Prediction marker of squamous cell carcinoma and construction and application of prediction model of prediction marker

Abstract

The invention discloses a prediction marker for squamous cell carcinoma and construction and application of a prediction model of the prediction marker, and relates to the field of tumor diagnosis. The invention finds that WNT5A can be used as a marker of any one or more of disease risk, prognosis risk, disease progress, treatment effect, residual focus and metastatic focus of squamous cell carcinoma, is beneficial to accurate diagnosis and treatment of squamous cell carcinoma, and accelerates the research and development of new drugs.

Description

Technical Field

[0001] The present invention relates to the field of tumor diagnosis, and in particular, to a prediction marker for pan-squamous cell carcinoma and the construction and application of a prediction model thereof. Background Art

[0002] Tumor diagnosis targets refer to specific molecular markers used for detecting and identifying tumors during clinical tumor diagnosis. These targets usually include gene mutations, metabolites, proteins, etc., which can accurately reflect the occurrence and development of tumors. With the progress of technology and the in-depth exploration of tumor multi-omics data, changes in the expression levels of multiple tumor-related proteins have provided strong support for early tumor detection and diagnosis. For example, CA125 is a glycoprotein that is often highly expressed in the serum of ovarian cancer patients and is widely used in the early screening, diagnosis, and post-treatment monitoring of clinical ovarian cancer; alpha-fetoprotein (AFP) is a common marker for hepatocellular carcinoma. In adults, AFP is usually very low, but it may be significantly elevated in primary liver cancer or germ cell tumors, and is clinically used for early screening of high-risk populations, diagnosis of liver cancer, and detection of treatment efficacy.

[0003] Squamous cell carcinoma is a malignant tumor originating from epithelial tissues and widely exists in various squamous epithelial tissues in the body, such as the skin, head and neck, respiratory tract, esophagus, and cervix. Squamous cell carcinoma has certain common characteristics. Regardless of its occurrence in which organ, it shows the following commonalities: (1) Epithelial origin: Squamous cell carcinoma originates from epithelial cells, especially keratinized squamous epithelium. These cells undergo lesions during differentiation, leading to the transformation of normal epithelial tissues into malignant tumors; (2) Invasiveness and metastasis: Squamous cell carcinoma usually has strong local invasiveness and can metastasize distantly through the blood and lymphatic systems; (3) Similar molecular characteristics: In most squamous cell carcinomas, mutations or dysfunctions of the p53 gene, high expression of EGFR, and activation of the Wnt / β-catenin pathway are common phenomena; (4) Similar clinical manifestations and diagnostic methods: Although the occurrence sites of squamous cell carcinoma are different, its early symptoms are usually hidden, and it is often in the middle and late stages when diagnosed. Common diagnostic methods include imaging examinations (such as CT, MRI, X-ray), endoscopic examinations, and biopsy histopathological examinations; (5) Common treatment methods: The treatment methods for squamous cell carcinoma include surgical resection, radiotherapy, chemotherapy, and targeted therapy. In the case of a small local tumor, surgical resection or radiotherapy is often the preferred treatment; for advanced or metastatic squamous cell carcinoma, chemotherapy and targeted therapy (such as EGFR inhibitors) can be used to control the progression of the disease. These commonalities make the research on pan-squamous cell carcinoma an important field.

[0004] Pan-squamous cell carcinoma has an insidious onset, lacks early symptoms, and is prone to recurrence and metastasis. Identifying unified markers can help improve the early diagnosis rate, accelerate the development of new drugs, and monitor recurrence and metastasis. Currently, clinically, several specific proteins, such as squamous cell carcinoma antigen (SCCA), p16, and TP53 mutant protein, are used as protein markers for the screening of squamous cell carcinoma. However, the specificity and sensitivity of these proteins are relatively low, and the diagnostic efficacy is not very ideal. There is a lack of specific protein markers related to the carcinogenesis of pan-squamous cell carcinoma.

[0005] In view of this, the present invention is specifically proposed. Summary of the Invention

[0006] The purpose of the present invention is to provide a prediction marker for pan-squamous cell carcinoma and the construction and application of its prediction model.

[0007] The present invention is implemented as follows:

[0008] In a first aspect, an embodiment of the present invention provides the use of a marker or a reagent for detecting the concentration or content of the marker in the preparation of a product for predicting pan-cancer, wherein the marker includes the WNT5A gene and / or the WNT5A protein, and the pan-cancer includes squamous cell carcinoma.

[0009] In a second aspect, an embodiment of the present invention provides a training method for a prediction model of pan-cancer, which includes: obtaining the detection results of the marker concentration or content in the training samples and their annotation results; wherein, the marker includes the WNT5A gene and / or the WNT5A protein, and the pan-cancer is the pan-cancer described in the foregoing embodiment; the annotation results include labels representing any one or more of the disease risk, prognosis risk, disease progression, treatment efficacy, residual lesions, and metastatic lesions of the sample for the pan-cancer; inputting the detection results of the training samples into a pre-constructed machine learning model to obtain a prediction result;

[0010] Updating the parameters of the machine learning model according to the prediction result and the annotation result to obtain a prediction model.

[0011] In a third aspect, an embodiment of the present invention provides a prediction device for pan-cancer, which includes:

[0012] An acquisition module for obtaining the detection results of the marker concentration or content in the sample to be tested; the marker includes the WNT5A gene and / or the WNT5A protein, and the pan-cancer is the pan-cancer described in the foregoing embodiment;

[0013] A prediction module for inputting the detection results of the sample to be tested into the prediction model trained by the training method described in the foregoing embodiment to obtain a prediction result.

[0014] Fourthly, an embodiment of the present invention provides an electronic device, which includes a processor and a memory. The memory is used to store a program. When the program is executed by the processor, the processor implements a prediction method for pan-cancer;

[0015] The prediction method includes: obtaining the detection result of the marker content in the sample to be tested; wherein, the marker includes the WNT5A gene and / or the WNT5A protein, and the pan-cancer is the pan-cancer described in the foregoing embodiments; inputting the detection result of the sample to be tested into the prediction model trained by the training method described in the foregoing embodiments to obtain a prediction result.

[0016] Fifthly, an embodiment of the present invention provides a computer-readable medium, on which a computer program is stored. When the computer program is executed by a processor, the prediction method described in the foregoing embodiments is implemented.

[0017] Sixthly, an embodiment of the present invention provides an application of a marker or a reagent for detecting the concentration or content of the marker in screening products for treating or adjuvant treating pan-cancer. The marker includes the WNT5A gene and / or the WNT5A protein, and the pan-cancer is the pan-cancer described in the foregoing embodiments.

[0018] The present invention has the following beneficial effects:

[0019] The present invention discovers that WNT5A can be used as a marker for any one or more of the disease risk, prognosis risk, disease progression, treatment efficacy, residual lesions, and metastatic lesions of pan-squamous cell carcinoma, which is beneficial to the accurate diagnosis and treatment of pan-squamous cell carcinoma and accelerates the research and development of new drugs. Description of the Drawings

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0021] Figure 1 WNT5A can be used as a molecular marker for predicting lung squamous cell carcinoma; wherein, A) in the TCGA-LUSC dataset, at the transcriptional level, WNT5A is significantly highly expressed in lung squamous cell carcinoma tissues; B) in the Shankha et.al. dataset, at the protein level, WNT5A is significantly highly expressed in lung squamous cell carcinoma tissues; C) in the TCGA-LUSC dataset, at the transcriptional level, the ROC curve of WNT5A for predicting lung squamous cell carcinoma and adjacent cancer samples; D) in the Shankha et.al. dataset, at the protein level, the ROC curve of WNT5A for predicting lung squamous cell carcinoma and adjacent cancer samples;

[0022] Figure 2 WNT5A can be used as a molecular marker for predicting esophageal squamous cell carcinoma; among them, A) Transcriptome data of Zhihua Liu et.al., WNT5A is significantly highly expressed in esophageal squamous cell carcinoma tissues; B) In the proteome data of Zhihua Liu et.al., WNT5A is significantly highly expressed in esophageal squamous cell carcinoma tissues; C) In the transcriptome data of Zhihua Liu et.al., the ROC curve of WNT5A for predicting esophageal squamous cell carcinoma and adjacent samples; D) In the proteome data of Zhihua Liu et.al., the ROC curve of WNT5A for predicting esophageal squamous cell carcinoma and adjacent samples;

[0023] Figure 3 It is the expression of WNT5A protein in esophageal squamous cell carcinoma tissue sections; among them, A) Using immunofluorescence method to detect the expression of WNT5A in different stages of tissue cancer in the same esophageal squamous cell carcinoma patient: normal - low - grade dysplasia - high - grade dysplasia; B) In the esophageal squamous cell carcinoma tissue microarray, using immunofluorescence method to detect the expression of WNT5A.

[0024] Figure 4 It is the expression of WNT5A protein in head and neck squamous cell carcinoma and adjacent tissue sections; among them, A) The expression of WNT5A in the first head and neck squamous cell carcinoma patient; B) The expression of WNT5A in the second head and neck squamous cell carcinoma patient; C) The expression of WNT5A in the third head and neck squamous cell carcinoma patient.

[0025] Figure 5 It is to detect the expression of WNT5A protein by immunofluorescence in esophageal squamous cell carcinoma tissue sections; among them, A) The first example found that WNT5A is hardly expressed in normal tissues, but is expressed in almost all tumor cells; B) The second example found that WNT5A is hardly expressed in normal tissues, but is expressed in almost all tumor cells; C) The third example found that WNT5A can detect tumor cells at the level of several cells or even single cells.

[0026] Figure 6 It is the ROC curve of WNT5A, KRT6 and SOX2 proteins for predicting squamous cell carcinoma and adjacent samples; among them, A) In the dataset of Shankha et.al., the ROC curve of WNT5A, KRT6 and SOX2 proteins for predicting lung squamous cell carcinoma and adjacent samples; B) In the dataset of Zhihua Liu et.al., the ROC curve of WNT5A, KRT6 and SOX2 proteins for predicting esophageal squamous cell carcinoma and adjacent samples. Specific implementation mode

[0027] To make the objectives, 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. For those not specified in the embodiments, they are carried out according to conventional conditions or conditions recommended by the manufacturer. For reagents or instruments not specified by the manufacturer, they are all conventional products that can be obtained through commercial purchase.

[0028] On the one hand, the embodiments of the present invention provide the use of a biomarker or a reagent for detecting the concentration or content of the biomarker in the preparation of a product for predicting pan-cancers, where the biomarker includes the WNT5A gene and / or the WNT5A protein, and the pan-cancers include squamous cell carcinoma.

[0029] In some embodiments, the pan-cancers include any one or more of esophageal squamous cell carcinoma, head and neck squamous cell carcinoma, lung squamous cell carcinoma, cutaneous squamous cell carcinoma, nasopharyngeal squamous cell carcinoma, vaginal squamous cell carcinoma, and cervical squamous cell carcinoma.

[0030] In some embodiments, the prediction of pan-cancers includes predicting any one or more of the disease risk, prognosis risk, disease progression, treatment efficacy, residual lesions, and metastatic lesions of the pan-cancer.

[0031] In some embodiments, the prediction of pan-cancers includes predicting pan-cancers at each stage, and each stage includes any one or more of the early stage, middle stage, and late stage.

[0032] The present application has no special limitation on the detection method of the WNT5A gene and / or the WNT5A protein, and the detection methods commonly used in the art for genes and / or proteins can be adopted.

[0033] In some embodiments, the product includes any one of a reagent, a chip, and a kit.

[0034] On the other hand, the embodiments of the present invention provide a method for training a prediction model for pan-cancers, which includes:

[0035] Obtaining the detection results of the concentration or content of the biomarker in the training samples and their annotation results; wherein, the biomarker includes the WNT5A gene and / or the WNT5A protein, and the pan-cancers are the pan-cancers described in any of the foregoing embodiments; the annotation results include labels representing any one or more of the disease risk, prognosis risk, disease progression, treatment efficacy, residual lesions, and metastatic lesions of the pan-cancer of the sample;

[0036] Inputting the detection results of the training samples into a pre-constructed machine learning model to obtain prediction results;

[0037] Updating the parameters of the machine learning model according to the prediction results and the annotation results to obtain a prediction model.

[0038] The present invention has no particular restrictions on the machine learning model, and any one or more prediction models commonly used in the art for the risk of disease, prognosis risk, disease progression, therapeutic efficacy, residual lesions, and metastatic lesions can be selected. In some embodiments, the machine learning model includes any one of a decision tree, a logistic regression model, a support vector machine, KNN, naive Bayes, and a random forest.

[0039] It is understandable that the categories and number of training samples can be routinely selected by those skilled in the art, and the total number of training samples and training samples of various categories (such as healthy people, patients) can be ≥ any value among 10, 50, 100, 200, 300, 400 and 500 or a range between any two of them.

[0040] In some implementations, the label may be a character or a string. The content of the prediction result corresponds to the content of the annotation result.

[0041] On the other hand, an embodiment of the present invention further provides a pan-cancer prediction device, which includes:

[0042] An acquisition module, used to obtain the detection result of the concentration or content of the marker in the sample to be tested; the marker includes the WNT5A gene and / or the WNT5A protein, and the pan-cancer species is the pan-cancer species described in any of the above embodiments;

[0043] The prediction module is used to input the detection result of the sample to be tested into the prediction model trained by the training method described in any of the above embodiments to obtain the prediction result.

[0044] The modules described in the embodiments of the present invention may be stored in a memory in the form of software or firmware or solidified in the operating system (OS) of the electronic device provided by the present application, and may be executed by a processor in the electronic device. At the same time, the data and program codes required to execute the above modules may be stored in the memory.

[0045] On the other hand, an embodiment of the present invention further provides an electronic device, comprising a processor and a memory, wherein the memory is used to store a program, and when the program is executed by the processor, the processor implements a pan-cancer prediction method;

[0046] The prediction method comprises:

[0047] Obtaining a detection result of a marker content in a sample to be tested; wherein the marker includes a WNT5A gene and / or a WNT5A protein, and the pan-cancer species is the pan-cancer species described in any of the foregoing embodiments;

[0048] Input the test result of the sample to be tested into the prediction model trained by the training method described in any of the foregoing embodiments to obtain a prediction result.

[0049] The electronic device may include a memory, a processor, a bus, and a communication interface. The memory, the processor, and the communication interface are electrically connected directly or indirectly to each other to achieve data transmission or interaction. For example, these components may be electrically connected to each other through one or more buses or signal lines.

[0050] 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 programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc.

[0051] The processor may be an integrated circuit chip with signal processing capabilities. The processor 120 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0052] The electronic device may be a server, a cloud platform, a mobile phone, a tablet computer, a laptop 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, etc. Therefore, the embodiments of the present application do not limit the types of electronic devices.

[0053] On the other hand, an embodiment of the present invention further provides a computer-readable medium, on which a computer program is stored, and when the computer program is executed by a processor, the prediction method described in any of the foregoing embodiments is implemented.

[0054] In some embodiments, the computer-readable medium may be a general storage medium, such as a removable disk, a hard disk, etc.

[0055] In addition, an embodiment of the present invention further provides an application of a biomarker or a reagent for detecting the concentration or content of the biomarker in screening products for treating or adjuvant treating pan-cancers, the biomarker includes the WNT5A gene and / or the WNT5A protein, and the pan-cancers are the pan-cancers described in any of the foregoing embodiments.

[0056] The features and performance of the present invention will be further described in detail below in conjunction with embodiments.

[0057] Example 1 WNT5A can be used as a molecular biomarker for predicting early-stage lung squamous cell carcinoma

[0058] Based on the transcriptome data of lung squamous cell carcinoma and adjacent normal tissues (TCGA-LUSC, N = 550, age: 39 - 90 years old; gender: female: 144, male: 406; sample type: primary tumor: 501, adjacent to cancer: 49), it was found that compared with adjacent tissues, the expression of WNT5A was significantly up-regulated in lung squamous cell carcinoma tissues ( Figure 1 A in

[0059] In all lung squamous cell carcinoma proteome data (Shankha et.al., N = 207, age: 40 - 88 years old; gender: female: 42, male 165; sample type: tumor: 108, adjacent to cancer: 99), it was further found that in early-stage lung squamous cell carcinoma tissues (stage I), the expression of WNT5A was significantly higher than that of adjacent tissues ( Figure 1 B in

[0060] Using the expression level of WNT5A mRNA to predict lung squamous cell carcinoma and adjacent samples, it was found that in the TCGA-LUSC dataset, its diagnostic efficacy was good (AUC = 0.743; Figure 1 C in Figure 1 Using the expression level of WNT5A protein as a biomarker for predicting lung squamous cell carcinoma and adjacent samples, it was found that in the Shankha et.al. dataset, its diagnostic efficacy was good (AUC = 0.845;

[0061] Example 2 WNT5A can be used as a molecular biomarker for predicting esophageal squamous cell carcinoma

[0062] In this example, all transcriptome data (Zhihua Liu et al., N = 310) and proteome data (Zhihua Liu et al., N = 188) of large-scale esophageal squamous cell carcinoma tissues were constructed. There were a total of 155 patients, including 103 males and 52 females, aged 41 - 80 years. The sample types were: 155 tumor samples and 155 adjacent cancer samples. Based on the analysis of transcriptome and proteome data, it was found that the expression of WNT5A was significantly increased in esophageal squamous cell carcinoma ( Figure 2 A - B in

[0063] Predicting squamous cell carcinoma of the lung and adjacent cancer samples with the expression level of WNT5A mRNA, it was found that in the Zhihua Liu et al. dataset, its diagnostic efficacy was good (AUC = 0.726; Figure 2 C in Figure 2 Predicting squamous cell carcinoma of the lung and adjacent cancer samples with the expression level of WNT5A protein, it was found that in the Zhihua Liu et al. dataset, its diagnostic efficacy was good (AUC = 0.770;

[0064] Example 3 Verification of the expression of WNT5A in pan - squamous cell carcinoma in clinical samples

[0065] A. In esophageal squamous cell carcinoma, the expression of WNT5A was significantly increased

[0066] Using the immunofluorescence method, this example detected the expression of WNT5A in esophageal squamous cell carcinoma tissues and found that in different stages of tissue cancer in the same esophageal squamous cell carcinoma patient: normal - low - grade dysplasia - high - grade dysplasia, the expression of WNT5A gradually increased ( Figure 3 A in Figure 3 Using esophageal squamous cell carcinoma tissue microarray and the immunofluorescence method, it was found that the expression of WNT5A in esophageal squamous cell carcinoma tissues was significantly higher than that in adjacent tissues (

[0067] B. In head and neck squamous cell carcinoma, the expression of WNT5A was significantly increased

[0068] Using the immunofluorescence method, it was found that in head and neck squamous cell carcinoma tissues, the expression of WNT5A was significantly higher than that in adjacent tissues ( Figure 4 A - C in

[0069] Example 4 WNT5A can detect residual tumor cells after treatment

[0070] Through immunofluorescence detection, it was found that WNT5A was hardly expressed in normal tissues, but was expressed in almost all tumor cells ( Figure 1 B in Figure 5), It can be seen that WNT5A can detect tumor cells at the level of several cells or even a single cell, which provides support for the subsequent development of targeting WNT5A to monitor the residual lesions after the treatment of esophageal squamous cell carcinoma.

[0071] Compared with the existing pan-squamous cell carcinoma markers SOX2 and KRT6B proteins, WNT5A protein has advantages in the diagnosis of lung squamous cell carcinoma and esophageal squamous cell carcinoma, and the AUC can be increased by 7-10 percentage points ( Figure 6 ).

[0072] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. Use of a marker or a reagent for detecting the concentration or content of the marker in the preparation of a product for predicting pan-cancer species, characterized in that: The markers include WNT5A gene and / or WNT5A protein, and the pan-cancer types include squamous cell carcinoma.

2. The use according to claim 1, characterized in that: The pan-cancer types include: any one or more of esophageal squamous cell carcinoma, head and neck squamous cell carcinoma, lung squamous cell carcinoma, skin squamous cell carcinoma, nasopharyngeal squamous cell carcinoma, vaginal squamous cell carcinoma and cervical squamous cell carcinoma.

3. The use according to claim 1, characterized in that: The predicting of pan-cancer includes: predicting any one or more of the risk of disease, prognosis risk, disease progression, treatment efficacy, residual lesions and metastatic lesions of the pan-cancer; Optionally, the predicting pan-cancer includes predicting pan-cancer types at various stages, and the various stages include any one or more of early, middle and late stages.

4. The use according to any one of claims 1 to 3, characterized in that: The product includes: any one of a reagent, a chip and a kit.

5. A method for training a pan-cancer prediction model, characterized in that: It includes: Obtaining the detection results of the concentration or content of the marker in the training sample and the annotation results thereof; wherein the marker includes the WNT5A gene and / or the WNT5A protein, and the pan-cancer species is the pan-cancer species described in claim 1 or 2; the annotation results include any one or more labels representing the risk of disease, prognosis risk, disease progression, treatment efficacy, residual lesions and metastatic lesions of the pan-cancer species in the sample; Inputting the detection results of the training samples into a pre-built machine learning model to obtain prediction results; The parameters of the machine learning model are updated according to the prediction results and the annotation results to obtain a prediction model.

6. The training method according to claim 5, characterized in that: The machine learning model includes any one of a decision tree, a logistic regression model, a support vector machine, KNN, naive Bayes and a random forest.

7. A pan-cancer prediction device, characterized in that: It includes: An acquisition module, used to obtain the detection result of the concentration or content of the marker in the sample to be tested; the marker includes the WNT5A gene and / or the WNT5A protein, and the pan-cancer species is the pan-cancer species described in claim 1 or 2; The prediction module is used to input the detection result of the sample to be tested into the prediction model trained by the training method described in claim 5 or 6 to obtain the prediction result.

8. An electronic device, characterized in that: It includes a processor and a memory, wherein the memory is used to store a program, and when the program is executed by the processor, the processor implements a pan-cancer prediction method; The prediction method comprises: Obtaining the detection result of the marker content in the sample to be tested; wherein the marker includes the WNT5A gene and / or the WNT5A protein, and the pan-cancer species is the pan-cancer species described in claim 1 or 2; The test result of the sample to be tested is input into the prediction model trained by the training method described in claim 5 or 6 to obtain the prediction result.

9. A computer-readable medium, characterized in that The computer readable medium stores a computer program, and when the computer program is executed by a processor, the prediction method described in claim 8 is implemented.

10. Use of a marker or a reagent for detecting the concentration or content of the marker in screening products for treatment or adjuvant treatment of pan-cancer species, characterized in that: The markers include WNT5A gene and / or WNT5A protein, and the pan-cancer species is the pan-cancer species described in claim 1 or 2.

Images