Application of blood extracellular vesicle miRNA panel as biomarker in early diagnosis of lung cancer

Abstract

The present invention discloses blood small extracellular vesicles hsa-let-7d-3p, hsa-let-7e-5p, hsa-let-7f-5p, hsa-miR-379-5p, hsa-miR-98-5p, hsa-miR-100-5p, hsa-miR-126-3p, hsa-miR-21-5p, hsa-miR-140-5p, hsa-miR-1908-5p, hsa-miR-328-3p, hsa-miR-486-5p and hsa-miR-99b-5p, which can be used as biomarkers for early diagnosis of lung cancer. The blood small extracellular vesicle miRNA of the present invention can distinguish early lung cancer patients from non-cancer subjects, especially people at high risk of lung cancer and patients with positive lung nodules. The blood small extracellular vesicle miRNA of the present invention has better sensitivity and specificity, higher diagnostic specificity and fewer false positives.

Description

Technical Field

[0001] The present invention belongs to the field of biomedicine. Specifically, the present invention relates to the early diagnosis of lung cancer, and more particularly to the use of blood extracellular vesicle miRNA as a biomarker in differentiating early-stage lung cancer patients from high-risk groups and patients with positive lung nodules. Background Art

[0002] Lung cancer is known as the world's "number one cancer killer" due to its high incidence and mortality rates. In the past 20 years, the 5-year survival rate of lung cancer in China was only 19.7%, far lower than other tumors such as breast cancer (82.0%) and prostate cancer (66.4%). It is currently believed that the key factor affecting the 5-year survival rate of lung cancer is negatively correlated with the clinical stage at the time of diagnosis. Existing studies have confirmed that if lung cancer is discovered in the early stages, its 5-year survival rate can be close to 60%. In the late stages, it is only 5% to 6%. At the same time, the 5-year survival rate of "early-stage" lung cancer <1cm can reach 92%. However, the early diagnosis rate of lung cancer in China is only 19%. Timely lung cancer screening, especially screening among high-risk groups for lung cancer, can effectively improve the early diagnosis rate of lung cancer in clinical practice.

[0003] Currently, lung cancer screening guidelines and consensus published worldwide recommend low-dose spiral CT (LDCT) as a screening method. This technology is simple, easy to use, highly sensitive, and highly engaging for patients, but it is not perfect. LDCT carries three main potential risks. First, a high false-positive rate. In the LDCT arm of the National Lung Screening Trial (NLST), the false-positive rate was 96.4%, with most positive results resolving upon follow-up imaging. Second, radiation hazards. Although the average radiation dose of LDCT is 0.61–1.50 mSv, far lower than the 7–8 mSv of conventional chest CT, it is estimated that 1 in every 108 lung cancers detected through screening is radiation-induced. Third, overdiagnosis and overtreatment. For slow-growing or non-progressive lung cancers (indolent) that appear as subsolid adenocarcinomas on imaging, overdiagnosis may occur, leading to unnecessary overtreatment, including surgical trauma and psychological stress, which can impact patients' quality of life. Therefore, there is an urgent need to develop highly specific and sensitive tumor markers to assist in the early screening and diagnosis of lung cancer. Summary of the Invention

[0004] The purpose of this invention is to discover and verify high-efficiency blood small extracellular vesicle miRNA biomarkers and establish a high-efficiency diagnostic model, so as to improve the accuracy of early diagnosis of lung cancer in my country, reduce the false positive rate of lung cancer diagnosis, reduce the phenomenon of over-medicalization, alleviate the additional suffering of patients, and prolong the survival time of lung cancer patients.

[0005] To this end, the present invention provides a biomarker that can be used clinically as a biomarker for early diagnosis of lung cancer, especially for distinguishing early lung cancer patients from high-risk groups and patients with positive lung nodules.

[0006] The present invention also provides a chip and a kit that can be used for early diagnosis of lung cancer, especially for distinguishing early lung cancer patients from high-risk groups and patients with positive lung nodules.

[0007] The present invention also provides a method for using the biomarker for early diagnosis of lung cancer, in particular for distinguishing early lung cancer patients from high-risk groups and patients with positive lung nodules.

[0008] In a first aspect, the present invention provides use of blood extracellular vesicle miRNA in preparing a chip, a detection reagent or a detection kit for early diagnosis of lung cancer.

[0009] In a specific embodiment, the blood extracellular vesicle miRNA is:

[0010] (i) a miRNA having a sequence as shown in SEQ ID NO: 1, a miRNA having a sequence as shown in SEQ ID NO: 2, a miRNA having a sequence as shown in SEQ ID NO: 3, a miRNA having a sequence as shown in SEQ ID NO: 4, a miRNA having a sequence as shown in SEQ ID NO: 5, a miRNA having a sequence as shown in SEQ ID NO: 6, a miRNA having a sequence as shown in SEQ ID NO: 7, and / or a miRNA having a sequence as shown in SEQ ID NO: 8, a miRNA having a sequence as shown in SEQ ID NO: 9, a miRNA having a sequence as shown in SEQ ID NO: 10, a miRNA having a sequence as shown in SEQ ID NO: 11, a miRNA having a sequence as shown in SEQ ID NO: 12, and / or a miRNA having a sequence as shown in SEQ ID NO: 13; or

[0011] (ii) a miRNA that is complementary to the miRNA sequence described in (i).

[0012] In a preferred embodiment, the blood extracellular vesicle miRNA is:

[0013] (i) a combination of a miRNA with a sequence as shown in SEQ ID NO: 1, a miRNA with a sequence as shown in SEQ ID NO: 2, a miRNA with a sequence as shown in SEQ ID NO: 3, a miRNA with a sequence as shown in SEQ ID NO: 4, a miRNA with a sequence as shown in SEQ ID NO: 5, a miRNA with a sequence as shown in SEQ ID NO: 6, a miRNA with a sequence as shown in SEQ ID NO: 7, and / or a miRNA with a sequence as shown in SEQ ID NO: 8, a miRNA with a sequence as shown in SEQ ID NO: 9, a miRNA with a sequence as shown in SEQ ID NO: 10, a miRNA with a sequence as shown in SEQ ID NO: 11, a miRNA with a sequence as shown in SEQ ID NO: 12, and a miRNA with a sequence as shown in SEQ ID NO: 13.

[0014] In a preferred embodiment, the miRNA is isolated from human.

[0015] In a preferred embodiment, the early diagnosis of lung cancer is to distinguish patients with early-stage lung cancer from non-cancer subjects.

[0016] In a preferred embodiment, the non-cancer subjects are people at high risk of lung cancer and patients with positive lung nodules.

[0017] In a second aspect, the present invention provides a miRNA chip, comprising:

[0018] a solid support; and

[0019] Oligonucleotide probes are sequentially fixed on the solid support, wherein the oligonucleotide probes specifically bind to miRNA;

[0020] Wherein, the miRNA is:

[0021] (i) a miRNA having a sequence as shown in SEQ ID NO: 1, a miRNA having a sequence as shown in SEQ ID NO: 2, a miRNA having a sequence as shown in SEQ ID NO: 3, a miRNA having a sequence as shown in SEQ ID NO: 4, a miRNA having a sequence as shown in SEQ ID NO: 5, a miRNA having a sequence as shown in SEQ ID NO: 6, a miRNA having a sequence as shown in SEQ ID NO: 7, and / or a miRNA having a sequence as shown in SEQ ID NO: 8, a miRNA having a sequence as shown in SEQ ID NO: 9, a miRNA having a sequence as shown in SEQ ID NO: 10, a miRNA having a sequence as shown in SEQ ID NO: 11, a miRNA having a sequence as shown in SEQ ID NO: 12, and / or a miRNA having a sequence as shown in SEQ ID NO: 13; or

[0022] (ii) a miRNA that is complementary to the miRNA sequence described in (i).

[0023] In a preferred embodiment, the blood extracellular vesicle miRNA is:

[0024] (i) a combination of a miRNA having a sequence as shown in SEQ ID NO: 1, a miRNA having a sequence as shown in SEQ ID NO: 2, a miRNA having a sequence as shown in SEQ ID NO: 3, a miRNA having a sequence as shown in SEQ ID NO: 4, a miRNA having a sequence as shown in SEQ ID NO: 5, a miRNA having a sequence as shown in SEQ ID NO: 6, a miRNA having a sequence as shown in SEQ ID NO: 7, and / or a miRNA having a sequence as shown in SEQ ID NO: 8, a miRNA having a sequence as shown in SEQ ID NO: 9, a miRNA having a sequence as shown in SEQ ID NO: 10, a miRNA having a sequence as shown in SEQ ID NO: 11, a miRNA having a sequence as shown in SEQ ID NO: 12, and a miRNA having a sequence as shown in SEQ ID NO: 13.

[0025] In a preferred embodiment, the oligonucleotide probe comprises:

[0026] complementary binding region; and / or

[0027] A linker region connected to a solid support.

[0028] In a preferred embodiment, the miRNA chip is used for early diagnosis of lung cancer.

[0029] In a preferred embodiment, the early diagnosis of lung cancer is to distinguish patients with early-stage lung cancer from non-cancer subjects.

[0030] In a preferred embodiment, the non-cancer subjects are people at high risk of lung cancer and patients with positive lung nodules.

[0031] In a preferred embodiment, the miRNA is isolated from human.

[0032] In a preferred embodiment, the miRNA is blood extracellular vesicle miRNA.

[0033] In a third aspect, the present invention provides a use of the miRNA chip described in the second aspect for preparing a kit for early diagnosis of lung cancer.

[0034] In a preferred embodiment, the early diagnosis of lung cancer is to distinguish patients with early-stage lung cancer from non-cancer subjects.

[0035] In a preferred embodiment, the non-cancer subjects are people at high risk of lung cancer and patients with positive lung nodules.

[0036] In a fourth aspect, the present invention provides a detection kit comprising a detection reagent for detecting miRNA;

[0037] Wherein, the miRNA is:

[0038] (i) a miRNA having a sequence as shown in SEQ ID NO: 1, a miRNA having a sequence as shown in SEQ ID NO: 2, a miRNA having a sequence as shown in SEQ ID NO: 3, a miRNA having a sequence as shown in SEQ ID NO: 4, a miRNA having a sequence as shown in SEQ ID NO: 5, a miRNA having a sequence as shown in SEQ ID NO: 6, a miRNA having a sequence as shown in SEQ ID NO: 7, and / or a miRNA having a sequence as shown in SEQ ID NO: 8, a miRNA having a sequence as shown in SEQ ID NO: 9, a miRNA having a sequence as shown in SEQ ID NO: 10, a miRNA having a sequence as shown in SEQ ID NO: 11, a miRNA having a sequence as shown in SEQ ID NO: 12, and / or a miRNA having a sequence as shown in SEQ ID NO: 13; or

[0039] (ii) a miRNA complementary to the miRNA sequence described in (i)

[0040] Alternatively, the detection kit is equipped with the miRNA chip described in the second aspect.

[0041] In a preferred embodiment, the blood extracellular vesicle miRNA is:

[0042] (i) a combination of a miRNA having a sequence as shown in SEQ ID NO: 1, a miRNA having a sequence as shown in SEQ ID NO: 2, a miRNA having a sequence as shown in SEQ ID NO: 3, a miRNA having a sequence as shown in SEQ ID NO: 4, a miRNA having a sequence as shown in SEQ ID NO: 5, a miRNA having a sequence as shown in SEQ ID NO: 6, a miRNA having a sequence as shown in SEQ ID NO: 7, and / or a miRNA having a sequence as shown in SEQ ID NO: 8, a miRNA having a sequence as shown in SEQ ID NO: 9, a miRNA having a sequence as shown in SEQ ID NO: 10, a miRNA having a sequence as shown in SEQ ID NO: 11, a miRNA having a sequence as shown in SEQ ID NO: 12, and a miRNA having a sequence as shown in SEQ ID NO: 13.

[0043] In a preferred embodiment, the detection kit is used for early diagnosis of lung cancer.

[0044] In a preferred embodiment, the early diagnosis of lung cancer is to distinguish patients with early-stage lung cancer from non-cancer subjects.

[0045] In a preferred embodiment, the non-cancer subjects are people at high risk of lung cancer and patients with positive lung nodules.

[0046] In a preferred embodiment, the miRNA is isolated from human.

[0047] In a preferred embodiment, the miRNA is blood extracellular vesicle miRNA.

[0048] In a fifth aspect, the present invention provides a miRNA isolated from extracellular vesicles of blood for early diagnosis of lung cancer;

[0049] Wherein, the miRNA is:

[0050] (i) a miRNA having a sequence as shown in SEQ ID NO: 1, a miRNA having a sequence as shown in SEQ ID NO: 2, a miRNA having a sequence as shown in SEQ ID NO: 3, a miRNA having a sequence as shown in SEQ ID NO: 4, a miRNA having a sequence as shown in SEQ ID NO: 5, a miRNA having a sequence as shown in SEQ ID NO: 6, a miRNA having a sequence as shown in SEQ ID NO: 7, and / or a miRNA having a sequence as shown in SEQ ID NO: 8, a miRNA having a sequence as shown in SEQ ID NO: 9, a miRNA having a sequence as shown in SEQ ID NO: 10, a miRNA having a sequence as shown in SEQ ID NO: 11, a miRNA having a sequence as shown in SEQ ID NO: 12, and / or a miRNA having a sequence as shown in SEQ ID NO: 13; or

[0051] (ii) a miRNA that is complementary to the miRNA sequence described in (i).

[0052] In a preferred embodiment, the blood extracellular vesicle miRNA is:

[0053] (i) a combination of a miRNA having a sequence as shown in SEQ ID NO: 1, a miRNA having a sequence as shown in SEQ ID NO: 2, a miRNA having a sequence as shown in SEQ ID NO: 3, a miRNA having a sequence as shown in SEQ ID NO: 4, a miRNA having a sequence as shown in SEQ ID NO: 5, a miRNA having a sequence as shown in SEQ ID NO: 6, a miRNA having a sequence as shown in SEQ ID NO: 7, and / or a miRNA having a sequence as shown in SEQ ID NO: 8, a miRNA having a sequence as shown in SEQ ID NO: 9, a miRNA having a sequence as shown in SEQ ID NO: 10, a miRNA having a sequence as shown in SEQ ID NO: 11, a miRNA having a sequence as shown in SEQ ID NO: 12, and a miRNA having a sequence as shown in SEQ ID NO: 13.

[0054] In a preferred embodiment, the miRNA is isolated from human.

[0055] In a preferred embodiment, the miRNA is blood extracellular vesicle miRNA.

[0056] In a preferred embodiment, the early diagnosis of lung cancer is between early stage lung cancer patients and non-cancer subjects.

[0057] In a preferred embodiment, the non-cancer subjects are people at high risk of lung cancer and patients with positive lung nodules.

[0058] In a sixth aspect, the present invention provides an isolated or artificially constructed precursor miRNA, which can be cleaved and expressed in human cells into the miRNA described in the fifth aspect.

[0059] In a seventh aspect, the present invention provides an isolated polynucleotide, which can be transcribed into a precursor miRNA by a human cell, and the precursor miRNA can be cleaved and expressed into the miRNA of the fifth aspect in a human cell.

[0060] In a preferred embodiment, the polynucleotide has a structure shown in Formula I:

[0061] Seq 正向 -X-Seq 反向 Formula I

[0062] In Formula I,

[0063] Seq 正向 A nucleotide sequence that can be expressed as the miRNA in human cells;

[0064] Seq 反向 is a nucleotide sequence that is substantially complementary or completely complementary to Seq in the forward direction;

[0065] X is located in Seq 正向 and Seq 反向 The spacer sequence between the two sequences is the same as Seq 正向 and Seq 反向 Not complementary;

[0066] After the structure shown in Formula I is introduced into human cells, it forms the secondary structure shown in Formula II:

[0067]

[0068] In Formula II, Seq 正向 、Seq 反向 and X is defined as above,

[0069] || means in Seq 正向 and Seq 反向 The base pairing relationship formed between them.

[0070] In an eighth aspect, the present invention provides a vector comprising the miRNA described in the fifth aspect or the polynucleotide described in the seventh aspect.

[0071] In a ninth aspect, the present invention provides a method for early diagnosis of lung cancer, comprising the steps of:

[0072] (a) detecting the expression level of miRNA in a sample of a subject to be tested;

[0073] (b) inputting the miRNA expression value obtained in step (a) into the risk scoring model to obtain the probability that the subject is a lung cancer patient, a high-risk group for lung cancer, or a patient with positive lung nodules;

[0074] (c) providing a prediction result that the subject suffers from lung cancer based on the probability obtained in step (b);

[0075] Wherein, the miRNA is:

[0076] (i) a miRNA having a sequence as shown in SEQ ID NO: 1, a miRNA having a sequence as shown in SEQ ID NO: 2, a miRNA having a sequence as shown in SEQ ID NO: 3, a miRNA having a sequence as shown in SEQ ID NO: 4, a miRNA having a sequence as shown in SEQ ID NO: 5, a miRNA having a sequence as shown in SEQ ID NO: 6, a miRNA having a sequence as shown in SEQ ID NO: 7, and / or a miRNA having a sequence as shown in SEQ ID NO: 8, a miRNA having a sequence as shown in SEQ ID NO: 9, a miRNA having a sequence as shown in SEQ ID NO: 10, a miRNA having a sequence as shown in SEQ ID NO: 11, a miRNA having a sequence as shown in SEQ ID NO: 12, and / or a miRNA having a sequence as shown in SEQ ID NO: 13; or

[0077] (ii) a miRNA that is complementary to the miRNA sequence described in (i).

[0078] In a preferred embodiment, the sample is a peripheral blood sample.

[0079] In a preferred embodiment, the blood extracellular vesicle miRNA is:

[0080] (i) a combination of a miRNA having a sequence as shown in SEQ ID NO: 1, a miRNA having a sequence as shown in SEQ ID NO: 2, a miRNA having a sequence as shown in SEQ ID NO: 3, a miRNA having a sequence as shown in SEQ ID NO: 4, a miRNA having a sequence as shown in SEQ ID NO: 5, a miRNA having a sequence as shown in SEQ ID NO: 6, a miRNA having a sequence as shown in SEQ ID NO: 7, and / or a miRNA having a sequence as shown in SEQ ID NO: 8, a miRNA having a sequence as shown in SEQ ID NO: 9, a miRNA having a sequence as shown in SEQ ID NO: 10, a miRNA having a sequence as shown in SEQ ID NO: 11, a miRNA having a sequence as shown in SEQ ID NO: 12, and a miRNA having a sequence as shown in SEQ ID NO: 13.

[0081] In a preferred embodiment, the miRNA is isolated from human.

[0082] In a preferred embodiment, the miRNA is blood extracellular vesicle miRNA.

[0083] In a preferred embodiment, the model formula of the risk prediction model in step (b) is as follows:

[0084]

[0085] Among them, x i represents the marker expression level of sample i, P(x i ) is the probability of the corresponding classification of sample i predicted by the diagnostic model, where 0 indicates non-cancerous (high-risk lung cancer and positive lung nodules) and 1 indicates lung cancer. The classification with the highest probability is taken as the final prediction result for sample i.

[0086] In a preferred embodiment, the risk prediction model is constructed using a machine learning algorithm; preferably, the machine learning algorithm is a linear model (LinearModel), random forest (random forest), extreme randomized trees (extremely randomized trees), neural network (neural network), gradient boosting machine (GBM) and ensemble model (Ensemble methods).

[0087] In a preferred embodiment, the method has a sensitivity > 80% and a specificity > 78%.

[0088] In a preferred embodiment, the early diagnosis of lung cancer is to distinguish patients with early-stage lung cancer from non-cancer subjects.

[0089] In a preferred embodiment, the non-cancer subjects are people at high risk of lung cancer and patients with positive lung nodules.

[0090] In a tenth aspect, the present invention provides an early diagnosis device for lung cancer, wherein the device comprises a storage device storing instructions for executing the method for early diagnosis of lung cancer according to the ninth aspect.

[0091] In a preferred embodiment, the apparatus comprises the following means:

[0092] (a) a detection device for detecting the expression level of miRNA in a sample of a subject to be tested;

[0093] (b) a computing device, wherein the computing device inputs the miRNA expression value obtained by the device (a) into a risk scoring model to obtain a probability that the subject is a lung cancer patient, a high-risk group for lung cancer, or a patient with positive lung nodules; and

[0094] (c) an output device, which outputs a prediction result that the subject suffers from lung cancer based on the probability obtained by device (b);

[0095] Wherein, the miRNA is:

[0096] (i) a miRNA having a sequence as shown in SEQ ID NO: 1, a miRNA having a sequence as shown in SEQ ID NO: 2, a miRNA having a sequence as shown in SEQ ID NO: 3, a miRNA having a sequence as shown in SEQ ID NO: 4, a miRNA having a sequence as shown in SEQ ID NO: 5, a miRNA having a sequence as shown in SEQ ID NO: 6, a miRNA having a sequence as shown in SEQ ID NO: 7, and / or a miRNA having a sequence as shown in SEQ ID NO: 8, a miRNA having a sequence as shown in SEQ ID NO: 9, a miRNA having a sequence as shown in SEQ ID NO: 10, a miRNA having a sequence as shown in SEQ ID NO: 11, a miRNA having a sequence as shown in SEQ ID NO: 12, and / or a miRNA having a sequence as shown in SEQ ID NO: 13; or

[0097] (ii) a miRNA that is complementary to the miRNA sequence described in (i).

[0098] In a preferred embodiment, the blood extracellular vesicle miRNA is:

[0099] (i) a combination of a miRNA having a sequence as shown in SEQ ID NO: 1, a miRNA having a sequence as shown in SEQ ID NO: 2, a miRNA having a sequence as shown in SEQ ID NO: 3, a miRNA having a sequence as shown in SEQ ID NO: 4, a miRNA having a sequence as shown in SEQ ID NO: 5, a miRNA having a sequence as shown in SEQ ID NO: 6, a miRNA having a sequence as shown in SEQ ID NO: 7, and / or a miRNA having a sequence as shown in SEQ ID NO: 8, a miRNA having a sequence as shown in SEQ ID NO: 9, a miRNA having a sequence as shown in SEQ ID NO: 10, a miRNA having a sequence as shown in SEQ ID NO: 11, a miRNA having a sequence as shown in SEQ ID NO: 12, and a miRNA having a sequence as shown in SEQ ID NO: 13.

[0100] In a preferred embodiment, the miRNA is isolated from human.

[0101] In a preferred embodiment, the miRNA is blood extracellular vesicle miRNA.

[0102] In a preferred embodiment, the model formula of the risk prediction model described in device (b) is as follows:

[0103]

[0104] Among them, x i represents the marker expression level of sample i, P(x i ) is the probability of the corresponding classification of sample i predicted by the diagnostic model, where 0 indicates non-cancerous (high-risk lung cancer and positive lung nodules) and 1 indicates lung cancer. The classification with the highest probability is taken as the final prediction result for sample i.

[0105] In a preferred embodiment, the risk prediction model is constructed using a machine learning algorithm; preferably, the machine learning algorithm is a linear model (LinearModel), random forest (random forest), extreme randomized trees (extremely randomized trees), neural network (neural network), gradient boosting machine (GBM) and ensemble model (Ensemble methods).

[0106] In a preferred embodiment, the early diagnosis of lung cancer is to distinguish patients with early-stage lung cancer from non-cancer subjects.

[0107] In a preferred embodiment, the non-cancer subjects are people at high risk of lung cancer and patients with positive lung nodules.

[0108] It should be understood that within the scope of the present invention, the above-mentioned technical features of the present invention and the technical features described in detail below (such as in the embodiments) can be combined with each other to form new or preferred technical solutions. Due to space limitations, they will not be listed here one by one. BRIEF DESCRIPTION OF THE DRAWINGS

[0109] Figure 1 Transmission electron microscopy identification of small extracellular vesicles is shown;

[0110] Figure 2 The size distribution of small extracellular vesicles is shown;

[0111] Figure 3 The ROC curve for the training cohort is shown;

[0112] Figure 4 ROC curves for the validation cohort are shown. DETAILED DESCRIPTION

[0113] Lung cancer is a malignant tumor with high morbidity and mortality. However, the widely used LDCT screening technology in clinical practice carries radiation hazards and a high false-positive rate for early diagnosis of lung cancer, which can lead to overdiagnosis and overtreatment. Currently, there are no blood-based tumor biomarkers or models that can be used to distinguish high-risk individuals and patients with positive nodules from those with early-stage lung cancer.

[0114] To provide a highly effective biomarker to help differentiate lung cancer patients from non-lung cancer patients, the inventors developed a liquid biopsy technology for detecting microRNA (miRNA) in small extracellular vesicles (EVs) in the blood for early screening and diagnosis of lung cancer. Specifically, the inventors conducted the following three parts of work:

[0115] (1) Study blood extracellular vesicle miRNA biomarkers for lung cancer diagnosis and construct a highly accurate diagnostic model using statistical and machine learning methods;

[0116] (2) The cross-validation method, self-sampling method and multiple evaluation indicators were used to evaluate the effectiveness of the diagnostic model in distinguishing lung cancer from non-lung cancer in the training set and validation set, and to clarify and verify the accuracy, area under the receiver operating characteristic curve (AUC), positive predictive value, negative predictive value, sensitivity and specificity of the model.

[0117] Through (1) and (2), we discovered and validated blood small extracellular vesicle miRNA biomarkers and their diagnostic models that can be used for early screening and differential diagnosis of lung cancer.

[0118] In the present invention, one of the contents of the small extracellular vesicles in the blood, namely miRNA, is selected to construct a lung cancer and non-cancer diagnostic model. However, those skilled in the art know that there are many contents of small extracellular vesicles, such as lipids, mRNA and proteins, which can also be used as tumor biomarkers and achieve similar effects as miRNA. In addition, there are many components in the patient's blood, such as lipids, proteins, ctDNA (Circulating tumor DNA), CTC (Circulating tumor cell), cytokines and other substances, which may be found as biomarkers for early diagnosis of lung cancer and developed into independent liquid biopsy diagnostic technology.

[0119] definition

[0120] The scientific and technical terms used herein are consistent with those commonly understood by those skilled in the art. To facilitate understanding of the present invention, the following explanations and definitions of the relevant terms are provided:

[0121] small extracellular vesicles

[0122] The terms "small extracellular vesicles (sEVs)", "small extracellular vesicles", "blood small extracellular vesicles" or "plasma small extracellular vesicles" used in this article have the same meaning and refer to a type of biologically active vesicle with a diameter of approximately 30-150 nm secreted by multicellular bodies, also known as exosomes. The double lipid membrane structure of exosomes allows them to be preserved for a long time, thereby ensuring the integrity of the microRNAs contained in them. Its stability and easy access make it a promising auxiliary means for precision medicine, especially early tumor screening, diagnosis and treatment. Small RNAs in sEVs, including microRNAs (miRNAs), have been considered as potential biomarkers for the early diagnosis of various cancers. Exosomes secreted by lung cancer cells can reflect the biological characteristics of their parent cells and can provide a specific microRNA expression profile associated with tumors.

[0123] People at high risk of lung cancer

[0124] The terms "high-risk population" or "high-risk population for lung cancer" or "high-risk population for lung cancer" used in this article have the same meaning, referring to a population with a relatively high incidence of lung cancer or a relatively high risk of developing lung cancer.

[0125] Specifically, according to the "Guidelines for Lung Cancer Screening, Early Diagnosis and Treatment in China 2021", the criteria for high-risk groups for lung cancer include: (1) Smoking: ≥30 pack-years of smoking, including former smokers ≥30 years but less than 15 years of quitting smoking; (2) Passive smoking: living or working in the same room with smokers for ≥20 years; (3) Suffering from COPD; (4) History of occupational exposure (to asbestos, radon, beryllium, chromium, cadmium, nickel, silicon, coal smoke and coal dust) for at least 1 year; (5) Having a first-degree relative diagnosed with lung cancer.

[0126] Positive lung nodules

[0127] In the present invention, "positive lung nodules" and "positive lung nodules" have the same meaning, both referring to the presence of nodules in the lungs. The causes of lung nodules are usually inflammation; tuberculosis; sarcoidosis; tumors; and other immune diseases.

[0128] Blood small extracellular vesicle miRNA of the present invention

[0129] Currently, there are few studies using next-generation sequencing to identify the expression of small extracellular vesicle miRNAs in the blood as highly sensitive and specific diagnostic biomarkers for distinguishing early-stage lung cancer from non-cancer patients. Researchers (PMID: 23945385) examined 742 microRNAs in the exosomes of 10 lung adenocarcinomas, 10 lung granulomas, and 10 healthy smokers. They identified a panel of four microRNAs (miR-378a, miR-379, miR-139-5p, and miR-200-5p) that could be used to screen nodules and healthy individuals. The analysis showed a sensitivity of 97.5% and a specificity of 72.0%. A further study used a combination of six microRNAs (miR-151a-5p, miR-30a-3p, miR-200b-5p, miR-629, miR-100, and miR-154-3p) to diagnose patients with nodules and differentiate between lung adenocarcinoma and pulmonary granulomas, achieving a sensitivity of 96% and a specificity of 60%. However, this study's diagnostic model for distinguishing lung cancer from non-cancer tissue was poor, and due to its use of microarray or RT-PCR technology, no other exosomal miRNA markers with better diagnostic efficacy were discovered.

[0130] Through extensive screening, the inventors of CN 117106919 A discovered exosomal miRNA markers that can be used for lung cancer detection and prognosis with high sensitivity and specificity. The markers include 8 miRNAs and corresponding multiple different combinations, including miR-27b, miR-328-5p, miR-152, miR-106a, miR-148a-3p, miR-140-5p, miR-146b and miR-142-5p. Seven of these miRNAs (miR-27b, miR-328-5p, miR-152, miR-106a, miR-148a-3p, miR-140-5p and miR-146b) were selected to construct an exosomal miRNA detection model for lung cancer. The sensitivity of this diagnostic model in the training cohort and validation cohort was 86.7% and 77.8%, respectively. The clinical application scenarios of this study are different, and it cannot be well applied to early lung cancer in high-risk groups and patients with positive nodules. At the same time, the diagnostic efficacy of early lung cancer is insufficient.

[0131] These research cohorts do not consider the true differences between high-risk and healthy populations. Studies on markers that can distinguish early-stage lung cancer from high-risk populations have yet to be reported.

[0132] The present invention uses blood from patients suspected of having lung cancer using various clinical detection methods as research samples, and high-risk groups for lung cancer and patients with positive lung nodules as control groups. The small extracellular vesicle (exosome) extraction reagent L3525 independently developed by Shanghai Silidi Biomedical Technology Co., Ltd. is used to enrich plasma exosomes. The expression of plasma small extracellular vesicle miRNAs in different groups is further detected using second-generation sequencing technology small RNA sequencing. Finally, a plasma small extracellular vesicle miRNA biomarker diagnostic model that can be used for lung cancer diagnosis is discovered and validated in two independent cohorts, thereby discovering a group of plasma small extracellular vesicle miRNAs that can serve as high-efficiency biomarkers for lung cancer screening and early diagnosis.

[0133] In the present invention, statistical methods and machine learning methods were used to discover 13 blood small extracellular vesicle miRNAs, including hsa-let-7d-3p, hsa-let-7e-5p, hsa-let-7f-5p, hsa-miR-379-5p, hsa-miR-98-5p, hsa-miR-100-5p, hsa-miR-126-3p, hsa-miR-21-5p, hsa-miR-140-5p, hsa-miR-1908-5p, hsa-miR-328-3p, hsa-miR-486-5p and hsa-miR-99b-5p. These blood small extracellular vesicle miRNAs can be used to establish a lung cancer risk prediction model with high specificity and high sensitivity. Finally, the inventors used another batch of independent data to verify the effectiveness of the 13 blood small extracellular vesicle miRNA biomarker combination in distinguishing between lung cancer and non-lung cancer populations.

[0134] In a specific embodiment, the blood extracellular vesicle miRNA of the present invention is a miRNA with a sequence as shown in SEQ ID NO: 1, a miRNA with a sequence as shown in SEQ ID NO: 2, a miRNA with a sequence as shown in SEQ ID NO: 3, a miRNA with a sequence as shown in SEQ ID NO: 4, a miRNA with a sequence as shown in SEQ ID NO: 5, a miRNA with a sequence as shown in SEQ ID NO: 6, a miRNA with a sequence as shown in SEQ ID NO: 7, and / or a miRNA with a sequence as shown in SEQ ID NO: 8, a miRNA with a sequence as shown in SEQ ID NO: 9, a miRNA with a sequence as shown in SEQ ID NO: 10, a miRNA with a sequence as shown in SEQ ID NO: 11, a miRNA with a sequence as shown in SEQ ID NO: 12, and / or a miRNA with a sequence as shown in SEQ ID NO: 13; or a miRNA complementary to the miRNA sequence described in (i).

[0135] In a preferred embodiment, the blood extracellular vesicle miRNA is a combination of a miRNA with a sequence as shown in SEQ ID NO: 1, a miRNA with a sequence as shown in SEQ ID NO: 2, a miRNA with a sequence as shown in SEQ ID NO: 3, a miRNA with a sequence as shown in SEQ ID NO: 4, a miRNA with a sequence as shown in SEQ ID NO: 5, a miRNA with a sequence as shown in SEQ ID NO: 6, a miRNA with a sequence as shown in SEQ ID NO: 7, and / or a miRNA with a sequence as shown in SEQ ID NO: 8, a miRNA with a sequence as shown in SEQ ID NO: 9, a miRNA with a sequence as shown in SEQ ID NO: 10, a miRNA with a sequence as shown in SEQ ID NO: 11, a miRNA with a sequence as shown in SEQ ID NO: 12, and a miRNA with a sequence as shown in SEQ ID NO: 13.

[0136] Based on the teachings of the present invention, those skilled in the art will appreciate that the blood extracellular vesicle miRNA of the present invention can be used for the early diagnosis of lung cancer, particularly for distinguishing early-stage lung cancer patients from non-cancer subjects. In a specific embodiment, the non-cancer subjects are high-risk groups for lung cancer and patients with positive lung nodules. Therefore, the blood extracellular vesicle miRNA of the present invention can be used to prepare miRNA chips, detection reagents, or detection kits for early diagnosis of lung cancer, particularly for distinguishing early-stage lung cancer patients from non-cancer subjects (including high-risk groups for lung cancer and patients with positive lung nodules).

[0137] In a specific embodiment, the miRNA chip of the present invention comprises: a solid support; and oligonucleotide probes sequentially immobilized on the solid support, wherein the oligonucleotide probes specifically bind to the blood extracellular vesicle miRNAs of the present invention. Based on conventional techniques in the art, those skilled in the art will know how to design the oligonucleotide probes. For example, the oligonucleotide probes may comprise: a complementary binding region; and / or a linker region connected to the solid support.

[0138] In a specific embodiment, the detection kit contains a detection reagent for detecting the miRNA of the present invention; or, the miRNA chip.

[0139] Based on the teachings of the present invention and common knowledge in the field of miRNA, those skilled in the art will know how to construct the miRNA of the present invention into an isolated or artificially constructed precursor miRNA, which can be cleaved and expressed in human cells as the miRNA of the present invention. Furthermore, those skilled in the art will also know how to construct the precursor miRNA into an isolated polynucleotide, which can be transcribed by human cells into the precursor miRNA, and the precursor miRNA can be cleaved and expressed in human cells as the miRNA of the present invention.

[0140] In a specific embodiment, the polynucleotide has the structure shown in Formula I:

[0141] Seq 正向 -X-Seq 反向 Formula I

[0142] In Formula I,

[0143] Seq 正向 is a nucleotide sequence that can be expressed as the miRNA in human cells; Seq 反向 is a nucleotide sequence substantially complementary or completely complementary to Seq; X is a nucleotide sequence located in Seq 正向 and Seq 反向 The spacer sequence between the two sequences is the same as Seq 正向 and Seq 反向 Not complementary;

[0144] After the structure shown in Formula I is introduced into human cells, it forms the secondary structure shown in Formula II:

[0145]

[0146] In Formula II, Seq 正向 、Seq 反向 and X are defined as above, || means in Seq 正向 and Seq反向 The base pairing relationship formed between them.

[0147] Based on the teachings of the present invention and common knowledge in the miRNA field, those skilled in the art will construct a vector containing the miRNA or polynucleotide of the present invention.

[0148] Method of the present invention and device for implementing the method of the present invention

[0149] The blood extracellular vesicle miRNA of the present invention can be used for the early diagnosis of lung cancer, in particular to distinguish early lung cancer patients from non-cancer subjects (e.g., high-risk lung cancer patients and patients with positive lung nodules). Therefore, the present invention also provides a method for the early diagnosis of lung cancer, comprising the steps of:

[0150] (a) detecting the expression level of miRNA in a sample of a subject to be tested;

[0151] (b) inputting the miRNA expression value obtained in step (a) into the risk scoring model to obtain the probability that the subject is a lung cancer patient, a high-risk group for lung cancer, or a patient with positive lung nodules;

[0152] (c) Based on the probability obtained in step (b), a prediction result is given that the subject suffers from lung cancer.

[0153] Based on the understanding of the technical content of the present invention, namely that specific blood extracellular vesicle miRNAs can be used to distinguish early-stage lung cancer patients from non-cancer subjects (e.g., high-risk lung cancer patients and patients with positive lung nodules), those skilled in the art can use various methods, such as various algorithms, to construct a risk prediction model. In a specific embodiment, the risk prediction model is constructed using a machine learning algorithm; preferably, the machine learning algorithm is a linear model (LinearModel), random forest (random forest), extremely randomized trees (extremely randomized trees), neural network (neural network), gradient boosting machine (GBM) and ensemble model (Ensemble methods).

[0154] In a specific embodiment, the model formula of the risk prediction model in step (b) is as follows:

[0155]

[0156] Among them, x i represents the marker expression level of sample i, P(x i ) is the probability of the corresponding classification of sample i predicted by the diagnostic model, where 0 indicates non-cancerous (high-risk lung cancer and positive lung nodules) and 1 indicates lung cancer. The classification with the highest probability is taken as the final prediction result for sample i.

[0157] The method of the present invention for distinguishing early-stage lung cancer patients from non-cancer subjects has a sensitivity of >80% and a specificity of >78%.

[0158] To facilitate the implementation of the method of the present invention for distinguishing early-stage lung cancer patients from non-cancer subjects, the present invention also provides an early diagnosis device for lung cancer, wherein the device has a storage device storing instructions for executing the early diagnosis method for lung cancer of the present invention.

[0159] In a specific embodiment, the device includes a detection device for detecting the expression level of miRNA in a sample of a subject to be tested; a calculation device for inputting the obtained miRNA expression value into a risk scoring model to obtain the probability that the subject is a lung cancer patient or a high-risk group for lung cancer and a patient with positive lung nodules; and an output device for providing a prediction result of the subject suffering from lung cancer based on the obtained probability.

[0160] Advantages of the present invention:

[0161] 1. The miRNA of the present invention can be used to distinguish high-risk groups for lung cancer and patients with positive nodules from patients with early-stage lung cancer;

[0162] 2. Compared with existing tumor biomarkers, the miRNA of the present invention has better sensitivity and specificity;

[0163] 3. Compared with LDCT screening technology, the method of the present invention has higher diagnostic specificity and fewer false positives.

[0164] The present invention will be further described below with reference to specific examples. It should be understood that these examples are intended to illustrate the present invention only and are not intended to limit the scope of the present invention. The experimental methods in the following examples, for which specific conditions are not specified, were generally performed under conventional conditions, such as those described in Sambrook et al., Molecular Cloning: A Laboratory Manual (Cold Spring Harbor Laboratory Press, 2001), or according to the conditions recommended by the manufacturer. Unless otherwise stated, percentages and parts are calculated by weight.

[0165] Example

[0166] Material

[0167] The materials used in the following examples are all commercially available.

[0168] method

[0169] 1. Study cohort and clinical information

[0170] A total of 178 subject samples were included in this study, including 71 patients with early lung cancer, 77 high-risk lung cancer patients, and 30 patients with positive lung nodules. Samples were collected from lung cancer patients before surgery. High-risk lung cancer patients are those who meet the following conditions through questionnaire screening, and blood samples were collected after informed consent. Criteria for high-risk lung cancer population (Guidelines for Screening, Early Diagnosis and Early Treatment of Lung Cancer in China 2021): (1) Smoking: Smoking pack-years ≥30 pack-years, including former smokers ≥30 years but less than 15 years after quitting. (2) Passive smoking: Living or working in the same room with smokers for ≥20 years. (3) Suffering from COPD. (4) History of occupational exposure (asbestos, radon, beryllium, chromium, cadmium, nickel, silicon, soot and coal dust) for at least 1 year. (5) Having a first-degree relative diagnosed with lung cancer.

[0171] A random sample of 30% of the samples served as the validation cohort, and the remainder served as the training cohort. The training cohort consisted of 49 lung cancer patients, 54 high-risk individuals, and 21 patients with positive lung nodules. The validation cohort consisted of 22 lung cancer patients, 23 high-risk individuals, and 9 patients with positive lung nodules. The high-risk individuals and patients with positive lung nodules are collectively referred to as the non-cancer population.

[0172] 2. Extraction and Characterization of Blood Small Extracellular Vesicles

[0173] 1) Blood collection and extraction of small extracellular vesicles

[0174] Blood samples from non-cancer and lung cancer patients included in this study were separated into plasma samples using a two-step centrifugation method. First, the blood collection tubes were placed in a pre-cooled centrifuge and centrifuged at 1600g at 4°C for 10 minutes. The supernatant was transferred to new 1.5ml centrifuge tubes, and the hemolysis level of the samples was graded and recorded. Samples with a level of 4 or less were used for subsequent experiments. The supernatant from the previous step was centrifuged again at 16,000g at 4°C for 10 minutes. Finally, the supernatant was aliquoted into 1ml tubes and stored in a -80°C refrigerator. The extraction steps of small extracellular vesicles are as follows: take out the plasma sample and incubate it in a 37℃ water bath until it is completely thawed, centrifuge it at 12000g and 4℃ for 10 min, transfer the supernatant to a 1.5ml centrifuge tube and add 1 / 4 volume of exosome precipitant (L3525, 3DMed, Shanghai, China) to mix, place it at 4℃ for 30 min, and then centrifuge it at 4700g and 4℃ for 30 min. After centrifugation, discard the supernatant and finally add 200μl PBS (phosphate buffer saline) to suspend the small extracellular vesicle precipitate.

[0175] The present invention uses the small extracellular vesicle (exosome) extraction reagent L3525 independently developed by Shanghai Silidi Biomedical Technology Co., Ltd. to extract plasma small extracellular vesicles. Based on the teachings of the present invention and conventional technical means in the prior art, those skilled in the art will recognize that reagents from other manufacturers can also be used.

[0176] Those skilled in the art may also use other separation methods to extract extracellular vesicles, including but not limited to: a. ultrafiltration centrifugation; b. ultracentrifugation; c. microfluidics technology; d. magnetic bead capture method; preferably other commercial exosome extraction kits.

[0177] 2) Characteristics of blood small extracellular vesicles

[0178] To characterize the presence of small extracellular vesicles (SECs) in the blood of lung cancer and non-cancer patients, the present invention employed transmission electron microscopy to examine SEC morphology and nanoparticle tracking analysis (NTA) to determine SEC size distribution. SEC morphological characterization was performed by resuspending the isolated SECs in PBS and fixing them with 4% paraformaldehyde. The SECs were then transferred to a carbon-coated 200-mesh electron microscope copper grid. The grids were washed twice with PBS, then washed with freshly prepared PBS containing 50 mM glycine for 3 minutes, and then washed again with freshly prepared PBS containing 0.5% BSA for 10 minutes. Finally, the grids were stained with 2% uranyl acetate. SEC morphology was then observed using a transmission electron microscope (H-7650, Hitachi High-Technologies, Japan).

[0179] Small extracellular vesicle size distribution detection: First, take the separated small extracellular vesicles and dilute them with PBS to 1*10^ 7 -1*10^ 9 / ml. Subsequently, the NTA (NanoSight NS300, Malvern, UK) was turned on and 1ml of the diluted sample was injected into the sample chamber. Using a 488nm excitation module, the camera lens parameters were set to a shutter value of 890, a gain of 146, and a detection threshold of 7. At least 200 complete tracks were analyzed and acquired for each video. Finally, the nanoparticle tracking data of small extracellular vesicles was analyzed using NTA analysis software (version 2.3).

[0180] 3. Extraction and Expression of Blood Small Extracellular Vesicles miRNA

[0181] 1) Extraction of miRNA from blood extracellular vesicles

[0182] Blood EV miRNAs were isolated using the miRNeasy Serum / Plasma Kit (217184, QIAGEN, Shanghai, China), following the manufacturer's instructions. MiRNA quantification and fragment distribution were then performed using an Agilent 2100 analyzer and a companion chip (5067-1548, Agilent, USA).

[0183] 2) Expression detection of blood small extracellular vesicles

[0184] The present invention uses small RNA sequencing to detect the expression levels of blood small extracellular vesicle miRNAs. The library was constructed using the NEBNext Multiplex Small RNA Library Prep Set for Illumina (E7300L, NEB, USA), and the specific experimental procedures were performed according to the product instructions. Each plasma sample was loaded with 100 ng of miRNA in a total volume of no more than 6 μl. Library construction was completed through ligation of 3' adapters, hybridization of reverse transcription primers, ligation of 5' adapters, reverse transcription, and PCR amplification. The PCR product was then purified using the NucleoSpin Gel and PCR Clean-up kit (740609.50, MACHEREY-NAGEL, Germany), and the DNA was eluted with 30 μl of NE buffer. DNA library quality control was performed using an Agilent 2100 bioanalyzer using the accompanying chip and reagents, Agilent High Sensitivity DNA Kit & Reagents (5067-4626, Agilent, USA). The DNA was sequenced using the Illumina Nova 6000 platform (sequencing strategy: PE150).

[0185] In the present invention, small RNA sequencing, a second-generation sequencing technology, is used to detect the expression of blood small extracellular vesicle miRNAs. Based on the teachings of this invention and conventional techniques in the prior art, those skilled in the art will recognize other alternative methods, including but not limited to: a. other second-generation sequencing methods; b. third-generation sequencing methods; c. microarray detection; dQ-PCR detection, etc.

[0186] 4. Sequencing Data Analysis Process

[0187] Based on small RNA sequencing technology, we obtained the expression levels of miRNAs in small extracellular vesicles in the patient's blood. The analysis process of sequencing data is as follows:

[0188] 1) Sequencing data alignment. After removing the sequencing adapters from the small RNA sequencing data, the sequencing data were aligned to the human reference genome hg19 (genome download link: http: / / hgdownload.soe.ucsc.edu / goldenPath / hg19 / bigZips / ) using BWA software (version: 0.7.12-r1039), and the number of reads aligned to the miRNA was counted.

[0189] 2) miRNA annotation. MiRNAs were annotated using the Gencode v25 and miRBase v21 databases, and those annotated as known mature miRNAs were retained for subsequent analysis.

[0190] 3) miRNA filtering. For the training cohort, mature miRNAs with a length of 30 nt or less and covered by at least 10 reads in at least g samples in the training cohort data were retained for subsequent analysis, where g is the minimum number of samples in the group after the cohort was grouped. For the validation cohort, miRNAs screened from the training cohort were retained for subsequent analysis.

[0191] 4) Normalization of miRNA expression levels. The raw miRNA expression levels of the training cohort samples were normalized using the trimmed mean of M-values (TMM) method, and the same parameters were used for the validation cohort samples.

[0192] 5. Discovery of biomarkers

[0193] Based on the expression levels of miRNAs in the training cohort, samples were grouped according to pathological test results, and statistical and machine learning methods were used to discover miRNAs that can be used to distinguish between non-cancer patients and lung cancer patients as biomarkers. The process is as follows:

[0194] 1) Training cohort grouping: Based on the pathological test results, the patient samples in the training cohort were divided into two groups: lung cancer and non-cancer groups.

[0195] 2) Statistical methods for biomarker screening. First, the Kruskal-Wallis H test and Conover test were used to analyze the expression differences of all miRNAs between the two groups. The mutual information (MI) between all miRNA expressions and sample groups was calculated. MiRNAs with a p-value <= 0.1 between the groups and a mutual information score in the top 10% of all markers were screened. Then, the correlation coefficients between these miRNAs were calculated. Among the miRNAs with a correlation coefficient > 0.8, only the miRNAs with the largest variance were retained as candidate biomarkers for subsequent analysis.

[0196] 3) Machine learning method for biomarker screening. The miRNAs screened in 2) were used as initial biomarkers and were first screened using three machine learning feature screening methods. Method 1: Each biomarker's classification performance for the sample was evaluated separately, and markers with a performance score <0.8 were marked as candidate markers for discarding. Method 2: All initial biomarkers were first evaluated for classification performance on the sample as a whole. The expression levels of each biomarker in the sample were then randomly shuffled. The reduction in classification performance after shuffling was calculated for each marker, and markers with a performance score reduction <0.01 were marked as candidate markers for discarding. Method 3: All initial biomarkers were first evaluated for classification performance on the sample as a whole, and the biomarkers were ranked by importance. Starting with the most important biomarker, each biomarker was added and the improvement in model score was evaluated. Markers with a score improvement <0.01 were marked as candidate markers for discarding. The intersection of the candidate markers obtained by the above three methods was discarded, resulting in the remaining 13 markers. Subsequently, six machine learning algorithms, including linear models, random forests, extremely randomized trees, neural networks, gradient boosting machines (GBMs), and ensemble methods, were used to evaluate the classification performance and feature weights of the 13 markers as a whole on the training data set. Markers with feature weights < 5% were marked as candidate markers for discarding. If a marker was marked as discarded by all algorithms, it was not retained. Combining these methods, 13 markers were obtained as candidate markers for subsequent analysis.

[0197] In addition to the above-mentioned model construction method, based on the teachings of the present invention and conventional technical means in the prior art, those skilled in the art may also adopt other construction methods, including but not limited to: a. support vector machine; b. deep learning; c. complex feature engineering.

[0198] 6. Construction of risk scoring model for lung cancer and non-cancer populations

[0199] Taking lung cancer and non-cancer populations as the classification prediction targets, the 13 markers discovered in (5) were used, and six machine learning algorithms were adopted: linear model, random forest, extremely randomized trees, neural network, gradient boosting machine (GBM), and ensemble methods. Different hyper-parameters were preset for each algorithm, and the diagnostic models of multiple different machine learning algorithms were trained using the training set sample data. The model formula is as follows:

[0200]

[0201] x i represents the marker expression level of sample i, P(x i ) is the probability of the corresponding classification for sample i predicted by the diagnostic model, where 0 indicates non-cancerous (high-risk lung cancer and positive lung nodules) and 1 indicates lung cancer. The classification with the highest probability is the final prediction for sample i. The trained model is saved as a file on the hard drive. When calling the model, input the sample marker expression value to obtain the model prediction result.

[0202] 7. Evaluation and Validation of Risk Scoring Model Performance

[0203] The model's classification performance and feature weights were evaluated using a 5-fold cross-validation method in the training set and an independent validation set. Model evaluation and validation metrics included accuracy (range, 0–1), area under the receiver operating characteristic curve (AUC, range, 0–1), positive predictive value (range, 0–1), and negative predictive value (range, 0–1). Samples classified as high-risk for lung cancer and positive for lung nodules were combined into a non-cancerous category, and specificity (range, 0–1) and sensitivity (range, 0–1) were evaluated; higher values indicate better model classification performance.

[0204] 8. Application of lung cancer and non-cancer risk scoring models

[0205] 1) Peripheral blood was collected from patients with suspected lung cancer, and small extracellular vesicles were obtained from the peripheral blood. Biomarker expression was determined using small RNA sequencing.

[0206] 2) Using the risk scoring model, the expression values of blood extracellular vesicles hsa-let-7d-3p, hsa-let-7e-5p, hsa-let-7f-5p, hsa-miR-379-5p, hsa-miR-98-5p, hsa-miR-100-5p, hsa-miR-126-3p, hsa-miR-21-5p, hsa-miR-140-5p, hsa-miR-1908-5p, hsa-miR-328-3p, hsa-miR-486-5p, and hsa-miR-99b-5p were obtained, and the values were substituted into the trained model formula to calculate the probability of each patient being predicted to have lung cancer;

[0207] 3) Select the output result with the highest probability and give the predicted result of each patient's risk of developing lung cancer.

[0208] Example 1.

[0209] In this example, blood samples were collected from 178 patients, 30% of which were randomly selected as the validation cohort, and the rest were used as the training cohort. The training cohort consisted of 124 cases, including 49 lung cancer patients and 75 non-cancer people. Further pathological diagnosis of the non-cancer population included 54 patients at high risk of lung cancer and 21 patients with positive lung nodules. The validation cohort consisted of 54 cases, including 22 lung cancer patients and 32 non-cancer patients, specifically 23 patients at high risk of lung cancer and 9 patients with positive lung nodules. Table 1 shows the clinical information of the patients. The analysis results show that there is no significant difference in the proportion of samples of different classifications between the two groups of patients.

[0210] Table 1. Clinical information of non-cancer population and lung cancer patients.

[0211]

[0212] Example 2. Extraction and Characterization of Small Extracellular Vesicles from Blood

[0213] In this example, the small extracellular vesicle (exosome) extraction reagent L3525 independently developed by Shanghai Silidi Biomedical Technology Co., Ltd. was used to extract small extracellular vesicles from the plasma of lung cancer and non-cancer patients. In order to detect the characteristic distribution of small extracellular vesicles in the blood of lung cancer and non-cancer patients, the present invention used transmission electron microscopy to detect the morphology of small extracellular vesicles and NTA to detect the particle size distribution of small extracellular vesicles. The transmission electron microscopy results showed that the small extracellular vesicles showed a typical "horseshoe-shaped" morphology (see Figure 1 The NTA test results show that the average particle size of the small extracellular vesicles in the representative samples extracted in this patent is 121.4nm, which is consistent with the particle size distribution of small extracellular vesicles (see Figure 2 ).

[0214] Example 3. Biomarker Discovery

[0215] In this example, small RNA sequencing was used to detect the expression levels of small extracellular vesicle miRNAs in the blood of lung cancer patients and non-cancer subjects. The statistical methods U test and T test were used to analyze the expression differences of all miRNAs between lung cancer patients and those at high risk of lung cancer and those with positive lung nodules, as well as the correlation coefficients between miRNAs. At the same time, three machine learning feature screening methods were used to screen miRNAs that can be used to distinguish lung cancer patients from those at high risk of lung cancer and those with positive lung nodules as biomarkers. The candidate molecular markers included hsa-let-7d-3p (CUAUACGACCUGCUGCCUUUCU, SEQ ID NO: 1), hsa-let-7e-5p (UGAGGUAGGAGGUUGUAUAGUU, SEQ ID NO: 2), hsa-let-7f-5p (UGAGGUAGUAGAUUGUAUAGUU, SEQ ID NO: 3), hsa-miR-379-5p (UGGUAGACUAUGGAACGUAGG, SEQ ID NO: 4), hsa-miR-98-5p (UGAGGUAGUAAGUUGUAUUGUU, SEQ ID NO: 5), and hsa-miR-109-5p (UGAGGUAGUAAGUUGUAUUGUU, SEQ ID NO: 6). NO: 5), hsa-miR-100-5p (AACCCGUAGAUCCGAACUUGUG, SEQ ID NO: 6), hsa-miR-126-3p (UCGUACCGUGAGUAAAUAAUGCG, SEQ ID NO: 7), hsa-miR-21-5p (UAGCUUAUCAGACUGAUGUUGA, SEQ ID NO: 8), hsa-miR-140-5p (CAGUGGUUUUACCCUAUGGUAG, SEQ ID NO: 9), hsa-miR-1908-5p (CGGCGGGGACGGCGAUUGGUC, SEQ ID NO: 10), hsa-miR-328-3p (CUGGCCCUCUCUGCCUUCCGU, SEQ ID NO:11), hsa-miR-486-5p(UCCUGUACUGAGCUGCCCCGAG, SEQ ID NO: 12) and hsa-miR-99b-5p (CACCCGUAGAACCGACCUUGCG, SEQ ID NO: 13), a total of 13, were used for subsequent analysis.Then we use linear model (LinearModel), random forest (random forest), extreme randomized trees (extremely randomized trees), neural network (neural network), gradient boosting machine (GBM) and ensemble model (Ensemble Methods) A total of 6 machine learning algorithms were used. Markers with feature weights < 5% were marked as candidate discarded markers. If a marker was marked as discarded by all algorithms, it was not retained. A total of 13 markers were obtained as candidate markers, including hsa-let-7d-3p, hsa-let-7e-5p, hsa-let-7f-5p, hsa-miR-379-5p, hsa-miR-98-5p, hsa-miR-100-5p, hsa-miR-126-3p, hsa-miR-21-5p, hsa-miR-140-5p, hsa-miR-1908-5p, hsa-miR-328-3p, hsa-miR-486-5p and hsa-miR-99b-5p, which were used to subsequently construct risk scoring models for lung cancer and non-cancer (high-risk lung cancer and lung-positive nodules).

[0216] Example 4. Lung cancer and non-cancer (high-risk lung cancer and lung-positive nodules) risk scoring model

[0217] In order to construct a risk classification model for lung cancer and non-cancer (high-risk lung cancer and lung-positive nodules), the miRNA expression data of the training cohort were used, and the classification effect and feature weight of the model were evaluated using the 5-fold cross-validation method in the training set. Combined with the results of pathological examination, a scoring model for lung cancer and non-cancer (high-risk lung cancer and lung-positive nodules) was constructed. The prediction results of the risk of lung cancer for each patient were given according to the model formula and procedure. The model evaluation indicators include accuracy (range 0 to 1), area under the receiver operating characteristic curve (AUC, range 0 to 1), sensitivity (range 0 to 1) and specificity (range 0 to 1), which are 0.8556, 0.9136 ( Figure 3 ), 0.8366 and 0.8823, 0.8178 and 0.8933 (Table 2). The results showed that in the training cohort, this risk prediction model had high accuracy, AUC, positive predictive value, negative predictive value, sensitivity and specificity, and the model had excellent predictive efficiency.

[0218] Table 2. Cross-validation evaluation results of biomarkers in the training set

[0219]

[0220] Example 5. Validation of the predictive efficacy of the risk scoring model for lung cancer and non-cancer (high-risk lung cancer and lung-positive nodules)

[0221] In order to verify the effectiveness of the risk score model in predicting lung cancer, patients with high-risk lung cancer and positive lung nodules were combined into a non-lung cancer control group, and another independent cohort was selected as a validation cohort to evaluate the classification effect and feature weights of the model. Taking the pathological test results as the true value, the model evaluation indicators included accuracy (range 0 to 1), area under the receiver operating characteristic curve (AUC, range 0 to 1), sensitivity (range 0 to 1) and specificity (range 0 to 1), which were 0.7997, 0.8906 ( Figure 4 ), 0.72 and 0.8621, 0.8182 and 0.7812 (Table 3). The results showed that in the validation cohort, this risk prediction model had high accuracy, AUC, sensitivity, and specificity, and had excellent predictive efficacy.

[0222] Table 3. Biomarker self-sampling evaluation results in the validation set

[0223]

[0224] All documents mentioned in this application are incorporated herein by reference, just as if each document were incorporated herein by reference individually. It should also be understood that after reading the above teachings of the present invention, those skilled in the art may make various changes or modifications to the present invention, and that such equivalents also fall within the scope of the claims appended hereto.

Claims

1. Use of blood extracellular vesicle miRNA in the preparation of chips, detection reagents or detection kits for early diagnosis of lung cancer; The blood extracellular vesicle miRNA is: (i) a miRNA with a sequence as shown in SEQ ID NO: 1, a miRNA with a sequence as shown in SEQ ID NO: 2, a miRNA with a sequence as shown in SEQ ID NO: 3, a miRNA with a sequence as shown in SEQ ID NO: 4, a miRNA with a sequence as shown in SEQ ID NO: 5, a miRNA with a sequence as shown in SEQ ID NO: 6, a miRNA with a sequence as shown in SEQ ID NO: 7, a miRNA with a sequence as shown in SEQ ID NO: 8, a miRNA with a sequence as shown in SEQ ID NO: 9, a miRNA with a sequence as shown in SEQ ID NO: 10, a miRNA with a sequence as shown in SEQ ID NO: 11, a miRNA with a sequence as shown in SEQ ID NO: 12, and a miRNA with a sequence as shown in SEQ ID NO: 13; or (ii) a miRNA that is complementary to the miRNA sequence described in (i).

2. A miRNA chip, comprising: solid phase carrier; as well as Oligonucleotide probes are sequentially fixed on the solid support, wherein the oligonucleotide probes specifically bind to miRNA; Wherein, the miRNA is: (i) a miRNA with a sequence as shown in SEQ ID NO: 1, a miRNA with a sequence as shown in SEQ ID NO: 2, a miRNA with a sequence as shown in SEQ ID NO: 3, a miRNA with a sequence as shown in SEQ ID NO: 4, a miRNA with a sequence as shown in SEQ ID NO: 5, a miRNA with a sequence as shown in SEQ ID NO: 6, a miRNA with a sequence as shown in SEQ ID NO: 7, a miRNA with a sequence as shown in SEQ ID NO: 8, a miRNA with a sequence as shown in SEQ ID NO: 9, a miRNA with a sequence as shown in SEQ ID NO: 10, a miRNA with a sequence as shown in SEQ ID NO: 11, a miRNA with a sequence as shown in SEQ ID NO: 12, and a miRNA with a sequence as shown in SEQ ID NO: 13; or (ii) a miRNA that is complementary to the miRNA sequence described in (i).

3. Use of the miRNA chip according to claim 2 for preparing a kit for early diagnosis of lung cancer.

4. A detection kit containing a detection reagent for detecting miRNA; in, The miRNA is: (i) a miRNA with a sequence as shown in SEQ ID NO: 1, a miRNA with a sequence as shown in SEQ ID NO: 2, a miRNA with a sequence as shown in SEQ ID NO: 3, a miRNA with a sequence as shown in SEQ ID NO: 4, a miRNA with a sequence as shown in SEQ ID NO: 5, a miRNA with a sequence as shown in SEQ ID NO: 6, a miRNA with a sequence as shown in SEQ ID NO: 7, a miRNA with a sequence as shown in SEQ ID NO: 8, a miRNA with a sequence as shown in SEQ ID NO: 9, a miRNA with a sequence as shown in SEQ ID NO: 10, a miRNA with a sequence as shown in SEQ ID NO: 11, a miRNA with a sequence as shown in SEQ ID NO: 12, and a miRNA with a sequence as shown in SEQ ID NO: 13; or (ii) a miRNA complementary to the miRNA sequence described in (i); Alternatively, the detection kit is equipped with the miRNA chip according to claim 2.

5. A miRNA isolated from extracellular vesicles in blood for early diagnosis of lung cancer; in, The miRNA is: (i) a miRNA with a sequence as shown in SEQ ID NO: 1, a miRNA with a sequence as shown in SEQ ID NO: 2, a miRNA with a sequence as shown in SEQ ID NO: 3, a miRNA with a sequence as shown in SEQ ID NO: 4, a miRNA with a sequence as shown in SEQ ID NO: 5, a miRNA with a sequence as shown in SEQ ID NO: 6, a miRNA with a sequence as shown in SEQ ID NO: 7, a miRNA with a sequence as shown in SEQ ID NO: 8, a miRNA with a sequence as shown in SEQ ID NO: 9, a miRNA with a sequence as shown in SEQ ID NO: 10, a miRNA with a sequence as shown in SEQ ID NO: 11, a miRNA with a sequence as shown in SEQ ID NO: 12, and a miRNA with a sequence as shown in SEQ ID NO: 13; or (ii) a miRNA that is complementary to the miRNA sequence described in (i).

6. An isolated or artificially constructed precursor miRNA, which can be cleaved and expressed in human cells into the miRNA according to claim 5.

7. An isolated polynucleotide, wherein the polynucleotide can be transcribed into a precursor miRNA by a human cell, and the precursor miRNA can be cleaved and expressed into the miRNA according to claim 5 in a human cell. A vector comprising the miRNA according to claim 5 or the polynucleotide according to claim 7.

9. An early diagnosis device for lung cancer, the device comprising a storage device storing instructions for executing a method for early diagnosis of lung cancer, the method comprising the steps of: (a) detecting the expression level of miRNA in a sample of a subject to be tested; (b) inputting the miRNA expression value obtained in step (a) into the risk scoring model to obtain the probability that the subject is a lung cancer patient, a high-risk group for lung cancer, or a patient with positive lung nodules; (c) providing a prediction result that the subject suffers from lung cancer based on the probability obtained in step (b); in, The miRNA is: (i) a miRNA with a sequence as shown in SEQ ID NO: 1, a miRNA with a sequence as shown in SEQ ID NO: 2, a miRNA with a sequence as shown in SEQ ID NO: 3, a miRNA with a sequence as shown in SEQ ID NO: 4, a miRNA with a sequence as shown in SEQ ID NO: 5, a miRNA with a sequence as shown in SEQ ID NO: 6, a miRNA with a sequence as shown in SEQ ID NO: 7, a miRNA with a sequence as shown in SEQ ID NO: 8, a miRNA with a sequence as shown in SEQ ID NO: 9, a miRNA with a sequence as shown in SEQ ID NO: 10, a miRNA with a sequence as shown in SEQ ID NO: 11, a miRNA with a sequence as shown in SEQ ID NO: 12, and a miRNA with a sequence as shown in SEQ ID NO: 13; or (ii) a miRNA that is complementary to the miRNA sequence described in (i).

Images