresponding to the drug-administered individual;

[0085] a data processing unit, for processing, for each of the orodissolving film preparation drugs, initial physicochemical property parameters and initial pharmacokinetic parameters at multiple drug doses corresponding to the orodissolving film preparation drugs according to a preset data processing method, to obtain physicochemical property parameters corresponding to the orodissolving film preparation drugs and pharmacokinetic parameters at multiple drug doses; wherein the preset data processing method includes at least one of data cleaning, data encoding, data transformation and data normalization;

[0086] A training sample determination unit is used to construct a training sample corresponding to the orodispersible film preparation drug based on the physicochemical property parameters corresponding to the orodispersible film preparation drug and the pharmacokinetic parameters at multiple drug doses, the oral physiological parameters and oral mucosal characteristic parameters corresponding to the drug-administered individual, and the real physiological pharmacokinetic parameters at the multiple drug doses.

[0087] Optionally, the sub-model determination module 320 includes: a parameter prediction unit, an evaluation result determination unit, and a sub-model determination unit.

[0088] A parameter prediction unit, for each training sample, inputting the physicochemical property parameters, pharmacokinetic parameters at multiple drug doses, oral physiological parameters and oral mucosal characteristic parameters in the training sample into the pharmacokinetic prediction sub-model to obtain predicted physiological pharmacokinetic parameters corresponding to the training sample;

[0089] An evaluation result determination unit, used to process the predicted physiological pharmacokinetic parameters and the real physiological pharmacokinetic parameters in the training sample according to at least one preset evaluation index to obtain an evaluation result corresponding to each of the preset evaluation indicators; wherein the preset evaluation indicators are used to evaluate the model prediction performance of the pharmacokinetic prediction sub-model;

[0090] The sub-model determination unit is used to modify the model parameters in the pharmacokinetic prediction sub-model based on at least one of the evaluation results until a preset training target is reached and a target pharmacokinetic prediction sub-model is obtained.

[0091] Optionally, the prediction model determination module 330 is specifically used to splice the target pharmacokinetics prediction sub-model with the target physiological pharmacokinetics sub-model, so as to use the model output of the target pharmacokinetics prediction sub-model as the model input of the target physiological pharmacokinetics sub-model, and use the model obtained after splicing as the bioavailability prediction model.

[0092] Optionally, the device further includes: a parameter acquisition module and a bioavailability prediction module.

[0093] A parameter acquisition module, used to acquire the physicochemical property parameters corresponding to the drug to be tested, the pharmacokinetic parameters corresponding to the drug to be tested at at least one dose of the drug to be tested, the oral physiological parameters and oral mucosal characteristic parameters corresponding to the individual to be tested;

[0094] The bioavailability prediction module is used to process the physicochemical property parameters, the pharmacokinetic parameters corresponding to the drug to be tested at the drug dose to be tested, the oral physiological parameters and the oral mucosal characteristic parameters for each drug dose to be tested based on the bioavailability prediction model to obtain the bioavailability of the drug to be tested at the drug dose to be tested and corresponding to the individual to be tested.

[0095] Optionally, the bioavailability prediction module includes: a prediction value determination unit and a bioavailability determination unit.

[0096] A prediction value determination unit, configured to process the physicochemical property parameters, the pharmacokinetic parameters, the oral physiological parameters and the oral mucosal characteristic parameters based on the target pharmacokinetics prediction sub-model in the bioavailability prediction model to obtain a physiological pharmacokinetic parameter prediction value of the drug to be tested corresponding to the individual to be tested at the dose of the drug to be tested;

[0097] The bioavailability determination unit is used to process the predicted value of the physiological pharmacokinetic parameter based on the target physiological pharmacokinetic sub-model in the bioavailability prediction model to obtain the bioavailability of the drug to be tested corresponding to the individual to be tested at the dose of the drug to be tested.

[0098] Optionally, the device further comprises: a bioavailability screening module and a design scheme determination module.

[0099] A bioavailability screening module, used to determine a target bioavailability from at least one of the bioavailabilities according to a preset design standard;

[0100] The design scheme determining module is used to determine the orodispersible film design scheme corresponding to the drug to be tested based on the target bioavailability and the dose of the drug to be tested corresponding to the target bioavailability.

[0101] The bioavailability prediction model generation device provided in the embodiment of the present invention can execute the bioavailability prediction model generation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0102] Embodiment 4

[0103] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0104] like Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0105] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0106] The processor 11 may be a variety of general and / or dedicated processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 executes the various methods and processes described above, such as a method for generating a bioavailability prediction model.

[0107] In some embodiments, the bioavailability prediction model generation method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the bioavailability prediction model generation method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the bioavailability prediction model generation method in any other appropriate manner (e.g., by means of firmware).

[0108] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0109] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0110] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0111] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0112] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0113] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0114] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0115] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for generating a bioavailability prediction model, characterized in that: include: Determine a plurality of training samples; wherein the training samples include physicochemical property parameters corresponding to an orodispersible film preparation drug, pharmacokinetic parameters corresponding to a plurality of drug doses of the orodispersible film preparation drug, oral physiological parameters and oral mucosal characteristic parameters corresponding to a drug administration individual, and a plurality of true physiological pharmacokinetic parameters corresponding to the drug doses; the true physiological pharmacokinetic parameters include at least one of an unbound fraction, an oral mucosal diffusion rate, and a clearance rate; Determining a target pharmacokinetic prediction sub-model based on the multiple training samples and the pharmacokinetic prediction sub-model to be trained; Based on the target pharmacokinetics prediction sub-model and a predetermined target physiological pharmacokinetics sub-model, a bioavailability prediction model is determined to predict the bioavailability of the drug to be tested corresponding to different drug doses based on the bioavailability prediction model.

2. The method for generating a bioavailability prediction model according to claim 1, characterized in that: The determining of a plurality of training samples comprises: Obtain the initial physicochemical property parameters corresponding to a variety of orodispersible film preparation drugs, the initial pharmacokinetic parameters and true physiological pharmacokinetic parameters at multiple drug doses, and the oral physiological parameters and oral mucosal characteristic parameters corresponding to the individual being dosed; For each of the orodissolving film preparation drugs, the initial physicochemical property parameters and the initial pharmacokinetic parameters at multiple drug doses corresponding to the orodissolving film preparation drugs are processed according to a preset data processing method to obtain the physicochemical property parameters and the pharmacokinetic parameters at multiple drug doses corresponding to the orodissolving film preparation drugs; wherein the preset data processing method includes at least one of data cleaning, data encoding, data transformation and data normalization; Based on the physicochemical property parameters corresponding to the orodispersible film preparation drug and the pharmacokinetic parameters at multiple drug doses, the oral physiological parameters and oral mucosal characteristic parameters corresponding to the drug-administered individual, and the actual physiological pharmacokinetic parameters at the multiple drug doses, a training sample corresponding to the orodispersible film preparation drug is constructed.

3. The method for generating a bioavailability prediction model according to claim 1, characterized in that: The step of determining a target pharmacokinetic prediction sub-model based on the plurality of training samples and the pharmacokinetic prediction sub-model to be trained comprises: For each training sample, the physicochemical property parameters, pharmacokinetic parameters at multiple drug doses, oral physiological parameters and oral mucosal characteristic parameters in the training sample are input into the pharmacokinetic prediction sub-model to obtain the predicted physiological pharmacokinetic parameters corresponding to the training sample; Processing the predicted physiological pharmacokinetic parameters and the actual physiological pharmacokinetic parameters in the training samples according to at least one preset evaluation index to obtain an evaluation result corresponding to each of the preset evaluation indicators; wherein the preset evaluation indicators are used to evaluate the model prediction performance of the pharmacokinetic prediction sub-model; The model parameters in the pharmacokinetic prediction sub-model are modified based on at least one of the evaluation results until a preset training target is reached, and a target pharmacokinetic prediction sub-model is obtained.

4. The method for generating a bioavailability prediction model according to claim 1, characterized in that: Determining a bioavailability prediction model based on the target pharmacokinetics prediction sub-model and a predetermined target physiological pharmacokinetics sub-model comprises: The target pharmacokinetics prediction submodel is spliced ​​with the target physiological pharmacokinetics submodel, so that the model output of the target pharmacokinetics prediction submodel is used as the model input of the target physiological pharmacokinetics submodel, and the model obtained after splicing is used as the bioavailability prediction model.

5. The method for generating a bioavailability prediction model according to claim 1, characterized in that: Also includes: Obtaining the physicochemical property parameters corresponding to the drug to be tested, the pharmacokinetic parameters corresponding to the drug to be tested at at least one dose of the drug to be tested, and the oral physiological parameters and oral mucosal characteristic parameters corresponding to the individual to be tested; For each of the drug doses to be tested, the physicochemical property parameters, the pharmacokinetic parameters corresponding to the drug dose to be tested, the oral physiological parameters and the oral mucosal characteristic parameters are processed based on the bioavailability prediction model to obtain the bioavailability of the drug to be tested at the drug dose to be tested and corresponding to the individual to be administered the drug.

6. The method for generating a bioavailability prediction model according to claim 5, characterized in that: The method of processing the physicochemical property parameters, the pharmacokinetic parameters of the drug to be tested at the dose of the drug to be tested, the oral physiological parameters and the oral mucosal characteristic parameters based on the bioavailability prediction model to obtain the bioavailability of the drug to be tested at the dose of the drug to be tested and corresponding to the individual to be administered the drug, comprises: Processing the physicochemical property parameters, the pharmacokinetic parameters, the oral physiological parameters and the oral mucosal characteristic parameters based on the target pharmacokinetics prediction submodel in the bioavailability prediction model to obtain the physiological pharmacokinetic parameter prediction value of the drug to be tested corresponding to the individual to be tested at the dose of the drug to be tested; The predicted value of the physiological pharmacokinetic parameter is processed based on the target physiological pharmacokinetic sub-model in the bioavailability prediction model to obtain the bioavailability of the drug to be tested corresponding to the individual to be tested at the dose of the drug to be tested.

7. The method for generating a bioavailability prediction model according to claim 5, characterized in that: Also includes: determining a target bioavailability from at least one of the bioavailabilities according to a preset design criterion; Based on the target bioavailability and the dose of the drug to be tested corresponding to the target bioavailability, a design scheme of the orodispersible film corresponding to the drug to be tested is determined.

8. A bioavailability prediction model generation device, characterized in that: include: A training sample determination module, used to determine a plurality of training samples; wherein the training samples include drug physicochemical property parameters corresponding to an orodispersible film preparation drug, pharmacokinetic parameters corresponding to a plurality of drug doses of the orodispersible film preparation drug, oral physiological parameters and oral mucosal characteristic parameters corresponding to a drug administration individual, and real physiological pharmacokinetic parameters corresponding to a plurality of the drug doses; the real physiological pharmacokinetic parameters include at least one of an unbound fraction, an oral mucosal diffusion rate, and a clearance rate; A sub-model determination module, used to determine a target pharmacokinetic prediction sub-model based on the multiple training samples and a predetermined pharmacokinetic prediction sub-model; The prediction model determination module is used to determine the bioavailability prediction model based on the target pharmacokinetics prediction sub-model and the predetermined target physiological pharmacokinetics sub-model, so as to predict the bioavailability of the drug to be tested corresponding to different drug doses based on the bioavailability prediction model.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the method for generating a bioavailability prediction model according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for generating a bioavailability prediction model according to any one of claims 1 to 7 when executed.

Images