KRAS mutation tumor drug sensitivity testing and evaluating method based on organoid model
By using an organoid model-based drug sensitivity testing method and constructing a dynamic assessment model of drug response status using historical data, the problem of insufficient assessment accuracy in existing technologies is solved, enabling efficient and accurate assessment of drug sensitivity in KRAS-mutant tumors and supporting personalized treatment.
Patent Information
- Application Number
- CN202511661327.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-13
- Publication Date
- 2026-02-17
AI Technical Summary
Existing tumor drug sensitivity testing methods cannot fully simulate the complexity of the tumor microenvironment in vivo. In particular, they lack predictive accuracy in assessing genotype-phenotype associations, drug synergistic effects, and drug resistance evolution. Furthermore, they lack dynamic adaptability and the use of historical data, leading to biased efficacy predictions and misjudgments.
Using an organoid model-based approach, historical drug concentration, cell viability, and KRAS mutation expression level data are acquired to establish interval threshold classification of drug response states, construct a time-to-drug response state mapping relationship, identify state transition events, calculate state transition probabilities and error transition probabilities, and dynamically adjust drug sensitivity thresholds to optimize the assessment.
It enables precise assessment of drug sensitivity in KRAS-mutant tumors, improves predictive accuracy and adaptability, reduces assessment bias, ensures efficient assessment results under different drug treatment states, and supports personalized treatment.
Smart Images
Figure CN121545779A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of tumor drug sensitivity testing technology, specifically to a method for evaluating the drug sensitivity of KRAS-mutant tumors based on organoid models. Background Technology
[0002] With the rapid development of precision medicine technology, the requirements for individualized and precise cancer treatment are constantly increasing. In vitro drug sensitivity testing technology has become a key factor influencing treatment regimen selection, clinical efficacy, and patient survival. Among numerous tumor driver genes, KRAS mutations are one of the most common oncogenic mutations, making the sensitivity assessment of corresponding targeted drugs and combination therapies particularly important. Traditional drug sensitivity testing methods typically employ two-dimensional cell line models or fixed concentration gradient screening strategies. While these methods can provide some assessment capabilities in certain application scenarios, they cannot fully simulate the complexity of the in vivo tumor microenvironment. Especially in areas where high predictive accuracy is required, such as assessing genotype-phenotype associations, drug synergistic effects, and drug resistance evolution, existing drug sensitivity testing protocols have certain limitations.
[0003] The shortcomings of existing technologies are mainly reflected in the following aspects: First, static IC50 (half-maximal inhibitory concentration) assessment methods lack dynamic adaptability and cannot be adjusted in real time according to drug exposure time and cell state changes, leading to biased efficacy prediction or missed detection of drug resistance; Second, some dynamic assessment methods rely on fixed threshold judgment strategies and fail to make full use of historical test data for pattern analysis, making it difficult to accurately predict drug response trends; In addition, existing methods are prone to misassessment during state transitions, resulting in a decrease in clinical guidance value. Summary of the Invention
[0004] The purpose of this invention is to provide a method for evaluating the drug sensitivity of KRAS-mutant tumors based on organoid models, in order to solve the problems mentioned in the background art.
[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution:
[0006] A method for evaluating drug sensitivity in KRAS-mutant tumors based on organoid models includes the following steps: Step S1: Obtain historical drug concentration data, historical cell viability data, and historical KRAS mutation expression levels of the organoid model during historical drug treatment; determine the drug response state of the organoid model; Step S2: Statistically analyze all historical test node times of the organoid model and generate a set of historical test node times, mapping the drug response state to the historical test node times in a time-to-drug response state correspondence; Step S3: Mark drug response state transition events according to the mapping relationship; identify all drug response state transition events and generate a drug response state transition matrix; calculate the state transition probability of any drug response state transition event; calculate the error transition probability between state transition probabilities; Step S4: Extract all state transition probabilities, and use the drug response state with the highest probability as the preliminary predicted next drug response state; calculate the target drug sensitivity threshold; preset an error threshold; if the total error transition probability is greater than or equal to the error threshold, execute the evaluation strategy; if the total error transition probability is less than the error threshold, directly use the target drug sensitivity threshold.
[0007] As a preferred embodiment of the method for evaluating drug sensitivity of KRAS-mutant tumors based on organoid models according to the present invention, historical biological parameters of the organoid model during historical drug treatment are obtained through bioinformatics analysis technology. The historical biological parameters include historical drug concentration data, historical cell viability data, and historical KRAS mutation expression levels. Based on the historical drug concentration data, historical cell viability data, and historical KRAS mutation expression levels, the drug response status of the organoid model is determined.
[0008] As a preferred embodiment of the method for evaluating drug sensitivity of KRAS-mutant tumors based on organoid models according to the present invention, the specific implementation process for determining the drug response status of the organoid model includes:
[0009] Preset drug concentration data range, cell viability data range, and KRAS mutation expression level range;
[0010] If the historical drug concentration data is less than or equal to the minimum value of the drug concentration data range, the historical cell viability data is greater than or equal to the maximum value of the cell viability data range, and the historical KRAS mutation expression level is less than or equal to the minimum value of the KRAS mutation expression level range, then the drug response state is determined to be a sensitive state.
[0011] If the historical drug concentration data is within the range of the drug concentration data, the historical cell viability data is within the range of the cell viability data, and the historical KRAS mutation expression level is within the range of the KRAS mutation expression level, then the drug response state is determined to be an intermediate state.
[0012] If the historical drug concentration data is greater than or equal to the maximum value of the drug concentration data range, the historical cell viability data is less than or equal to the minimum value of the cell viability data range, and the historical KRAS mutation expression level is greater than or equal to the maximum value of the KRAS mutation expression level range, then the drug response state is determined to be a drug resistance state.
[0013] As a preferred embodiment of the organoid model-based drug sensitivity testing and evaluation method for KRAS-mutant tumors described in this invention, all historical test node times of the organoid model are statistically analyzed, and a set of historical test node times is generated, denoted as TY = {TY...} t |t∈[1,T]}, where TY t Let t represent the time of the t-th historical test node, and T represent the total number of historical test node times. Sensitive states, intermediate states, and drug-resistant states are labeled S1, S2, and S3, respectively. Based on the set of historical test node times, a time-to-drug-response mapping is established between drug response states and historical test node times, where one historical test node time corresponds to one drug response state, i.e., TY. t →S v And S v ∈[S1,S2,S3].
[0014] As a preferred embodiment of the organoid model-based KRAS-mutant tumor drug sensitivity testing and evaluation method described in this invention, drug response state transition events are sorted out according to the mapping relationship. If a drug response state transition occurs between two adjacent historical test nodes, it is marked as a drug response state transition event, and the drug response state transition is represented as S. i →S j , among which, S i ,S j ∈[S1,S2,S3] and i, j≠v; identify all drug response state transition events and generate a drug response state transition matrix, denoted as:
[0015]
[0016] Among them, S ij Indicates the drug response state S i Shift to drug response state S j S i →S j .
[0017] As a preferred embodiment of the organoid model-based drug sensitivity testing and evaluation method for KRAS-mutant tumors described in this invention, the number of drug response state transition events for each type is counted based on the drug response state transition matrix and the historical test node time set, denoted as Q. ij Based on the number of state transition events for each drug response, the state transition probability of any given drug response state transition event is calculated using the following formula:
[0018]
[0019] Wherein, P(S) i →S j ) indicates that S i →S j The state transition probability of drug response state transition events;
[0020] Calculate drug response state S i Shift to drug response state S j State transition probability and drug response state S i Shift to drug response state S k The error transition probability between the state transition probabilities is calculated using the following formula:
[0021]
[0022] Among them, ERR(S) j →S k P(S) represents the error transition probability. i →S k ) represents the drug response state S i Shift to drug response state S j The state transition probability, This indicates the preset coefficient.
[0023] As a preferred embodiment of the organoid model-based drug sensitivity testing and evaluation method for KRAS-mutant tumors described in this invention, if the current drug response status is S i Extract all state transition probabilities P(S) i →S j ), j=1,2,3, select the drug response state S with the highest probability. j As a preliminary prediction of the next drug response state, the specific details are as follows:
[0024] Based on the next drug response state S j and error transition probability ERR(S) j →S kAdjust the target drug sensitivity threshold as follows:
[0025]
[0026] in, Indicates the sensitivity threshold of the target drug. Indicates the drug response state S j The corresponding half-maximal inhibitory concentration, μ represents the preset adjustment coefficient, ∑ k≠j ERR(S j →S k ) represents the drug response state S j The total error transition probability to all other non-self states.
[0027] As a preferred embodiment of the organoid model-based KRAS mutant tumor drug sensitivity testing and evaluation method described in this invention, a preset error threshold is defined. If the total error transfer probability ∑ k≠j ERR(S j →S k If the error threshold is greater than or equal to the target drug sensitivity threshold, then the target drug sensitivity threshold is used. The evaluation strategy will be implemented as follows:
[0028]
[0029] Among them, ΔIC 50 This indicates the drug concentration adjustment step size, where δ represents the preset step size coefficient. This indicates the current half-maximal inhibitory concentration;
[0030] If the total error transfer probability Σ k≠j ERR(S j →S k If the value is less than the error threshold, then the target drug sensitivity threshold is used directly.
[0031] The present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein the computer program instructions, when executed by the processor, implement the steps of the method for evaluating drug sensitivity of KRAS-mutant tumors based on organoid models as described in the present invention.
[0032] The present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, the steps of the method for evaluating drug sensitivity of KRAS-mutant tumors based on organoid models as described in the present invention are implemented.
[0033] Compared with existing technologies, the beneficial effects achieved by this invention are as follows: The method for evaluating drug sensitivity in KRAS-mutant tumors based on organoid models provided by this invention collects historical drug concentration, cell viability, and KRAS mutation expression level data from organoid models. By setting interval thresholds, it classifies drug response states as sensitive, intermediate, or resistant, thereby establishing a basic criterion for determining drug response states and ensuring the accuracy of subsequent analyses. It statistically analyzes all historical test time points, constructing a time-to-drug response state mapping relationship, enabling the quantification of drug response state changes through time series analysis, thus providing data support for subsequent state transition probability calculations. It identifies drug response state transition events, constructs a drug response state transition matrix, and calculates the transition probability and error transition probability between different states based on historical data, quantifying the regularity and uncertainty of drug response changes and providing a reliable basis for dynamic drug sensitivity assessment. This invention predicts the next state by extracting the drug response state with the highest transfer probability and calculates the target drug sensitivity threshold based on the error transfer probability. When the error exceeds the preset threshold, a concentration adjustment assessment strategy is executed, thereby dynamically optimizing the sensitivity assessment and ensuring the predictive accuracy and clinical guidance value of the organoid model under different drug treatment states. This invention realizes intelligent drug sensitivity assessment based on historical data, improves the adaptability to drug sensitivity testing for KRAS-mutant tumors, reduces assessment bias, and optimizes predictive performance, enabling it to maintain efficient and stable assessment results under different drug response states. Attached Figure Description
[0034] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof.
[0035] Figure 1 This is a schematic diagram of the steps in the method for evaluating drug sensitivity of KRAS-mutant tumors based on organoid models according to the present invention. Detailed Implementation
[0036] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0037] Please see Figure 1 In this first embodiment: a method for evaluating drug sensitivity of KRAS-mutant tumors based on organoid models is provided, which includes the following steps:
[0038] Step S1: Obtain historical drug concentration data, historical cell viability data, and historical KRAS mutation expression levels of the organoid model during historical drug treatment; determine the drug response status of the organoid model.
[0039] Specifically, bioinformatics analysis techniques are used to obtain historical biological parameters of the organoid model during historical drug treatment. These historical biological parameters include historical drug concentration data, historical cell viability data, and historical KRAS mutation expression levels. Based on the historical drug concentration data, historical cell viability data, and historical KRAS mutation expression levels, the drug response status of the organoid model is determined.
[0040] The specific implementation process for determining the drug response status of the organoid model includes:
[0041] Preset drug concentration data range, cell viability data range, and KRAS mutation expression level range;
[0042] If the historical drug concentration data is less than or equal to the minimum value of the drug concentration data range, the historical cell viability data is greater than or equal to the maximum value of the cell viability data range, and the historical KRAS mutation expression level is less than or equal to the minimum value of the KRAS mutation expression level range, then the drug response state is determined to be a sensitive state.
[0043] If the historical drug concentration data is within the range of the drug concentration data, the historical cell viability data is within the range of the cell viability data, and the historical KRAS mutation expression level is within the range of the KRAS mutation expression level, then the drug response state is determined to be an intermediate state.
[0044] If the historical drug concentration data is greater than or equal to the maximum value of the drug concentration data range, the historical cell viability data is less than or equal to the minimum value of the cell viability data range, and the historical KRAS mutation expression level is greater than or equal to the maximum value of the KRAS mutation expression level range, then the drug response state is determined to be a drug resistance state.
[0045] It should be noted that this step establishes a historical drug response state dataset for the organoid model and classifies different states according to set interval thresholds, providing fundamental data support for subsequent state analysis and prediction. By accurately determining the drug response state, the model's response characteristics under different drug treatments can be identified, providing data support for intelligent assessment of drug sensitivity. Simultaneously, it avoids the inaccuracies of traditional methods that rely on a single parameter to determine the response state, improving the accuracy of state classification. This ensures the scientific rigor and rationality of subsequent sensitivity assessments, allowing dynamic adjustments to drug sensitivity to better adapt to the actual testing conditions of the organoid model, thereby optimizing prediction accuracy and clinical relevance.
[0046] Step S2: Statistically analyze all historical test node times of the organoid model and generate a set of historical test node times. Map the drug response state to the historical test node times to establish a time-to-drug response state correspondence.
[0047] Specifically, the historical test node times of the organoid model are statistically analyzed, and a set of historical test node times is generated, denoted as TY = {TY...} t |t∈[1,T]}, where TY t Let t represent the time of the t-th historical test node, and T represent the total number of historical test node times. Sensitive states, intermediate states, and drug-resistant states are labeled S1, S2, and S3, respectively. Based on the set of historical test node times, a time-to-drug-response mapping is established between drug response states and historical test node times, where one historical test node time corresponds to one drug response state, i.e., TY. t →S v And S v ∈[S1,S2,S3].
[0048] It's important to note that this step quantifies the changes in drug response status and establishes a mathematical model of how drug response status changes over time. This allows the system to understand the historical testing patterns of the model. By constructing a mapping relationship between time and drug response status, the model's response habits at different time points can be identified. For example, resistance occurs more frequently at certain time points, while sensitivity is predominant at other time points. This provides a data foundation for predicting the next drug response status and adjusting drug sensitivity. This method enables predictive adjustments based on historical trends, improving the foresight of drug sensitivity assessments, thereby managing the testing process more efficiently and avoiding assessment delays caused by sudden changes in status.
[0049] Step S3: According to the mapping relationship, label the drug response state transition events; identify all drug response state transition events and generate a drug response state transition matrix; calculate the state transition probability of any drug response state transition event; calculate the error transition probability between state transition probabilities.
[0050] Specifically, based on the mapping relationship, drug response state transition events are analyzed. If a drug response state transition occurs between two adjacent historical test time points, it is marked as a drug response state transition event, denoted as S. i →S j , among which, S i ,S j ∈[S1,S2,S3] and i, j≠v; identify all drug response state transition events and generate a drug response state transition matrix, denoted as:
[0051]
[0052] Among them, S ij Indicates the drug response state S i Shift to drug response state S j S i →S j .
[0053] Based on the drug response state transition matrix and the historical test node time set, the number of drug response state transition events is counted and denoted as Q. ij Based on the number of state transition events for each drug response, the state transition probability of any given drug response state transition event is calculated using the following formula:
[0054]
[0055] Wherein, P(S) i →S j ) indicates that S i →S j The state transition probability of drug response state transition events;
[0056] Calculate drug response state S i Shift to drug response state S j State transition probability and drug response state S i Shift to drug response state S k The error transition probability between the state transition probabilities is calculated using the following formula:
[0057]
[0058] Among them, ERR(S) j →S k P(S) represents the error transition probability. i →S k ) represents the drug response state S i Shift to drug response state S j The state transition probability, This indicates the preset coefficient.
[0059] It's important to note that this step calculates the probability of state transitions by statistically analyzing the frequency of transitions between different states, and further calculates the error transition probability, providing data support for predicting the next drug response state. Traditional drug sensitivity assessments typically rely on endpoint measurement data, making it difficult to predict state changes in advance. By calculating the state transition matrix, the system can predict the next possible drug response state the model might enter based on statistical regularities, and optimize prediction accuracy by combining this with the error transition probability. This allows the system to adjust its assessment strategy before state transitions occur, improving the response speed and accuracy of sensitivity assessment. This step enhances the system's ability to predict future drug response states, thereby reducing prediction bias or decreased clinical value caused by assessment lag, making sensitivity assessment more intelligent, and improving overall testing efficiency.
[0060] Step S4: Extract all state transition probabilities and take the drug response state with the highest probability as the next drug response state for preliminary prediction; calculate the target drug sensitivity threshold; preset the error threshold. If the total error transition probability is greater than or equal to the error threshold, then execute the evaluation strategy; if the total error transition probability is less than the error threshold, then directly use the target drug sensitivity threshold.
[0061] Specifically, if the current drug response state is S i Extract all state transition probabilities P(S) i →S j ), j=1,2,3, select the drug response state S with the highest probability. j As a preliminary prediction of the next drug response state, the specific details are as follows:
[0062] Based on the next drug response state S j and error transition probability ERR(S) j →S k Adjust the target drug sensitivity threshold as follows:
[0063]
[0064] in, Indicates the sensitivity threshold of the target drug. Indicates the drug response state S j The corresponding half-maximal inhibitory concentration, μ represents the preset adjustment coefficient, ∑ k≠j ERR(S j →S k ) represents the drug response state S j The total error transition probability to all other non-self states.
[0065] A preset error threshold is set, if the total error transition probability ∑ k≠jERR(S j →S k If the error threshold is greater than or equal to the target drug sensitivity threshold, then the target drug sensitivity threshold is used. The evaluation strategy will be implemented as follows:
[0066]
[0067] Among them, ΔIC 50 This indicates the drug concentration adjustment step size, where δ represents the preset step size coefficient. This indicates the current half-maximal inhibitory concentration;
[0068] If the total error transfer probability ∑ k≠j ERR(S j →S k If the value is less than the error threshold, then the target drug sensitivity threshold is used directly.
[0069] This embodiment also provides a computer device, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the KRAS-mutant tumor drug sensitivity testing and evaluation method based on organoid models proposed in the above embodiments.
[0070] It should be noted that by combining drug response state prediction, error transfer probability calculation, adaptive threshold setting, and a progressive adjustment strategy, accurate assessment of drug sensitivity is achieved. This method not only improves the prospectiveness and accuracy of the assessment but also avoids unnecessary testing, thereby improving the efficiency and reliability of organoid model testing. Ultimately, this method enables drug sensitivity assessment to flexibly adapt to clinical prediction needs under different response conditions, reducing assessment costs while improving predictive performance, providing technical support for efficient and intelligent tumor drug sensitivity testing.
[0071] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.
[0072] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the method for evaluating the drug sensitivity of KRAS-mutant tumors based on organoid models as proposed in the above embodiments.
[0073] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.
[0074] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.
Claims
1. A method for evaluating drug sensitivity test of KRAS mutant tumor based on organoid model, characterized in that, The method comprises the following steps: Step S1: obtaining historical drug concentration data, historical cell viability data and historical KRAS mutation expression level of the organoid model in the historical drug treatment process; determining the drug response state of the organoid model; Step S2: counting all historical test node times of the organoid model, and generating a historical test node time set, mapping the drug response state and the historical test node time in a time→drug response state corresponding relationship; Step S3: according to the mapping relationship, marking the drug response state transition event; identifying all drug response state transition events, and generating a drug response state transition matrix; calculating the state transition probability of any drug response state transition event; calculating the error transition probability between the state transition probabilities; Step S4: extracting all state transition probabilities, taking the drug response state with the highest probability as the next preliminary predicted drug response state; calculating the target drug sensitivity threshold; presetting an error threshold, if the total error transition probability is greater than or equal to the error threshold, executing the evaluation strategy; if the total error transition probability is less than the error threshold, directly using the target drug sensitivity threshold.
2. The KRAS mutant tumor drug sensitivity test evaluation method based on an organoid model according to claim 1, characterized by, The specific implementation process of step S1 comprises: Through bioinformatics analysis technology, obtain the historical biological parameters of the organoid model in the historical drug treatment process, the historical biological parameters include historical drug concentration data, historical cell viability data and historical KRAS mutation expression level; based on the historical drug concentration data, historical cell viability data and historical KRAS mutation expression level, determine the drug response state of the organoid model.
3. The KRAS mutant tumor drug sensitivity test evaluation method based on organoid model according to claim 2, characterized in that, The specific implementation process of determining the drug response state of the organoid model comprises: presetting the drug concentration data interval, the cell viability data interval and the KRAS mutation expression level interval; if the historical drug concentration data is less than or equal to the minimum value of the drug concentration data interval, the historical cell viability data is greater than or equal to the maximum value of the cell viability data interval, and the historical KRAS mutation expression level is less than or equal to the minimum value of the KRAS mutation expression level interval, then the drug response state is determined to be sensitive state; if the historical drug concentration data is within the drug concentration data interval, the historical cell viability data is within the cell viability data interval, and the historical KRAS mutation expression level is within the KRAS mutation expression level interval, then the drug response state is determined to be intermediate state; if the historical drug concentration data is greater than or equal to the maximum value of the drug concentration data interval, the historical cell viability data is less than or equal to the minimum value of the cell viability data interval, and the historical KRAS mutation expression level is greater than or equal to the maximum value of the KRAS mutation expression level interval, then the drug response state is determined to be drug resistance state.
4. The KRAS mutant tumor drug sensitivity test evaluation method based on organoid model according to claim 3, characterized in that, The specific implementation process of step S2 comprises: The historical test node times of the organoid model are statistically analyzed, and a set of historical test node times is generated, denoted as TY = {TY...} t |t∈[1,T]}, where TY t Let t represent the time of the t-th historical test node, and T represent the total number of historical test node times. Sensitive states, intermediate states, and drug-resistant states are labeled S1, S2, and S3, respectively. Based on the set of historical test node times, a time-to-drug-response mapping is established between drug response states and historical test node times, where one historical test node time corresponds to one drug response state, i.e., TY. t →S v And S v ∈[S1,S2,S3].
5. The KRAS mutant tumor drug sensitivity test evaluation method based on organoid model according to claim 4, characterized in that, The specific implementation process of step S3 comprises: According to the mapping relationship, the drug reaction state transition events are sorted out. If drug reaction state transition occurs between two adjacent historical test node times, it is marked as a drug reaction state transition event, and the drug reaction state transition is represented as S i →S j , wherein S i ,S j ∈[S1,S2,S3] and i, j≠v; all drug reaction state transition events are identified, and a drug reaction state transition matrix is generated, denoted as: where S ij represents the state of the drug reaction S i is transferred to the state of the drug reaction S j , i.e. S i → S j .
6. The KRAS mutant tumor drug sensitivity test evaluation method based on organoid model according to claim 5, characterized in that, The specific implementation process of step S3 further comprises: According to the drug reaction state transition matrix and the historical test node time set, the number of each drug reaction state transition event is counted, denoted as Q ij According to the number of each drug reaction state transition event, the state transition probability of any drug reaction state transition event is calculated, and the specific calculation formula is as follows: where P(S i → S j ) denotes the state transition probability of the drug response state transition event from S i → S j . Calculate drug response state S i Shift to drug response state S j State transition probability and drug response state S i Shift to drug response state S k The error transition probability between the state transition probabilities is calculated using the following formula: where ERR(S j → S k ) denotes an error transition probability, P(S i → S k ) denotes a state transition probability of the drug reaction state S i to the drug reaction state S j , denotes a preset coefficient.
7. The KRAS mutant tumor drug sensitivity test evaluation method based on organoid model according to claim 6, characterized in that, The specific implementation process of step S4 comprises: If the current drug response state is S i , extract all state transition probabilities P(S i → S j ), j = 1, 2, 3, and take the drug response state S j with the highest probability as the preliminary predicted next drug response state, specifically: According to the next drug response state S j and the error transition probability ERR(S j → S k ), the target drug sensitivity threshold is adjusted as follows: wherein, denotes a target drug sensitivity threshold, denotes a drug response state S j corresponding half-inhibitory concentration, μ denotes a preset adjustment coefficient, ∑ k≠j ERR(S j → S k ) denotes a drug response state S j total error transition probability to all other non-self states.
8. The KRAS mutant tumor drug sensitivity test evaluation method based on organoid model according to claim 7, characterized in that, The specific implementation process of step S4 further comprises: a preset error threshold, if the total error transition probability ∑ k≠j ERR(S j →S k ) is greater than or equal to the error threshold, based on the target drug sensitivity threshold an evaluation strategy is executed, specifically as follows: Wherein, ΔIC 50 represents the drug concentration adjustment step, δ represents the preset step coefficient, represents the current half-inhibitory concentration; If the total error transfer probability ∑ k≠j ERR(S j → S k ) is less than the error threshold, then directly adopt the target drug sensitivity threshold 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is characterized in that: The computer program is executed by the processor to implement the steps of the organoid model-based KRAS mutant tumor drug sensitivity test evaluation method according to any one of claims 1-8.
10. A computer readable storage medium having stored thereon a computer program, characterized in that: The computer program is executed by the processor to implement the steps of the organoid model-based KRAS mutant tumor drug sensitivity test evaluation method according to any one of claims 1-8.