Construction system of advanced colorectal cancer targeted therapy prediction model

Abstract

The invention relates to the technical field of treatment prediction, in particular to a construction system of an advanced colorectal cancer targeted treatment prediction model, which comprises a cell tissue acquisition module used for acquiring tumor cell tissues according to a colorectal cancer operation specimen; the organoid culture module is used for obtaining mature organoid according to the tumor cell tissues; the drug sensitivity test module is used for performing a drug sensitivity test on the mature organs to obtain a drug sensitivity analysis result; the factor evaluation module is used for screening risk factors influencing the progression-free lifetime of the colorectal cancer patient based on clinical pathological characteristics of the colorectal cancer patient; the model construction module is used for constructing an advanced colorectal cancer targeted therapy prediction model in combination with the drug sensitivity analysis result and the risk factors; and the comprehensive control module serves as a system center and is used for controlling each module to realize functions. According to the method, a targeted therapy prediction model is constructed, the progression-free survival state of the patient is evaluated, and reference is provided for determining a therapeutic scheme.

Description

Technical Field

[0001] The present invention relates to the technical field of treatment prediction, and in particular to a system for constructing a prediction model for targeted treatment of advanced colorectal cancer. Background Art

[0002] Organoids are in vitro research models that are optimized to simulate in vivo culture conditions with the development of stem cells and three-dimensional culture technology. That is, under certain culture conditions, the different differentiation potentials of adult cells or stem cells are used to cultivate spatial organizational structures that are highly similar to in vivo tissues and organs in vitro. Cancer stem cell research has shown that tumor tissues contain a small number of tumor cells with stem cell activity. Organoid culture technology is applied to in vitro research on tumors to derive tumor organoids. Patient-derived tumor organoids (PDO) are spatial organizational structures that are highly similar to in vivo tumor tissues cultivated in an environment that simulates the growth of in vivo tumor cells using tumor-derived tissue cells or purified and isolated tumor stem cells. They have broad application prospects in in vitro tumor research, especially in anticancer drug development platforms and personalized precision treatment. The emergence of PDO makes up for the defects of previous models. Cell line models cannot reliably represent the physiological characteristics of the original tumor. PDX models take a long time to build, have a low success rate and are very expensive. Compared with PDO, less tissue can be used to build, and the construction can be completed in a shorter time with a higher culture success rate.

[0003] Previous studies have shown that organoids can predict patients' responses to targeted therapies, but for KRAS wild-type patients, whether the IC50 cutoff value of the anti-EGFR drug (cetuximab) can be defined, and whether the response to cetuximab at the organoid level can predict the therapeutic efficacy of patients is still poorly studied. Therefore, the present invention aims to prove that the drug response of organoids to cetuximab can predict patients' responses to clinical treatment, and as an important factor in constructing a prediction model, predict the survival status of patients. Summary of the invention

[0004] In view of the defects in the prior art, the present invention provides a system for constructing a prediction model for targeted therapy of advanced colorectal cancer.

[0005] In order to achieve the above-mentioned objectives, the present invention provides a system for constructing a prediction model for targeted treatment of advanced colorectal cancer, the system comprising: a cell tissue acquisition module, the cell tissue acquisition module is used to obtain tumor cell tissue based on colorectal cancer surgical specimens; an organoid cultivation module, the organoid cultivation module is used to obtain mature organoids based on the tumor cell tissue; a drug sensitivity test module, the drug sensitivity test module is used to perform a drug sensitivity test on the mature organoids to obtain drug sensitivity analysis results; a factor evaluation module, the factor evaluation module screens the risk factors that affect the progression-free survival of colorectal cancer patients based on the clinical pathological characteristics of colorectal cancer patients; a model construction module, the model construction module combines the drug sensitivity analysis results and the risk factors to construct a prediction model for targeted treatment of advanced colorectal cancer; and a comprehensive control module, the comprehensive control module is used as the system center to control each module to realize functions. The present invention can accurately analyze the sensitivity of colorectal cancer cells to drugs through cell tissue acquisition, organoid cultivation and drug sensitivity testing, providing a strong basis for personalized treatment; at the same time, it combines the patient's clinical pathological characteristics to evaluate the risk factors affecting the progression-free survival of colorectal cancer patients, thereby improving the accuracy and reliability of predicting treatment effects; the comprehensive control module ensures the collaborative work between the modules and improves the operating efficiency of the overall system. The system provides a more scientific and accurate targeted treatment plan for patients with advanced colorectal cancer, which helps to improve the treatment effect on the patient's condition.

[0006] Optionally, the cell tissue acquisition module includes: a specimen acquisition unit, the specimen acquisition unit is used to obtain a colorectal cancer surgical specimen; and a cell extraction unit, the cell extraction unit is used to obtain tumor cell tissue from the colorectal cancer surgical specimen. The present invention is based on the specimen acquisition unit in the cell tissue acquisition module to obtain surgical specimens under sterile conditions, ensuring that the surgical specimens are pure and pollution-free, improving the reliability of surgical specimens, and improving the availability of surgical specimens; the cell extraction unit accurately extracts tumor cell tissues, providing support for subsequent organoid cultivation and drug sensitivity testing, and improving the degree of personalization and accuracy of colorectal cancer treatment.

[0007] Optionally, the organoid cultivation module includes: a cell processing unit, the cell tissue processing unit is used to pre-treat the tumor cell tissue to obtain tumor cell tissue fragments; a cell cultivation unit, the cell cultivation unit cultivates the tumor cell tissue fragments to obtain organoids; a cell dissociation unit, the cell dissociation unit dissociates the organoid to obtain small cell cluster tissues; and a cell cultivation unit, the cell cultivation unit cultivates the small cell cluster tissues to obtain mature organoids after passage. The present invention is based on the organoid cultivation module, which uses the cell processing unit to pre-treat the tumor cell tissue to ensure the quality of the cell material used to cultivate the organoid; the cell cultivation unit effectively promotes the growth of tumor cell tissue fragments into organoids, thereby improving the cultivation success rate; and re-cultivation after cell dissociation further promotes the maturation and functional improvement of the organoid, providing a more accurate and reliable organoid model for the research and targeted treatment of colorectal cancer.

[0008] Optionally, the cell culture unit cultures the small cell mass tissue to obtain mature organoids after passage, and the growth of the organoids satisfies the following relationship:

[0009]

[0010] in, is the growth volume of the organoid with respect to time, is the initial volume, is the environmental holding volume, is the organoid growth rate coefficient, The present invention cultivates small cell mass tissues based on a cell culture unit to obtain mature organoids after passage, and describes the growth volume of the organoids through a formula, which is helpful for quantitatively evaluating the cultivation status of the organoids, can accurately reflect the growth changes of the organoids, and provides reliable data support for further research.

[0011] Optionally, the drug sensitivity test module includes: a drug addition unit, which is used to add drugs to the mature organoid; a cell detection unit, which is used to perform viability detection on the cells of the mature organoid after adding the drug to obtain a cell viability detection result; and a drug sensitivity analysis unit, which is used to construct a half-inhibitory concentration curve according to the cell viability detection result to obtain a half-inhibitory concentration value of the mature organoid. The present invention is based on the drug sensitivity test module, which allows the drug to act on the mature organoid through the drug addition unit, and the cell detection unit accurately detects the cell viability. Then the drug sensitivity analysis unit deeply analyzes the drug sensitivity of the mature organoid based on the test results, intuitively presents the sensitivity of the mature organoid to the drug, provides a reference for the dosage of the drug, improves the accuracy and efficiency of the drug use, helps to improve the pertinence and effectiveness of drug treatment, facilitates the rapid determination of the best treatment plan, saves medical resources and reduces trial and error costs.

[0012] Optionally, the factor evaluation module includes: an information acquisition unit, the information acquisition unit is used to acquire clinical pathological information data of colorectal cancer patients; a feature analysis unit, the feature analysis unit is used to analyze the clinical pathological information data to screen risk factors that affect the progression-free survival of the colorectal cancer patients; a data processing unit, the data processing unit is used to standardize the clinical pathological information data of the risk factors to obtain clinical pathological feature information. Based on the close cooperation of the three units of information acquisition, feature analysis and data processing of the factor evaluation module, the present invention efficiently integrates and analyzes the clinical pathological information of colorectal cancer patients, deeply explores the risk factors that affect the progression-free survival of the colorectal cancer patients, and provides a scientific basis for formulating personalized treatment plans by standardizing the clinical pathological information data of risk factors, which helps to improve the accuracy of treatment and the treatment effect of colorectal cancer.

[0013] Optionally, the data processing unit is used to perform standardization processing on the clinical pathology information data of the risk factors to obtain clinical pathology characteristic information, satisfying the following relationship:

[0014]

[0015] in, The clinical pathological characteristics information, For clinical pathology information data, is the mean of clinical pathological information data, The present invention performs standardization processing on clinical pathology information data based on a data processing unit, which can eliminate dimensional differences between data, improve the comparability between different data, enhance the availability of data, and provide more accurate and reliable data support for subsequent feature analysis.

[0016] Optionally, the model building module includes: a factor screening unit, the factor screening unit is used to obtain key factors for constructing a prediction model for targeted treatment of advanced colorectal cancer; and a model building unit, the model building unit is used to construct the prediction model for targeted treatment of advanced colorectal cancer in combination with the drug sensitivity analysis results and the key factors. The present invention is based on the collaboration of factor screening and model building units in the model building module, and can screen key factors for constructing a prediction model, and construct a prediction model for targeted treatment of advanced colorectal cancer based on drug sensitivity and key factors, thereby improving the accuracy and reliability of the prediction model and providing strong technical support for the formulation of personalized treatment plans.

[0017] Optionally, the model building unit is used to build the advanced colorectal cancer targeted therapy prediction model in combination with the drug sensitivity analysis result and the key factors, satisfying the following relationship:

[0018]

[0019] in, is the probability of progression-free survival, is the weight coefficient of drug sensitivity analysis results, The results of drug sensitivity analysis are as follows: is the weight coefficient of the degree of differentiation of mature organoid tumor cells, is the degree of differentiation of mature organoid tumor cells, is the weight coefficient of preoperative CEA concentration, is the preoperative CEA concentration, is the weight coefficient of clinical pathological characteristic information, The present invention integrates drug sensitivity and key factors based on the model building unit, and uses a systematic formula to describe the model to construct a prediction model for targeted treatment of advanced colorectal cancer, making the prediction model more scientific and accurate, and being able to comprehensively consider multiple factors, providing doctors with more reliable treatment suggestions, helping to optimize treatment plans, improve treatment effects, and thus prolong patients' progression-free survival.

[0020] Optionally, the integrated control module includes: a module retrieval unit, the module retrieval unit is used to retrieve the cell tissue acquisition module, the organoid cultivation module, the drug sensitivity test module, the factor evaluation module and the model construction module; a function realization unit, the function realization unit is used to control the cell tissue acquisition module, the organoid cultivation module, the drug sensitivity test module, the factor evaluation module and the model construction module to realize the module function. The present invention is based on the two units of module retrieval and function realization of the integrated control module, which effectively coordinates and drives the operation of other modules, improves the operating efficiency and synergy of the overall system, ensures that each step from cell tissue acquisition to model construction can be accurately executed, and provides strong technical support and guarantee for the precision treatment of advanced colorectal cancer. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a schematic diagram of the structure of a system for constructing a prediction model for targeted treatment of advanced colorectal cancer according to an embodiment of the present invention;

[0022] Figure 2 This is a schematic diagram of a drug dose-mature organoid response curve according to an embodiment of the present invention;

[0023] Figure 3 This is a schematic diagram of the half inhibition concentration value of an embodiment of the present invention;

[0024] Figure 4 This is a comparison diagram of the mature organoid response before and after adding drugs according to an embodiment of the present invention;

[0025] Figure 5 This is a schematic diagram of a progression-free survival probability curve according to an embodiment of the present invention;

[0026] Figure 6 A logistic regression nomogram for colorectal cancer patients according to an embodiment of the present invention;

[0027] Figure 7 tROC curve diagram of the prediction model for targeted therapy of advanced colorectal cancer according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The specific embodiments of the present invention will be described in detail below. It should be noted that the embodiments described herein are only for illustration and are not intended to limit the present invention. In the following description, a large number of specific details are set forth in order to provide a thorough understanding of the present invention. However, it is obvious to those of ordinary skill in the art that these specific details do not need to be adopted to implement the present invention. In other examples, in order to avoid confusing the present invention, known circuits, software or methods are not specifically described.

[0029] Throughout the specification, references to "one embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in conjunction with the embodiment or example is included in at least one embodiment of the present invention. Therefore, the phrases "in one embodiment," "in an embodiment," "an example," or "an example" appearing in various places throughout the specification do not necessarily all refer to the same embodiment or example. In addition, particular features, structures, or characteristics may be combined in one or more embodiments or examples in any suitable combination and / or subcombination. In addition, it should be understood by those of ordinary skill in the art that the figures provided herein are for illustrative purposes and that the figures are not necessarily drawn to scale.

[0030] See also Figure 1 One embodiment of the present invention provides a system for constructing a prediction model for targeted therapy of advanced colorectal cancer, the system comprising:

[0031] A1. A cell tissue acquisition module, wherein the cell tissue acquisition module is used to acquire tumor cell tissue based on colorectal cancer surgical specimens.

[0032] The cell tissue acquisition module comprises:

[0033] A11. A specimen acquisition unit, which is used to obtain colorectal cancer surgical specimens.

[0034] Specifically, a laparoscopic monitor is used to capture abdominal images, an ultrasonic scalpel is used to cut tissue under sterile conditions, and then separation forceps are used to extract colorectal cancer surgical specimens.

[0035] Furthermore, the obtained colorectal cancer surgical specimens were stored in RPMI1640 culture medium.

[0036] The colorectal cancer surgical specimens were stored at 4°C, and the RPMI1640 culture medium was supplemented with 5% penicillin / streptomycin.

[0037] A12. A cell extraction unit, which is used to obtain tumor cell tissue from the colorectal cancer surgical specimen.

[0038] Specifically, under sterile conditions, the tumor cell tissue is obtained from the colorectal cancer surgical specimen using a cell tissue processor in the cell extraction unit.

[0039] A2. An organoid cultivation module, wherein the organoid cultivation module is used to obtain organoids based on the tumor cell tissue.

[0040] The organoid cultivation module comprises:

[0041] A21. A cell processing unit, wherein the cell tissue processing unit is used to pre-process the tumor cell tissue to obtain tumor cell tissue fragments.

[0042] Specifically, under sterile conditions, the tumor cell tissue is washed using Dulbecco's phosphate buffered saline using a cell washer.

[0043] Wherein, the Dulbecco's phosphate buffered saline contains 5% antibiotics.

[0044] More specifically, under sterile conditions, the washed tumor cell tissue is minced using a cell tissue pulverizer.

[0045] The volume of the minced tumor cell tissue is 1 mm 3 -3 mm 3 .

[0046] Further, under sterile conditions, the minced tumor cell tissue was placed in 10 ml of DMEM / F12 mixed collagenase and hyaluronidase saline for digestion.

[0047] A constant temperature water bath was used to ensure that the temperature during digestion was 37°C and the digestion time was 15 min.

[0048] Furthermore, under sterile conditions, the digested tumor cell tissue is filtered using a cell filter.

[0049] Furthermore, the filtered tumor cell tissue is centrifuged using a medical centrifuge.

[0050] Among them, the tumor cell tissue used for centrifugation is 250g, and the centrifugation operation time is 3min.

[0051] Furthermore, under sterile conditions, lysate is added to the centrifuged tumor cell tissue, and a medical centrifuge is used to separate red blood cells and other cell components in the tumor cell tissue.

[0052] A22. A cell cultivation unit, which cultivates the tumor cell tissue fragments to obtain mature organoids.

[0053] Specifically, under sterile conditions, the tumor cell tissue fragments are placed in Matrigel and then resuspended using a pipette.

[0054] More specifically, under sterile conditions, the resuspended tumor cell tissue is inoculated into the first well plate using a pipette and a pipette tip.

[0055] The first well plate has 24 wells, and each well is inoculated with 30 μL.

[0056] Furthermore, under sterile conditions, the first well plate is placed in a cell culture incubator for solidification.

[0057] The temperature of the cell culture incubator is set to 37° C. A CO2 sensor is used to monitor and control the concentration of CO2 in the cell culture incubator to 5%. The solidification time is 25 min.

[0058] Furthermore, under sterile conditions, the culture medium is added to the first well plate using an automated liquid workbench.

[0059] The volume of the culture medium added was 500 μL, and the culture medium was replaced every 2 to 3 days.

[0060] A23. A cell dissociation unit, which dissociates the organoid to obtain small cell cluster tissue.

[0061] Specifically, under sterile conditions, an automated pipetting system is used to obtain the organoids from the first well plate.

[0062] Furthermore, under sterile conditions, the organoids in the first well plate are dissociated using a cell filter based on a cell dissociation reagent to obtain small cell clusters.

[0063] A24. A cell culture unit, which cultures the small cell cluster tissue to obtain mature organoids after passage.

[0064] Specifically, under sterile conditions, the small cell cluster tissue is resuspended using organoid culture medium.

[0065] Wherein, 5% Matrigel was added to the organoid culture medium.

[0066] More specifically, under sterile conditions, the resuspended small cell cluster tissue is inoculated into a second well plate using a pipette and a pipette tip.

[0067] The second well plate has 96 wells, and each well is inoculated with 6 μL.

[0068] Further, under sterile conditions, the second well plate is placed in the cell culture incubator for culture.

[0069] The temperature of the cell culture incubator was set at 37°C, and a CO2 sensor was used to monitor and control the concentration of CO2 to be precisely adjusted to 5%. The culture time was 96 hours.

[0070] Furthermore, the growth of organoids satisfies the following relationship:

[0071]

[0072] in, is the growth volume of the organoid with respect to time, is the initial volume, is the environmental holding volume, is the organoid growth rate coefficient, For time.

[0073] A3. A drug sensitivity test module, which is used to perform a drug sensitivity test on the mature organoid to obtain a drug sensitivity analysis result.

[0074] The drug sensitivity test module comprises:

[0075] A31. A drug adding unit, which is used to add drugs to the mature organoid.

[0076] Specifically, under sterile conditions, a microinjection pump is used to add cetuximab into the second well plate according to a certain concentration gradient.

[0077] Wherein, the concentration gradient of cetuximab is 10µg / L, 5µg / L, 2.5µg / L, 1.25µg / L, 0.625µg / L, 0.3125µg / L.

[0078] More specifically, the mature organoids were treated with cetuximab for 96 hours.

[0079] A32. A cell detection unit, which is used to perform viability detection on the cells of the mature organoid after the addition of drugs to obtain a cell viability detection result.

[0080] For details, see Figure 2 , the figure shows a schematic diagram of the drug dose-mature organoid response curve. Under sterile conditions, 30 mature organoids derived from colorectal cancer patients that met the exclusion criteria were selected for the experiment, a micropipette was used to add a cell viability detection reagent to the second well plate, and then an oscillator was used to fully mix the cell viability detection reagent and the cells of the mature organoids, and the CellTiter-Glo 3D cell viability assay was performed, and the luminescence signal was recorded using a luminescence detector, and the luminescence signal was collected using a data acquisition device.

[0081] A33. A drug sensitivity analysis unit, which is used to construct a half-inhibitory concentration curve according to the cell viability detection result to obtain the half-inhibitory concentration value of the mature organoid.

[0082] For details, see Figure 3, the figure shows a schematic diagram of the half-maximal inhibitory concentration value (IC50). The data of the drug dose-mature organoid response curve diagram is analyzed using statistical analysis software configured by a computer processor, and the half-maximal inhibitory concentration values ​​(IC50) of the mature organoids derived from tumors of the 30 colorectal cancer patients are obtained.

[0083] Among them, based on the half inhibitory concentration value, progression-free survival time and progression-free survival status of the mature organoids derived from tumors of the 30 colorectal cancer patients, the R software was used to select and determine the optimal IC50 cutoff value of the mature organoids' response to cetuximab.

[0084] More specifically, the program instructions configured to execute a computer processor are used to determine the response of the mature organoid to cetuximab.

[0085] Among them, the basis for the judgment is the cutoff value of the half-maximal inhibitory concentration, and the object of the judgment is 52 mature organoids derived from tumors of colorectal cancer patients selected separately.

[0086] Furthermore, the 52 mature organoids derived from colorectal cancer patients' tumors were used as a blind validation group, and the blind validation group was validated based on the cutoff value combined with the clinical response of colorectal cancer patients, and then the predictive efficacy of the blind validation group under the cutoff value condition was obtained, as shown in Table 1:

[0087] Table 1

[0088]

[0089] For details, see Figure 4 , the figure shows a comparison of the reactions of mature organoids in the blind validation group before and after the addition of drugs. It is obvious that the shape of the sensitive mature organoids is destroyed and disintegrated; while the resistant mature organoids have no obvious disintegration phenomenon and continue to grow under the action of the drug.

[0090] For further information, see Figure 5 , the figure is a schematic diagram of the progression-free survival probability curve, and the mature organoids are divided into two groups according to the cutoff value and the results are visualized using a computer processor.

[0091] A4. A factor evaluation module, which screens risk factors that affect the progression-free survival of colorectal cancer patients based on their clinical pathological characteristics.

[0092] The factor evaluation module comprises:

[0093] A41. An information acquisition unit, wherein the information acquisition unit is used to acquire clinical pathological information data of colorectal cancer patients.

[0094] Specifically, the data acquisition instructions configured by the computer processor are used to acquire clinical pathological information data of colorectal cancer patients based on the clinical database.

[0095] A42. A feature analysis unit, which is used to analyze the clinical pathological information data and screen risk factors that affect the progression-free survival of the colorectal cancer patient.

[0096] Specifically, the data analysis instructions configured by the computer processor are used to analyze the clinical pathology information data using factor analysis to obtain the risk factors.

[0097] A43. A data processing unit, which is used to standardize the clinical pathological information data of the risk factors to obtain clinical pathological characteristic information.

[0098] Specifically, the clinical pathological information data of the risk factors are standardized using the data processing instructions configured by the computer processor to satisfy the following relationship:

[0099]

[0100] in, The clinical pathological characteristics information, For clinical pathology information data, is the mean of clinical pathological information data, is the standard deviation of clinical pathological information data.

[0101] A5. A model building module, wherein the model building module combines the drug sensitivity analysis results and the risk factors to build a prediction model for targeted treatment of advanced colorectal cancer.

[0102] The model building module comprises:

[0103] A51. A factor screening unit, wherein the factor screening unit is used to obtain key factors for constructing a prediction model for targeted treatment of advanced colorectal cancer.

[0104] Specifically, the key factors for constructing a prediction model for targeted treatment of advanced colorectal cancer are screened out based on factor analysis using program instructions configured by a computer processor.

[0105] Among them, the key factors include the drug sensitivity analysis results of mature organoids, the degree of tumor cell differentiation of mature organoids and the preoperative carcinoembryonic antigen (CEA) concentration.

[0106] A52. A model building unit, wherein the model building unit is used to construct the prediction model for targeted treatment of advanced colorectal cancer by combining the drug sensitivity analysis results and the key factors.

[0107] Specifically, a model building instruction configured by a computer processor is used to build a prediction model for targeted therapy of advanced colorectal cancer based on the key factors affecting the effect of targeted therapy, and the prediction model satisfies the following relationship:

[0108]

[0109] in, is the probability of progression-free survival, is the weight coefficient of drug sensitivity analysis results, The results of drug sensitivity analysis are as follows: is the weight coefficient of the degree of differentiation of mature organoid tumor cells, is the degree of differentiation of mature organoid tumor cells, is the weight coefficient of preoperative CEA concentration, is the preoperative CEA concentration, is the weight coefficient of clinical pathological characteristic information, Clinical pathological characteristics information.

[0110] For more details, see Figure 6 , the figure shows a logistic regression nomogram for colorectal cancer patients. The results of the prediction model are processed using data processing instructions configured by a computer processor, which intuitively shows the results of the prediction model and the contribution of key factors to the prediction results.

[0111] Among them, the prediction results include the six-month progression-free survival probability, one-year progression-free survival probability and two-year progression-free survival probability of colorectal cancer patients.

[0112] For further information, see Figure 7 , the figure shows the tROC curve of the prediction model for targeted treatment of advanced colorectal cancer, in which a half-year tROC curve, a one-year tROC curve and a two-year tROC curve are plotted respectively.

[0113] Among them, the AUC value in the figure represents the area under tROC, and the AUC values ​​of the half-year tROC curve, the one-year tROC curve and the two-year tROC curve are calculated respectively, which are used to quantify the predictive performance of the prediction model for targeted treatment of advanced colorectal cancer. The closer the AUC value is to 1, the higher the predictive performance. It is obvious that the prediction model constructed by the present invention has a higher predictive performance, and the shorter the prediction requirement time, the higher the predictive performance.

[0114] A6. Integrated control module, which serves as the system center and is used to control each module to realize functions.

[0115] The integrated control module comprises:

[0116] A61. A module calling unit, wherein the module calling unit is used to call the cell tissue acquisition module, the organoid cultivation module, the drug sensitivity test module, the factor evaluation module and the model construction module.

[0117] Specifically, the function module is called by using the calling program instruction configured by the computer processor.

[0118] A62. A function realization unit, which is used to control the cell tissue acquisition module, organoid cultivation module, drug sensitivity test module, factor evaluation module and model construction module to realize module functions.

[0119] Specifically, the driver program instructions configured by the computer processor enable the hardware devices in each functional module to realize their functions.

[0120] In summary, the system for constructing a prediction model for targeted treatment of advanced colorectal cancer provided by the present invention can construct mature organoids that truly restore the physiological and pathological characteristics of the parent tissue, can be frozen, amplified and stably propagated, and have the characteristics of low cost and high efficiency. It is suitable as a preclinical model. The prediction model constructed based on the drug sensitivity analysis results of mature organoids and clinical pathological characteristics can accurately predict the patient's survival and progression-free survival status.

[0121] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A system for constructing a prediction model for targeted therapy of advanced colorectal cancer, characterized in that: include: A cell tissue acquisition module, wherein the cell tissue acquisition module is used to acquire tumor cell tissue based on colorectal cancer surgical specimens; An organoid cultivation module, wherein the organoid cultivation module is used to obtain mature organoids based on the tumor cell tissue; A drug sensitivity test module, which is used to perform a drug sensitivity test on the mature organoid to obtain a drug sensitivity analysis result; A factor evaluation module, wherein the factor evaluation module screens risk factors that affect progression-free survival of colorectal cancer patients based on clinical pathological characteristics of the colorectal cancer patients; A model building module, wherein the model building module combines the drug sensitivity analysis results and the risk factors to build a prediction model for targeted treatment of advanced colorectal cancer; The integrated control module is used as the system center to control each module to realize its functions.

2. The system for constructing a prediction model for targeted therapy of advanced colorectal cancer according to claim 1, characterized in that: The cell tissue acquisition module comprises: A specimen acquisition unit, wherein the specimen acquisition unit is used to obtain a colorectal cancer surgical specimen; A cell extraction unit is used to obtain tumor cell tissue from the colorectal cancer surgical specimen.

3. The system for constructing a prediction model for targeted therapy of advanced colorectal cancer according to claim 1, characterized in that: The organoid cultivation module comprises: A cell processing unit, wherein the cell tissue processing unit is used to pre-process the tumor cell tissue to obtain tumor cell tissue fragments; A cell cultivation unit, wherein the cell cultivation unit cultivates the tumor cell tissue fragments to obtain organoids; A cell dissociation unit, wherein the cell dissociation unit dissociates the organoid to obtain small cell cluster tissue; A cell culture unit is used to culture the small cell cluster tissue to obtain mature organoids after passage.

4. The system for constructing a prediction model for targeted therapy of advanced colorectal cancer according to claim 3, characterized in that: The cell culture unit cultivates the small cell mass tissue to obtain mature organoids after passage, and the growth of the organoids satisfies the following relationship: ； in, is the growth volume of the organoid with respect to time, is the initial volume, is the environmental holding volume, is the organoid growth rate coefficient, For time.

5. The system for constructing a prediction model for targeted therapy of advanced colorectal cancer according to claim 1, characterized in that: The drug sensitivity test module comprises: a drug adding unit, the drug adding unit being used to add drugs to the mature organoid; A cell detection unit, wherein the cell detection unit is used to perform a viability detection on the cells of the mature organoid after the addition of the drug to obtain a cell viability detection result; A drug sensitivity analysis unit is used to construct a half-inhibitory concentration curve according to the cell viability detection result to obtain the half-inhibitory concentration value of the mature organoid.

6. The system for constructing a prediction model for targeted therapy of advanced colorectal cancer according to claim 1, characterized in that: The factor evaluation module comprises: An information acquisition unit, wherein the information acquisition unit is used to acquire clinical pathological information data of colorectal cancer patients; A feature analysis unit, wherein the feature analysis unit is used to analyze the clinical pathological information data to screen risk factors that affect the progression-free survival of the colorectal cancer patient; A data processing unit is used to perform standardization processing on the clinical pathological information data of the risk factors to obtain clinical pathological characteristic information.

7. The system for constructing a prediction model for targeted therapy of advanced colorectal cancer according to claim 6, characterized in that: The data processing unit is used to perform standardization processing on the clinical pathological information data of the risk factors to obtain clinical pathological characteristic information, which satisfies the following relationship: ； in, The clinical pathological characteristics information, For clinical pathology information data, is the mean of clinical pathological information data, is the standard deviation of clinical pathological information data.

8. The system for constructing a prediction model for targeted therapy of advanced colorectal cancer according to claim 1, characterized in that: The model building module comprises: A factor screening unit, wherein the factor screening unit is used to obtain key factors for constructing a prediction model for targeted treatment of advanced colorectal cancer; A model building unit is used to build the targeted treatment prediction model for advanced colorectal cancer by combining the drug sensitivity analysis results and the key factors.

9. The system for constructing a prediction model for targeted therapy of advanced colorectal cancer according to claim 8, characterized in that: The model building unit is used to build the advanced colorectal cancer targeted therapy prediction model in combination with the drug sensitivity analysis results and the key factors, satisfying the following relationship: ； in, is the probability of progression-free survival, is the weight coefficient of drug sensitivity analysis results, The results of drug sensitivity analysis are as follows: is the weight coefficient of the degree of differentiation of mature organoid tumor cells, is the degree of differentiation of mature organoid tumor cells, is the weight coefficient of preoperative CEA concentration, is the preoperative CEA concentration, is the weight coefficient of clinical pathological characteristic information, Clinical pathological characteristics information.

10. The system for constructing a prediction model for targeted therapy of advanced colorectal cancer according to claim 1, characterized in that: The integrated control module comprises: A module retrieval unit, the module retrieval unit is used to retrieve the cell tissue acquisition module, the organoid cultivation module, the drug sensitivity test module, the factor evaluation module and the model construction module; A function realization unit is used to control the cell tissue acquisition module, the organoid cultivation module, the drug sensitivity test module, the factor evaluation module and the model construction module to realize module functions.

Images