Method and system for predicting sensitivity of anti-cancer agent based on cell growth factor

Abstract

The anti-cancer agent sensitivity prediction method of the embodiment can include: receiving biological test data based on a cell experiment of a biological sample separated from an individual by a receiving unit; determining, by a processor, the sensitivity of an anti-cancer agent of the individual as a positive treatment response or a negative treatment response based on the biological test data using a sensitivity prediction model; and providing an evaluation result of the sensitivity of the anti-cancer agent of the individual; wherein the sensitivity prediction model is configured to determine the sensitivity of the anti-cancer agent based on an anti-cancer agent response factor and a cell growth factor of a cell experiment.

Description

Technical Field

[0001] This invention relates to a method and system for predicting anticancer agent sensitivity based on cell growth factors, and more specifically, to a method and system for predicting anticancer agent sensitivity based on cell growth factors that evaluates anticancer agent sensitivity based on multiple predictive factors related to anticancer agent sensitivity. Background Technology

[0002] Treatment options for diagnosed cancer generally include surgery, chemotherapy, and radiation therapy. While chemotherapy, based on anticancer agents, is a popular treatment for cancer, the resistance of cancer cells to these agents is becoming a growing concern.

[0003] More specifically, due to long-term use of anticancer drugs, cells exposed to the drugs develop resistance through various mechanisms, such as reducing intracellular drug accumulation, activating detoxification or excretion, or denaturing target proteins. This process is not only the biggest obstacle in cancer treatment but is also closely related to the failure of anticancer therapy.

[0004] Especially when cancer patients try chemotherapy, if one anticancer agent fails to work, the patient may develop tolerance to other anticancer agents. Furthermore, even in the initial stages of treatment, combining chemotherapy with multiple anticancer agents with different mechanisms of action can sometimes result in no therapeutic effect.

[0005] In other words, assessing the sensitivity of cancer drugs is essential for determining the treatment direction for cancer patients. Therefore, there is a continuous demand for the development of an assessment system capable of evaluating the sensitivity of individuals to cancer drugs.

[0006] The background art has been prepared to facilitate a better understanding of the present invention. It should not be construed as an admission that the matters described in the background art are prior art. Summary of the Invention

[0007] [The problem the invention aims to solve]

[0008] On the other hand, as a scheme for evaluating the sensitivity to anticancer agents, a new IC-based method has been proposed. 50 The IC value is used to evaluate the sensitivity of anticancer agents. 50 The value is defined as the drug concentration at which cell activity reaches 50%, based on cells that have not undergone drug treatment and exhibit 100% activity.

[0009] More specifically, based on IC 50The anticancer agent sensitivity evaluation system based on the IC50value can be configured to calculate the IC50value as a concentration that inhibits 50% of the proliferation of cancer cells after treating cancer cells obtained from an individual with an anticancer agent 50 and predict the therapeutic response of the anticancer agent to the individual.

[0010] However, the anticancer agent sensitivity evaluation system based on the IC 50 value in the past only considers the IC50value related to the efficacy of the anticancer agent and does not consider the growth degree of the target cells, and thus the accuracy of the prediction can be very low. 50

[0011] In particular, the anticancer agent sensitivity evaluation system based on the IC 50 value does not consider the cell growth factor (e.g., cell growth rate) of the individual patient when comparing the efficacy of the anticancer agent using cancer cells from different individuals, and thus the accuracy of the sensitivity prediction can decrease.

[0012] Therefore, the inventors of the present application have recognized that there are limitations in predicting the therapeutic response of the anticancer agent in actual clinical practice when only the IC 50 value as a drug response value is used to evaluate the sensitivity of the anticancer agent.

[0013] In this regard, the inventors of the present application have recognized that, as a factor for predicting the therapeutic responsiveness to the anticancer agent, when the cell growth factor, e.g., the cell growth rate, is considered together with the anticancer agent response factor value, the growth rate of the cells can be reflected, and the limitations of the anticancer agent sensitivity evaluation system based on only the IC 50 value in the past can be overcome.

[0014] As a result, the inventors of the present application have developed an anticancer agent sensitivity evaluation system based on multiple prediction factors.

[0015] More specifically, the inventors of the present application have recognized that, with respect to the anticancer agent sensitivity evaluation system, it can be designed to evaluate the sensitivity to the anticancer agent based on multiple factors such as the anticancer agent response factor and the growth factor of the cancer cells. As a result, it can be expected to provide an evaluation result with high reliability that is sufficient to match the individual clinical results.

[0016] At this time, the inventors of the present application can further apply the sensitivity prediction model to a new anticancer agent sensitivity evaluation system, which is configured to input biological test data of a biological sample isolated from an individual, determine the anticancer agent, the anticancer agent response factor (IC 50 , %IC 50 , cell activity change rate, etc.), the cell growth factor (cell growth rate, Ki67, etc.), and output the degree of the sensitivity to the anticancer agent based thereon.

[0017] ​More specifically, the degree of therapeutic response can be determined based on a "cell growth factor" consisting of, for example, a cell growth rate, a growth-related marker such as Ki67, and an "anticancer agent response factor" consisting of IC 50 , %IC 50 (IC 50 / maximum concentration * 100), a degree of cell activity at a specific A concentration (A concentration cell activity / cell activity without drug treatment * 100), and a rate of change in cell activity at a specific A concentration (cell activity / initial activity of cells * 100).

[0018] More specifically, the degree of cell activity can be measured as a quantitative value using ordinary cell activity staining (Calcein AM), cell immunological chemical staining (F-action and the like cell activity-related markers), color matrix activity measurement (MTS, MTT, CCK-8 and the like), fluorescent luminescence (Celltiterglo and the like Luminescent), and the like.

[0019] Accordingly, the inventors of the present application have provided a novel anticancer agent sensitivity evaluation system, and it is expected that the sensitivity to an anticancer agent can be predicted, and the sensitivity of an individual to an anticancer agent can be evaluated with high accuracy.

[0020] In particular, the inventors of the present application have provided an anticancer agent sensitivity index based on the shortest distance from a prediction division line (or, a fitting line) defined as a therapeutic response prediction boundary for the evaluation system, and it is expected that the therapeutic response of an individual (sample) present at the boundary of the prediction division line can be evaluated.

[0021] The anticancer agent therapeutic response evaluation can be determined according to the anticancer agent sensitivity index as follows.

[0022] Sensitivity index -100% to -10%: low therapeutic response,

[0023] Sensitivity index -10% to 10%: moderate therapeutic response, and

[0024] Sensitivity index 10% to 100%: high therapeutic response

[0025] That is, the present application has been developed in order to solve the above-described technical problems, and the object of the present application is to substantially improve various problems occurring due to the limitations and disadvantages of the conventional art, and to provide an anticancer agent sensitivity evaluation method capable of evaluating the sensitivity of an individual to an anticancer agent with high accuracy, and a system using the same.

[0026] [Means for solving the problems]

[0027] To solve the above problems, a method for predicting sensitivity to an anticancer agent according to an embodiment of the present application is provided. The method for predicting sensitivity to an anticancer agent, which is embodied by a processor, includes: a step of receiving biological test data of a biological sample separated from an individual; a step of determining sensitivity to an anticancer agent of the individual as being positive or negative in therapeutic response based on the biological test data using a sensitivity prediction model configured to determine sensitivity to an anticancer agent based on an anticancer agent response factor and a cell growth factor; and a step of providing an evaluation result of the sensitivity to the anticancer agent of the individual, wherein the sensitivity prediction model is configured to determine sensitivity to an anticancer agent based on an anticancer agent response factor and a cell growth factor.

[0028] According to a feature of the present application, the biological test data based on a cell experiment can be at least one of a name of an anticancer agent, a concentration of an anticancer agent, a dilution ratio of an anticancer agent, and a degree of cell activity.

[0029] According to another feature of the present application, the sensitivity prediction model can be further configured to extract a sensitivity feature related to an anticancer agent response factor and a cell growth factor based on the biological test data based on a cell experiment, and the step of determining sensitivity to an anticancer agent of the individual as being positive or negative in therapeutic response can further include: a step of extracting the sensitivity feature based on the biological test data using the sensitivity prediction model; and a step of determining sensitivity to an anticancer agent of the individual as being positive or negative in therapeutic response based on the sensitivity feature.

[0030] According to still another feature of the present application, the sensitivity feature can be a fitting line generated by performing curve fitting with respect to the biological test data including the cell growth factor and the anticancer agent response factor of the cell.

[0031] According to still another feature of the present application, the step of determining sensitivity to an anticancer agent of the individual as being positive or negative in therapeutic response can further include: a step of additionally receiving clinical reference data of the individual. In addition, the step of determining sensitivity to an anticancer agent of the individual as being positive or negative in therapeutic response can further include: a step of determining sensitivity to an anticancer agent of the individual as being positive or negative in therapeutic response based on the biological test data and the reference data using the sensitivity prediction model.

[0032] According to still another feature of the present application, the step of determining sensitivity to an anticancer agent of the individual as being positive or negative in therapeutic response can include a step of determining a degree of therapeutic response to an anticancer agent using the sensitivity prediction model. In addition, the step of providing an evaluation result of the sensitivity to the anticancer agent can include a step of providing the degree of therapeutic response to an anticancer agent determined by the sensitivity prediction model as an anticancer agent sensitivity index.

[0033] According to still another feature of the present application, the evaluation method can further include a step of authenticating a user who is to receive the evaluation result of the sensitivity to an anticancer agent of the individual, which is performed before the step of receiving the biological test data.

[0034] According to still another feature of the present application, the sensitivity prediction model can be a model based on at least one of Logistic Regression (LR), Probit Regression (PR), Quadratic classifiers, Kernel Estimation, Learning Vector Quantization (LVQ), Artificial Neural Networks (ANN), Random Forest (RF), Bootstrap Aggregating, AdaBoost, Gradient Boosting, XGBoost, Support Vector Machine (SVM), Least Absolute Shrinkage and Selection Operator (LASSO), Ridge Regression, and Elastic Net.

[0035] According to still another feature of the present application, the anticancer agent can be a drug for anticancer treatment such as Doxorubicin, and the subject can be a subject suffering from cancer such as ovarian cancer, lung cancer, stomach cancer, and breast cancer.

[0036] To solve the problem, an anticancer agent sensitivity prediction system according to an embodiment of the present application is provided. The prediction providing includes a communication unit configured to receive biological test data based on a cell experiment of a biological sample separated from a subject, and a processor connected to the communication unit. At this time, the processor is configured to determine the sensitivity of the anticancer agent of the subject as a treatment response positive or a treatment response negative based on the biological test data using a sensitivity prediction model, and to provide an evaluation result of the sensitivity of the anticancer agent of the subject, wherein the sensitivity prediction model is configured to determine the sensitivity of the anticancer agent based on an anticancer agent response factor and a growth factor of the cell based on the cell experiment.

[0037] According to the features of the present application, the biological test data based on the cell experiment can be at least one of the name of the anticancer agent, the concentration of the anticancer agent, the dilution ratio of the anticancer agent, and the degree of cell activity.

[0038] According to another feature of the present application, the sensitivity prediction model can be further configured to extract sensitivity features related to anticancer agent response factors and growth factors of cells based on biological test data of cell experiments, and the processor can be further configured to extract the sensitivity features based on the biological test data using the sensitivity prediction model, and determine the sensitivity of the individual to the anticancer agent as positive or negative based on the sensitivity features.

[0039] According to still another feature of the present application, the receiving unit can be further configured to receive reference data of clinical outcomes of individuals, and the processor can be further configured to determine the sensitivity of the individual to the anticancer agent as positive or negative based on the biological test data and the reference data using the sensitivity prediction model.

[0040] According to still another feature of the present application, the processor can be further configured to calculate the degree of therapeutic response of the anticancer agent as an anticancer agent sensitivity index using the sensitivity prediction model, and determine the anticancer agent sensitivity prediction result based on the degree of therapeutic response of the anticancer agent determined using the sensitivity prediction model.

[0041] According to still another feature of the present application, the processor can be further configured to authenticate a user who is to receive the evaluation result of the sensitivity of the individual to the anticancer agent.

[0042] According to still another feature of the present application, the sensitivity prediction model can be a model based on at least one of logistic regression (LR), probit regression (PR), quadratic classifiers, kernel estimation, learning vector quantization (LVQ), artificial neural networks (ANN), random forest (RF), bootstrap aggregating, AdaBoost, gradient boosting, XGBoost, support vector machine (SVM), least absolute shrinkage and selection operator (LASSO), ridge regression, and Elastic Net.

[0043] According to another feature of the present application, the anticancer agent can be a drug for anticancer treatment such as Doxorubicin, and the subject can be a subject suffering from cancer such as ovarian cancer, lung cancer, stomach cancer, breast cancer, etc.

[0044] In addition, in order to solve the above problem, there is provided a computer-readable recording medium recording a program for implementing an evaluation method of anticancer agent sensitivity according to an embodiment of the present application. The evaluation method is a prediction method of anticancer agent sensitivity implemented by means of a processor, and includes the steps of receiving biological test data of a biological sample isolated from a subject; determining the anticancer agent sensitivity of the subject as a treatment response positive or a treatment response negative based on the biological test data using a sensitivity prediction model; and providing an evaluation result of the anticancer agent sensitivity of the subject; wherein the sensitivity prediction model is configured to determine the sensitivity of the anticancer agent based on an anticancer agent response factor and a cell growth factor.

[0045] Details of other embodiments are included in the detailed description and drawings.

[0046] [Effects of Invention]

[0047] The present application provides an anticancer agent sensitivity evaluation system configured to evaluate and output the treatment response of an anticancer agent for a subject with high accuracy, and thus has the effect of overcoming the limitations of the conventional IC 50 value-based anticancer agent sensitivity evaluation system.

[0048] More specifically, the present application can overcome the limitations of the conventional IC 50 value-based anticancer agent sensitivity evaluation system, i.e., simply using the IC 50 value, considering only the potency of the anticancer agent without considering the growth degree of the target cell, and thus the accuracy of the prediction can be very low.

[0049] In particular, the present application provides a novel anticancer agent sensitivity evaluation system through a sensitivity prediction model configured to input biological test data of a biological sample isolated from a subject, determine the type of anticancer agent, the IC 50 value, and the cell growth factor, and based thereon, output the degree of anticancer agent sensitivity, and thus can provide an analysis result with high accuracy.

[0050] Further, the present application provides an anticancer agent sensitivity evaluation system based on multiple factors such as an anticancer agent response factor and a cancer cell growth factor, and thus can provide an evaluation result with high reliability sufficient to match the clinical results of a subject.

[0051] That is, the present application can provide a highly reliable analysis result for the evaluation of anticancer agent sensitivity necessary for determining the direction of treatment of a cancer patient. Therefore, a medical team can easily select a suitable therapeutic agent according to the individual's condition, and the present application can contribute to good therapeutic prognosis.

[0052] The effects of the present application are not limited by the above examples, and various effects are included in the present specification. BRIEF DESCRIPTION OF DRAWINGS

[0053] Fig. 1a An anticancer agent treatment response evaluation system based on an anticancer agent sensitivity evaluation system according to one embodiment of the present application is exemplarily illustrated;

[0054] Fig. 1b The configuration of an anticancer agent sensitivity evaluation system according to one embodiment of the present application is exemplarily illustrated;

[0055] Fig. 1c The configuration of a user system that receives information on the result of evaluation of anticancer agent sensitivity from an anticancer agent sensitivity evaluation system according to one embodiment of the present application and outputs the same is exemplarily illustrated;

[0056] Figs. 2a to 2f The steps of a method for evaluating anticancer agent sensitivity according to one embodiment of the present application are exemplarily illustrated;

[0057] Fig. 3 The evaluation results of anticancer agent sensitivity evaluation systems according to various embodiments of the present application are exemplarily illustrated.

[0058] BRIEF DESCRIPTION OF DRAWINGS

[0059] 100: Anticancer agent sensitivity evaluation system

[0060] 110, 230: Storage unit

[0061] 120, 210: Communication unit

[0062] 130, 240: Processor

[0063] 200: User system

[0064] 220: Display unit

[0065] 300: Database providing server

[0066] 412: Biological test data

[0067] 420: Sensitivity prediction model

[0068] 422: Input module

[0069] 424: Analysis module

[0070] 426: output module

[0071] 428: analysis result

[0072] 432: reference data

[0073] 1000: anticancer agent sensitivity evaluation system DETAILED DESCRIPTION

[0074] The following is only an example of the principles of the invention. Therefore, although not explicitly described or illustrated in the specification, those skilled in the art can embody the principles of the invention to develop a variety of devices included in the concept and scope of the invention. In addition, all conditional terms and examples listed in the specification are, in principle, explicitly used only to help understand the concept of the invention, and are not limited to such specifically listed examples and states.

[0075] In addition, in the following description, the representation of the order form such as first, second, etc. should be understood as for the description of objects equal to each other and independent of each other, and there is no main / sub or master / slave meaning in the order thereof.

[0076] The above objects, features and advantages will become more apparent from the following detailed description taken in conjunction with the accompanying drawings, and it will be readily understood that the technical idea of the present invention can be easily embodied by those skilled in the art, without departing from the concept and scope of the present invention.

[0077] Each feature of the various embodiments of the present invention can be partially or wholly combined with or combined with each other, and as those skilled in the art can fully understand, can be technically variously linked and driven, and each embodiment can be independently implemented or implemented together in a related relationship.

[0078] In order to make the explanation of the present specification more clear, the terms used in the present specification are defined as follows.

[0079] The term "individual" used in the present specification can mean all subjects to be evaluated for anticancer agent sensitivity. For example, the individual can be an individual who has developed at least one cancer among ovarian cancer, breast cancer, squamous cell carcinoma, uterine cancer, cervical cancer, prostate cancer, head and neck cancer, pancreatic cancer, brain tumor, liver cancer, skin cancer, channel cancer, testicular cancer, kidney cancer, colon cancer, rectal cancer, stomach cancer, kidney cancer, bladder cancer, bile duct cancer, and gallbladder cancer. Preferably, the individual can be an individual to be evaluated for sensitivity of doxorubicin to an anticancer agent, or an individual who has developed ovarian cancer or breast cancer, but is not limited thereto. Further, the individual disclosed in the present specification can also be all mammals other than humans, but is not limited thereto.

[0080] The term "anticancer agent" as used in this specification refers to a chemotherapy therapeutic agent used to inhibit the proliferation of cancer cells, and can include chemoanticancer agents and targeted anticancer agents. For example, an anticancer agent can be paclitaxel containing doxorubicin, tislelizumab, doxorubicin, endostatin, angiostatin, mitomycin, bleomycin, cisplatin, carboptin, donomycin, idarubicin, 5-fluorouracil, methotrexate, actinomycin-D, or mixtures thereof. Preferably, the anticancer agent in this specification can be doxorubicin, but it is not limited thereto.

[0081] The term "anticancer agent sensitivity" as used in this specification can mean sensitivity to an anticancer agent, and can serve as a measure to evaluate whether a treatment response is observed with the administration of a targeted anticancer agent. In this context, anticancer agent sensitivity can be used interchangeably with anticancer agent responsiveness, drug responsiveness, etc. Therefore, based on the anticancer agent sensitivity assessment, an individual can be determined as either a treatment-responsive or treatment-responding individual to a specific anticancer agent. More specifically, individuals with relatively high sensitivity to targeted anticancer agents can be determined as treatment-responsive individuals, and individuals with relatively low sensitivity to targeted anticancer agents can be determined as treatment-responding individuals.

[0082] At this point, the sensitivity to anticancer agents is compared to the IC50 value of drug response from cancer cells isolated from the individual. 50 This is closely related to the growth rate of cancer cells. More specifically, the degree of drug response (drug efficacy) of cancer cells can be inversely proportional to the growth rate of cancer cells. That is, when anticancer drug response factors based on cell experiments and cancer cell growth rate, which serve as quantitative indicators of efficacy, are reflected in anticancer drug sensitivity evaluation, the accuracy and sensitivity of anticancer drug sensitivity evaluation can be improved compared to considering only a single factor. In particular, the accuracy of anticancer drug sensitivity evaluation based on multiple factors such as anticancer drug response factors and cancer cell growth factors can be improved to a level that can match individual clinical outcomes.

[0083] The term "anticancer agent response factor" as used in this specification refers to a cell-based, quantitative standard for measuring anticancer agent response, including the activity of cells corresponding to the anticancer agent.

[0084] For example, cell viability can be determined by staining surviving cells and measuring the overall intensity / size of fluorescent substances, the intensity / size of sorted substances, etc.; or by staining dead cells to determine cell death and then measuring cell viability in reverse.

[0085] Additionally, cell viability can be determined by measuring the transformation of cells or solutions containing cells using chemical elements such as MTT or APT.

[0086] The term "cell growth factor" used in the present specification includes a quantitative index for determining the growth of cells over time. As an example, the cell growth factor can be obtained by measuring the activity of cells over time.

[0087] At this time, the growth factor can be the cell activity increase rate, the cell growth rate, the cell size increase rate, or the colony formation rate. The term "cell growth rate" used in the present specification can mean the change in the volume, size, or number of cells within a given time.

[0088] At this time, the cell growth rate can be calculated for specific cells. The cell growth factor can be calculated for a group of cells in which cell division or growth is active among a plurality of cells.

[0089] The term "biological test data" used in the present specification can mean test result data based on a cell experiment for a biological material isolated from an individual, or test conditions, etc. At this time, the biological material can be at least one of a tissue, a cell, whole blood, serum, plasma, saliva, cerebrospinal fluid, and urine.

[0090] Preferably, in the present specification, the biological test data can be test data and / or test condition data for cancer cells (or, cancer tissue) isolated from an individual. For example, the biological test data can be raw data related to the activity of cells after treatment of cancer cells with an anticancer agent, and anticancer agent treatment condition data, for at least one of the name of the anticancer agent, the concentration of the anticancer agent, the dilution ratio of the anticancer agent, and the activity of cells. However, the biological test data is not limited to the foregoing.

[0091] On the other hand, according to the features of the present application, when the biological material is a cell, the cell can be cultured on a culture plate including a plurality of columnar portions formed with a receiving space capable of receiving a cell culture solution, as a portion on which a cell as a culture target is placed, protruding in a columnar shape with a given height from a flat bottom surface, and a groove portion formed in a recessed shape opposite to the columnar portion protruding from the flat bottom surface, so that the culture solution placed in the receiving space does not disperse and remains on the flat bottom surface but can be collected on one side. Then, after performing a biological test for anticancer agent sensitivity evaluation on the cell cultured on the culture plate, biological test data can be obtained. At this time, regarding the cell culture, the published patent bulletin No. 10-2020-0055230 is incorporated by reference. On the other hand, the culture plate and the culture conditions required for cell culture are not limited to the foregoing.

[0092] The term "sensitivity prediction model" used in the present specification can be a model configured to input an anticancer agent response factor based on a cell experiment and a cell growth factor or biological test data, and output the degree of sensitivity to an anticancer agent.

[0093] More specifically, the sensitivity prediction model can be a model that learns such that biological test data related to a cell experiment-based anticancer agent response factor and a growth factor of a cell is inputted, thereby extracting a sensitivity feature, and based on the same, an anticancer agent sensitivity degree is predicted and outputted.

[0094] According to a feature of the present application, the sensitivity prediction model can be configured to additionally input clinical outcome reference data, and based on the sensitivity feature extracted from the biological test data based on the cell experiment and the clinical outcome reference data, predict the anticancer agent sensitivity degree.

[0095] At this time, the clinical outcome reference data can be IC 50 - a growth factor-clinical outcome reference data, but is not limited thereto.

[0096] According to another feature of the present application, the sensitivity prediction model can be configured of an input module, an analysis module, and an output module.

[0097] More specifically, the input module can be configured to input biological test data, and further, input clinical outcome reference data. The analysis module can be configured to extract a sensitivity feature from the biological test data, and based on the sensitivity feature and / or the clinical outcome reference data, evaluate an anticancer agent sensitivity degree. Further, the output module can be configured to output the evaluated anticancer agent sensitivity degree.

[0098] According to another feature of the present invention, curve fitting can be performed based on at least one of the following: Logistic Regression (LR), Probit Regression (PR), Quadratic Classifiers, Kernel Estimation, Learning Vector Quantization (LVQ), Artificial Neural Networks (ANN), Random Forest (RF), Bootstrap Aggregating, AdaBoost, Gradient Boosting, XGBoost, Support Vector Machine (SVM), Lasso Algorithm (LASSO), Ridge Regression, and Elastic Net. Preferably, the sensitivity prediction model can be a classification model based on the LR algorithm, but it is not limited thereto.

[0099] The following reference Figs. 1a to 1c This invention describes an anticancer drug treatment response evaluation system based on an embodiment of the anticancer drug sensitivity evaluation system.

[0100] Fig. 1a An exemplary illustration shows an anticancer drug treatment response evaluation system based on an embodiment of the present invention. Fig. 1b An exemplary illustration shows the configuration of an anticancer agent sensitivity evaluation system according to an embodiment of the present invention. Fig. 1c An exemplary illustration shows the configuration of a user system that receives and outputs information related to anticancer agent sensitivity evaluation results from an anticancer agent sensitivity evaluation system according to an embodiment of the present invention.

[0101] First, if we refer to Fig. 1aThe anticancer agent treatment response evaluation system 1000 can be a system configured to provide information related to anticancer agent sensitivity based on biological test data of an individual. At this time, the anticancer agent treatment response evaluation system 1000 can include an anticancer agent sensitivity evaluation system 100 configured to determine the degree of anticancer agent sensitivity of an individual based on biological test data, a user system 200 receiving information related to anticancer agent sensitivity, and a database providing server 300 providing biological test data and / or clinical outcome reference data.

[0102] First, the anticancer agent sensitivity evaluation system 100 can include a general-purpose computer, a notebook computer, a data server, and / or the like, which performs various operations in order to diagnose the degree of sensitivity of an anticancer agent based on user biological test data and / or clinical outcome reference data provided from the database providing server 300. At this time, the user system 200 can be a system required to access a web server or a mobile web server providing a web page related to the evaluation of anticancer agent sensitivity, but is not limited thereto.

[0103] More specifically, the anticancer agent sensitivity evaluation system 100 can receive biological test data from the database providing server 300, and provide information related to the degree of anticancer agent sensitivity from the received biological test data. At this time, the anticancer agent sensitivity evaluation system 100 can be configured to perform evaluation of anticancer agent sensitivity based on a sensitivity prediction model. For example, the anticancer agent sensitivity evaluation system 100 can be configured to evaluate the predicted treatment response of an A anticancer agent together with the sensitivity index of the A anticancer agent.

[0104] The anticancer agent sensitivity evaluation system 100 can provide evaluation information of anticancer agent sensitivity of an individual to the user system 200.

[0105] Data thus provided from the anticancer agent sensitivity evaluation system 100 can be provided to a web page through a web browser installed in the user system 200, or can be provided in the form of an application or a program. In various embodiments, such data can be provided in the form of being included in a platform in a client-server environment.

[0106] The user system 200 is an electronic system including at least one of a smartphone, a tablet, a notebook computer, and / or a PC, which is an electronic system requesting to provide information related to anticancer agent sensitivity of an individual, and provides a user interface required to display evaluation result data.

[0107] The user system 200 can receive the evaluation result of the anticancer agent sensitivity of the individual from the anticancer agent sensitivity evaluation system 100, and display the received result by the display section. The evaluation result can include, for example, the degree of sensitivity to the A anticancer agent (e.g., high, medium, or low, treatment response positive or treatment response negative) output by the sensitivity prediction model, and the sensitivity index of the A anticancer agent (e.g., 50% (-100% to 100%)) used to determine the same.

[0108] Hereinafter, the configuration elements of the anticancer agent sensitivity evaluation system 100 of the present application will be specifically described with reference to Fig. 1b

[0109] If referring to Fig. 1b , the anticancer agent sensitivity evaluation system 100 includes a storage section 110, a communication section 120, and a processor 130.

[0110] First, the storage section 110 can store various data generated during the diagnosis of the degree of sensitivity to the anticancer agent of the individual. For example, the storage section 110 can be configured to store the sensitivity features extracted from the biological test data by the sensitivity prediction model, and the evaluation result of the degree of sensitivity. In various embodiments, the storage section 110 can include at least one type of storage medium of a flash memory type, a hard disk type, a micro multimedia card, a card memory (e.g., SD or XD memory, etc.), a random access memory, a static random access memory, a read-only memory, an electrically erasable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk.

[0111] The communication section 120 is connected so that the anticancer agent sensitivity evaluation system 100 can communicate with external systems. The communication section 120 can transmit and receive various data by connecting with the user system 200 and the database providing server 300 using wired / wireless communication. Specifically, the communication section 120 can receive the biological test data of the individual and the clinical result reference data from the database providing server 300. Further, the communication section 120 can also transmit the evaluation result to the user system 200.

[0112] The processor 130 can be operatively connected with the storage section 110 and the communication section 120, analyze the biological test data of the individual, extract the relevant sensitivity features, and execute various commands for determining the degree of sensitivity to the anticancer agent based thereon.

[0113] ​Specifically, the processor 130 can be configured to classify the sensitivity characteristic based on the biological test data received through the communication unit 120, and determine the degree of sensitivity to the anticancer agent. For example, the sensitivity characteristic can be a fitting line generated by performing curve fitting based on regression analysis on the biological test data including a cell growth factor and a cell anticancer agent response factor. At this time, the cell growth factor is a concept including a factor or a Z score (statistical index) of a factor that can represent cell proliferation such as a cell growth rate, and the anticancer agent response factor is a concept including a factor or a Z score (statistical index) of a factor that can represent the anticancer agent efficacy such as IC 50 , %IC 50 , drug response area under the curve (AUC), cell activity, cell activity change rate, etc. can be a concept including a factor or a Z score (statistical index) of a factor that can represent the anticancer agent efficacy.

[0114] At this time, the processor 130 can be configured based on a sensitivity prediction model that determines the degree of sensitivity to the anticancer agent based on the biological test data.

[0115] On the other hand, the anticancer agent sensitivity evaluation system 100 is not limited to a design on hardware. For example, the processor 130 of the anticancer agent sensitivity evaluation system 100 can be embodied in software. Therefore, the evaluation result of the resistance to the anticancer agent can also be displayed through the display unit of the user system 200 described later.

[0116] On the other hand, if referring to Fig. 1c , the user system 200 includes a communication unit 210, a display unit 220, a storage unit 230, and a processor 240.

[0117] The communication unit 210 can be configured to enable the user system 200 to communicate with an external system. The communication unit 210 can be connected to the anticancer agent sensitivity evaluation system 100 using wired / wireless communication, and transmit various data related to the anticancer agent sensitivity. Specifically, the communication unit 210 can receive the evaluation result related to the sensitivity of the individual to the anticancer agent, such as the degree of sensitivity of the individual to the anticancer agent (high, medium, or low), or whether the treatment response is positive, from the anticancer agent sensitivity evaluation system 100, and an efficacy evaluation chart of the anticancer agent in which the degree of anticancer agent sensitivity is displayed in a chart, etc.

[0118] The display unit 220 can display various interface screens of the evaluation result related to the sensitivity of the individual to the anticancer agent. For example, the display unit 220 can display and provide the degree of sensitivity of the individual to the anticancer agent (high, medium, or low), or whether the treatment response is positive, and an efficacy evaluation chart of the anticancer agent in which the degree of anticancer agent sensitivity is displayed in a chart, etc.

[0119] In various embodiments, the display 220 can include a touch screen, for example, can receive a touch, a gesture, a proximity, a drag, a swipe, or a hovering input of an electronic pen or a part of a user's body, etc.

[0120] The storage 230 can store various data used to provide a user interface for displaying the result data. In various embodiments, the storage 230 can include at least one type of storage medium of a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., an SD or XD memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory, a Read-Only Memory (ROM), an Electrically Erasable Programmable Read-Only Memory, a Programmable Read-Only Memory, a magnetic memory, a magnetic disk, an optical disk, etc.

[0121] The processor 240 can be operatively connected with the communication 210, the display 220, and the storage 230, and execute various commands required to provide a user interface for displaying the result data.

[0122] Hereinafter, a method for evaluating anticancer agent sensitivity according to one embodiment of the present application will be described with reference to Figs. 2a to 2f Figs. 2a to 2f An exemplary method for evaluating anticancer agent sensitivity according to one embodiment of the present application is illustrated.

[0123] First, if referring to Fig. 2a The method for evaluating anticancer agent sensitivity according to one embodiment of the present application is as follows. First, biological test data of an individual is received S210. Then, the sensitivity of the individual to an anticancer agent is evaluated based on the biological test data by means of a sensitivity prediction model S220. Finally, the evaluation result is provided S230.

[0124] More specifically, in the step of receiving biological test data S210, biological test data such as the name of an anticancer agent, the concentration of an anticancer agent, the dilution ratio of an anticancer agent, and cell activity can be received.

[0125] ​According to a feature of the present application, in the step S210 of receiving biological test data, biological data can receive biological test results and test condition data required for evaluating the anticancer agent efficacy on cancer cells isolated from an individual suffering from ovarian cancer or breast cancer. At this time, the anticancer agent can be doxorubicin, but is not limited thereto.

[0126] Preferably, in the step S210 of receiving biological test data, biological test data of cancer cells cultured on a culture plate can be received, but is not limited thereto, wherein the culture plate includes a plurality of column portions and groove portions, the column portions are formed with accommodation spaces capable of accommodating cell culture solution, as a portion for placing cells of a culture object, and are protruded in a column shape with a predetermined height from a flat bottom surface, and the groove portions are recessed in contrast to the column portions protruded from the flat bottom surface, so that the culture solution placed in the accommodation spaces can be gathered on one side without being dispersed and remaining on the flat bottom surface.

[0127] On the other hand, according to another feature of the present application, before the step S210 of receiving biological test data, a step of authenticating a user who is to receive a result of evaluating the sensitivity of an individual to an anticancer agent can be further performed.

[0128] That is, in the step S210 of receiving biological test data, biological test data of an individual can be received only after a user who is authenticated logs in.

[0129] Then, in the step S220 of evaluating the sensitivity to an anticancer agent, the sensitivity of an individual to an anticancer agent can be determined as a treatment response positive or a treatment response negative by means of a sensitivity prediction model, wherein the sensitivity prediction model is configured to input an anticancer agent response factor and a growth factor of cells, and output a degree of sensitivity to an anticancer agent.

[0130] According to a feature of the present application, in the step S220 of evaluating the sensitivity to an anticancer agent, a sensitivity feature can be extracted based on biological test data by means of a sensitivity prediction model, and the sensitivity of an individual to an anticancer agent can be determined as a treatment response positive or a treatment response negative based on the sensitivity feature.

[0131] For example, the sensitivity feature can be a fitting line generated by performing curve fitting on biological test data including a cell growth factor and a cancer drug response factor of a cell. Also, according to still another feature of the present application, in the step S220 of evaluating the sensitivity to the cancer drug, the curve fitting can be performed by means of at least one of Logistic Regression (LR), Probit Regression (PR), Quadratic Classifiers, Kernel Estimation, Learning Vector Quantization (LVQ), Artificial Neural Networks (ANN), Random Forest (RF), Bootstrap Aggregating, AdaBoost, Gradient Boosting, XGBoost, Support Vector Machine (SVM), Least Absolute Shrinkage and Selection Operator (LASSO), Ridge Regression, and Elastic Net. At this time, the degree of sensitivity to the cancer drug can be determined based on the fitting line determined by means of the curve fitting. Also, the cell growth factor is a concept including a factor or a Z-score (statistical index) of a factor that can represent cell proliferation such as a cell growth rate, and the cancer drug response factor is a concept including a factor or a Z-score (statistical index) of a factor that can represent the efficacy of the cancer drug such as IC 50 , %IC 50 , Drug Response Area Under Curve (AUC), cell activity, cell activity change rate, etc.

[0132] According to still another feature of the present application, before the step S220 of evaluating the sensitivity to the cancer drug, reference data of a clinical result can be further received, and in the step S220 of evaluating the sensitivity to the cancer drug, the sensitivity evaluation of the individual to the cancer drug can be performed based on the biological test data (or, the sensitivity feature) and the reference data by means of the sensitivity prediction model.

[0133] According to still another feature of the present application, in the step S220 of evaluating the sensitivity to the cancer drug, the degree of the treatment response of the individual to the cancer drug can be determined as at least one of high, medium, and low by means of the sensitivity prediction model.

[0134] At this time, the degree of treatment response can be determined based on the sensitivity index of the anticancer agent.

[0135] For example, if reference is made to Fig. 2b In the step S220 of evaluating the sensitivity to the anticancer agent, after the user authentication by the login, the received biological test data 412 is input to the sensitivity prediction model 420. At this time, the biological test data 412 can be input to the input module 422 of the sensitivity prediction model 420. On the other hand, the input module 422 can further receive the clinical result reference data 432. Then, the sensitivity features are extracted from the biological test data 412 by means of the analysis module 424, and the degree of sensitivity to the anticancer agent is determined based on the sensitivity features and output by means of the output module 426. At this time, the output module 426 can determine the degree of treatment response of the individual to the anticancer agent as high, medium or low using the sensitivity features extracted from the biological test data 412 and the clinical result reference data 432, and provide the analysis result 428. More specifically, the analysis module 424 can calculate the sensitivity index of the anticancer agent from the biological test data 412, and the output module 426 can be configured to determine the degree of treatment response as "low" when the sensitivity index is -100 to -10%, as "medium" when the sensitivity index is -10 to +10%, and as "high" when the sensitivity index is +10 to +100%.

[0136] However, the method of evaluating the degree of treatment response is not limited thereto, and the output module 426 can also output the degree of treatment response based on the degree of drug response of the cells such as the anticancer agent response factor (IC 50 , %IC 50 , the rate of change of cell activity, etc.), the multiple factors of the cell growth factor (e.g., the cell growth rate), as positive or negative, or output the degree of treatment response in the form of probability. Further, the output module 426 can also determine the anticancer agent efficacy evaluation chart expressing the degree of sensitivity to the anticancer agent as a chart.

[0137] According to still another feature of the present application, in the step S220 of evaluating the sensitivity to the anticancer agent, the degree of treatment response can be determined based on the cell growth factor and the drug response factor.

[0138] More specifically, the degree of treatment response can be determined based on the "cell growth factor" consisting of the cell growth rate, the growth-related marker such as ki67, and the "anticancer agent response factor" consisting of IC 50 , %IC 50 (IC 50The results are composed of: (maximum concentration * 100), cell viability at a specific concentration A (cell viability at concentration A / cell viability without drug treatment * 100), and the rate of change in cell viability at a specific concentration A (cell viability / initial cell viability * 100).

[0139] More specifically, if referring to a typical example representing the anticancer agent sensitivity evaluation system proposed in this invention... Fig. 2c (1), (2), and (3) were used to treat cell lines that responded to anticancer agent A at various concentrations. After 3, 5, and 7 days of treatment with anticancer agent A, the results, as shown in the figures, differed at each date. This can be attributed to the influence of growth rate on the anticancer response at each date.

[0140] exist Fig. 2c In (1), (2), and (3), the cell area representing cell viability at each date differed at the minimum anticancer agent concentration. This cell growth, when used to measure the anticancer agent response, resembles... Fig. 2c (4) uses the cell activity of anticancer agent concentration as a benchmark to average the cell activity of each concentration, which will lead to different reactivity to anticancer agents.

[0141] Therefore, even with the same cells and the same anticancer agent, the IC50, as one type of cellular anticancer agent response, 50 The concentration at which half of the cells die is also affected by cell growth.

[0142] As mentioned above, the response to anticancer agents changes with cell growth, thus exhibiting the following characteristics: Fig. 2d The chart shows cell growth and response to anticancer agents.

[0143] Therefore, as Fig. 2d As shown, in one embodiment of the present invention, the model construction corresponds to a sensitivity baseline for the drug, thus ensuring that even for drugs with the same anticancer response (IC50), the sensitivity baseline is maintained. 50 For samples with a cellular value, the positive control region (anticancer agent sensitive response group) and the negative control region (anticancer agent resistant group) can also be distinguished by considering cell growth. For example... Fig. 2d As shown, even with the same anticancer agent response (IC50), 50 The value is also divided into positive and negative depending on the different cell growth.

[0144] At this point, if we refer to Fig. 2e (a) and (b), the treatment response prediction model can evaluate the presence or absence of a treatment response based on cell growth factors and drug response factors. Fig. 2ethe model (b) of the present application. Fig. 2e

[0145] If further referring to Fig. 2f the model (b) of the present application. Fig. 2d In the model (a) of the present application, Fig. 2e In the model (a) of the present application, the anticancer agent sensitivity index can be calculated according to the following mathematical formula 1 based on the shortest distance from the determined predictive discrimination line (or, fitted line) to the new data.

[0146] [mathematical formula 1]

[0147]

[0148] That is, the anticancer agent sensitivity index can be determined according to the shortest distance from the individual position determined by the cell growth factor and the drug response degree to the predictive discrimination line.

[0149] At this time, in order to normalize the anticancer agent sensitivity index in percentage, as a reference, the half distance of the distance between the x-axis 100 and the y-axis 100, i.e., the half distance of the maximum distance of the anticancer agent sensitivity index, can be used as the maximum distance.

[0150] As another example, in the normalization, the half distance of the x-intercept and the y-intercept of the anticancer agent sensitivity reference line can be used as the maximum distance, or the half distance of the maximum value connecting the x-axis and the y-axis within the data range can be used.

[0151] The anticancer agent sensitivity evaluation system of the present application can be configured such that even if the individual is located on one side of the treatment response positive region, the treatment response negative region according to the evaluation, if it is close to an arbitrary point or less from the predictive discrimination line (fitted line), it is judged as a region where the prediction is not possible. Therefore, in the case where the individual (sample) belongs to the ambiguous region, the corresponding individual (sample) can be excluded from the evaluation, and thus the accuracy of the overall treatment response prediction can be improved.

[0152] At this time, when the sensitivity index is -100 to -10%, the treatment response degree can be determined as "low", when the sensitivity index is -10 to +10%, the treatment response degree can be determined as "medium", and when the sensitivity index is +10 to +100%, the treatment response degree can be determined as "high", but it is not limited thereto.

[0153] ​​According to a further feature of the present application, in the step S220 of evaluating the sensitivity to the anticancer agent, the sensitivity to the anticancer agent can be determined by means of a sensitivity prediction model based on at least one algorithm of Logistic Regression (LR), Probit Regression (PR), Quadratic classifiers, Kernel Estimation, Learning Vector Quantization (LVQ), Artificial Neural Networks (ANN), Random Forest (RF), Bootstrap Aggregating, AdaBoost, Gradient Boosting, XGBoost, Support Vector Machine (SVM), Least Absolute Shrinkage and Selection Operator (LASSO), Ridge Regression, and Elastic Net. Preferably, the sensitivity prediction model can be a classification model based on the LR algorithm, but is not limited thereto.

[0154] If referring back to Fig. 2a In the step S230 of providing the evaluation result, the evaluation result of the sensitivity to the anticancer agent of the individual generated by means of the sensitivity prediction model can be provided.

[0155] According to a feature of the present application, in the step S230 of providing the evaluation result, an efficacy evaluation chart of the anticancer agent can be provided, in which the degree of the sensitivity to the anticancer agent (high, medium, or low) or the positive response to the treatment and the degree of the sensitivity to the anticancer agent of the individual are expressed as a chart.

[0156] For example, if referring back to Fig. 2b In the step S230 of providing the evaluation result, the analysis result 428 generated by means of the output module 426 of the sensitivity prediction model 420 can be transmitted to the user system and provided through the display unit of the user system.

[0157] On the other hand, according to a further feature of the present application, after the step S230 of providing the evaluation result, the user can also be logged out.

[0158] According to the anticancer agent sensitivity evaluation system of the above various embodiments, the level of anticancer agent sensitivity can be predicted and provided with high accuracy. Thus, the present application provides the anticancer agent sensitivity evaluation system, which can overcome the limitations of the conventional anticancer agent sensitivity evaluation system, i.e., providing low reliability results that do not match actual clinical evaluation by considering only a single factor such as IC 50 . Further, the medical team can quickly select an appropriate therapeutic agent based on the evaluation results, and the anticancer agent treatment response evaluation system of the present application has an effect of being able to contribute to early treatment and good prognosis.

[0159] Evaluation: Evaluation of the anticancer agent sensitivity evaluation system of the various embodiments of the present application

[0160] Hereinafter, the evaluation results of the sensitivity evaluation system of the various embodiments of the present application are described with reference to Fig. 3 . Fig. 3 FIGS. 1 to 3 illustrate the evaluation results of the anticancer agent sensitivity evaluation system of the various embodiments of the present application.

[0161] At this time, the anticancer agent sensitivity evaluation system can use a sensitivity prediction model based on a Logistics Regression (LR) algorithm, which is learned for evaluating cancer cell sensitivity, so as to extract the sensitivity characteristics of the kind of targeted anticancer agent, the anticancer agent response factor of the cell, and the growth factor of the cell based on the processed name of the anticancer agent, the concentration of the anticancer agent, and the dilution ratio of the anticancer agent, and the biological test data of the activity degree of the cancer cell, thereby outputting the sensitivity to the anticancer agent as high, medium, or low. However, the learning conditions of the sensitivity evaluation model are not limited thereto.

[0162] First, if referring to Fig. 3 , FIG. 1 illustrates the results of the sensitivity evaluation system based on the embodiment using the cell Colony generation rate as the cell growth factor and using the IC 50 value as the cell anticancer agent sensitivity factor, for the Doxorubicin (DOX) sensitivity evaluation of 7 breast cancer individuals (#1, #2, #3, #5, #8, #11, #15). At this time, it is understood that, based on the anticancer agent sensitivity reference line, the anticancer agent sensitivity of the individual on the upper side is lower, and the anticancer agent sensitivity of the individual on the lower side is higher.

[0163] More specifically, the IC 50The value is low, and thus the patient is judged to have high sensitivity to the anticancer agent in the existing classification, but it is confirmed from the clinical result that a new tumor appears after the anticancer treatment, and thus it is known that there is a limit in predicting the clinical result using only the anticancer agent response factor. However, when the growth factor is considered, the tissue of the patient #2 exhibits 100% Colony generation rate and is above the anticancer agent sensitivity reference line, and thus is determined to have low sensitivity to the anticancer agent, and thus has similarity to the clinical result.

[0164] Further, the tissues of the patients #15, #5, #11, and #1 are also above the anticancer agent sensitivity reference line, and thus are determined to have low sensitivity to the anticancer agent, and the tissues of the patients #3 and #8 are below the anticancer agent sensitivity reference line, and thus are determined to have high sensitivity to the anticancer agent.

[0165] The embodiments of the present application are described in more detail with reference to the drawings, but the present application is not necessarily limited to such embodiments, and can be variously modified without departing from the scope of the technical idea of the present application. Therefore, the embodiments disclosed in the present application are not intended to limit but to describe the technical idea of the present application, and the scope of the technical idea of the present application is not limited by such embodiments. Thus, the above-described embodiments should be understood in all aspects as merely illustrative and not restrictive. The scope of the present application should be interpreted by the following claims, and all technical ideas within the equivalent scope should be interpreted as included in the scope of the present application.

Claims

1. A method for predicting sensitivity to an anticancer agent, comprising an anticancer agent sensitivity prediction system including a receiving section, a display section, and a processor, characterized by The method comprises the following steps: receiving, by the receiving unit, cell experiment-based biological test data of a biological sample separated from an individual; providing a sensitivity prediction model comprising a two-dimensional graph including a first axis representing an anticancer agent response factor, a second axis representing a cell growth factor, and a prediction discrimination line; determining, by the processor, the sensitivity of the biological individual to the anticancer agent based on the prediction discrimination line determining a positive treatment response or a negative treatment response; and providing, by the display unit, an evaluation result of the sensitivity of the biological individual to the anticancer agent; wherein the prediction discrimination line is created based on the cell experiment-based anticancer agent response factor and the cell growth factor; wherein the cell growth factor is selected from at least one of the following group: cell activity increase rate, cell size increase rate, and colony forming rate indicating cell growth according to cell experiments on cell growth rate; wherein the anticancer agent response factor is at least one selected from IC 50 , %IC 50 , and area under the drug response curve AUC.

2. The anticancer agent sensitivity prediction method according to claim 1, wherein The cell experiment-based biological test data is at least one of the name of the anticancer agent, the concentration of the anticancer agent, the dilution ratio of the anticancer agent, and the degree of cell activity.

3. The anticancer agent sensitivity prediction method according to claim 1, wherein The sensitivity prediction model is further configured to extract a sensitivity feature related to the anticancer agent response factor and the cell growth factor based on the cell experiment, The step of determining a positive treatment response or a negative treatment response further comprises: a step of extracting the sensitivity feature based on the biological test data using the sensitivity prediction model; and a step of determining the sensitivity of the individual to the anticancer agent treatment as a positive treatment response or a negative treatment response based on the sensitivity feature.

4. The anticancer agent sensitivity prediction method according to Claim 3, wherein The sensitivity feature is a fitting line generated by performing curve fitting on a cell experiment including the cell growth factor and the anticancer agent response factor of the cell.

5. The method of predicting sensitivity to an anticancer agent according to Claim 4, wherein The curve fitting is performed by at least one of logistic regression, probit regression, quadratic classifier, kernel estimation, learning vectorization, artificial neural network, bootstrap aggregation, adaptive boosting algorithm, gradient boosting, extreme gradient boosting, support vector machine, lasso algorithm, ridge regression, and elastic net.

6. The method of predicting sensitivity to an anticancer agent according to claim 4, wherein The curve fitting is performed by random forest.

7. The anticancer agent sensitivity prediction method according to claim 1, wherein Before the step of determining a positive treatment response or a negative treatment response, the method further comprises a step of additionally receiving clinical outcome reference data of the individual; The step of determining a positive treatment response or a negative treatment response further comprises a step of determining the sensitivity of the individual to the anticancer agent as a positive treatment response or a negative treatment response based on the biological test data and the reference data using the sensitivity prediction model.

8. The anticancer agent sensitivity prediction method according to claim 1, wherein The step of determining a positive treatment response or a negative treatment response further comprises a step of determining the degree of treatment response of the anticancer agent using the sensitivity prediction model; The step of providing an evaluation result of the sensitivity to the anticancer agent comprises a step of providing the degree of treatment response of the anticancer agent determined by the sensitivity prediction model.

9. The anticancer agent sensitivity prediction method according to claim 1, wherein It further comprises a step of authenticating a user who is to receive the evaluation result of the sensitivity of the individual to the anticancer agent before the step of receiving the biological test data.

10. The anticancer agent sensitivity prediction method according to claim 1, wherein The anticancer agent is doxorubicin, The individual is an individual who has developed ovarian cancer or breast cancer.

11. An anticancer agent sensitivity prediction system characterized by comprising: Comprises: a communication section configured to receive biological test data based on a cell experiment of a biological sample separated from an individual; a display section; and a processor connected to the communication section; the processor is configured to determine the sensitivity of the anticancer agent using a sensitivity prediction model wherein the sensitivity prediction model comprises a two-dimensional graph including a first axis representing an anticancer agent response factor, a second axis representing a cell growth factor, and a prediction discrimination line; the processor determines the sensitivity of the biological individual to the anticancer agent based on the prediction discrimination line determining a positive treatment response or a negative treatment response; wherein the prediction discrimination line is created based on the anticancer agent response factor and the growth factor of the cell based on the cell experiment; wherein the cell growth factor is selected from at least one of the following group: cell activity increase rate, cell size increase rate, and colony forming rate indicating cell growth according to cell experiment on cell growth rate; wherein the display section provides an evaluation result of the sensitivity of the biological individual to the anticancer agent; wherein the anticancer agent response factor is at least one selected from IC 50 , %IC 50 , and area under the drug response curve AUC.

12. The anticancer agent sensitivity prediction system according to claim 11, wherein The cell experiment-based biological test data is at least one of the name of the anticancer agent, the concentration of the anticancer agent, the dilution ratio of the anticancer agent, and the degree of cell activity.

13. The anticancer agent sensitivity prediction system according to claim 11, wherein The sensitivity prediction model is further configured to extract a sensitivity feature related to the anticancer agent response factor and the growth factor of the cell based on the cell experiment, The processor is further configured to extract the sensitivity feature based on the biological test data using the sensitivity prediction model, and determine the sensitivity of the individual to the anticancer agent as a positive treatment response or a negative treatment response based on the sensitivity feature.

14. The anticancer agent sensitivity prediction system according to claim 13, wherein The sensitivity feature is a fitting line generated by performing curve fitting on a cell experiment including a cell growth factor and an anticancer agent response factor of a cell.

15. The anticancer agent sensitivity prediction system according to claim 14, wherein The curve fitting is performed by at least one of logistic regression, probit regression, quadratic classifier, kernel estimation, learning vectorization, artificial neural network, bootstrap aggregation, adaptive boosting algorithm, gradient boosting, extreme gradient boosting, support vector machine, lasso algorithm, ridge regression, and elastic net.

16. The anticancer agent sensitivity prediction system according to claim 14, wherein The curve fitting is performed by random forest.

17. The anticancer agent sensitivity prediction system according to claim 11, wherein It further comprises a receiving section that receives clinical outcome reference data for the individual; The processor is further configured to determine the sensitivity of the individual to the anticancer agent as a positive treatment response or a negative treatment response based on the biological test data and the reference data using the sensitivity prediction model.

18. The anticancer agent sensitivity prediction system according to claim 11, wherein, The processor is further configured to determine the degree of treatment response of the anticancer agent using the sensitivity prediction model, and provide the determined degree of treatment response of the anticancer agent.

19. The anticancer agent sensitivity prediction system according to claim 11, wherein The processor is further configured to authenticate a user who is to receive an evaluation result of the sensitivity of the individual to the anticancer agent.

20. The anticancer agent sensitivity prediction system according to claim 11, wherein, The anticancer agent is a drug for anticancer treatment such as doxorubicin, The individual is an individual who has developed cancer including ovarian cancer, lung cancer, gastric cancer, or breast cancer.

21. A computer-readable recording medium, characterized by A program capable of implementing the anticancer agent sensitivity prediction method according to any one of claims 1 to 10 is recorded.

22. A method for predicting sensitivity to an anticancer agent, comprising an anticancer agent sensitivity prediction system including a receiving section, a display section, and a processor, characterized by comprises the following steps: receiving, by the receiving section, biological test data based on a cell experiment of a biological sample isolated from an individual; providing a sensitivity prediction model for extracting a sensitivity feature related to a Z-score of an anticancer agent response factor and a Z-score of a cell growth factor based on the biological test data; determining, by the processor, the sensitivity of the biological individual to the anticancer agent based on a prediction discrimination line that determines a positive treatment response or a negative treatment response; and providing, by the display section, an evaluation result of the sensitivity of the biological individual to the anticancer agent; wherein the sensitivity prediction model comprises a two-dimensional graph containing a first axis representing an anticancer agent response factor, a second axis representing a cell growth factor, and a prediction discrimination line; wherein the cell growth factor is selected from at least one of the following group: a cell activity increase rate, a cell size increase rate, and a colony forming rate indicating cell growth according to a cell experiment on cell growth rate; wherein the prediction discrimination line is created based on a Z-score of an anticancer agent response factor and a Z-score of a cell growth factor based on a cell experiment; wherein the anticancer agent response factor is at least one selected from IC 50 , %IC 50 , area under the drug response curve AUC.

Images