CN114999653A - Training method and prediction device of prediction model of non-small cell lung cancer immunotherapy curative effect - Google Patents
Training method and prediction device of prediction model of non-small cell lung cancer immunotherapy curative effect Download PDFInfo
- Publication number
- CN114999653A CN114999653A CN202210693286.0A CN202210693286A CN114999653A CN 114999653 A CN114999653 A CN 114999653A CN 202210693286 A CN202210693286 A CN 202210693286A CN 114999653 A CN114999653 A CN 114999653A
- Authority
- CN
- China
- Prior art keywords
- keap1
- mutation
- immunotherapy
- lung cancer
- small cell
- 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.)
- Granted
Links
Images
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
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- C—CHEMISTRY; METALLURGY
- C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
- C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
- C12Q1/00—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions
- C12Q1/68—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions involving nucleic acids
- C12Q1/6876—Nucleic acid products used in the analysis of nucleic acids, e.g. primers or probes
- C12Q1/6883—Nucleic acid products used in the analysis of nucleic acids, e.g. primers or probes for diseases caused by alterations of genetic material
- C12Q1/6886—Nucleic acid products used in the analysis of nucleic acids, e.g. primers or probes for diseases caused by alterations of genetic material for cancer
-
- 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
- G16B20/00—ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
- G16B20/50—Mutagenesis
-
- C—CHEMISTRY; METALLURGY
- C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
- C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
- C12Q2600/00—Oligonucleotides characterized by their use
- C12Q2600/106—Pharmacogenomics, i.e. genetic variability in individual responses to drugs and drug metabolism
-
- C—CHEMISTRY; METALLURGY
- C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
- C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
- C12Q2600/00—Oligonucleotides characterized by their use
- C12Q2600/156—Polymorphic or mutational markers
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Proteomics, Peptides & Aminoacids (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Organic Chemistry (AREA)
- Genetics & Genomics (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- Pathology (AREA)
- Wood Science & Technology (AREA)
- Immunology (AREA)
- Biotechnology (AREA)
- Biophysics (AREA)
- Public Health (AREA)
- Molecular Biology (AREA)
- Zoology (AREA)
- Epidemiology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Theoretical Computer Science (AREA)
- Hospice & Palliative Care (AREA)
- Primary Health Care (AREA)
- Oncology (AREA)
- Microbiology (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Biochemistry (AREA)
- General Engineering & Computer Science (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
The invention discloses a training method and a prediction device of a prediction model of non-small cell lung cancer immunotherapy curative effect, and relates to the technical field of biological medical treatment. According to the invention, the risk coefficient of the patient to immunotherapy is predicted by detecting KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3 and PBRM1 gene mutations of the tumor cells of the patient, so that the non-small cell lung cancer patient who possibly benefits from immunotherapy can be effectively screened out, and the patient can obtain a more appropriate and timely therapeutic scheme.
Description
Technical Field
The invention relates to the technical field of biological medical treatment, in particular to a training method and a prediction device of a prediction model of non-small cell lung cancer immunotherapy curative effect.
Background
Lung cancer is one of the most common malignancies in the world, with non-small cell lung cancer accounting for approximately 80% of all lung cancers. Most of the patients with non-small cell lung cancer are found to be in middle and advanced stages, the survival rate in 5 years is very low, the related treatment difficulty is large, the prognosis result is poor, and the non-small cell lung cancer is a middle and large chronic disease which troubles the patients. Smoking, chronic lung infection, long-term exposure, air pollution, genetic factors and the like are main inducing factors of the non-small cell lung cancer. Clinically, the common treatment methods for non-small cell lung cancer include: radiotherapy, chemotherapy, surgical treatment, immunotherapy, and the like.
Immune checkpoint inhibitors have revolutionized the therapeutic promise of various cancers, including non-small cell lung cancer. However, clinical application shows that only a part of patients respond to immunotherapy, thereby achieving a better therapeutic effect. Therefore, it is currently an important task to find potential methods to screen patients for potential benefit and immunotherapy.
In view of the above, the present invention is particularly proposed.
Disclosure of Invention
The invention aims to provide a training method and a prediction device of a prediction model of non-small cell lung cancer immunotherapy curative effect.
The invention is realized by the following steps:
in a first aspect, an embodiment of the present invention provides a training method for a prediction model of an immune therapeutic effect of non-small cell lung cancer, including: obtaining the detection results of the genetic mutations of training samples KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3 and PBRM1 and the corresponding labeling results; inputting the detection result of the gene mutation into a pre-constructed prediction model to obtain a prediction result; wherein the prediction model is used for predicting the curative effect of the immunotherapy of the non-small cell lung cancer of the sample according to the number of the KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3 and PBRM1 gene mutations; and updating parameters of the prediction model based on the labeling result and the prediction result.
In a second aspect, an embodiment of the present invention provides a device for predicting an efficacy of an immunotherapy for non-small cell lung cancer, which includes an obtaining module and a predicting module. The acquisition module is used for acquiring detection results of gene mutations of KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3 and PBRM1 of samples to be detected; and the prediction module is used for inputting the detection result of the gene mutation into the prediction model trained by the training method in the embodiment to obtain the prediction result of the sample to be tested.
In a third aspect, an embodiment of the present invention provides a training apparatus for non-small cell lung cancer immunotherapy curative effect, which includes an obtaining module, a predicting module, and a parameter updating module. The acquisition module is used for acquiring the detection results of the genetic mutations of the training samples KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3 and PBRM1 and the corresponding labeling results; the prediction module is used for inputting the detection result of the gene mutation into a pre-constructed prediction model to obtain a prediction result; wherein the prediction model is used for predicting the curative effect of the immunotherapy of the non-small cell lung cancer of the sample according to the number of the KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3 and PBRM1 gene mutations; and the parameter updating module is used for updating parameters of the prediction model according to the labeling result and the prediction result.
In a fourth aspect, an embodiment of the present invention provides an electronic device, including: a processor and a memory; the electronic device comprises a processor and a memory; the memory is used for storing a program which, when executed by the processor, causes the processor to implement a training method for a predictive model of non-small cell lung cancer immunotherapy efficacy or prediction of non-small cell lung cancer immunotherapy efficacy as described in the previous embodiments; the prediction of the curative effect of the non-small cell lung cancer immunotherapy comprises the following steps: inputting the results of the mutations of the KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3, and PBRM1 genes into the prediction model trained by the training method described in the foregoing embodiment, and obtaining the prediction result of the sample to be tested.
In a fifth aspect, the present invention provides a computer readable medium, on which a computer program is stored, the computer program, when executed by a processor, implements a training method for a prediction model of non-small cell lung cancer immunotherapy effectiveness or prediction of non-small cell lung cancer immunotherapy effectiveness according to the foregoing embodiments; the prediction of the curative effect of the non-small cell lung cancer immunotherapy comprises the following steps: inputting the results of the mutations of the KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3, and PBRM1 genes into the prediction model trained by the training method described in the foregoing embodiment, and obtaining the prediction result of the sample to be tested.
In a sixth aspect, embodiments of the present invention provide an agent for predicting the efficacy of immunotherapy for non-small cell lung cancer, comprising an agent for detecting mutations in KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3, and PBRM1 genes.
In a seventh aspect, the embodiments of the present invention provide a use of the reagent described in the previous embodiments in preparing a kit for predicting the curative effect of non-small cell lung cancer immunotherapy.
The invention has the following beneficial effects:
according to the invention, the risk coefficient of the patient on immunotherapy is predicted by detecting KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3 and PBRM1 gene mutations of the tumor cells of the patient, so that the non-small cell lung cancer patient possibly benefiting from the immunotherapy can be effectively screened, and the patient can obtain a more appropriate and timely treatment scheme.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
FIG. 1 is a LASSO regression analysis;
FIG. 2 is a LASSO coefficient distribution map of a candidate gene;
FIG. 3 is the correlation of hotspot genes with prognosis;
FIG. 4 is a graph of the survival times of the high risk group and the low risk group of the modeled samples;
FIG. 5 is a validation cohort patient survival time curve;
FIG. 6 is a validation cohort patient immunotherapy continuing benefit analysis;
FIG. 7 is a validation cohort tumor mutational burden;
FIG. 8 is a graph of example patient survival time;
FIG. 9 is a graph of the sustained benefit of immunotherapy in the patients of the example group.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below. The examples, in which specific conditions are not specified, were carried out according to conventional conditions or conditions recommended by the manufacturer. The reagents or instruments used are conventional products which are not indicated by manufacturers and are commercially available.
The embodiment of the invention provides a training method of a prediction model of non-small cell lung cancer immunotherapy curative effect, which comprises the following steps: obtaining the detection results of the genetic mutations of training samples KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3 and PBRM1 and the corresponding labeling results;
inputting the detection result of the gene mutation into a pre-constructed prediction model to obtain a prediction result; wherein the prediction model is used for predicting the curative effect of the immunotherapy of the sample non-small cell lung cancer according to the number of the KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3 and PBRM1 gene mutations;
and updating parameters of the prediction model based on the labeling result and the prediction result.
The gene is discovered from mutation data of a treatment queue of 330 patients with non-small cell lung cancer by a bioinformatics method. Screening candidate genes based on mutation data, setting screening parameters through Univariate Cox regression analysis, further screening the candidate genes, and finally performing LASSO regression analysis based on the genes to obtain a calculation formula of a prediction model.
The LASSO regression analysis is shown in FIG. 1, the LASSO coefficient distribution of candidate genes is shown in FIG. 2, and the correlation between the hot spot genes and prognosis is shown in FIG. 3.
In some embodiments, the genetic mutation comprises a mutation in a coding region. Mutations in the coding region may include mutations in one or more CDS or ORF, or mutations in the entire coding region. In other embodiments, the genetic mutation is a mutation that results in a change in the amino acid sequence of the encoded protein. Types of gene mutations include, but are not limited to, single-base mutations, multiple-base mutations, base deletions, base insertions, and the like, which have an effect on gene translation and protein expression.
The manner of obtaining the gene mutation is not limited at all as long as it is a manner capable of detecting the gene mutation, such as gene sequencing.
In some embodiments, the labeled result may be the corresponding immunotherapy effect of the training sample, such as: whether a therapeutic effect is obtained, and/or the degree of the therapeutic effect.
The embodiment of the invention also provides a device for predicting the curative effect of the non-small cell lung cancer immunotherapy, which comprises an acquisition module and a prediction module.
The acquisition module is used for acquiring detection results of gene mutations of KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3 and PBRM1 of samples to be detected;
and the prediction module is used for inputting the detection result of the gene mutation into the prediction model trained by the training method in any embodiment to obtain the prediction result of the sample to be tested.
In some embodiments, the genetic mutation comprises a mutation of a coding region. Mutations in the coding region may include mutations in one or more CDS or ORF, or mutations in the entire coding region. In some embodiments, the genetic mutation is a mutation that results in a change in the amino acid sequence of the encoded protein.
In some embodiments, the prediction model is calculated by the following formula and obtains a prediction result;
Risk Score=(a×KEAP1)+(b×PTPRD)+(c×EPHA3)+(d×EPHA5)+(e×ZFHX3)+(f×MGA)+(g×NTRK3)+(h×PBRM1);
wherein a is 0.2 to 0.6, b is-0.1 to-0.6, c is-0.2 to-0.6, d is-0.6 to-1.0, e is-1 to-1.4, f is-0.4 to-0.8, g is-0.5 to-0.9, and h is 0.8 to 1.2;
KEAP1 is a mutation parameter of KEAP1 gene, if the coding region of the KEAP1 gene has gene mutation, the KEAP1 is marked as 1, otherwise, the KEAP1 is marked as 0; the other genes are analogized in turn. The analogy specifically means that: PTPRD is a mutation parameter of the PTPRD gene, if the coding region of the PTPRD gene has gene mutation, the PTPRD is marked as 1, otherwise, the PTPRD is marked as 0; EPHA3 is the mutation parameter of EPHA3 gene, if the coding region of EPHA3 gene has gene mutation, EPHA3 is marked as 1, otherwise, it is marked as 0; EPHA5 is the mutation parameter of EPHA5 gene, if the coding region of EPHA5 gene has gene mutation, EPHA5 is marked as 1, otherwise, it is marked as 0; ZFHX3 is a mutation parameter of ZFHX3 gene, if the coding region of ZFHX3 gene has gene mutation, then ZFHX3 is marked as 1, otherwise, is marked as 0; MGA is mutation parameters of MGA gene, if gene mutation exists in coding region of MGA gene, MGA is marked as 1, otherwise, MGA is marked as 0; NTRK3 is mutation parameter of NTRK3 gene, if gene mutation exists in coding region of NTRK3 gene, then NTRK3 is marked as 1, otherwise, it is marked as 0; PBRM1 is the mutation parameter of PBRM1 gene, if there is gene mutation in the coding region of PBRM1 gene, PBRM1 is marked as 1, otherwise, it is marked as 0.
In some embodiments, in the Risk Score equation, a is 0.395, b is-0.384, c is-0.433, d is-0.827, e is-1.253, f is-0.584, g is-0.703, and h is 1.023.
In some embodiments, the predictive model further comprises determining the efficacy of the sample non-small cell lung cancer immunotherapy based on the Score of the Risk Score: if the Score value of the Risk Score is not less than the set threshold, judging that the immunotherapy curative effect of the sample is poor, and determining the sample as a high-Risk group; if the Score value of the Risk Score is less than the set threshold, judging that the immunotherapy curative effect of the sample is good and the sample is a low-Risk group;
in some embodiments, the set threshold is 0.5-0.7, and specifically may be any one or a range between any two of 0.5, 0.55, 0.6, 0.6496, and 0.7. In some embodiments, the test sample comprises a cancer cell sample of a patient with non-small cell lung cancer, or a biological tissue sample of a healthy person, which may be fresh or frozen, and may be obtained by means of surgery or puncture.
Preferably, the formula of the prediction model is: risk Score ═ 0.395 XKEAP 1 (+) (-0.384 XPTPRD) + (-0.433 XEPHA 3) + (-0.827 XEPHA 5) + (-1.253 XZFHX 3) + (-0.584 XMGA) + (-0.703 XNTRK 3) + (1.023 XPBRM 1). The threshold was set at 0.6496. The prediction effect of the model is verified by an ROC curve, and the AUC at 1years of the model is 0.653, and the AUC at 3years of the model is 0.662. Meanwhile, other prediction models are constructed based on the same treatment queue of the non-small cell lung cancer patients, but when the types of gene mutations contained in the prediction models are changed, the optimal prediction effect cannot be achieved. For example, the prediction model constructed after deleting the PBRM1 mutation has reduced prediction effect on the curative effect of immunotherapy at different periods (AUC at 2years ═ 0.621, AUC at 3years ═ 0.643).
The embodiment of the invention also provides a training device for the curative effect of the non-small cell lung cancer immunotherapy, which comprises an acquisition module, a prediction module and a parameter updating module.
The acquisition module is used for acquiring the detection results of the genetic mutations of the training samples KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3 and PBRM1 and the corresponding labeling results;
the prediction module is used for inputting the detection result of the gene mutation into a pre-constructed prediction model to obtain a prediction result; wherein the prediction model is used for predicting the curative effect of the immunotherapy of the sample non-small cell lung cancer according to the number of the KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3 and PBRM1 gene mutations;
and the parameter updating module is used for updating parameters of the prediction model according to the labeling result and the prediction result.
It is understood that the training device is adapted to implement the training method according to any of the foregoing embodiments, and specific technical means may be described with reference to any of the foregoing embodiments.
Alternatively, the modules described in any of the above embodiments may be stored in a memory in the form of software or Firmware (Firmware) or be fixed in an Operating System (OS) of the electronic device provided in the present application, and may be executed by a processor in the electronic device. Meanwhile, data, codes of programs, and the like required to execute the above modules may be stored in the memory.
An embodiment of the present invention further provides an electronic device, which includes: a processor and a memory; the electronic device comprises a processor and a memory; the memory is configured to store a program that, when executed by the processor, causes the processor to implement a training method of a predictive model of non-small cell lung cancer immunotherapy efficacy or prediction of non-small cell lung cancer immunotherapy efficacy as described in the foregoing embodiments. The prediction of the curative effect of the non-small cell lung cancer immunotherapy comprises the following steps: inputting the results of the mutations of the KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3, and PBRM1 genes into the prediction model trained by the training method as described in any of the foregoing embodiments, and obtaining the prediction result of the sample to be tested.
The electronic device may include a memory, a processor, a bus, and a communication interface, which are electrically connected to each other, directly or indirectly, to enable the transfer or interaction of data. For example, the components may be electrically connected to each other via one or more buses or signal lines.
The Memory may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Read Only Memory (EPROM), an electrically Erasable Read Only Memory (EEPROM), and the like.
The processor may be an integrated circuit chip having signal processing capabilities. The Processor 120 may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.
The electronic device may be a server, a cloud platform, a mobile phone, a tablet computer, a notebook computer, an ultra-mobile personal computer (UMPC), a handheld computer, a netbook, a Personal Digital Assistant (PDA), a wearable electronic device, a virtual reality device, or the like, and thus the embodiment of the present application does not limit the type of the electronic device.
Embodiments of the present invention further provide a computer-readable medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a training method for a prediction model of non-small cell lung cancer immunotherapy curative effect or prediction of non-small cell lung cancer immunotherapy curative effect according to the foregoing embodiments; the prediction of the curative effect of the non-small cell lung cancer immunotherapy comprises the following steps: inputting the results of the mutations of the KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3, and PBRM1 genes into the prediction model trained by the training method described in the foregoing embodiment, and obtaining the prediction result of the sample to be tested.
It is understood that the predictive models in the electronic device and the computer readable medium can be as described in any of the foregoing embodiments and will not be described in detail.
The computer readable medium may be a general storage medium such as a removable disk, a hard disk, etc.
The embodiment of the invention also provides a reagent for predicting the curative effect of non-small cell lung cancer immunotherapy, which comprises a reagent for detecting KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3 and PBRM1 gene mutation.
In some embodiments, the genetic mutation comprises a mutation in the coding region, and in particular may be a mutation that results in a change in the amino acid sequence of the encoded protein.
In some embodiments, the reagents comprise primers and/or probes.
In addition, the embodiment of the invention also provides application of the reagent described in any of the preceding embodiments in preparation of a kit for predicting the curative effect of the non-small cell lung cancer immunotherapy.
The features and properties of the present invention are described in further detail below with reference to examples.
Example 1
A method for predicting the efficacy of non-small cell lung cancer immunotherapy, comprising:
sequencing the genes of KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3 and PBRM1 to obtain the detection result of gene mutation; mutations of these genes include single base mutations, multiple base mutations, base deletions, base insertions, and the like, which have an effect on gene translation and protein expression.
Inputting the detection result into a prediction model to obtain a risk score; the calculation formula of the prediction model is as follows:
Risk Score=(0.395×KEAP1)+(-0.384×PTPRD)+(-0.433×EPHA3)+(-0.827×EPHA5)+(-1.253×ZFHX3)+(-0.584×MGA)+(-0.703×NTRK3)+(1.023×PBRM1);
in the formula, KEAP1 is a mutation parameter of KEAP1 gene, if there is gene mutation in the coding region of KEAP1 gene, KEAP1 is marked as 1, otherwise, it is marked as 0; the other genes are analogized in turn.
The predictive model also includes the determination of the efficacy of the sample non-small cell lung cancer immunotherapy based on the Risk Score: if the Score value of the Risk Score is not less than the set threshold, judging that the immunotherapy curative effect of the sample is poor, and determining the sample as a high-Risk group; if the Score value of the Risk Score is less than the set threshold, judging that the immunotherapy curative effect of the sample is good and the sample is a low-Risk group; the set threshold is 0.6496.
Example 2
The prediction model in example 1 was used to predict the therapeutic effects of 330 patients with non-small cell lung cancer, resulting in 53 patients in the high risk group and 277 patients in the low risk group. The survival analysis of the samples shows that there is a significant difference between the two groups, the survival time of the high risk group is significantly lower than that of the low risk group (as shown in figure 4), and P is less than 0.0001.
Clinical data of 240 patients who received immunotherapy in the sample was used as a validation cohort 1, and a prediction model was used to perform analysis, thereby obtaining 162 patients in a high risk group and 78 patients in a low risk group. There was a significant difference in the time to live analysis of both groups (as in figure 5), P < 0.0001. The proportion of patients with persistent clinical benefit (DCB) in the high risk group was 21.6%, and the proportion of patients with no persistent clinical benefit (NDB) was 78.4%; the proportion of patients with sustained clinical benefit was 48.6% in the low risk group and 51.4% in the patients with no sustained clinical benefit (see fig. 6). The proportion of patients who have clinically beneficial immunotherapy between the high-risk group and the low-risk group is significantly different, and P is less than 0.05. The predictive model was demonstrated to be effective in identifying patients who continued to benefit from immunotherapy.
Furthermore, the Tumor Mutation Burden (TMB) analysis results showed that the tumor mutation burden was significantly lower in the high risk group than in the low risk group, P<1.5e -15 (see fig. 7). According to the literature, the higher the tumor mutation load, the greater the patient's sustained benefit from immunotherapy [ Jianao, X., et al. (2021). NPJ Precis Oncol 5(1): 36).]The results are in agreement with the results of the examples.
Example 3
91 clinical samples were predicted using the prediction method provided in example 1.
91 non-small cell lung cancer patients were sampled by surgery, cancer cells were isolated, gene sequencing was performed to obtain gene sequencing results of KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3, and PBRM1 genes, and by analyzing parameters of mutation of these genes, Risk Score was calculated, and the patients were classified into high Risk group 64 persons and low Risk group 27 persons (see fig. 8) using Risk Score 0.6496 as a threshold.
There was a significant difference in the time to live analysis of the two groups (see fig. 8), P-0.00091. Both groups were analyzed for immunotherapy benefit with a high risk group with a 39.1% proportion of patients with persistent clinical benefit (DCB) and a 60.9% proportion of patients without persistent clinical benefit (NDB); the proportion of patients with sustained clinical benefit was 70.4% in the low risk group and 29.6% in the patients with no sustained clinical benefit (see fig. 9). The proportion of patients who have clinically beneficial immunotherapy between the high-risk group and the low-risk group is significantly different, and P is less than 0.05. The model described herein was demonstrated to be effective in identifying patients who would benefit from sustained immunotherapy.
Example 4
Non-small cell lung cancer-clinical immunotherapy has sustained benefitting (DCB) cases.
Example 3 samples from 65 year old male patients who had a previous history of smoking were taken and tumor samples were RNA sequenced by genes to obtain RNA sequencing results for the KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3 and PBRM1 genes, parameters of mutations in these genes were analyzed based on the prediction method of example 1, and Risk Score of-1.242 was calculated as a low Risk patient with sustained benefit of immunotherapy, who had a survival time of 9.37 years, which was significantly higher than the average survival time of 5.59 years.
Example 5
Non-small cell lung cancer-cases with no sustained benefit of clinical immunotherapy (NDB).
Example 4 samples from 71 year old male patients with prior smoking history were taken, tumor samples from these patients were RNA sequenced by gene RNA to obtain RNA sequencing results of KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3 and PBRM1 genes, parameters of mutations of these genes were analyzed based on the prediction method of example 1, Risk Score was calculated to be 1.418 for high Risk patients with no sustained benefit of immunotherapy, and survival time of the patients was 1.87 years, significantly lower than the average survival time of 5.59 years.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A training method of a prediction model of non-small cell lung cancer immunotherapy curative effect is characterized by comprising the following steps:
obtaining the detection results of the genetic mutations of training samples KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3 and PBRM1 and the corresponding labeling results;
inputting the detection result of the gene mutation into a pre-constructed prediction model to obtain a prediction result; wherein the prediction model is used for predicting the curative effect of the immunotherapy of the sample non-small cell lung cancer according to the number of the KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3 and PBRM1 gene mutations;
updating parameters of the prediction model based on the labeling result and the prediction result;
preferably, the genetic mutation comprises a mutation of a coding region;
preferably, the genetic mutation is a mutation resulting in a change in the amino acid sequence of the encoded protein.
2. A prediction device of the curative effect of non-small cell lung cancer immunotherapy is characterized by comprising the following components:
the acquisition module is used for acquiring detection results of gene mutations of KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3 and PBRM1 of samples to be detected;
the prediction module is used for inputting the detection result of the gene mutation into the prediction model trained by the training method according to claim 1 to obtain the prediction result of the sample to be tested.
3. The apparatus for predicting the efficacy of immunotherapy for non-small cell lung cancer according to claim 2, wherein said genetic mutation comprises a mutation of a coding region;
preferably, the gene mutation is a mutation resulting in a change in the amino acid sequence of the encoded protein;
preferably, the prediction model is calculated by the following formula and obtains a prediction result;
Risk Score=(a×KEAP1)+(b×PTPRD)+(c×EPHA3)+(d×EPHA5)+(e×ZFHX3)+(f×MGA)+(g×NTRK3)+(h×PBRM1);
wherein a is 0.2 to 0.6, b is-0.1 to-0.6, c is-0.2 to-0.6, d is-0.6 to-1.0, e is-1 to-1.4, f is-0.4 to-0.8, g is-0.5 to-0.9, and h is 0.8 to 1.2;
KEAP1 is a mutation parameter of KEAP1 gene, if the coding region of the KEAP1 gene has gene mutation, the KEAP1 is marked as 1, otherwise, the KEAP1 is marked as 0; the rest genes are analogized in turn;
preferably, in the Risk Score formula, a is 0.395, b is-0.384, c is-0.433, d is-0.827, e is-1.253, f is-0.584, g is-0.703, and h is 1.023.
4. The apparatus for predicting the efficacy of the NSCLC immunotherapy according to claim 3, wherein the prediction model further comprises a Risk Score-based Score for determining the efficacy of the NSCLC immunotherapy: if the Score value of the Risk Score is not less than the set threshold, judging that the immunotherapy curative effect of the sample is poor, and determining the sample as a high-Risk group; if the Score value of the Risk Score is less than the set threshold, judging that the immunotherapy curative effect of the sample is good and the sample is a low-Risk group;
preferably, the set threshold is 0.5-0.7, preferably 0.6496.
5. A training device for the curative effect of non-small cell lung cancer immunotherapy is characterized by comprising:
the acquisition module is used for acquiring the detection results of the genetic mutations of the training samples KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3 and PBRM1 and the corresponding labeling results;
the prediction module is used for inputting the detection result of the gene mutation into a pre-constructed prediction model to obtain a prediction result; wherein the prediction model is used for predicting the curative effect of the immunotherapy of the sample non-small cell lung cancer according to the number of the KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3 and PBRM1 gene mutations;
the parameter updating module is used for updating parameters of the prediction model according to the labeling result and the prediction result;
preferably, the genetic mutation comprises a mutation of a coding region;
preferably, the genetic mutation is a mutation resulting in a change in the amino acid sequence of the encoded protein.
6. An electronic device, comprising: a processor and a memory; the electronic device comprises a processor and a memory; the memory for storing a program that, when executed by the processor, causes the processor to implement a training method for the predictive model of non-small cell lung cancer immunotherapy efficacy of claim 1 or prediction of non-small cell lung cancer immunotherapy efficacy;
the prediction of the curative effect of the non-small cell lung cancer immunotherapy comprises the following steps: inputting the results of the mutation of the KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3, and PBRM1 genes into the prediction model trained by the training method as claimed in claim 1, and obtaining the prediction result of the sample to be tested.
7. The electronic device of claim 6, wherein the predictive model has the formula: risk Score ═ (a × KEAP1) + (b × PTPRD) + (c × EPHA3) + (d × EPHA5) + (e × ZFHX3) + (f × MGA) + (g × NTRK3) + (h × PBRM 1);
wherein a is 0.2 to 0.6, b is-0.1 to-0.6, c is-0.2 to-0.6, d is-0.6 to-1.0, e is-1 to-1.4, f is-0.4 to-0.8, g is-0.5 to-0.9, and h is 0.8 to 1.2;
KEAP1 is a mutation parameter of KEAP1 gene, if the coding region of the KEAP1 gene has gene mutation, the KEAP1 is marked as 1, otherwise, the KEAP1 is marked as 0; the rest genes are analogized in turn;
preferably, in the Risk Score formula, a is 0.395, b is-0.384, c is-0.433, d is-0.827, e is-1.253, f is-0.584, g is-0.703, h is 1.023;
preferably, the predictive model further comprises the step of judging the curative effect of the non-small cell lung cancer immunotherapy of the sample based on the Score of Risk Score: if the Score value of the Risk Score is not less than the set threshold, judging that the immunotherapy of the sample has poor curative effect and is a high-Risk group; if the Score value of the Risk Score is less than the set threshold, judging that the immunotherapy curative effect of the sample is good and the sample is a low-Risk group;
preferably, the set threshold is 0.5-0.7, preferably 0.6496.
8. A computer-readable medium, wherein a computer program is stored on the computer-readable medium, and when executed by a processor, the computer program implements a method for training the predictive model of non-small cell lung cancer immunotherapy efficacy or predicting non-small cell lung cancer immunotherapy efficacy according to claim 1;
the prediction of the curative effect of the non-small cell lung cancer immunotherapy comprises the following steps: inputting the results of the mutations of the KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3 and PBRM1 genes of the sample into a prediction model trained by the training method as claimed in claim 1, and obtaining the prediction result of the sample to be tested;
preferably, the formula of the prediction model is as follows: risk Score ═ (a × KEAP1) + (b × PTPRD) + (c × EPHA3) + (d × EPHA5) + (e × ZFHX3) + (f × MGA) + (g × NTRK3) + (h × PBRM 1);
wherein a is 0.2 to 0.6, b is-0.1 to-0.6, c is-0.2 to-0.6, d is-0.6 to-1.0, e is-1 to-1.4, f is-0.4 to-0.8, g is-0.5 to-0.9, and h is 0.8 to 1.2;
KEAP1 is a mutation parameter of KEAP1 gene, if the coding region of the KEAP1 gene has gene mutation, the KEAP1 is marked as 1, otherwise, the KEAP1 is marked as 0; the rest genes are analogized in turn;
preferably, in the Risk Score formula, a is 0.395, b is-0.384, c is-0.433, d is-0.827, e is-1.253, f is-0.584, g is-0.703, h is 1.023;
preferably, the predictive model further comprises the step of judging the curative effect of the non-small cell lung cancer immunotherapy of the sample based on the Score of Risk Score: if the Score value of the Risk Score is not less than the set threshold, judging that the immunotherapy curative effect of the sample is poor, and determining the sample as a high-Risk group; if the Score value of the Risk Score is less than the set threshold, judging that the immunotherapy curative effect of the sample is good and the sample is a low-Risk group;
preferably, the set threshold is 0.5-0.7, preferably 0.6496.
9. An agent for predicting the therapeutic effect of non-small cell lung cancer immunotherapy, which comprises an agent for detecting mutations in KEAP1, PTPRD, EPHA3, EPHA5, ZFHX3, MGA, NTRK3, and PBRM1 genes;
preferably, the genetic mutation comprises a mutation of a coding region;
preferably, the genetic mutation is a mutation resulting in a change in the amino acid sequence of the encoded protein.
10. Use of an agent according to claim 9 in the preparation of a kit for predicting the efficacy of an immunotherapy for non-small cell lung cancer.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210693286.0A CN114999653B (en) | 2022-06-17 | 2022-06-17 | Training method and prediction device of prediction model of non-small cell lung cancer immunotherapy curative effect |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210693286.0A CN114999653B (en) | 2022-06-17 | 2022-06-17 | Training method and prediction device of prediction model of non-small cell lung cancer immunotherapy curative effect |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114999653A true CN114999653A (en) | 2022-09-02 |
CN114999653B CN114999653B (en) | 2023-06-20 |
Family
ID=83035252
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210693286.0A Active CN114999653B (en) | 2022-06-17 | 2022-06-17 | Training method and prediction device of prediction model of non-small cell lung cancer immunotherapy curative effect |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114999653B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115620894A (en) * | 2022-09-20 | 2023-01-17 | 贵州医科大学第二附属医院 | Lung cancer immune curative effect prediction method and system based on gene mutation and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20210090694A1 (en) * | 2019-09-19 | 2021-03-25 | Tempus Labs | Data based cancer research and treatment systems and methods |
CN112813165A (en) * | 2021-02-03 | 2021-05-18 | 复旦大学附属金山医院(上海市金山区核化伤害应急救治中心、上海市金山区眼病防治所) | Lung squamous carcinoma prognosis prediction model and application thereof |
US20210207198A1 (en) * | 2020-01-06 | 2021-07-08 | Duke University | Biomarkers associated with checkpoint immune therapy and methods of using same |
CN113249483A (en) * | 2021-06-10 | 2021-08-13 | 北京泛生子基因科技有限公司 | Gene combination, system and application for detecting tumor mutation load |
CN113851185A (en) * | 2021-11-29 | 2021-12-28 | 求臻医学科技(北京)有限公司 | Prognosis evaluation method for immunotherapy of non-small cell lung cancer patient |
CN114242157A (en) * | 2021-12-28 | 2022-03-25 | 江苏先声医学诊断有限公司 | Predicting non-small cell lung cancer immunotherapy efficacy based on bGMS |
CN114512184A (en) * | 2021-10-11 | 2022-05-17 | 上海市胸科医院 | Method for predicting cancer curative effect and prognosis, device and application thereof |
-
2022
- 2022-06-17 CN CN202210693286.0A patent/CN114999653B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20210090694A1 (en) * | 2019-09-19 | 2021-03-25 | Tempus Labs | Data based cancer research and treatment systems and methods |
US20210207198A1 (en) * | 2020-01-06 | 2021-07-08 | Duke University | Biomarkers associated with checkpoint immune therapy and methods of using same |
CN112813165A (en) * | 2021-02-03 | 2021-05-18 | 复旦大学附属金山医院(上海市金山区核化伤害应急救治中心、上海市金山区眼病防治所) | Lung squamous carcinoma prognosis prediction model and application thereof |
CN113249483A (en) * | 2021-06-10 | 2021-08-13 | 北京泛生子基因科技有限公司 | Gene combination, system and application for detecting tumor mutation load |
CN114512184A (en) * | 2021-10-11 | 2022-05-17 | 上海市胸科医院 | Method for predicting cancer curative effect and prognosis, device and application thereof |
CN113851185A (en) * | 2021-11-29 | 2021-12-28 | 求臻医学科技(北京)有限公司 | Prognosis evaluation method for immunotherapy of non-small cell lung cancer patient |
CN114242157A (en) * | 2021-12-28 | 2022-03-25 | 江苏先声医学诊断有限公司 | Predicting non-small cell lung cancer immunotherapy efficacy based on bGMS |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115620894A (en) * | 2022-09-20 | 2023-01-17 | 贵州医科大学第二附属医院 | Lung cancer immune curative effect prediction method and system based on gene mutation and storage medium |
CN115620894B (en) * | 2022-09-20 | 2023-05-02 | 贵州医科大学第二附属医院 | Lung cancer immune curative effect prediction system, device and storage medium based on gene mutation |
Also Published As
Publication number | Publication date |
---|---|
CN114999653B (en) | 2023-06-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
AU2019229273B2 (en) | Ultra-sensitive detection of circulating tumor DNA through genome-wide integration | |
JP7506380B2 (en) | Residual disease detection system and method | |
JP2021058194A (en) | Methods and processes for non-invasive assessment of genetic variations | |
CN110958853B (en) | Methods and systems for identifying or monitoring lung disease | |
AU2020221845A1 (en) | An integrated machine-learning framework to estimate homologous recombination deficiency | |
JP2023504529A (en) | Systems and methods for automating RNA expression calls in cancer prediction pipelines | |
CN111933219B (en) | Detection method of molecular marker tumor deletion mutation load | |
CN113096728B (en) | Method, device, storage medium and equipment for detecting tiny residual focus | |
US20190018930A1 (en) | Method for building a database | |
WO2020191413A1 (en) | De novo compartment deconvolution and weight estimation of tumor tissue samples using decoder | |
JP7499239B2 (en) | Methods and systems for somatic mutations and uses thereof | |
JP2023540257A (en) | Validation of samples to classify cancer | |
Liu et al. | A comprehensive evaluation of computational tools to identify differential methylation regions using RRBS data | |
CA3123297A1 (en) | Fragment size characterization of cell-free dna mutations from clonal hematopoiesis | |
CN114999653B (en) | Training method and prediction device of prediction model of non-small cell lung cancer immunotherapy curative effect | |
JP2021101629A (en) | System and method for genome analysis and gene analysis | |
WO2017220782A1 (en) | Screening method for endometrial cancer | |
US11217329B1 (en) | Methods and systems for determining biological sample integrity | |
CN113053460A (en) | Systems and methods for genomic and genetic analysis | |
CN112458176B (en) | Kit for predicting postoperative survival time of lung squamous cell carcinoma patient and application of kit | |
EP3588506A1 (en) | Systems and methods for genomic and genetic analysis | |
CN113957148A (en) | Marker, kit and device for predicting susceptibility of colorectal cancer patient to immunotherapy | |
CN113710818A (en) | Virus-associated cancer risk stratification | |
Esim et al. | Determination of malignant melanoma by analysis of variation values | |
CN114134228A (en) | Kit, system and storage medium for evaluating PI3K/Art/mTOR pathway related gene mutation and application thereof |
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 |