CN117373545B - System for predicting and scoring intestinal cancer chemoradiotherapy and application and construction method of model - Google Patents
System for predicting and scoring intestinal cancer chemoradiotherapy and application and construction method of model Download PDFInfo
- Publication number
- CN117373545B CN117373545B CN202311673383.4A CN202311673383A CN117373545B CN 117373545 B CN117373545 B CN 117373545B CN 202311673383 A CN202311673383 A CN 202311673383A CN 117373545 B CN117373545 B CN 117373545B
- Authority
- CN
- China
- Prior art keywords
- positive rate
- tumor tissue
- intestinal cancer
- model
- outside
- 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
- 201000002313 intestinal cancer Diseases 0.000 title claims abstract description 107
- 208000005016 Intestinal Neoplasms Diseases 0.000 title claims abstract description 100
- 238000011127 radiochemotherapy Methods 0.000 title claims abstract description 24
- 238000010276 construction Methods 0.000 title claims abstract description 12
- 206010028980 Neoplasm Diseases 0.000 claims abstract description 176
- 239000000090 biomarker Substances 0.000 claims abstract description 127
- 102100022005 B-lymphocyte antigen CD20 Human genes 0.000 claims abstract description 50
- 101000897405 Homo sapiens B-lymphocyte antigen CD20 Proteins 0.000 claims abstract description 50
- 238000000034 method Methods 0.000 claims abstract description 42
- 238000012216 screening Methods 0.000 claims abstract description 8
- 230000004044 response Effects 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 14
- 230000008859 change Effects 0.000 claims description 12
- 238000002512 chemotherapy Methods 0.000 claims description 12
- 238000001959 radiotherapy Methods 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 8
- 201000003741 Gastrointestinal carcinoma Diseases 0.000 claims description 7
- 230000004797 therapeutic response Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 8
- 210000004027 cell Anatomy 0.000 description 45
- 238000012360 testing method Methods 0.000 description 20
- 238000012549 training Methods 0.000 description 14
- 206010009944 Colon cancer Diseases 0.000 description 11
- 208000001333 Colorectal Neoplasms Diseases 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 239000013642 negative control Substances 0.000 description 4
- 210000001744 T-lymphocyte Anatomy 0.000 description 3
- 230000003321 amplification Effects 0.000 description 3
- 210000003719 b-lymphocyte Anatomy 0.000 description 3
- 239000003086 colorant Substances 0.000 description 3
- 150000001875 compounds Chemical class 0.000 description 3
- 239000007850 fluorescent dye Substances 0.000 description 3
- 238000003364 immunohistochemistry Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 238000003199 nucleic acid amplification method Methods 0.000 description 3
- 238000010186 staining Methods 0.000 description 3
- 210000004881 tumor cell Anatomy 0.000 description 3
- 108010001336 Horseradish Peroxidase Proteins 0.000 description 2
- 201000011510 cancer Diseases 0.000 description 2
- 210000000170 cell membrane Anatomy 0.000 description 2
- 208000029742 colonic neoplasm Diseases 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 210000002865 immune cell Anatomy 0.000 description 2
- 238000010166 immunofluorescence Methods 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000011247 total mesorectal excision Methods 0.000 description 2
- 208000037956 transmissible mink encephalopathy Diseases 0.000 description 2
- FWBHETKCLVMNFS-UHFFFAOYSA-N 4',6-Diamino-2-phenylindol Chemical compound C1=CC(C(=N)N)=CC=C1C1=CC2=CC=C(C(N)=N)C=C2N1 FWBHETKCLVMNFS-UHFFFAOYSA-N 0.000 description 1
- 102000019034 Chemokines Human genes 0.000 description 1
- 108010012236 Chemokines Proteins 0.000 description 1
- 102000004127 Cytokines Human genes 0.000 description 1
- 108090000695 Cytokines Proteins 0.000 description 1
- DZGWFCGJZKJUFP-UHFFFAOYSA-N Tyramine Natural products NCCC1=CC=C(O)C=C1 DZGWFCGJZKJUFP-UHFFFAOYSA-N 0.000 description 1
- 210000000436 anus Anatomy 0.000 description 1
- 238000006555 catalytic reaction Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001086 cytosolic effect Effects 0.000 description 1
- 210000001151 cytotoxic T lymphocyte Anatomy 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 210000002950 fibroblast Anatomy 0.000 description 1
- 230000013632 homeostatic process Effects 0.000 description 1
- 230000028993 immune response Effects 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 238000003125 immunofluorescent labeling Methods 0.000 description 1
- 230000002055 immunohistochemical effect Effects 0.000 description 1
- 238000011532 immunohistochemical staining Methods 0.000 description 1
- 230000001024 immunotherapeutic effect Effects 0.000 description 1
- 238000007901 in situ hybridization Methods 0.000 description 1
- 230000000968 intestinal effect Effects 0.000 description 1
- 230000009545 invasion Effects 0.000 description 1
- 210000002540 macrophage Anatomy 0.000 description 1
- 230000036210 malignancy Effects 0.000 description 1
- 108020004999 messenger RNA Proteins 0.000 description 1
- 210000004088 microvessel Anatomy 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 230000007170 pathology Effects 0.000 description 1
- 238000010837 poor prognosis Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 238000011272 standard treatment Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 230000002195 synergetic effect Effects 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
- 238000013518 transcription Methods 0.000 description 1
- 230000035897 transcription Effects 0.000 description 1
- 229960003732 tyramine Drugs 0.000 description 1
- DZGWFCGJZKJUFP-UHFFFAOYSA-O tyraminium Chemical group [NH3+]CCC1=CC=C(O)C=C1 DZGWFCGJZKJUFP-UHFFFAOYSA-O 0.000 description 1
- 125000001493 tyrosinyl group Chemical group [H]OC1=C([H])C([H])=C(C([H])=C1[H])C([H])([H])C([H])(N([H])[H])C(*)=O 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B40/00—ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
- G01N21/64—Fluorescence; Phosphorescence
- G01N21/6428—Measuring fluorescence of fluorescent products of reactions or of fluorochrome labelled reactive substances, e.g. measuring quenching effects, using measuring "optrodes"
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
- G01N33/50—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing
- G01N33/53—Immunoassay; Biospecific binding assay; Materials therefor
- G01N33/574—Immunoassay; Biospecific binding assay; Materials therefor for cancer
- G01N33/57407—Specifically defined cancers
- G01N33/57446—Specifically defined cancers of stomach or intestine
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
- G01N33/50—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing
- G01N33/53—Immunoassay; Biospecific binding assay; Materials therefor
- G01N33/574—Immunoassay; Biospecific binding assay; Materials therefor for cancer
- G01N33/57484—Immunoassay; Biospecific binding assay; Materials therefor for cancer involving compounds serving as markers for tumor, cancer, neoplasia, e.g. cellular determinants, receptors, heat shock/stress proteins, A-protein, oligosaccharides, metabolites
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
- G01N33/50—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing
- G01N33/58—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing involving labelled substances
- G01N33/582—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing involving labelled substances with fluorescent label
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2333/00—Assays involving biological materials from specific organisms or of a specific nature
- G01N2333/435—Assays involving biological materials from specific organisms or of a specific nature from animals; from humans
- G01N2333/46—Assays involving biological materials from specific organisms or of a specific nature from animals; from humans from vertebrates
- G01N2333/47—Assays involving proteins of known structure or function as defined in the subgroups
- G01N2333/4701—Details
- G01N2333/4742—Keratin; Cytokeratin
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2333/00—Assays involving biological materials from specific organisms or of a specific nature
- G01N2333/435—Assays involving biological materials from specific organisms or of a specific nature from animals; from humans
- G01N2333/705—Assays involving receptors, cell surface antigens or cell surface determinants
- G01N2333/70503—Immunoglobulin superfamily, e.g. VCAMs, PECAM, LFA-3
- G01N2333/70539—MHC-molecules, e.g. HLA-molecules
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2333/00—Assays involving biological materials from specific organisms or of a specific nature
- G01N2333/435—Assays involving biological materials from specific organisms or of a specific nature from animals; from humans
- G01N2333/705—Assays involving receptors, cell surface antigens or cell surface determinants
- G01N2333/70596—Molecules with a "CD"-designation not provided for elsewhere in G01N2333/705
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2474/00—Immunochemical assays or immunoassays characterised by detection mode or means of detection
- G01N2474/20—Immunohistochemistry assay
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Immunology (AREA)
- Chemical & Material Sciences (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Hematology (AREA)
- Molecular Biology (AREA)
- Urology & Nephrology (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Analytical Chemistry (AREA)
- Biotechnology (AREA)
- Cell Biology (AREA)
- Biochemistry (AREA)
- Pathology (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Microbiology (AREA)
- Medical Informatics (AREA)
- Oncology (AREA)
- Hospice & Palliative Care (AREA)
- Epidemiology (AREA)
- Theoretical Computer Science (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Software Systems (AREA)
- Public Health (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biophysics (AREA)
- Bioethics (AREA)
- Artificial Intelligence (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Optics & Photonics (AREA)
Abstract
The invention discloses a system for predicting and scoring intestinal cancer chemoradiotherapy and an application and a construction method of a model, and the technical scheme is characterized in that fluorescent expression intensities of a plurality of biomarkers in tumor tissues of the intestinal cancer and outside the tumor tissues are obtained, wherein the biomarkers comprise: panCK, CD20 and MHC-II; obtaining the positive rate of the biomarkers in the tumor tissue, outside the tumor tissue and inside and outside the tumor tissue according to the fluorescence expression intensity; screening out characteristic factors from all positive rates by using a stepwise regression method, and constructing a scoring model according to the characteristic factors; the characteristic factors comprise the overall double positive rate of MHC-II and CD20 inside and outside tumor tissues, the double positive rate of MHC-II and CD20 inside tumor tissues, the single positive rate of MHC-II outside tumor tissues, the single positive rate of CD20 outside tumor tissues and the double positive rate of MHC-II and CD20 outside tumor tissues. The invention combines the positive rate of the biomarkers in and out of the tumor tissue, and can construct a scoring model with better scoring prediction effect on the chemoradiotherapy of the intestinal cancer.
Description
Technical Field
The invention belongs to the field of biomedicine, and particularly relates to a prediction scoring model for intestinal cancer chemoradiotherapy, application, a system and a construction method thereof.
Background
Colorectal cancer (CRC) is the third most fatal malignancy worldwide, with up to 50% of CRC patients eventually metastasizing, resulting in poor prognosis. The radiotherapy and chemotherapy in the current treatment of the locally advanced colorectal cancer is a standard treatment mode, and has the advantages of controlling and treating the tumor on one hand, reducing the tumor body on the other hand, facilitating the subsequent operation and the anus protection treatment, and improving the survival quality of patients after the treatment. The method has the defects that 20-40% of patients are insensitive to radiotherapy and chemotherapy, so that treatment resources are wasted, and the patients are additionally subjected to economic pressure and physical and psychological burden. Therefore, developing a suitable biomarker for distinguishing people who can respond to radiotherapy and chemotherapy in patients with locally advanced colorectal cancer has great significance.
The existing biomarkers are not enough to distinguish the chemoradiotherapy response population. New markers require analysis of large sample volumes of clinical data and in-depth knowledge of the disease, as well as expansion of the field of intrinsic knowledge by new technologies. In recent years many newly discovered biomarkers, particularly immunotherapeutic biomarkers, have been associated with the tumor immune microenvironment (tumor microenvironment, TME). The tumor immune microenvironment is a complex comprehensive system, mainly composed of tumor cells, surrounding immune cells, tumor-related fibroblasts, nearby interstitial tissues, microvessels, various cytokines, chemokines and the like, and the occurrence and development of tumors are closely related to the tumor cells and tumor immune microenvironment as well.
The many biomarker interactions that exist within TMEs are interrelated, new spatial genomic and spatial proteomic techniques push the biomarker discovery of TMEs to new heights, and mRNA and protein of tissue specimens can be mapped and quantified by means of multiplex in situ hybridization and multiplex immunohistochemistry, and these indices are statistically analyzed. For a tissue sample of intestinal cancer, not only the distribution condition of the biomarker in the tissue of the intestinal cancer is analyzed, but also the distribution condition of the biomarker in the interstitium is further considered, and the effective biomarker is searched for carrying out the effect prediction by combining the effect difference of the medicines.
Traditional immunohistochemical staining/immunofluorescence staining (i m m u n o h i s t o C H E M I S T R Y/immunofluorescence, IHC/IF) is the most commonly used detection method for TME research at present, plays a vital role in the evaluation of pathological types and biomarkers of intestinal cancer, can assist clinicians in timely and accurately making treatment decisions, and still has a number of limitations.
Disclosure of Invention
The invention aims to provide a prediction scoring model, application, a system and a construction method thereof for intestinal cancer chemoradiotherapy, and can construct a scoring model with better prediction effect on treatment response of intestinal cancer chemoradiotherapy by combining the positive rates of biomarkers in tumor tissues and outside tumor tissues.
The first aspect of the invention provides a method for constructing a prediction scoring model for chemoradiotherapy of intestinal cancer, which comprises the following steps:
obtaining fluorescence expression intensities of a plurality of biomarkers within and outside tumor tissue of a bowel cancer, wherein the biomarkers comprise: panCK, CD20 and MHC-II;
Obtaining the positive rate of the biomarkers in the tumor tissue, outside the tumor tissue and inside and outside the tumor tissue according to the fluorescence expression intensity;
Screening out characteristic factors from all positive rates by using a stepwise regression method, and constructing a scoring model according to the characteristic factors;
wherein the characteristic factors comprise MHC2_cd20, MHC2_cd20_turner, mhc2_back, cd20_back and MHC2_cd20_back, the MHC2_cd20 represents the overall double positive rate of MHC-II and CD20 inside and outside tumor tissues, the MHC2_cd20_turner represents the double positive rate of MHC-II and CD20 inside tumor tissues, MHC2_back represents the single positive rate of MHC-II outside tumor tissues, the cd20_back represents the single positive rate of CD20 outside tumor tissues, and the MHC2_cd20_back represents the double positive rate of MHC-II and CD20 outside tumor tissues.
Optionally, the formula of the scoring model is:
,
And the Type represents a predictive value, and if the predictive value is larger than a preset threshold value, the response of the intestinal cancer patient is judged to be good, and if the predictive value is not larger than the preset threshold value, the response of the intestinal cancer patient is judged to be poor.
By establishing a corresponding ROC curve for the scoring model, calculating the AUC value of the ROC curve, the corresponding AUC value of the scoring model is 0.91 and is close to 1, and the scoring model is good in performance and good in prediction effect.
Optionally, the step regression method is used to screen out feature factors from all positive rates, including:
Fitting all positive rates through a binomial distribution method of a generalized linear model to obtain a plurality of first models to be selected;
establishing corresponding first ROC curves for the first to-be-selected models, and calculating corresponding first AUC values of the first ROC curves;
Selecting a first model to be selected with the highest first AUC value as a primary model;
Gradually removing the positive rate from the primary model, checking whether the primary model has significant change after removing, if so, reserving the positive rate, and if not, removing the positive rate until all positive rates with significant change on the primary model are reserved as characteristic factors.
The first AUC value corresponding to each first model to be selected is calculated, then the primary model is determined according to the first AUC value, and the first model to be selected with the highest AUC value is taken as the primary model as the best AUC value is indicated to be better in performance of the model, the best first model to be selected can be objectively screened as the primary model, after the primary model is determined, stepwise regression analysis is carried out on the primary model to obtain a scoring model, and the AUC value corresponding to the primary model can be compared with the AUC value corresponding to the scoring model to judge whether the performance of the scoring model is better than that of the primary model.
Optionally, the constructing a scoring model according to the feature factors includes:
Fitting all the characteristic factors through a binomial distribution method of a generalized linear model to obtain a plurality of second candidate models;
Establishing a corresponding second ROC curve for each second model to be selected, and calculating a corresponding second AUC value of each second ROC curve;
and selecting a second candidate model with the highest second AUC value as a scoring model.
And calculating second AUC values corresponding to the second candidate models, and determining a scoring model according to the second AUC values, wherein the second candidate model with the highest AUC value is taken as a primary model as the better performance of the model is explained due to the fact that the AUC values are approximately close to 1, so that the best second candidate model can be objectively screened out to be taken as the scoring model.
Optionally, the obtaining the positive rate of the biomarker in the tumor tissue, outside the tumor tissue and inside and outside the tumor tissue according to the fluorescence expression intensity includes:
comparing the fluorescence expression intensity of the cells of each biomarker in the tumor tissue of the intestinal cancer with a corresponding preset intensity threshold value, and judging the cells as positive cells corresponding to the biomarkers in the tumor tissue under the condition that the fluorescence expression intensity of the cells of the biomarkers in the tumor tissue of the intestinal cancer is greater than the corresponding intensity threshold value, so as to obtain the single positive rate of each biomarker in the tumor tissue of the intestinal cancer and the double positive rate of the biomarkers in the tumor tissue of the intestinal cancer;
Comparing the fluorescence expression intensity of the cells of each biomarker outside the tumor tissue of the intestinal cancer with a corresponding preset intensity threshold value, and judging the cells as positive cells corresponding to the biomarkers outside the tumor tissue under the condition that the fluorescence expression intensity of the cells of each biomarker outside the tumor tissue of the intestinal cancer is greater than the corresponding intensity threshold value, so as to obtain the single positive rate of each biomarker outside the tumor tissue of the intestinal cancer and the double positive rate of each biomarker inside the tumor tissue of the intestinal cancer;
And obtaining the double positive rate of the biomarker according to the single positive rate of each biomarker in the tumor tissue of the intestinal cancer and the single positive rate of each biomarker outside the tumor tissue of the intestinal cancer.
By comparing the fluorescence expression intensity of each biomarker in the cells with a corresponding preset intensity threshold, whether the cells are positive cells or not is conveniently judged, so that the single positive rate of each biomarker and the double positive rate of the biomarker are calculated.
The second aspect of the invention provides a prediction scoring model for intestinal cancer chemoradiotherapy, which is formed by the construction method.
The third aspect of the invention provides an application of the scoring model in construction of a prediction scoring system or device for chemoradiotherapy of intestinal cancer, and response of an intestinal cancer patient is predicted according to a prediction score calculated by the scoring model.
The fourth aspect of the present invention provides a prediction scoring system for chemoradiotherapy of intestinal cancer, comprising: the grading model is used for predicting the treatment response of the intestinal cancer chemoradiotherapy by taking the positive rate of the biomarker as an input variable.
A fifth aspect of the invention provides a computer device comprising a memory storing a computer program and a processor implementing the steps of the method described above when the processor executes the computer program.
A sixth aspect of the invention provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method described above.
The technical scheme provided by the invention has the following advantages and effects: combining the positive rates of the three biomarkers of PanCK, CD20 and MHC-II in and out of tumor tissues, and then adopting a stepwise regression method to screen the positive rates of all the biomarkers to obtain characteristic factors, and constructing a scoring model according to the characteristic factors so as to ensure that the prediction effect of the obtained scoring model is better.
Drawings
FIG. 1 is a flow chart of a method for constructing a prediction scoring model for intestinal cancer chemoradiotherapy provided by the invention;
FIG. 2 is a fluorescent staining chart of PanCK provided by the present invention;
FIG. 3 is a bright field and negative control plot of PanCK provided by the present invention;
FIG. 4 is a fluorescent staining pattern of MHC-II provided by the present invention;
FIG. 5 is a bright field and negative control of MHC-II provided by the present invention;
FIG. 6 is a fluorescent staining pattern of CD20 provided by the present invention;
FIG. 7 is a bright field and negative control plot of CD20 provided by the present invention;
FIG. 8 is a graph of PanCK and MHC-II double positive rates provided by the present invention;
FIG. 9 is a graph of MHC-II and CD20 double positive rates provided by the present invention;
FIG. 10 is a tissue duty cycle scatter plot of MHC-II provided by the present invention;
FIG. 11 is a plot of tissue occupancy scatter for CD20 provided by the present invention;
FIG. 12 is a positive display in tumor tissue of MHC-II provided by the present invention;
FIG. 13 is a positive display of MHC-II tumor tissue provided by the present invention;
FIG. 14 is a diagram showing the difference between Response classes and Non-Response classes provided by the present invention;
FIG. 15 is a ROC graph of a primary model provided by the present invention;
FIG. 16 is a ROC graph of a scoring model provided by the present invention;
Fig. 17 is an internal structural diagram of a computer device provided by the present invention.
Detailed Description
In order that the invention may be readily understood, a more particular description of specific embodiments thereof will be rendered by reference to specific embodiments that are illustrated in the appended drawings.
The terms "first" and "second" … "as used herein, unless specifically indicated or otherwise defined, are merely used to distinguish between names and do not denote a particular quantity or order.
The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items, unless specifically stated or otherwise defined.
The term "fixed" or "connected" as used herein may be directly fixed or connected to an element, or indirectly fixed or connected to an element.
The invention analyzes three marks and four colors of intestinal cancer, wherein the three marks and four colors refer to three biomarkers including PanCK, CD20 and MHC-II, and a DAPI is added as a background for cell identification to form four colors. The analysis method covers main immune cells such as B cells, T cells, macrophages and the like, and PanCK cancer cells are added, MHC-II is a biomarker related to intestinal cancer, and is a critical ring of tumor immunity. Interactions between MHC-II and T cells are necessary to maintain intestinal immune homeostasis, and normal interactions between MHC-II and T cells can maintain a type 1 immune response within TME (tumor microenvironment ) to limit colon cancer progression and invasion. Tumor-infiltrating cd20+ B lymphocytes exhibit a positive effect in colorectal cancer (CRC, colorectal cancer) patient response. In addition, cd20+ B lymphocytes and cytotoxic T lymphocytes have a synergistic effect in the response of CRC patients, which gives important clues to the response of colon cancer and also helps to mine new therapeutic targets. Through the analysis of polychromatic immunohistochemical three-mark four-color, the single positive rate can be obtained, and after tissue identification, the single positive rate of the biomarker inside and outside the tissue is obtained. Meanwhile, the double positive rate between the interesting biomarkers can be obtained, data conversion and statistical analysis are carried out according to the single positive rate and the double positive rate, the conditions of the biomarkers between two groups with different curative effects in different areas are obtained, and the specific conditions of intestinal cancer immune microenvironment can be displayed more intuitively.
Branch fluorescence TSA is a brand new fluorescent signal Amplification technology, and TSA is short for tyramine signal Amplification technology (TYRAMIDE SIGNAL Amplification). Using the "< primary-secondary-HRP > substrate" principle and procedure based on immunohistochemistry (immunohistochemistry, IHC), TSA fluorescent compounds bind to tyrosine residues near the target site under horseradish peroxidase (HRP) catalysis, generating stable fluorescent compounds. Compared with common immunofluorescence, the TSA technology can amplify signals by 10-1000 times, and fluorescent compounds have ideal light, heat and pH stability, so that the multi-color fluorescent markers are not limited by primary antibody species. Compared with large-scale cell detection and single-cell transcription analysis, the method not only can enable the tumor sample to display the relationship between tumor cells and tumor immune microenvironment under better resolution, but also has the advantages of relatively mature technical principle and more convenient operation, and has particular advantages in the current clinical medical research. The TSA technique used may reduce the drawbacks of the experiment compared to other methods.
An embodiment provides a method for constructing a prediction scoring model for radiotherapy and chemotherapy of intestinal cancer, as shown in fig. 1, including:
Step 100, obtaining fluorescence expression intensities of a plurality of biomarkers in tumor tissues of intestinal cancer and outside the tumor tissues, wherein the biomarkers comprise: panCK, CD20 and MHC-II;
Specifically, a sample, namely tumor tissue inner cells and tumor tissue outer cells of intestinal cancer, is stained and sealed by using PanCK, CD20 and MHC-II antibodies and using a TSA staining technology to obtain a stained slide, the specific antibody information is shown in Table 1,
TABLE 1
HLA-DRDPDQ is a specific name of an MHC-II antibody, then scanning the obtained stained slide by using tissue quest software, acquiring a scanned picture from the tissue quest software, importing a picture file into StrataQuest analysis software, generating an analysis file, entering a main interface, and then entering the analysis interface according to a region selected by a pathologist in an initial mode by taking an ROI as an initial mode.
According to experimental records, the setting parameters are shown in table 2, corresponding fluorescence channels are found, and the fluorescence parameters of the 4 channel targets are sequentially converted from 16 bits to 8 bits.
TABLE 2
Wherein, type1 represents a first scan parameter, in other embodiments, other scan parameters can be set, 440N represents 440 channels, 470SN represents 470 frequency multiplication channels, 520N represents 520 channels, 650N represents 650 channels, and in order to identify nuclei first, parameter setting is performed: the fluorescence range is set to-1 to 256; then, masks (CD 20 is cell membrane recognition; MHC-II, panCK is cell membrane and cytoplasmic recognition; for example, 440 channels, panCK, parameter settings: fluorescence range is set to-1 to 256, maximum growth step number (Max Growing Steps) is set to 7.5.
Three regions were then set by StrataQuest software: background (representing background area), stroma (representing extra-tumor tissue area), objects (representing intra-tumor tissue area); and optimizing the organization, and obtaining the organization which is most in line with reality by StrataQuest software through multiple times of training.
As shown in fig. 2-7, each biomarker can be screened for a threshold based on the results of the bright field and negative controls, such as: the fluorescence expression intensity threshold parameter corresponding to PanCK + cells is set to 37, that is, the preset intensity threshold corresponding to PanCK biomarker is set to 37, the fluorescence expression intensity threshold parameter corresponding to MHC-II+ cells is set to 25, that is, the preset intensity threshold corresponding to MHC-II biomarker is set to 25, the fluorescence expression intensity threshold parameter corresponding to CD20+ cells is set to 26, that is, the preset intensity threshold corresponding to CD20 biomarker is set to 25, and each cell can be traced back according to a flow-like mode, so that the fluorescence expression intensity of the biomarker on each cell is obtained.
Step 200, obtaining the positive rate of the biomarkers in the tumor tissue, outside the tumor tissue and inside and outside the tumor tissue according to the fluorescence expression intensity, wherein the positive rate comprises the following steps: panck _ MHC2, which represents the overall double positive rate of PanCK and MHC-II within and outside tumor tissue; MHC2_cd20, which represents the overall double positive rate of MHC-II and CD20 in and out of tumor tissue; MHC2_tumor, which indicates MHC-II single positive rate in tumor tissue; cd20_tumor, which represents the single positive rate of CD20 in tumor tissue; MHC2 cd20_tumor, which indicates the double positive rate of MHC-II and CD20 in tumor tissue; MHC2_back, which indicates the single positive rate of MHC-II outside tumor tissue; cd20_back, which indicates single positive rate of CD20 outside tumor tissue; MHC2_cd20_back, indicates the double positive rate of MHC-II and CD20 outside tumor tissue.
Specifically, the step of obtaining the positive rate of the biomarker in the tumor tissue, outside the tumor tissue and inside and outside the tumor tissue according to the fluorescence expression intensity comprises the following steps:
comparing the fluorescence expression intensity of the cells of each biomarker in the tumor tissue of the intestinal cancer with a corresponding preset intensity threshold value, and judging the cells as positive cells corresponding to the biomarkers in the tumor tissue under the condition that the fluorescence expression intensity of the cells of the biomarkers in the tumor tissue of the intestinal cancer is greater than the corresponding intensity threshold value, so as to obtain the single positive rate of each biomarker in the tumor tissue of the intestinal cancer and the double positive rate of the biomarkers in the tumor tissue of the intestinal cancer;
Comparing the fluorescence expression intensity of the cells of each biomarker outside the tumor tissue of the intestinal cancer with a corresponding preset intensity threshold value, and judging the cells as positive cells corresponding to the biomarkers outside the tumor tissue under the condition that the fluorescence expression intensity of the cells of each biomarker outside the tumor tissue of the intestinal cancer is greater than the corresponding intensity threshold value, so as to obtain the single positive rate of each biomarker outside the tumor tissue of the intestinal cancer and the double positive rate of each biomarker inside the tumor tissue of the intestinal cancer;
And obtaining the double positive rate of the biomarker according to the single positive rate of each biomarker in the tumor tissue of the intestinal cancer and the single positive rate of each biomarker outside the tumor tissue of the intestinal cancer.
As shown in FIG. 8, the double positive rates of PanCK and MHC-II are shown, as shown in FIG. 9, the double positive rates of MHC-II and CD20 are shown, both in FIG. 10 and FIG. 11 are scatter plots, FIG. 10 shows the tissue ratio of MHC-II, gate 2 in FIG. 10 shows the tissue ratio of CD20 outside the tumor tissue, gate 3 shows the tissue ratio of CD20 in FIG. 11, gate 4 in the tumor tissue, gate 5 shows the tissue outside the tumor tissue, and trace back into the tissue, and a distinct tissue inside-outside distinction can be seen, as shown in FIG. 12, for positive display of MHC-II inside the tumor tissue, as shown in FIG. 13, for positive display of MHC-II outside the tumor tissue.
Step 300, screening out characteristic factors from all positive rates by using a stepwise regression method, and constructing a scoring model according to the characteristic factors;
wherein the characteristic factors comprise MHC2_cd20, MHC2_cd20_turner, mhc2_back, cd20_back and MHC2_cd20_back, the MHC2_cd20 represents the overall double positive rate of MHC-II and CD20 inside and outside tumor tissues, the MHC2_cd20_turner represents the double positive rate of MHC-II and CD20 inside tumor tissues, MHC2_back represents the single positive rate of MHC-II outside tumor tissues, the cd20_back represents the single positive rate of CD20 outside tumor tissues, and the MHC2_cd20_back represents the double positive rate of MHC-II and CD20 outside tumor tissues.
Specifically, the step-by-step regression method is used for screening the characteristic factors from all positive rates, and comprises the following steps:
Fitting all positive rates through a binomial distribution method of a generalized linear model to obtain a plurality of first models to be selected;
establishing corresponding first ROC curves for the first to-be-selected models, and calculating corresponding first AUC values of the first ROC curves;
Selecting a first model to be selected with the highest first AUC value as a primary model;
Gradually removing the positive rate from the primary model, checking whether the primary model has significant change after removing, if so, reserving the positive rate, and if not, removing the positive rate until all positive rates with significant change on the primary model are reserved as characteristic factors.
In this example, 30 samples were randomly divided into 70% and 30%, 70% samples were used as training sets, 30% samples were used as test sets, and then the samples were divided into two groups according to mIHC pathology images of each sample and clinical efficacy of ROI, as shown in table 3,
TABLE 3 Table 3
Wherein, response represents a sample with good Response, non-Response represents a sample with poor Response, corresponding labels are marked on each sample according to the classification of table 3, a corresponding staining slide is obtained by staining and sealing each sample by using TSA technology, positive rates of biomarkers of each sample, namely positive rates of biomarkers of each sample of a training set and positive rates of biomarkers of each sample of a test set are obtained after sequentially using tissue quest software and StrataQuest analysis software, as shown in table 4, positive rates of samples 0 to 10 are obtained,
TABLE 4 Table 4
The result of the difference between the Response class and the Non-Response class is obtained through statistical analysis, as shown in fig. 14, then a labeled training set is adopted to train each first model to be tested, the positive rate of the biomarker of each sample of the training set is input into the first model to be tested, the first model to be tested is obtained after training, then a labeled testing set is adopted to test each first model to be tested, the positive rate of the biomarker of each sample of the testing set is input into the first model to be tested, the first model to be tested is tested, a corresponding testing result is obtained, a first ROC curve corresponding to each first model is drawn according to each testing result, an area under the ROC curve is used for measuring the performance of the model by using an R packet pROC, the AUC value is close to 1, and represents that the performance of the model is good, otherwise, the AUC value is close to 0, and therefore, the AUC value is the first model to be tested is the primary model which is the highest in AUC value of the order of 15, and the AUC value is the primary model which is the primary model of 15, the AUC value of the first model is the primary model which is the primary model of 0. In practical application, some positive rates are not significant, namely, some positive rates can be removed from the primary model step by step, whether the primary model has significant change after removal is checked, if yes, the positive rate is reserved, and if not, the positive rate is removed until all positive rates with significant change to the primary model are reserved as characteristic factors.
Specifically, constructing a scoring model according to the feature factors, including:
Fitting all the characteristic factors through a binomial distribution method of a generalized linear model to obtain a plurality of second candidate models;
Establishing a corresponding second ROC curve for each second model to be selected, and calculating a corresponding second AUC value of each second ROC curve;
and selecting a second candidate model with the highest second AUC value as a scoring model.
In this embodiment, a second candidate model is also trained by using a labeled training set, the positive rate of the biomarker of each sample of the training set is input into the second candidate model, the second candidate model is trained to obtain each trained second candidate model, each trained second candidate model is then tested by using a labeled test set, the positive rate of the biomarker of each sample of the test set is input into each trained second candidate model, the trained second candidate model is tested to obtain corresponding test results, a second ROC curve corresponding to each second candidate model is drawn according to each test result, the corresponding second AUC value of each second ROC curve is calculated by using an R packet pROC, then the second candidate model with the highest second AUC value is selected as a scoring model, as shown in fig. 16, the AUC value of the scoring model is 0.91, the sensitivity, specificity, backtracking accuracy, accuracy and accuracy of the primary model and the accuracy score are shown in the accuracy score table of 5,
TABLE 5
。
Specifically, the formula of the scoring model is:
,
And the Type represents a predictive value, and if the predictive value is larger than a preset threshold value, the response of the intestinal cancer patient is judged to be good, and if the predictive value is not larger than the preset threshold value, the response of the intestinal cancer patient is judged to be poor.
In this embodiment, the value of the predictive score is between 0 and 1, a median value of 0.5 is selected as a preset threshold, and the overall double positive rate of the MHC-II and CD20 inside and outside the tumor tissue, the single positive rate of the MHC-II outside the tumor tissue, the single positive rate of the CD20 outside the tumor tissue, and the double positive rate of the MHC-II and CD20 outside the tumor tissue are substituted into the formula of the scoring model to obtain the corresponding predictive score, where the predictive score is greater than the preset threshold, and where the predictive score is not greater than the preset threshold, the poor response of the radiotherapy and chemotherapy treatment of the patient with the bowel cancer is indicated.
The second embodiment provides a prediction scoring model for radiotherapy and chemotherapy of intestinal cancer, which is formed by using the construction method in the first embodiment, adopting a stepwise regression method to screen out characteristic factors from panck _ MHC2, MHC2_cd20, MHC2 _telemor, cd20_telemor, MHC2_cd20_telemor, mhc2_back, cd20_back and MHC2_cd20_back, wherein the characteristic factors comprise MHC2_cd20, MHC2_cd20_umor, mhc2_back, cd20_back and MHC2_cd20_back, and then fitting according to the characteristic factors by a binomial distribution method of an R language generalized linear model to obtain a plurality of second candidate models.
Training a second to-be-selected model by adopting a labeled training set, inputting the positive rate of the biomarker of each sample of the training set into the second to-be-selected model, training the second to-be-selected model to obtain each trained second to-be-selected model, testing each trained second to-be-selected model by adopting a labeled testing set, inputting the positive rate of the biomarker of each sample of the testing set into the second to-be-selected model after training, testing the second to-be-selected model after training to obtain corresponding testing results, drawing second ROC curves corresponding to each second to-be-selected model by utilizing ggplot, calculating corresponding second AUC values of each second ROC curve by utilizing R-packets pROC, and selecting the second to-be-selected model with the highest second AUC value as a scoring model.
In the third embodiment, the application of the scoring model in constructing the prediction scoring system or device for the radiotherapy and chemotherapy of the intestinal cancer is that the model applied in constructing the prediction scoring system or device for the radiotherapy and chemotherapy of the intestinal cancer is the scoring model in the second embodiment, the scoring model in the second embodiment is adopted to test each sample in the test set to obtain a corresponding test result, a ROC curve corresponding to the scoring model is drawn by ggplot according to each test result, an AUC value corresponding to the ROC curve is calculated by using an R packet pROC, as shown in fig. 16, the AUC value of the ROC curve is 0.91, and the sensitivity, specificity, accuracy, backtracking accuracy, accuracy and ACU value of the scoring model are shown in table 5.
The fourth embodiment provides a prediction scoring system for radiotherapy and chemotherapy of intestinal cancer, comprising: the prediction scoring model of the intestinal cancer chemoradiotherapy constructed by the construction method in the first embodiment takes the positive rate of the biomarker as an input variable for predicting the therapeutic response of the intestinal cancer chemoradiotherapy.
A fifth embodiment provides a computer device, which may be a server, and an internal structural diagram thereof may be as shown in fig. 17. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to realize a method for constructing a prediction scoring model of intestinal cancer chemoradiotherapy.
It will be appreciated by those skilled in the art that the structure shown in FIG. 17 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
The computer device provided in this embodiment includes a memory and a processor, where the memory stores a computer program, and the processor implements the following steps when executing the computer program:
obtaining fluorescence expression intensities of a plurality of biomarkers within and outside tumor tissue of a bowel cancer, wherein the biomarkers comprise: panCK, CD20 and MHC-II;
Obtaining the positive rate of the biomarkers in the tumor tissue, outside the tumor tissue and inside and outside the tumor tissue according to the fluorescence expression intensity;
Screening out characteristic factors from all positive rates by using a stepwise regression method, and constructing a scoring model according to the characteristic factors;
wherein the characteristic factors comprise MHC2_cd20, MHC2_cd20_turner, mhc2_back, cd20_back and MHC2_cd20_back, the MHC2_cd20 represents the overall double positive rate of MHC-II and CD20 inside and outside tumor tissues, the MHC2_cd20_turner represents the double positive rate of MHC-II and CD20 inside tumor tissues, MHC2_back represents the single positive rate of MHC-II outside tumor tissues, the cd20_back represents the single positive rate of CD20 outside tumor tissues, and the MHC2_cd20_back represents the double positive rate of MHC-II and CD20 outside tumor tissues.
In one embodiment, the scoring model is formulated as:
,
And the Type represents a predictive value, and if the predictive value is larger than a preset threshold value, the response of the intestinal cancer patient is judged to be good, and if the predictive value is not larger than the preset threshold value, the response of the intestinal cancer patient is judged to be poor.
In one embodiment, the step-by-step regression method is used to screen feature factors from all positive rates, including:
Fitting all positive rates through a binomial distribution method of a generalized linear model to obtain a plurality of first models to be selected;
establishing corresponding first ROC curves for the first to-be-selected models, and calculating corresponding first AUC values of the first ROC curves;
Selecting a first model to be selected with the highest first AUC value as a primary model;
Gradually removing the positive rate from the primary model, checking whether the primary model has significant change after removing, if so, reserving the positive rate, and if not, removing the positive rate until all positive rates with significant change on the primary model are reserved as characteristic factors.
In one embodiment, the constructing a scoring model according to the feature factors includes:
Fitting all the characteristic factors through a binomial distribution method of a generalized linear model to obtain a plurality of second candidate models;
Establishing a corresponding second ROC curve for each second model to be selected, and calculating a corresponding second AUC value of each second ROC curve;
and selecting a second candidate model with the highest second AUC value as a scoring model.
In one embodiment, the obtaining the positive rate of the biomarker in the tumor tissue, outside the tumor tissue and inside and outside the tumor tissue according to the fluorescence expression intensity comprises:
comparing the fluorescence expression intensity of the cells of each biomarker in the tumor tissue of the intestinal cancer with a corresponding preset intensity threshold value, and judging the cells as positive cells corresponding to the biomarkers in the tumor tissue under the condition that the fluorescence expression intensity of the cells of the biomarkers in the tumor tissue of the intestinal cancer is greater than the corresponding intensity threshold value, so as to obtain the single positive rate of each biomarker in the tumor tissue of the intestinal cancer and the double positive rate of the biomarkers in the tumor tissue of the intestinal cancer;
Comparing the fluorescence expression intensity of the cells of each biomarker outside the tumor tissue of the intestinal cancer with a corresponding preset intensity threshold value, and judging the cells as positive cells corresponding to the biomarkers outside the tumor tissue under the condition that the fluorescence expression intensity of the cells of each biomarker outside the tumor tissue of the intestinal cancer is greater than the corresponding intensity threshold value, so as to obtain the single positive rate of each biomarker outside the tumor tissue of the intestinal cancer and the double positive rate of each biomarker inside the tumor tissue of the intestinal cancer;
And obtaining the double positive rate of the biomarker according to the single positive rate of each biomarker in the tumor tissue of the intestinal cancer and the single positive rate of each biomarker outside the tumor tissue of the intestinal cancer.
A sixth embodiment provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
obtaining fluorescence expression intensities of a plurality of biomarkers within and outside tumor tissue of a bowel cancer, wherein the biomarkers comprise: panCK, CD20 and MHC-II;
Obtaining the positive rate of the biomarkers in the tumor tissue, outside the tumor tissue and inside and outside the tumor tissue according to the fluorescence expression intensity;
Screening out characteristic factors from all positive rates by using a stepwise regression method, and constructing a scoring model according to the characteristic factors;
wherein the characteristic factors comprise MHC2_cd20, MHC2_cd20_turner, mhc2_back, cd20_back and MHC2_cd20_back, the MHC2_cd20 represents the overall double positive rate of MHC-II and CD20 inside and outside tumor tissues, the MHC2_cd20_turner represents the double positive rate of MHC-II and CD20 inside tumor tissues, MHC2_back represents the single positive rate of MHC-II outside tumor tissues, the cd20_back represents the single positive rate of CD20 outside tumor tissues, and the MHC2_cd20_back represents the double positive rate of MHC-II and CD20 outside tumor tissues.
In one embodiment, the scoring model is formulated as:
,
And the Type represents a predictive value, and if the predictive value is larger than a preset threshold value, the response of the intestinal cancer patient is judged to be good, and if the predictive value is not larger than the preset threshold value, the response of the intestinal cancer patient is judged to be poor.
In one embodiment, the step-by-step regression method is used to screen feature factors from all positive rates, including:
Fitting all positive rates through a binomial distribution method of a generalized linear model to obtain a plurality of first models to be selected;
establishing corresponding first ROC curves for the first to-be-selected models, and calculating corresponding first AUC values of the first ROC curves;
Selecting a first model to be selected with the highest first AUC value as a primary model;
Gradually removing the positive rate from the primary model, checking whether the primary model has significant change after removing, if so, reserving the positive rate, and if not, removing the positive rate until all positive rates with significant change on the primary model are reserved as characteristic factors.
In one embodiment, the constructing a scoring model according to the feature factors includes:
Fitting all the characteristic factors through a binomial distribution method of a generalized linear model to obtain a plurality of second candidate models;
Establishing a corresponding second ROC curve for each second model to be selected, and calculating a corresponding second AUC value of each second ROC curve;
and selecting a second candidate model with the highest second AUC value as a scoring model.
In one embodiment, the obtaining the positive rate of the biomarker in the tumor tissue, outside the tumor tissue and inside and outside the tumor tissue according to the fluorescence expression intensity comprises:
comparing the fluorescence expression intensity of the cells of each biomarker in the tumor tissue of the intestinal cancer with a corresponding preset intensity threshold value, and judging the cells as positive cells corresponding to the biomarkers in the tumor tissue under the condition that the fluorescence expression intensity of the cells of the biomarkers in the tumor tissue of the intestinal cancer is greater than the corresponding intensity threshold value, so as to obtain the single positive rate of each biomarker in the tumor tissue of the intestinal cancer and the double positive rate of the biomarkers in the tumor tissue of the intestinal cancer;
Comparing the fluorescence expression intensity of the cells of each biomarker outside the tumor tissue of the intestinal cancer with a corresponding preset intensity threshold value, and judging the cells as positive cells corresponding to the biomarkers outside the tumor tissue under the condition that the fluorescence expression intensity of the cells of each biomarker outside the tumor tissue of the intestinal cancer is greater than the corresponding intensity threshold value, so as to obtain the single positive rate of each biomarker outside the tumor tissue of the intestinal cancer and the double positive rate of each biomarker inside the tumor tissue of the intestinal cancer;
And obtaining the double positive rate of the biomarker according to the single positive rate of each biomarker in the tumor tissue of the intestinal cancer and the single positive rate of each biomarker outside the tumor tissue of the intestinal cancer.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (SYNCHLINK) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
Claims (7)
1. The construction method of the prediction scoring model for the radiotherapy and chemotherapy of the intestinal cancer is characterized by comprising the following steps:
obtaining fluorescence expression intensities of a plurality of biomarkers within and outside tumor tissue of a bowel cancer, wherein the biomarkers comprise: panCK, CD20 and MHC-II;
Obtaining the positive rate of the biomarkers in the tumor tissue, outside the tumor tissue and inside and outside the tumor tissue according to the fluorescence expression intensity;
Screening out characteristic factors from all positive rates by using a stepwise regression method, and constructing a scoring model according to the characteristic factors;
Wherein the characteristic factors comprise MHC2_cd20, MHC2_cd20_turner, mhc2_back, cd20_back and MHC2_cd20_back, the MHC2_cd20 represents the overall double positive rate of MHC-II and CD20 inside and outside tumor tissues, the MHC2_cd20_turner represents the double positive rate of MHC-II and CD20 inside tumor tissues, MHC2_back represents the single positive rate of MHC-II outside tumor tissues, the cd20_back represents the single positive rate of CD20 outside tumor tissues, and the MHC2_cd20_back represents the double positive rate of MHC-II and CD20 outside tumor tissues;
,
The Type represents a predictive value, and if the predictive value is larger than a preset threshold, the response of the intestinal cancer patient is judged to be good, and if the predictive value is not larger than the preset threshold, the response of the intestinal cancer patient is judged to be poor;
The step regression method is used for screening characteristic factors from all positive rates, and comprises the following steps:
Fitting all positive rates through a binomial distribution method of a generalized linear model to obtain a plurality of first models to be selected;
establishing corresponding first ROC curves for the first to-be-selected models, and calculating corresponding first AUC values of the first ROC curves;
Selecting a first model to be selected with the highest first AUC value as a primary model;
Gradually removing the positive rate from the primary model, checking whether the primary model has significant change after removing, if so, reserving the positive rate, and if not, removing the positive rate until all positive rates with significant change on the primary model are reserved as characteristic factors.
2. The method for constructing a predictive scoring model for radiotherapy and chemotherapy of intestinal cancer according to claim 1, wherein the constructing the scoring model according to the characteristic factors comprises:
Fitting all the characteristic factors through a binomial distribution method of a generalized linear model to obtain a plurality of second candidate models;
Establishing a corresponding second ROC curve for each second model to be selected, and calculating a corresponding second AUC value of each second ROC curve;
and selecting a second candidate model with the highest second AUC value as a scoring model.
3. The method for constructing a predictive scoring model for chemoradiotherapy of intestinal cancer according to claim 1, wherein the obtaining the positive rate of the biomarker in the tumor tissue, outside the tumor tissue and inside and outside the tumor tissue according to the fluorescence expression intensity comprises:
comparing the fluorescence expression intensity of the cells of each biomarker in the tumor tissue of the intestinal cancer with a corresponding preset intensity threshold value, and judging the cells as positive cells corresponding to the biomarkers in the tumor tissue under the condition that the fluorescence expression intensity of the cells of the biomarkers in the tumor tissue of the intestinal cancer is greater than the corresponding intensity threshold value, so as to obtain the single positive rate of each biomarker in the tumor tissue of the intestinal cancer and the double positive rate of the biomarkers in the tumor tissue of the intestinal cancer;
Comparing the fluorescence expression intensity of the cells of each biomarker outside the tumor tissue of the intestinal cancer with a corresponding preset intensity threshold value, and judging the cells as positive cells corresponding to the biomarkers outside the tumor tissue under the condition that the fluorescence expression intensity of the cells of each biomarker outside the tumor tissue of the intestinal cancer is greater than the corresponding intensity threshold value, so as to obtain the single positive rate of each biomarker outside the tumor tissue of the intestinal cancer and the double positive rate of each biomarker inside the tumor tissue of the intestinal cancer;
And obtaining the double positive rate of the biomarker according to the single positive rate of each biomarker in the tumor tissue of the intestinal cancer and the single positive rate of each biomarker outside the tumor tissue of the intestinal cancer.
4. The application of the intestinal cancer chemoradiotherapy predictive scoring model in constructing an intestinal cancer chemoradiotherapy predictive scoring system or device is characterized in that the intestinal cancer chemoradiotherapy predictive scoring model is formed by the construction method according to any one of claims 1-3, and responses of intestinal cancer patients are predicted according to the predictive score calculated by the intestinal cancer chemoradiotherapy predictive scoring model.
5. A system for predicting score of radiotherapy and chemotherapy for intestinal cancer, comprising: a prediction score model of bowel cancer chemoradiotherapy constituted by the construction method of any one of claims 1-3, wherein the score model uses the positive rate of the biomarker as an input variable for predicting the therapeutic response of bowel cancer chemoradiotherapy.
6. Computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1-3 when the computer program is executed.
7. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1-3.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311673383.4A CN117373545B (en) | 2023-12-07 | 2023-12-07 | System for predicting and scoring intestinal cancer chemoradiotherapy and application and construction method of model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311673383.4A CN117373545B (en) | 2023-12-07 | 2023-12-07 | System for predicting and scoring intestinal cancer chemoradiotherapy and application and construction method of model |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117373545A CN117373545A (en) | 2024-01-09 |
CN117373545B true CN117373545B (en) | 2024-05-10 |
Family
ID=89391408
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311673383.4A Active CN117373545B (en) | 2023-12-07 | 2023-12-07 | System for predicting and scoring intestinal cancer chemoradiotherapy and application and construction method of model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117373545B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20180024822A (en) * | 2016-08-31 | 2018-03-08 | 숭실대학교산학협력단 | Apparatus for judging false positive of de novo mutation using logistic regression and method thereof |
WO2020160006A1 (en) * | 2019-01-28 | 2020-08-06 | The Board Of Trustees Of The Leland Stanford Junior University | Rapid identification of close surgical margins on surgical specimens |
CN114529541A (en) * | 2022-03-28 | 2022-05-24 | 中国人民解放军海军军医大学第一附属医院 | Methods, electronic devices, media, and systems for predicting cell expression in pancreatic cancer microenvironment |
CN115141887A (en) * | 2022-08-18 | 2022-10-04 | 南方医科大学南方医院 | Scoring model for prognosis of colon cancer and benefit of adjuvant chemotherapy based on secretory cell enrichment characteristics, construction method and application |
CN115705928A (en) * | 2021-08-05 | 2023-02-17 | 华瑞同康生物技术(深圳)有限公司 | TC (total cholesterol) disease risk prediction modeling method based on cell proliferation marker |
CN116030880A (en) * | 2022-11-01 | 2023-04-28 | 苏州科技大学 | Biomarker for colorectal cancer prognosis risk prediction, model and application thereof |
CN116313107A (en) * | 2023-01-31 | 2023-06-23 | 浙江大学 | Liver cancer liver transplantation postoperative lung metastasis prediction model and construction method thereof |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7892740B2 (en) * | 2006-01-19 | 2011-02-22 | The University Of Chicago | Prognosis and therapy predictive markers and methods of use |
-
2023
- 2023-12-07 CN CN202311673383.4A patent/CN117373545B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20180024822A (en) * | 2016-08-31 | 2018-03-08 | 숭실대학교산학협력단 | Apparatus for judging false positive of de novo mutation using logistic regression and method thereof |
WO2020160006A1 (en) * | 2019-01-28 | 2020-08-06 | The Board Of Trustees Of The Leland Stanford Junior University | Rapid identification of close surgical margins on surgical specimens |
CN115705928A (en) * | 2021-08-05 | 2023-02-17 | 华瑞同康生物技术(深圳)有限公司 | TC (total cholesterol) disease risk prediction modeling method based on cell proliferation marker |
CN114529541A (en) * | 2022-03-28 | 2022-05-24 | 中国人民解放军海军军医大学第一附属医院 | Methods, electronic devices, media, and systems for predicting cell expression in pancreatic cancer microenvironment |
CN115141887A (en) * | 2022-08-18 | 2022-10-04 | 南方医科大学南方医院 | Scoring model for prognosis of colon cancer and benefit of adjuvant chemotherapy based on secretory cell enrichment characteristics, construction method and application |
CN116030880A (en) * | 2022-11-01 | 2023-04-28 | 苏州科技大学 | Biomarker for colorectal cancer prognosis risk prediction, model and application thereof |
CN116313107A (en) * | 2023-01-31 | 2023-06-23 | 浙江大学 | Liver cancer liver transplantation postoperative lung metastasis prediction model and construction method thereof |
Non-Patent Citations (1)
Title |
---|
多项肿瘤标志物联合检测模型在肺癌诊断中的应用价值;张海晨 等;检验医学(第07期);第18-24页 * |
Also Published As
Publication number | Publication date |
---|---|
CN117373545A (en) | 2024-01-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20220291219A1 (en) | Systems and compositions for diagnosing barrett's esophagus and methods of using the same | |
Rubin et al. | Quantitative determination of expression of the prostate cancer protein α-methylacyl-CoA racemase using automated quantitative analysis (AQUA): a novel paradigm for automated and continuous biomarker measurements | |
Masmoudi et al. | Automated quantitative assessment of HER-2/neu immunohistochemical expression in breast cancer | |
Lloyd et al. | Using image analysis as a tool for assessment of prognostic and predictive biomarkers for breast cancer: How reliable is it? | |
Holten-Rossing et al. | Optimizing HER2 assessment in breast cancer: application of automated image analysis | |
Feuchtinger et al. | Image analysis of immunohistochemistry is superior to visual scoring as shown for patient outcome of esophageal adenocarcinoma | |
US20110111435A1 (en) | Detecting Cell Surface Markers | |
CN108136216B (en) | Method of scoring a sample comprising tumor tissue | |
Al‐Kofahi et al. | Cell‐based quantification of molecular biomarkers in histopathology specimens | |
US20120052063A1 (en) | Automated detection of breast cancer lesions in tissue | |
CN109124660B (en) | Gastrointestinal stromal tumor postoperative risk detection method and system based on deep learning | |
Rost et al. | Multiplexed ion beam imaging analysis for quantitation of protein expresssion in cancer tissue sections | |
Ma et al. | Data integration from pathology slides for quantitative imaging of multiple cell types within the tumor immune cell infiltrate | |
Peck et al. | Validation of tumor protein marker quantification by two independent automated immunofluorescence image analysis platforms | |
Clarke et al. | A novel, automated technology for multiplex biomarker imaging and application to breast cancer | |
Takamatsu et al. | Immunohistochemical evaluation of tumor budding for stratifying T1 colorectal cancer: optimal cut-off value and a novel computer-assisted semiautomatic method | |
Gustavson et al. | Development of an unsupervised pixel-based clustering algorithm for compartmentalization of immunohistochemical expression using Automated QUantitative Analysis | |
Surace et al. | Characterization of the immune microenvironment of NSCLC by multispectral analysis of multiplex immunofluorescence images | |
Wu et al. | A review of artificial intelligence in precise assessment of programmed cell death-ligand 1 and tumor-infiltrating lymphocytes in non− small cell lung cancer | |
Serna et al. | Sequential immunohistochemistry and virtual image reconstruction using a single slide for quantitative KI67 measurement in breast cancer | |
JP6417602B2 (en) | How to determine the prognosis of colorectal cancer | |
Boyraz et al. | Discerning subsets of breast cancer with very low and absent HER2 protein expression | |
Jamalzadeh et al. | QuantISH: RNA in situ hybridization image analysis framework for quantifying cell type-specific target RNA expression and variability | |
Beaufrère et al. | Primary liver cancer classification from routine tumour biopsy using weakly supervised deep learning | |
Dolled-Filhart et al. | Automated analysis of tissue microarrays |
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 |