CN118571500B - Colorectal cancer chemotherapy response prediction system and storage medium - Google Patents
Colorectal cancer chemotherapy response prediction system and storage medium Download PDFInfo
- Publication number
- CN118571500B CN118571500B CN202411035307.5A CN202411035307A CN118571500B CN 118571500 B CN118571500 B CN 118571500B CN 202411035307 A CN202411035307 A CN 202411035307A CN 118571500 B CN118571500 B CN 118571500B
- Authority
- CN
- China
- Prior art keywords
- model
- colorectal cancer
- chemotherapy
- relative
- treatment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000002512 chemotherapy Methods 0.000 title claims abstract description 112
- 206010009944 Colon cancer Diseases 0.000 title claims abstract description 100
- 208000001333 Colorectal Neoplasms Diseases 0.000 title claims abstract description 100
- 230000004044 response Effects 0.000 title claims abstract description 56
- 238000011282 treatment Methods 0.000 claims abstract description 128
- 238000004458 analytical method Methods 0.000 claims abstract description 113
- 206010028980 Neoplasm Diseases 0.000 claims abstract description 105
- 239000003814 drug Substances 0.000 claims abstract description 84
- 229940079593 drug Drugs 0.000 claims abstract description 69
- 230000035755 proliferation Effects 0.000 claims abstract description 42
- 238000006243 chemical reaction Methods 0.000 claims abstract description 31
- 230000005764 inhibitory process Effects 0.000 claims abstract description 25
- 238000004590 computer program Methods 0.000 claims abstract description 10
- 230000005929 chemotherapeutic response Effects 0.000 claims description 30
- 230000002401 inhibitory effect Effects 0.000 claims description 29
- GHASVSINZRGABV-UHFFFAOYSA-N Fluorouracil Chemical compound FC1=CNC(=O)NC1=O GHASVSINZRGABV-UHFFFAOYSA-N 0.000 claims description 26
- 229960002949 fluorouracil Drugs 0.000 claims description 26
- 238000012360 testing method Methods 0.000 claims description 20
- 206010059866 Drug resistance Diseases 0.000 claims description 15
- 238000011269 treatment regimen Methods 0.000 claims description 15
- 230000000973 chemotherapeutic effect Effects 0.000 claims description 11
- 229940044683 chemotherapy drug Drugs 0.000 claims description 11
- 239000002246 antineoplastic agent Substances 0.000 claims description 10
- 238000002474 experimental method Methods 0.000 claims description 9
- 231100000673 dose–response relationship Toxicity 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 2
- 230000001225 therapeutic effect Effects 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 35
- 238000000034 method Methods 0.000 description 25
- 210000001519 tissue Anatomy 0.000 description 16
- 210000004027 cell Anatomy 0.000 description 12
- 238000011160 research Methods 0.000 description 12
- 239000000243 solution Substances 0.000 description 12
- 239000007928 intraperitoneal injection Substances 0.000 description 11
- 230000008569 process Effects 0.000 description 11
- 230000035945 sensitivity Effects 0.000 description 11
- 230000008901 benefit Effects 0.000 description 10
- 230000012010 growth Effects 0.000 description 10
- DWAFYCQODLXJNR-BNTLRKBRSA-L oxaliplatin Chemical compound O1C(=O)C(=O)O[Pt]11N[C@@H]2CCCC[C@H]2N1 DWAFYCQODLXJNR-BNTLRKBRSA-L 0.000 description 9
- 229960001756 oxaliplatin Drugs 0.000 description 9
- 241000699670 Mus sp. Species 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 7
- 229960004768 irinotecan Drugs 0.000 description 7
- UWKQSNNFCGGAFS-XIFFEERXSA-N irinotecan Chemical compound C1=C2C(CC)=C3CN(C(C4=C([C@@](C(=O)OC4)(O)CC)C=4)=O)C=4C3=NC2=CC=C1OC(=O)N(CC1)CCC1N1CCCCC1 UWKQSNNFCGGAFS-XIFFEERXSA-N 0.000 description 7
- 239000002609 medium Substances 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 230000037396 body weight Effects 0.000 description 6
- 238000011156 evaluation Methods 0.000 description 6
- 238000001727 in vivo Methods 0.000 description 6
- 241000699660 Mus musculus Species 0.000 description 5
- 239000000306 component Substances 0.000 description 5
- 238000000338 in vitro Methods 0.000 description 5
- 238000011580 nude mouse model Methods 0.000 description 5
- 210000002220 organoid Anatomy 0.000 description 5
- 210000004881 tumor cell Anatomy 0.000 description 5
- 230000004614 tumor growth Effects 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000009104 chemotherapy regimen Methods 0.000 description 4
- 201000010099 disease Diseases 0.000 description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 4
- 230000002829 reductive effect Effects 0.000 description 4
- UCSJYZPVAKXKNQ-HZYVHMACSA-N streptomycin Chemical compound CN[C@H]1[C@H](O)[C@@H](O)[C@H](CO)O[C@H]1O[C@@H]1[C@](C=O)(O)[C@H](C)O[C@H]1O[C@@H]1[C@@H](NC(N)=N)[C@H](O)[C@@H](NC(N)=N)[C@H](O)[C@H]1O UCSJYZPVAKXKNQ-HZYVHMACSA-N 0.000 description 4
- 206010027476 Metastases Diseases 0.000 description 3
- 239000007864 aqueous solution Substances 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 201000011510 cancer Diseases 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 208000015181 infectious disease Diseases 0.000 description 3
- 108010082117 matrigel Proteins 0.000 description 3
- 230000009401 metastasis Effects 0.000 description 3
- 206010002091 Anaesthesia Diseases 0.000 description 2
- 239000006144 Dulbecco’s modified Eagle's medium Substances 0.000 description 2
- 241000204031 Mycoplasma Species 0.000 description 2
- 229930182555 Penicillin Natural products 0.000 description 2
- JGSARLDLIJGVTE-MBNYWOFBSA-N Penicillin G Chemical compound N([C@H]1[C@H]2SC([C@@H](N2C1=O)C(O)=O)(C)C)C(=O)CC1=CC=CC=C1 JGSARLDLIJGVTE-MBNYWOFBSA-N 0.000 description 2
- 239000012980 RPMI-1640 medium Substances 0.000 description 2
- FAPWRFPIFSIZLT-UHFFFAOYSA-M Sodium chloride Chemical compound [Na+].[Cl-] FAPWRFPIFSIZLT-UHFFFAOYSA-M 0.000 description 2
- 230000037005 anaesthesia Effects 0.000 description 2
- 230000004791 biological behavior Effects 0.000 description 2
- 230000010261 cell growth Effects 0.000 description 2
- 230000003833 cell viability Effects 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 2
- 229940127089 cytotoxic agent Drugs 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000029087 digestion Effects 0.000 description 2
- 238000009509 drug development Methods 0.000 description 2
- 210000003743 erythrocyte Anatomy 0.000 description 2
- 239000001963 growth medium Substances 0.000 description 2
- 238000013537 high throughput screening Methods 0.000 description 2
- 210000002865 immune cell Anatomy 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000010874 in vitro model Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000001575 pathological effect Effects 0.000 description 2
- 229940049954 penicillin Drugs 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000004321 preservation Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000012827 research and development Methods 0.000 description 2
- 238000010206 sensitivity analysis Methods 0.000 description 2
- 239000011780 sodium chloride Substances 0.000 description 2
- 229960005322 streptomycin Drugs 0.000 description 2
- 230000004083 survival effect Effects 0.000 description 2
- 230000004797 therapeutic response Effects 0.000 description 2
- 206010067484 Adverse reaction Diseases 0.000 description 1
- 201000004569 Blindness Diseases 0.000 description 1
- 108091003079 Bovine Serum Albumin Proteins 0.000 description 1
- 102000029816 Collagenase Human genes 0.000 description 1
- 108060005980 Collagenase Proteins 0.000 description 1
- 208000030453 Drug-Related Side Effects and Adverse reaction Diseases 0.000 description 1
- 102000004190 Enzymes Human genes 0.000 description 1
- 108090000790 Enzymes Proteins 0.000 description 1
- 108010037362 Extracellular Matrix Proteins Proteins 0.000 description 1
- 102000010834 Extracellular Matrix Proteins Human genes 0.000 description 1
- 239000012981 Hank's balanced salt solution Substances 0.000 description 1
- 241000282412 Homo Species 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 241000699666 Mus <mouse, genus> Species 0.000 description 1
- 206010061309 Neoplasm progression Diseases 0.000 description 1
- 206010066901 Treatment failure Diseases 0.000 description 1
- 206010052428 Wound Diseases 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 210000000683 abdominal cavity Anatomy 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000006838 adverse reaction Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000003444 anaesthetic effect Effects 0.000 description 1
- 230000006907 apoptotic process Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 210000002469 basement membrane Anatomy 0.000 description 1
- 230000003115 biocidal effect Effects 0.000 description 1
- 210000000601 blood cell Anatomy 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 238000004113 cell culture Methods 0.000 description 1
- 239000006285 cell suspension Substances 0.000 description 1
- 230000003749 cleanliness Effects 0.000 description 1
- 229940121657 clinical drug Drugs 0.000 description 1
- 229960002424 collagenase Drugs 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000000356 contaminant Substances 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000034994 death Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000002405 diagnostic procedure Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000001647 drug administration Methods 0.000 description 1
- 229940000406 drug candidate Drugs 0.000 description 1
- 239000000890 drug combination Substances 0.000 description 1
- 238000007876 drug discovery Methods 0.000 description 1
- 230000000857 drug effect Effects 0.000 description 1
- 238000007877 drug screening Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 229940088598 enzyme Drugs 0.000 description 1
- 210000002919 epithelial cell Anatomy 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 239000003777 experimental drug Substances 0.000 description 1
- 210000002744 extracellular matrix Anatomy 0.000 description 1
- 239000012091 fetal bovine serum Substances 0.000 description 1
- 210000002950 fibroblast Anatomy 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000001879 gelation Methods 0.000 description 1
- 239000003102 growth factor Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000002631 hypothermal effect Effects 0.000 description 1
- 210000000987 immune system Anatomy 0.000 description 1
- 238000009169 immunotherapy Methods 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 230000036512 infertility Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000012139 lysis buffer Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000003278 mimic effect Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 230000035764 nutrition Effects 0.000 description 1
- 235000016709 nutrition Nutrition 0.000 description 1
- 206010033675 panniculitis Diseases 0.000 description 1
- 239000008188 pellet Substances 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000000144 pharmacologic effect Effects 0.000 description 1
- 239000002504 physiological saline solution Substances 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000002980 postoperative effect Effects 0.000 description 1
- 238000004902 predicting drug resistance Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000011272 standard treatment Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000004659 sterilization and disinfection Methods 0.000 description 1
- 210000002536 stromal cell Anatomy 0.000 description 1
- 210000004304 subcutaneous tissue Anatomy 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000000725 suspension Substances 0.000 description 1
- 239000003356 suture material Substances 0.000 description 1
- YFDSDPIBEUFTMI-UHFFFAOYSA-N tribromoethanol Chemical compound OCC(Br)(Br)Br YFDSDPIBEUFTMI-UHFFFAOYSA-N 0.000 description 1
- 230000004565 tumor cell growth Effects 0.000 description 1
- 230000005748 tumor development Effects 0.000 description 1
- 230000005751 tumor progression Effects 0.000 description 1
- 230000002792 vascular Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
- 230000029663 wound healing Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
- G16H20/17—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients delivered via infusion or injection
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Data Mining & Analysis (AREA)
- Medicinal Chemistry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Chemical & Material Sciences (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention relates to the technical field of chemotherapy prediction, and discloses a colorectal cancer chemotherapy response prediction system, wherein a computer readable storage medium stores a computer program, the computer program comprises program instructions, and the program instructions when being executed by a processor cause the processor to execute the following steps: obtaining a colorectal cancer chemotherapy sample of a patient; establishing a first analysis model of a chemotherapy reaction and a second analysis model of the chemotherapy reaction; obtaining the relative proliferation rate of the tumor according to the colorectal cancer chemotherapy sample and the first analysis model of the chemotherapy reaction; obtaining a relative half maximum inhibition concentration value according to the colorectal cancer chemotherapy sample and the chemotherapy reaction second analysis model; and constructing a colorectal cancer chemotherapy response prediction model, and predicting the chemotherapy resistance probability of colorectal cancer patients based on the relative proliferation rate of tumors and the relative half maximum inhibition concentration value. The invention can accurately predict the response of colorectal cancer patients to different therapeutic schemes, help clinicians select the optimal medication scheme, and realize accurate treatment.
Description
Technical Field
The invention relates to the technical field of chemotherapy prediction, in particular to a colorectal cancer chemotherapy response prediction system and a storage medium.
Background
Colorectal cancer (CRC) is the third most common cancer type worldwide, with a number of treatment strategies, but in the face of the complexity, heterogeneity and potential risk of recurrent metastasis of tumor development, the patient's therapeutic response tends to exhibit significant individual differences, particularly when colorectal cancer progresses to stage IV, with common chemotherapeutic regimens such as 5-fluorouracil (5-FU) alone or in combination with Oxaliplatin (OX) and IRI Li Tikang. Although chemotherapy can effectively shrink tumors, related drugs are accompanied by problems such as drug resistance and side effects, so that patients with advanced colorectal cancer cannot bear the treatment burden.
Therefore, there is an urgent need to construct a model that can accurately screen the optimal drug regimen, which can reduce the cost of treatment, achieve inhibition of tumor progression, prolongation of patient survival and improvement of patient quality of life, and bring more personalized and effective treatment regimen for colorectal cancer patients.
Disclosure of Invention
In view of the shortcomings in the prior art, the present invention provides, in a first aspect, a computer-readable storage medium storing a computer program comprising program instructions that, when executed by a processor, cause the processor to perform the steps of: obtaining a colorectal cancer chemotherapy sample of a patient; establishing a first analysis model of a chemotherapy reaction and a second analysis model of the chemotherapy reaction; obtaining a tumor relative proliferation rate according to the colorectal cancer chemotherapy sample and the first analysis model of the chemotherapy reaction; obtaining a relative half maximum inhibitory concentration value from the colorectal cancer chemotherapeutic sample and the chemotherapeutic response second analytical model; and constructing a colorectal cancer chemotherapy response prediction model, wherein the colorectal cancer chemotherapy response prediction model predicts the chemotherapy resistance probability of colorectal cancer patients based on the relative proliferation rate of the tumor and the relative half maximum inhibition concentration value. According to the invention, a doctor can be helped to evaluate the treatment effect of different chemotherapy schemes rapidly through the prediction model, so that the optimal scheme is selected, the treatment efficiency is improved, a more personalized chemotherapy scheme is provided for a patient, and the problems of unnecessary side effects and drug resistance of the drug are avoided.
Optionally, the obtaining a colorectal cancer chemotherapy sample of the patient includes: treatment groups including a 5-FU treatment group, a 5-fu+ox treatment group, and a 5-fu+iri treatment group are set according to colorectal cancer chemotherapy samples of the patient. The control group provides a benchmark for evaluating the effects of different treatment groups, and the treatment effects of various chemotherapy schemes can be evaluated more accurately by comparing the tumor growth conditions of the treatment groups and the control group.
Optionally, the establishing the first analysis model of the chemotherapy response and the second analysis model of the chemotherapy response comprises: setting treatment test conditions of the first analysis model of the chemotherapy response according to different drug types, wherein the treatment test conditions comprise solution concentration, administration frequency, administration mode, administration metering and experimental time; the drug treatment regimen of the second analysis model of the chemotherapeutic response is set according to different drug categories, and comprises a chemotherapeutic drug concentration range and a treatment regimen time. The invention sets specific treatment test conditions aiming at different medicines, can ensure that the model more accurately simulates the action mechanism of the medicines in the actual treatment process, and is beneficial to more accurately predicting the chemotherapy response of patients.
Optionally, the obtaining the tumor relative proliferation rate according to the colorectal cancer chemotherapy sample and the first analysis model of the chemotherapy response comprises: performing treatment test analysis on the treatment group and the control group by using a first analysis model of chemotherapy reaction to obtain a first model analysis result; obtaining a relative tumor volume according to the first model analysis result; and obtaining the relative proliferation rate of the tumor according to the analysis result of the first model and the relative tumor volume. The invention can quantitatively evaluate the treatment effect through the relative proliferation rate of the tumor, is beneficial to doctors to know the treatment response of patients more accurately, and provides scientific basis for the subsequent treatment scheme adjustment.
Optionally, the relative tumor volumes satisfy the following relationship:
，
wherein, Represents the relative tumor volume of the sample,Representative ofThe volume of the tumor measured in time was determined,Represents the tumor volume measured at the beginning of the experiment;
the relative proliferation rate of the tumor meets the following relation:
，
wherein, Indicating the relative proliferation rate of the tumor,Represents the relative tumor volume of the treatment group,The relative tumor volumes of the control group are indicated. The related data index can intuitively reflect the volume change and proliferation rate of the tumor in the treatment process, so that the evaluation process of the treatment effect becomes simple, the treatment effect can be quantitatively evaluated, the interference of subjective judgment is avoided, and the accuracy of the evaluation result is improved.
Optionally, said obtaining a relative half maximum inhibitory concentration value from said colorectal cancer chemotherapeutic sample and said chemotherapeutic response second analysis model comprises: analyzing the treatment group and the control group according to the drug treatment scheme and the second analysis model of the chemotherapy response so as to obtain a second model analysis result; fitting a dose response curve according to the analysis result of the second model, and determining the half maximum inhibition concentration; the relative half maximal inhibitory concentration values of the treatment group and the control group in the different drug treatment regimens are analyzed based on the half maximal inhibitory concentration. The invention optimizes the treatment scheme by comparing the relative half maximum inhibition concentration values of different drug treatment schemes to select the chemotherapeutic drug combination and the concentration range with the best inhibition effect on tumor cells.
Optionally, the relative half maximum inhibitory concentration values satisfy the following relationship:
，
wherein, Represents the relative half maximum inhibitory concentration value,Coefficients representing different drug treatment regimens are presented,Representing the measured half maximal inhibitory concentration values. The invention calculates the Re values of different drug treatment schemes, can more intuitively compare the curative effect difference between different schemes, and is helpful for selecting the most suitable treatment scheme according to the specific condition of patients.
Optionally, the constructing the colorectal cancer chemotherapeutic response prediction model includes: and constructing a colorectal cancer chemotherapeutic response prediction model based on the chemotherapeutic response first analysis model and the chemotherapeutic response second analysis model. According to the invention, through two analysis models at different angles, the curative effect of the chemotherapeutic medicine and the therapeutic response of the patient can be more comprehensively evaluated, so that the prediction model becomes more accurate and reliable.
Optionally, the colorectal cancer chemotherapeutic response prediction model satisfies the following relationship:
，
wherein, The probability of drug resistance is indicated,/Represents the relative tumor proliferation rate and the relative tumor proliferation rate,Representing the relative half maximum inhibitory concentration values. The invention combines the information of tumor growth and drug inhibition, can more accurately predict the drug resistance probability of patients to chemotherapeutic drugs, has more predictive power than single index, and is helpful for doctors to more accurately judge the treatment response of patients.
In another aspect, the present invention also provides a colorectal cancer chemotherapeutic response prediction system, comprising an input device, a processor, an output device, and a memory, wherein the input device, the processor, the output device, and the memory are interconnected, the memory comprises a computer-readable storage medium according to the first aspect of the present invention, the memory is used for storing a computer program, the computer program comprises program instructions, and the processor is configured to invoke the program instructions.
Drawings
FIG. 1 is a flowchart of program instructions in a computer readable storage medium provided by the present invention;
FIG. 2 is a schematic diagram of specificity and sensitivity analysis of a colorectal cancer chemotherapeutic response prediction model of the present invention;
FIG. 3 is a schematic diagram of the structure of the colorectal cancer chemotherapeutic response prediction system of the present invention.
Detailed Description
Specific embodiments of the invention will be described in detail below, it being noted that the embodiments described herein are for illustration only and are not intended to limit the invention. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, it will be apparent to one of ordinary skill in the art that: no such specific details are necessary to practice the invention. In other instances, well-known circuits, software, or methods have not been described in detail in order not to obscure the invention.
Throughout the specification, references to "one embodiment," "an embodiment," "one example," or "an example" mean: a particular feature, structure, or characteristic described in connection with the embodiment or example is included within at least one embodiment of the invention. Thus, the appearances of the phrases "in one embodiment," "in an embodiment," "one example," or "an example" in various places throughout this specification are not necessarily all referring to the same embodiment or example. Furthermore, the particular features, structures, or characteristics may be combined in any suitable combination and/or sub-combination in one or more embodiments or examples. Moreover, those of ordinary skill in the art will appreciate that the illustrations provided herein are for illustrative purposes and that the illustrations are not necessarily drawn to scale.
Referring to fig. 1, in one embodiment, the present invention provides a computer readable storage medium storing a computer program comprising program instructions that, when executed by a processor, cause the processor to perform the steps of:
S1, obtaining colorectal cancer chemotherapy samples of patients, wherein the implementation steps and related contents are as follows:
Firstly, obtaining colorectal cancer chemotherapy samples of patients; then, a treatment group and a control group are set according to colorectal cancer chemotherapy samples of the patient, wherein the treatment group mainly comprises a 5-FU treatment group, a 5-FU+OX treatment group and a 5-FU+IRI treatment group, and the specific implementation contents are as follows:
First, a patient's colorectal cancer chemotherapy sample is obtained.
In an alternative embodiment, a surgical specimen of a colorectal cancer patient is obtained under strictly sterile operating conditions as a colorectal cancer chemotherapeutic sample of an embodiment. To ensure the integrity and bioactivity of colorectal cancer chemotherapeutic samples, they were immediately placed in RPMI 1640 medium supplemented with 5% penicillin/streptomycin and kept well in a low temperature environment at 4 ℃. The colorectal cancer chemotherapeutic samples are then rapidly and safely transported to a laboratory for subsequent scientific research and experimental analysis.
The method for obtaining colorectal cancer chemotherapy samples in the embodiment has the advantages of strict aseptic operability, professional sample preservation conditions, timely transportation and the like, so that the colorectal cancer chemotherapy samples are guaranteed to be representative and feasible.
S2, establishing a first analysis model of a chemotherapy reaction and a second analysis model of the chemotherapy reaction, wherein the implementation steps and the related contents are as follows:
Based on the existing medical study information, a first analysis model of the chemotherapy response, i.e. a patient-derived xenograft model (PDX model), and a second analysis model of the chemotherapy response, i.e. a patient-derived organoid culture model (PDO model), were established.
In the invention, a patient derived xenograft model (PDX model) of the same patient source sample and a patient derived organoid culture model (PDO model) are established, the analysis accuracy of the chemotherapy reaction of the patient with the colorectal cancer in the IV phase can be improved by jointly using the model, the PDX model is taken as an in-vivo model and the PDO model is taken as an in-vitro model, and when the model is independently used, the analysis result difference exists.
In an alternative embodiment, the patient-derived xenograft model (PDX model) has a unique in vivo environment as compared to the cell line model. The PDX model not only comprises a plurality of cell types such as stroma cells, epithelial cells, fibroblasts, immune cells, blood vessels and the like, but also retains the heterogeneity of more human tumors, and is more similar to a real tumor state from morphology, tissue to genetics. Therefore, the PDX model shows better accuracy in analyzing the curative effect of clinical medicines.
In another alternative embodiment, a patient-derived organoid culture model (PDO model) exhibits significant advantages in vitro studies. The method can truly restore physiological and pathological characteristics of parent tissues, and is beneficial to research on the growth, metastasis and other processes of tumors. The PDO model has the ability to freeze, amplify and stabilize passages in vitro, providing the possibility for high throughput screening, enabling researchers to rapidly assess the effects of a large number of candidate drugs or therapeutic approaches. In addition, compared with a PDX model, the PDO model is simpler in an operation level, and experimental complexity and operation difficulty are reduced.
In another alternative embodiment, the advantages and disadvantages of the first analysis model of the chemotherapeutic response and the second analysis model of the chemotherapeutic response are taken into account in combination, so that the advantages of the analysis models are complementary to form a set of analysis models of the combined chemotherapeutic response.
While the PDX model has many advantages, its limitations are not negligible. Since the PDX model is usually implanted in an immunodeficient mouse, the effect of potential immunotherapy in the PDX model cannot be accurately estimated, the success rate of transplanting the PDX model is relatively low, and the cultivation period is as long as several months, so that the time and cost of research are increased, and the establishment and maintenance process of the PDX model is relatively complex from the technical aspect, so that the application of the PDX model in extensive research is limited to a certain extent. Therefore, when the PDX model is used for predicting and analyzing the curative effect of the medicine, the advantages and limitations of the PDX model need to be comprehensively considered, and the accuracy and the reliability of analysis results are ensured by combining other technical analysis methods and models.
On the other hand, since the PDO model is cultured in an in vitro environment, there is a lack of support for complex in vivo environments, particularly the vascular network and the immune system, meaning that the PDO model may not completely mimic the biological behavior of a tumor in humans. In addition, PDO models require specific culture environments, including growth factors and extracellular matrix components, to maintain their growth and differentiation, and the associated special culture conditions add to the cost and complexity of the experiment. If the PDO model is overgrown, aging or apoptosis may be caused by consumption and deficiency of nutrients, thereby affecting the accuracy and reliability of experimental analysis results. Therefore, in conducting research using PDO models, it is necessary to fully understand their advantages and limitations and to fully evaluate the experimental results in combination with other experimental methods and models.
In the present invention, a patient-derived xenograft model (PDX model) and a patient-derived organoid culture model (PDO model) of the same patient-derived sample are created, and a set of combinatorial chemoresponse analysis models is formed in combination.
The PDX model (patient-derived xenograft model) and the PDO model (patient-derived organoid culture model) represent two important methods in vivo and in vitro, respectively, in tumor studies, each of which has unique advantages and limitations, and combining the two models can produce significant complementary effects, forming a set of joint chemoresponse analysis models.
The combined chemotherapy reaction analysis model can more accurately simulate the biological behaviors of tumors in human bodies, so that the clinical reactions of patients can be more accurately analyzed, and related researchers can more comprehensively evaluate the curative effect and the safety of medicines by integrating the in-vivo complex environment of the PDX model and the high-throughput screening capability of the PDO model, thereby providing more scientific and reasonable guidance for clinical medication.
Specifically, the PDX model can retain heterogeneity of human tumors, including complex components such as stromal cells, immune cells and the like, so that the growth and metastasis processes of the tumors in the human body can be simulated to a certain extent; the PDO model can rapidly and stably amplify tumor cells in an in-vitro environment, simulate physiological and pathological characteristics of tumor tissues and is convenient for high-throughput drug screening and drug effect evaluation.
The advantages of the two models are combined, and the combined chemotherapy reaction analysis model can evaluate the effect of the medicine in tumor treatment more comprehensively, so that blindness and risk of clinical medicine are reduced. Meanwhile, the combined chemotherapy reaction analysis model can provide powerful support for personalized treatment, and helps doctors to formulate more accurate and effective treatment schemes for patients. Therefore, the combination of the PDX model and the PDO model is a potential tumor research method, can provide more scientific and reasonable guidance for clinical medication, and plays an important role in future tumor treatment.
In the embodiment, the two chemoreaction analysis models of the PDX model and the PDO model are matched for use, so that the data of the in-vivo model and the in-vitro model can be synthesized, more comprehensive and accurate chemoreaction prediction can be facilitated, the limitation of a single model on prediction capability is overcome, and the application value of the biological library in the aspects of accurate treatment and drug discovery is greatly enhanced.
Furthermore, it is necessary to set the treatment test conditions of the first analysis model of chemotherapy response according to different drug types, wherein the treatment test conditions mainly include solution concentration, administration frequency, administration mode, administration dosage and experimental time, and the specific implementation contents are as follows:
Treatment test conditions of the first analysis model of the chemotherapeutic response are designed and strategically optimized according to the experimental objectives and the drug characteristics. Firstly, intraperitoneal Injection (IP) is selected as an administration route, so that the medicine can be effectively delivered into the abdominal cavity and acts on tumor tissues; the dosing volume was determined to be 10ml of solution per kg of body weight to ensure proper distribution and concentration of the drug in the animal.
Then, a treatment group and a control group are set according to colorectal cancer chemotherapy samples of the patient, wherein the treatment group mainly comprises a 5-FU treatment group, a 5-FU+OX treatment group and a 5-FU+IRI treatment group.
In order to clearly compare the differences of the effects of different treatment schemes in colorectal cancer treatment, and help doctors evaluate the treatment effects of different drugs or drug combinations, treatment groups and control groups are now set according to colorectal cancer chemotherapy samples of patients.
1. Control group settings.
The control group will receive saline as a solution and will be administered by intraperitoneal Injection (IP), twice a week, with the amount of saline injected each time being sufficient to match the amount of drug solution in the treatment group to ensure that the control group will also undergo a similar course of treatment.
2. The experimental set-up, which mainly included the 5-FU treatment group, the 5-fu+ox treatment group, and the 5-fu+iri treatment group.
Wherein the 5-FU treatment group: the medicament is administered with an aqueous solution of 5-fluorouracil (5-FU); the dosage is 50 mg/kg body weight; the administration mode is intraperitoneal Injection (IP); the frequency was once per week.
5-Fu+ox treatment group: the medicament is administered with an aqueous Oxaliplatin (OX) solution and an aqueous 5-fluorouracil (5-FU) solution; the dosage is 10 mg of OX per kilogram of body weight, and 50 mg of 5-FU per kilogram of body weight; the modes of administration were all intraperitoneal Injections (IP), with the frequency of administration of both drugs once a week, but not on the same day.
5-Fu+iri treatment group: the medicament is administered with an aqueous solution of irinotecan (IRI) and an aqueous solution of 5-fluorouracil (5-FU); the dosage is 15 mg of IRI per kilogram of body weight, and 50 mg of 5-FU per kilogram of body weight; the administration modes are intraperitoneal Injection (IP); the frequency was that the two drugs were administered once a week and also not on the same day.
Wherein the period of administration and other precautions.
The dosing cycle was three consecutive weeks for all treatment groups and control groups. During this time, the administration and dosage of the components are strictly followed. During the administration, all operations should be ensured to be carried out under aseptic conditions to avoid any possible infection, the samples should be weighed before administration to ensure the accuracy of the drug dosage, and the physical sign information and the reaction condition of each group should be closely monitored after administration so as to take measures in time, and when the drugs are used in combination, the drugs are not administered on the same day to avoid interactions or side effects between the drugs.
Furthermore, in this embodiment, the method of obtaining the colorectal cancer chemotherapy sample and the treatment group is only an optional condition of this embodiment, the treatment sample and the setting method of the components may be adjusted according to the test requirement and the sample obtaining standard, different researches have different targets, attention parameters or resource limitations, and the sample obtaining and the setting method of the components are adjusted according to the test requirement, so that the adaptability and pertinence of the research sample may be ensured, and positive effects are brought to the research and development in the colorectal cancer treatment field.
More importantly, the pharmacological properties and treatment requirements of different medicaments are fully considered in the embodiment, and specific concentration and administration frequency are set for each medicament. The treatment test conditions can ensure that the medicine can exert the optimal curative effect in the PDX model, reduce unnecessary side effects, more accurately simulate the clinical medication condition by setting the treatment test conditions, and provide more reliable data support for the research of tumor treatment.
Meanwhile, the drug treatment scheme of the second analysis model of the chemotherapy response is set according to different drug types, wherein the drug treatment scheme mainly comprises a concentration range of the chemotherapy drug and treatment scheme time, and the specific implementation contents are as follows:
Different drug treatment regimens were set in the second analytical model of the chemotherapeutic response, first, the chemotherapeutic drug concentration range was set to 6.25 μmol/L to 200 μmol/L to evaluate the inhibitory effect of the drug on tumor cell growth. The concentration ratio of the two chemotherapeutics was maintained at 1:1 for the combination regimen, and the chemotherapeutics concentration range was likewise set at 6.25. Mu. Mol/L to 200. Mu. Mol/L. A blank control group was also established using physiological saline for a dosing time of 96 hours (cell viability was measured after 96 hours, calculated from drug addition).
To quantify drug sensitivity, the second analytical model of chemotherapy response will focus primarily on the half maximal inhibitory concentration (IC 50) index, which represents the concentration of chemotherapeutic drug that is capable of inhibiting 50% of cell growth. Cell viability was measured at different concentrations 96 hours after drug exposure to tumor cells, helping to guide clinical drug administration and drug development efforts.
Furthermore, in the method for establishing a chemoreaction analysis model in this embodiment, only one optional condition of this embodiment is that the method for establishing a chemoreaction analysis model may be changed according to the prediction target of colorectal cancer and the cancer test condition, and the establishment of the chemoreaction analysis model is a flexible and changeable process, and needs to be adjusted and optimized according to the prediction target of colorectal cancer, the actual condition of the cancer test and the specific experimental condition, so that the accuracy of the analysis result of the model may be improved by continuous improvement and perfection, and more scientific and effective guidance is provided for the chemo-treatment of colorectal cancer.
S3, obtaining the relative proliferation rate of the tumor according to the colorectal cancer chemotherapy sample and the first analysis model of the chemotherapy reaction, wherein the specific implementation steps and the related contents are as follows:
Firstly, performing treatment test analysis on a treatment group and a control group by using a first analysis model of chemotherapy reaction to obtain a first model analysis result; and obtaining a relative tumor volume according to the analysis result of the first model, wherein the specific implementation content is as follows:
obtaining a first model analysis result based on the first analysis model of the chemotherapy response, the detailed analysis steps of the patient-derived xenograft model (PDX model) in the examples are as follows;
first step action preparation: SPF-class female nude mice are selected, the weight of the nude mice is ensured to be within 15-25 g, the age of the nude mice is 4-5 weeks, and health examination is required to be carried out on the nude mice, so that no disease signs are ensured, and the nude mice are suitable for experiments.
Second step tumor tissue sample treatment: with the colorectal cancer chemotherapy sample of the patient in step S1, the tumor tissue sample was rinsed three times with a cold solution containing fetal bovine serum, penicillin/streptomycin and RPMI 1640 medium to remove excess blood cells and contaminants.
Thirdly, carrying out anesthesia and operation preparation on the mice: 1.25% 2, 2-tribromoethanol solution was prepared, and the mice were anesthetized by intraperitoneal injection at a dose of 0.2ml/10g, while monitoring the anesthetized state of the mice, ensuring a moderate anesthetic depth and a duration of 10 to 40 minutes, and further preparing surgical instruments and suturing materials were required to ensure sterility.
Fourth step, tumor tissue is transplanted subcutaneously: skin disinfection was performed under the back of the mice, a small incision was cut, the treated tumor tissue sample was cut into 2mm x 2mm x1 mm pieces using a sterile instrument, the tumor tissue pieces were carefully transplanted into subcutaneous tissue in the surgical area of the mice, and the incision was carefully sutured using a sterile suturing material, ensuring wound closure and insusceptibility to infection.
Fifth step postoperative care and observation: in the anesthesia and awakening process, the temperature of the mice is kept by using heat preservation equipment, death caused by hypothermia is prevented, the mice are closely observed after operation, good wound healing is ensured, no infection signs exist, the transplanted tumors are observed and measured regularly, and the growth condition and change of the tumors are recorded.
Sixth step, experiment and data analysis: according to the experimental requirement, the transplanted tumor is subjected to subsequent treatment or sampling to perform researches of molecular biology, cytology and the like, meanwhile experimental data are collected to perform statistical analysis and interpretation so as to obtain a second model analysis result, and on the other hand, the construction effect and tumor characteristics of a patient-derived xenograft model (PDX model) can be estimated based on the analysis result.
Then, a relative tumor volume is obtained according to the analysis result of the first model.
Because the PDX model is derived from the actual tumor tissue of the patient, the first model analysis result can reflect the response condition of the patient individual to the medicine, thereby being beneficial to realizing personalized medicine and providing a more accurate treatment scheme for the patient.
In the examples, the relative tumor volume is calculated by comparing the tumor volume at each time point with the initial volume, and the relative tumor volume satisfies the following relationship:
，
wherein, Represents the relative tumor volume of the sample,Representative ofThe volume of the tumor measured in time was determined,Represents the tumor volume measured at the beginning of the experiment;
In this example, the relative tumor volume at each time point was recorded and plotted as a graph, such as a line graph, to visually show the trend of tumor growth, by comparing the different treatment groups, the example included mainly the control group, 、AndThe inhibition or promotion of growth of the sample by the drug can be assessed based on the relative tumor volume for different treatment groups corresponding to different drug concentrations, different time points.
According to the analysis result of the first model and the relative tumor volume, the relative proliferation rate of the tumor is obtained, and the specific implementation content is as follows:
the relative proliferation rate of the tumor provides a quantitative index for the inhibition of the tumor growth by the drug. By comparing the relative proliferation rates at different time points or different drug treatment groups, doctors and researchers can intuitively evaluate the difference of the treatment effects of patients, thereby more accurately judging the curative effects of the drugs.
The relative proliferation rate of the tumor satisfies the following relationship:
，
wherein, Indicating the relative proliferation rate of the tumor,Represents the relative tumor volume of the treatment group,The relative tumor volumes of the control group are indicated.
Based on the control group and the treatment group. Wherein the control group received no treatment or standard treatment, the treatment group received experimental drug treatment, and the relative tumor volume and relative proliferation rate of the control group and the treatment group at each time point were calculated by the above formula, respectively.
Wherein, the higher the value of the tumor relative proliferation rate, the higher the tumor proliferation rate of the treatment group relative to the control group, namely the treatment effect is poorer, and the national evaluation reference standard is known based on the prior research result40% Of the total number of the samples were not valid,Is effective at less than or equal to 40 percent.
Furthermore, in the method for calculating the tumor relative proliferation rate in this embodiment, only one optional condition in this embodiment is used, the method for calculating the tumor relative proliferation rate may be replaced according to the model analysis data condition and the disease analysis requirement, and the calculation method may be adjusted according to the specific model analysis data, so that the growth condition of the tumor and the inhibition effect of the drug on tumor proliferation may be reflected more accurately, which is helpful for obtaining the analysis result more in line with the actual situation.
S4, obtaining a relative half maximum inhibition concentration value according to the colorectal cancer chemotherapy sample and a chemotherapy reaction second analysis model, wherein the specific implementation steps and related contents are as follows:
analyzing the treatment group and the control group according to the drug treatment scheme and the second analysis model of the chemotherapy response so as to obtain a second model analysis result; and fitting a dose response curve according to the analysis result of the second model, and determining the half maximum inhibition concentration, wherein the implementation content is as follows:
treatment trial analysis was performed on the treatment group and the control group using a chemo-response second analysis model, i.e., a patient-derived organotypic culture model (PDO model), to obtain a second model analysis result.
First, a colorectal cancer chemotherapy sample of a patient is prepared: the samples were thoroughly washed 8 to 10 times with Hank's balanced salt solution containing 5% antibiotic to ensure cleanliness of the samples; subsequently, the tissue sample is cut into small pieces of about 1x1x 1mm in size using scissors to facilitate the subsequent digestion process; then, the cut tissue block is placed in a DMEM/F12 solution containing 5mg/mL type II collagenase to ensure that the tissue block is fully soaked, the solution is placed on a shaking table at 37 ℃ to enable the tissue block to be digested for about 3 hours under the action of the enzyme so as to decompose the tissue and release cells; after digestion is completed, undigested tissue pieces and impurities are removed by filtration, and the resulting cell suspension is centrifuged at 1200×g for 2 minutes to pellet cells; immediately afterwards, erythrocyte lysis buffer was added and incubated for 5 minutes to remove erythrocytes, ensuring the purity of the cells; after washing and counting, tumor cells were resuspended in a mixture of Matrigel basement membrane matrix and higher DMEM/F12 medium, and the Matrigel suspension containing cells was dropped into a cell incubator at a titer of 30. Mu.L at 37℃and 5%The Matrigel is fully gelled to form a matrix supporting cell growth, the subsequent cultivation and monitoring are carried out, a proper amount of culture medium is added into each plate after the gelation to provide nutrition required by growth for cells, the cells are placed into a cell incubator with 37 ℃ and 5% CO2 for cultivation, a constant growth environment is ensured, the culture medium is replaced every 2 to 3 days to keep the activity of the cells, mycoplasma pollution is checked periodically, rapid detection is carried out by using a MycoAlert mycoplasma detection kit, and the purity of the cell cultivation environment is ensured. The second model analysis result obtained through the steps can provide a powerful tool for subsequent drug susceptibility testing and other researches.
Then, a dose response curve is fitted according to the analysis result of the second model, and the half maximum inhibition concentration is determined, and the implementation is as follows:
in this embodiment, the second model analysis results are sorted and analyzed, including but not limited to calculating statistics such as average value, standard deviation, etc., and appropriate conversion or normalization processing may be performed on the data to obtain better quality second model analysis results.
In an alternative embodiment, to accurately analyze the relationship between drug dose and response, a specialized software tool such as GRAPHPAD PRISM may be used to fit the dose response curve. Based on the detailed analysis results of the second model, and in combination with the specific characteristics of the experimental data, a suitable curve model is selected, e.g. an S-curve for describing a non-linear relationship between drug concentration and effect, a straight line is suitable for describing a linear relationship or a parabolic line for describing a more complex relationship, etc. Inputting the analysis result of the second model and the collected experimental data into GRAPHPAD PRISM software for accurate curve fitting operation, and adjusting curve parameters according to the preliminary result generated by the software in the fitting process to ensure that the fitted curve can reflect the real trend and characteristics of the experimental data to the maximum extent.
Furthermore, the fitting curve and experimental data reach the optimal matching degree through repeated iteration and parameter adjustment, so that an accurate and reliable dose response relation analysis result is provided for the follow-up, the deep understanding of the action mechanism of the medicine is facilitated, and powerful data support is provided for the follow-up medicine research and development and clinical application.
In another alternative embodiment, to evaluate the effectiveness of the drug and determine the optimal dose, the corresponding drug concentration at which the inhibitory effect reaches 50% is found on the fitted dose response curve, the above-mentioned key concentration point is commonly referred to as the half maximal inhibitory concentration (IC 50). The IC50 value can be automatically calculated by special software or tools such as GRAPHPAD PRISM when the step is implemented, so that the calculation efficiency and accuracy are greatly improved. In yet another aspect, the determination of the IC50 value may be affected by a variety of factors including, but not limited to, experimental conditions, data processing methods, sample quality, and the like. Therefore, in the whole process, it is important to ensure accuracy and reliability, experimental conditions should be strictly controlled in the examples, standard data processing methods should be adopted, and samples should be strictly screened and quality controlled.
In addition, the IC50 value needs to be verified and evaluated in combination with the actual situation. The calculated IC50 value can be compared with a standard value, or the validity and the accuracy of the IC50 value can be verified through further experiments, so that the accuracy and the reliability of the IC50 value are ensured, and powerful support is provided for subsequent drug development and clinical treatment.
The relative half maximal inhibitory concentration values of the treatment and control groups in the different drug treatment regimens were then analyzed based on the half maximal inhibitory concentration (IC 50) described above and were specifically implemented as follows:
and substituting the IC50 values measured by different drug schemes in the second analysis model of the chemotherapy reaction into formulas respectively for calculation to obtain a relative IC50 value.
In the embodiment, the relative half maximum inhibitory concentration values satisfy the following relationship:
wherein, Represents the relative half maximum inhibitory concentration value,Coefficients representing different drug treatment regimens are presented,Representing the measured half maximal inhibitory concentration values.
In the examples, the coefficient of the 5-FU treatment group is 0.4490, which represents the calculated formula for Re when the patient is using the 5-FU regimen:
the coefficients of the 5-FU+OX treatment group were 0.9276. The corresponding Re calculation formula for the patient using the 5-FU and OX protocol is:
the coefficients of the 5-FU+IRI treatment group were 1.5899. When the patient uses the 5-FU and IRI scheme, the corresponding Re calculation formula is as follows:
S5, constructing a colorectal cancer chemotherapy response prediction model, wherein the colorectal cancer chemotherapy response prediction model predicts the chemotherapy drug resistance probability of colorectal cancer patients based on the relative proliferation rate and the relative half maximum inhibition concentration value of tumors, and the specific implementation steps and the related contents are as follows:
Firstly, a colorectal cancer chemotherapy response prediction model is constructed based on the first chemotherapy response analysis model and the second chemotherapy response analysis model, and the implementation contents are as follows:
The relative tumor proliferation rate of the first analysis model of the chemotherapy reaction and the relative half maximum inhibition concentration value of the second analysis model of the chemotherapy reaction are used as key parameters of a colorectal cancer chemotherapy reaction prediction model.
The relative tumor proliferation rate reflects the change of the growth rate of the tumor during chemotherapy, and is an important index for evaluating the effect of the chemotherapeutic drugs on the growth control of the tumor. Higher relative tumor proliferation rates indicate that the tumor is insensitive to the chemotherapeutic agent, while lower relative tumor proliferation rates indicate that the chemotherapeutic agent has a significant inhibitory effect on tumor growth.
The relative half maximum inhibition concentration value measures the inhibition capacity of the chemotherapeutic drug on tumor cells and is a key parameter for evaluating the effectiveness of the drug. The lower relative half maximum inhibitory concentration values indicate that the drug is able to achieve significant inhibitory effects at lower concentrations, potentially increasing the efficacy of chemotherapy and reducing the risk of adverse effects.
The colorectal cancer chemotherapy response prediction model comprehensively considers two key parameters of relative tumor increment rate and relative half maximum inhibition concentration value, so that the prediction of colorectal cancer patient chemotherapy response is realized, the model converts the parameters into specific prediction results through an algorithm, decision support is provided for a clinician, and the patient is helped to formulate a personalized treatment scheme.
The colorectal cancer chemotherapy response prediction model meets the following relation:
，
wherein, The probability of drug resistance is indicated,/Represents the relative tumor proliferation rate and the relative tumor proliferation rate,Representing the relative half maximum inhibitory concentration values.
Then, the colorectal cancer chemotherapy response prediction model predicts the chemotherapy drug resistance probability of colorectal cancer patients based on the relative proliferation rate of tumors and the relative half maximum inhibition concentration value, and the specific steps are as follows:
Outputting a result according to a combined chemotherapy reaction analysis model formed by the PDX model and the PDO model, and obtaining a drug resistance probability prediction result by utilizing a colorectal cancer chemotherapy reaction prediction model. In the embodiment, after the colorectal cancer chemotherapy response prediction model comprehensively analyzes the relative proliferation rate and the relative half maximum inhibition concentration value of the tumor, a quantized drug resistance probability prediction result is generated, and the result is presented in the form of a numerical value or a percentage and reflects the risk degree of the patient possibly generating drug resistance after receiving a specific chemotherapy regimen.
In an embodiment, the drug resistance probability prediction results provide an important decision support tool for the clinician. By comprehensively considering individual differences, disease severity, tumor biological characteristics and output results of the prediction model of the patient, a treatment scheme can be formulated more scientifically and accurately, the treatment effect is improved, the occurrence rate of adverse reactions is reduced, and better survival benefit is brought to the patient.
If the prediction shows a higher probability of drug resistance, indicating that the patient may be insensitive to the chemotherapy regimen, there is a higher risk of treatment failure, and the physician may choose other potentially more effective drugs or treatment strategies based on the prediction, taking into account the adjustment of the chemotherapy regimen. Conversely, if the prediction shows a lower probability of drug resistance, it indicates that the patient may be more responsive to the chemotherapy regimen, and that the likelihood of success of the treatment is greater, facilitating the successful performance of the disease treatment plan.
In another aspect, the outcome of the drug resistance probability prediction is not constant and dynamically changes as the patient's condition changes and the treatment regimen adjusts. Therefore, the patient's condition change and treatment response need to be continuously monitored in the treatment process, and the parameters and output results of the prediction model need to be adjusted according to the needs, which is helpful to ensure the pertinence and effectiveness of the treatment scheme and improve the overall treatment effect of the patient.
Furthermore, the prediction result of the colorectal cancer chemo-treatment reaction prediction model is verified and analyzed to ensure the accuracy of the prediction result, and the specific implementation content is as follows;
in this example, the prediction results of the colorectal cancer chemotherapeutic response prediction model were collected and collated, and the clinical analysis information of the prediction results was shown in table 1.
TABLE 1 prediction results analysis form of colorectal cancer chemotherapeutic response prediction model
Wherein N represents the total number of experimental samples participating in the experiment, and based on the table information, the model is excellent in identifying the actual responsive cases, and the accuracy rate reaches 86.67%. Of the 18 predicted cases, 13 were actually responsive, indicating high accuracy of the model in identifying sensitive cases.
The model also shows extremely high accuracy in predicting drug resistance. Of the 54 unresponsive cases, 52 of them are correctly predicted by the model, the accuracy is up to 91.23%, and the reliability of the model in the aspect of identifying drug-resistant cases is further proved.
The colorectal cancer chemoresponse prediction model provided by the invention has excellent performance on the aspect of predicting chemoresponse, whether in sensitive or drug-resistant cases, so that the model becomes a powerful tool for predicting colorectal cancer chemoresponse.
The colorectal cancer chemotherapy response prediction model not only has high prediction accuracy, but also has great value in practical application, and a doctor can more accurately formulate a treatment scheme by predicting the chemotherapy response of a patient in advance, so that the treatment effect is improved, unnecessary side effects of medicines are reduced, and better treatment experience and life quality are brought to the patient. The colorectal cancer chemoresponse prediction model provided by the invention realizes high-precision prediction of chemoresponse through advanced algorithm and data analysis technology, not only improves the treatment level of colorectal cancer, but also provides a new thought and method for chemoresponse prediction of other cancers.
In another alternative embodiment, several sentences of analysis results are validated for the specificity, sensitivity and proportion classification of the model for predicting colorectal cancer chemotherapeutic response.
The specificity of the colorectal cancer chemotherapy response prediction model refers to the proportion of the model correctly predicted to be non-response in all actual non-response cases, the specificity can measure the recognition capability of the model to the actual non-response cases, and the specificity needs to meet the following calculation relation: specificity= (actual case negative number/actual total negative number) ×100%.
The sensitivity of the colorectal cancer chemotherapy response prediction model refers to the proportion of the model which is correctly predicted to be responsive in all actual responsive cases, and the recognition capability of the model to the responsive cases can be measured through the sensitivity. The sensitivity is the proportion of actual response, which is correctly predicted by the model, and the calculation formula is as follows: sensitivity= (true case positive number/actual total positive number) ×100%.
The sensitivity of the colorectal cancer chemoresponse prediction model reflects the accuracy and reliability of the model in identifying truly responsive cases, and the higher sensitivity indicates that the model can accurately identify responsive cases, so that timely treatment suggestions are provided for patients.
In the examples, the specificity and sensitivity analysis of the colorectal cancer chemotherapeutic response prediction model is shown in fig. 2, in which auc=0.9475, p <0.0001.
The ROC curve (Receiver Operator Characteristic Curve) is also called a subject work characteristic curve, and in fig. 2, the sensitivity (true positive rate) is plotted on the ordinate, and the 1-specificity (false positive rate) is plotted on the abscissa, and the points are combined into a curve, namely the ROC curve. In diagnostic tests, the correct choice of normal critical point (Cutoff) is mainly used.
AUC (Area Under Curve) is the area enclosed by the ROC curve and the coordinate axis, and the value range is between 0.5 and 1. The closer the AUC is to 1.0, the higher the detection method authenticity; when the value is equal to 0.5, the authenticity is the lowest, and the application value is not provided.
P refers to a probabilistic indicator that p in statistics can use to determine if the hypothesis test result is statistically significant. For ROC curves, the p-value is used to determine whether the classifier has significant classification capability, the smaller the p-value, the better the classifier's performance. In this embodiment, the p value is smaller than the preset significance level, which indicates that the prediction result has statistical significance, and indicates that the performance evaluation result of the colorectal cancer chemotherapy response prediction model has extremely high statistical significance, and has certain feasibility and accuracy.
Cut-off point (cut-off point) can be used to determine the critical points of normal and abnormal, negative and positive. When determining the optimal cut-off value, the optimal cut-off point of the ROC curve can be used, wherein the point closest to the upper left corner in the ROC curve is the optimal cut-off point, the sensitivity and the specificity are high, and the false positives and the false negatives are the least. Or using the Youden index maximization method, i.e. maximization (sensitivity + specificity-1) to determine the optimal cut-off value.
In this embodiment, the PDX model and the PDO model have complementarity in colorectal cancer chemotherapy response prediction, where the PDO model can rapidly screen potentially effective drugs, and the PDX model can further perform preclinical verification on the drugs to predict their efficacy and side effects in the human body, and based on the above models, a more comprehensive and accurate colorectal cancer chemotherapy response prediction model is constructed.
Further, as shown in fig. 3, in an alternative embodiment, the colorectal cancer chemotherapeutic response prediction system further comprises an input device, an output device, and a processor, wherein the input device, the processor, the memory, and the output device are interconnected to enable information exchange and data processing.
In this embodiment, the input device is used to provide input related data or instructions to the present system. In the colorectal cancer chemotherapy response prediction system, the input device may include a keyboard, a mouse, a touch screen, and other common man-machine interaction interface devices. Through the input device, the doctor or researcher can input necessary parameters.
The processor is a core component of the system and is responsible for executing computer program instructions for data processing and analysis. In the colorectal cancer chemotherapy response prediction system, a processor analyzes and interprets input test data by running a preprogrammed algorithm and model, calculates a relative proliferation rate and a relative half maximum inhibition concentration value of a tumor, and predicts a chemotherapy resistance probability according to a prediction model. The processor may be a Central Processing Unit (CPU), a Graphics Processor (GPU), or other specialized processing unit.
The memory is used for storing computer programs, data and parameters required by the system. It may include Random Access Memory (RAM) for temporary data storage and processing, and persistent storage (e.g., hard disk or solid state disk) for long-term storage and retention of data. In the prognostic evaluation system, the memory may store relevant predictive models, predictive analysis values, relevant data for colorectal cancer chemotherapeutic samples, and the like.
The output device is used for presenting the results of system processing and analysis to a user or an external device. In the prognostic evaluation system, the output device may be a display, a printer, a chart drawing device, or the like. Through the output device, the system can display the prediction analysis result, and can be used for doctors, researchers or patients to refer to the prediction analysis result so as to assist decision making and communication.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention, and are intended to be included within the scope of the appended claims and description.
Claims (6)
1. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program comprising program instructions that, when executed by a processor, cause the processor to perform the steps of:
obtaining a colorectal cancer chemotherapy sample of a patient;
Establishing a first analysis model of a chemotherapy reaction and a second analysis model of the chemotherapy reaction;
obtaining a tumor relative proliferation rate according to the colorectal cancer chemotherapy sample and the first analysis model of the chemotherapy reaction;
Obtaining a relative half maximum inhibitory concentration value from the colorectal cancer chemotherapeutic sample and the chemotherapeutic response second analytical model;
Constructing a colorectal cancer chemotherapy response prediction model, wherein the colorectal cancer chemotherapy response prediction model predicts the chemotherapy resistance probability of colorectal cancer patients based on the tumor relative proliferation rate and the relative half maximum inhibition concentration value;
Said obtaining a relative half maximal inhibitory concentration value from said colorectal cancer chemotherapeutic sample and said chemotherapeutic response second analytical model comprises:
analyzing the treatment group and the control group according to the drug treatment scheme and the second analysis model of the chemotherapy response so as to obtain a second model analysis result;
fitting a dose response curve according to the analysis result of the second model, and determining the half maximum inhibition concentration;
Analyzing the relative half maximal inhibitory concentration values of the treatment group and the control group in different drug treatment regimens based on the half maximal inhibitory concentration;
The relative half maximum inhibition concentration value satisfies the following relationship:
，
wherein, Represents the relative half maximum inhibitory concentration value,Coefficients representing different drug treatment regimens are presented,Representing the measured half maximal inhibitory concentration value;
the construction of the colorectal cancer chemotherapy response prediction model comprises the following steps:
Constructing a colorectal cancer chemotherapeutic response prediction model based on the chemotherapeutic response first analysis model and the chemotherapeutic response second analysis model;
The colorectal cancer chemotherapy response prediction model meets the following relation:
，
wherein, The probability of drug resistance is indicated,/Represents the relative tumor proliferation rate and the relative tumor proliferation rate,Representing the relative half maximum inhibitory concentration values.
2. The computer readable storage medium of claim 1, wherein the obtaining a colorectal cancer chemotherapy sample of the patient comprises:
Treatment groups including a 5-FU treatment group, a 5-fu+ox treatment group, and a 5-fu+iri treatment group are set according to colorectal cancer chemotherapy samples of the patient.
3. The computer readable storage medium of claim 1, wherein the establishing a first analysis model of a chemotherapeutic response and a second analysis model of a chemotherapeutic response comprises:
setting treatment test conditions of the first analysis model of the chemotherapy response according to different drug types, wherein the treatment test conditions comprise solution concentration, administration frequency, administration mode, administration metering and experimental time;
the drug treatment regimen of the second analysis model of the chemotherapeutic response is set according to different drug categories, and comprises a chemotherapeutic drug concentration range and a treatment regimen time.
4. The computer readable storage medium of claim 1, wherein said deriving a tumor relative proliferation rate from said colorectal cancer chemotherapeutic sample and said first analytical model of chemotherapeutic response comprises:
performing treatment test analysis on the treatment group and the control group by using a first analysis model of chemotherapy reaction to obtain a first model analysis result;
Obtaining a relative tumor volume according to the first model analysis result;
And obtaining the relative proliferation rate of the tumor according to the analysis result of the first model and the relative tumor volume.
5. The computer readable storage medium of claim 4, wherein the relative tumor volumes satisfy the following relationship:
，
wherein, Represents the relative tumor volume of the sample,Representative ofThe volume of the tumor measured in time was determined,Represents the tumor volume measured at the beginning of the experiment;
the relative proliferation rate of the tumor meets the following relation:
，
wherein, Indicating the relative proliferation rate of the tumor,Represents the relative tumor volume of the treatment group,The relative tumor volumes of the control group are indicated.
6. A colorectal cancer chemoresponse prediction system, comprising an input device, a processor, an output device, and a memory, wherein the input device, the processor, the output device, and the memory are interconnected, the memory comprising the computer-readable storage medium of any of claims 1-5, the memory for storing a computer program comprising program instructions, the processor configured to invoke the program instructions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411035307.5A CN118571500B (en) | 2024-07-31 | 2024-07-31 | Colorectal cancer chemotherapy response prediction system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411035307.5A CN118571500B (en) | 2024-07-31 | 2024-07-31 | Colorectal cancer chemotherapy response prediction system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118571500A CN118571500A (en) | 2024-08-30 |
| CN118571500B true CN118571500B (en) | 2024-09-27 |
Family
ID=92478520
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411035307.5A Active CN118571500B (en) | 2024-07-31 | 2024-07-31 | Colorectal cancer chemotherapy response prediction system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118571500B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114134116A (en) * | 2021-12-10 | 2022-03-04 | 上海交通大学医学院附属瑞金医院 | Kit for predicting curative effect of chemotherapy drugs of colorectal cancer patient and application thereof |
| CN116463291A (en) * | 2022-11-21 | 2023-07-21 | 华中科技大学同济医学院附属同济医院 | Human colorectal cancer primary focus and liver transfer focus pairing organoid cell line and culture method and application thereof |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021113846A1 (en) * | 2019-12-05 | 2021-06-10 | Tempus Labs, Inc. | Large scale organoid analysis |
| CN117079716B (en) * | 2023-09-13 | 2024-04-05 | 江苏运动健康研究院 | Deep learning prediction method of tumor drug administration scheme based on gene detection |
-
2024
- 2024-07-31 CN CN202411035307.5A patent/CN118571500B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114134116A (en) * | 2021-12-10 | 2022-03-04 | 上海交通大学医学院附属瑞金医院 | Kit for predicting curative effect of chemotherapy drugs of colorectal cancer patient and application thereof |
| CN116463291A (en) * | 2022-11-21 | 2023-07-21 | 华中科技大学同济医学院附属同济医院 | Human colorectal cancer primary focus and liver transfer focus pairing organoid cell line and culture method and application thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118571500A (en) | 2024-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Torkamani et al. | High-definition medicine | |
| EP2911642B1 (en) | Drug monitoring and regulation systems and methods | |
| CA2596816A1 (en) | Method for defining virtual patient populations | |
| US20150046465A1 (en) | System and method for targeting relevant research activity in response to diagnostic marker analyses | |
| CN113142135A (en) | Construction method of digestive tract tumor PDX model and standardized model library | |
| WO2022232615A1 (en) | Machine learning techniques for estimating tumor cell expression complex tumor tissue | |
| CN110257518B (en) | Gene set for predicting curative effect of metastatic colorectal cancer transformation treatment | |
| Cao et al. | The association between essential trace element (copper, zinc, selenium, and cobalt) status and the risk of early embryonic arrest among women undergoing assisted reproductive techniques | |
| CN118571500B (en) | Colorectal cancer chemotherapy response prediction system and storage medium | |
| CN1751129B (en) | Identification, monitoring and treatment of infectious disease and characterization of inflammatory conditions related to infectious disease using gene expression profiles | |
| Edwards et al. | Challenges and Opportunities for Data Science in Women's Health | |
| Gao et al. | Prespecification of subgroup analyses and examination of treatment-subgroup interactions in cancer individual participant data meta-analyses are suboptimal | |
| Zyla et al. | Evaluation of zero counts to better understand the discrepancies between bulk and single-cell RNA-Seq platforms | |
| CN119286974A (en) | A system for constructing a prediction model for targeted therapy of advanced colorectal cancer | |
| JP2017530716A (en) | A method for performing a stimulus response test using perinatal cells or tissue-derived induced pluripotent stem cells | |
| US20250027929A1 (en) | Method and system for predicting susceptibility to anticancer agent | |
| CN118412148B (en) | Medication evaluation method based on AI technology and organ chip | |
| Daniel et al. | Cerebrospinal Fluid Composition of Infants with Ischemic Stroke | |
| Wang et al. | Identifying Potential Diagnostic and Therapeutic Targets for Infantile Hemangioma Using WGCNA and Machine Learning Algorithms | |
| Afkham et al. | A new look at cancer immunotherapy via artificial intelligence | |
| Clements | Development and Implementation of Standardized Documentation Tools/“Smart Phrases” Within the Electronic Medical Record (EMR) of an Outpatient Transplant Clinic | |
| Thompson | No c. diffs ands or butts; optimizing c. diff tracking | |
| Ma | Tumor and pan-tumor diversity and heterogeneity of cancer tissue microbiomes: a medical ecology analysis across 32 cancer types | |
| Alqawba et al. | Classification Models of Idiopathic Pulmonary Fibrosis Patients | |
| DEKEL | EXPLORING DIAGNOSTIC METHODS FOR DETECTING TISSUE ABNORMALITIES THROUGH CLINICAL TRIALS |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |