A prediction method for breast cancer metastasis and its application

Abstract

The present invention provides a method and application for predicting breast cancer metastasis. The present invention uses body fluid exosomes as samples, utilizes liquid chromatography tandem mass spectrometry, obtains the protein phenotype of patients with breast cancer metastasis, establishes a metastasis diagnosis model based on proteomics, and provides a kit or chip for detecting breast cancer lymph node metastasis, and the application of breast cancer lymph node metastasis protein markers in the preparation of kits and / or chips. Compared with traditional diagnostic methods such as axillary lymph node dissection and tissue biopsy, the present invention has the characteristics of non-invasive and convenient detection, and can accurately determine whether the sample to be tested is a breast cancer metastasis sample.

Description

Technical Field

[0001] The present invention relates to the application of protein mass spectrometry detection and machine learning in the technical field of cancer prediction and clinical medicine, and in particular to a method for predicting breast cancer metastasis, a kit or chip for detecting breast cancer lymph node metastasis, and the use of protein markers of breast cancer lymph node metastasis in the preparation of kits and / or chips. Background Art

[0002] Breast Cancer (BC) is a phenomenon in which mammary epithelial cells proliferate uncontrollably under the influence of multiple carcinogens. According to the 2021 global cancer statistics, breast cancer is the most common cancer and the leading cause of cancer death in women. New cases of breast cancer diagnosed worldwide each year account for approximately 11.7% of all new tumor cases. Breast cancer metastasis is one of the most common staging and prognostic determinants of breast cancer.

[0003] Traditional axillary lymph node dissection can accurately stage breast cancer, but it is associated with many complications and a long recovery period for patients. In addition, although tissue biopsy plays a key role in formulating treatment plans for patients, the incision is large and requires accurate pathological diagnosis and preoperative positioning to obtain correct results. In addition, non-invasive imaging methods such as ultrasound, computed tomography, and magnetic resonance imaging have been widely used in clinical preoperative lymph node status assessment, but the sensitivity of these methods is not satisfactory.

[0004] Disease biomarkers are measurable changes related to pathophysiological processes and can be used to diagnose diseases, monitor disease course, predict disease prognosis, and evaluate treatment effects. Therefore, there is an urgent need to establish new detection methods for breast cancer metastasis, find biomarkers of metastasis, and objectively, sensitively, and stably diagnose breast cancer metastasis, so as to carry out timely and targeted treatment, improve patients' quality of life and survival rate, reduce medical costs, and save social resources. Summary of the invention

[0005] The purpose of the present invention is to provide a method for predicting breast cancer metastasis and a kit or chip for detecting breast cancer lymph node metastasis, and the use of protein markers for breast cancer lymph node metastasis in the preparation of kits and / or chips, so as to provide a method for determining whether a breast cancer patient has metastasis.

[0006] In order to achieve the above object, according to one aspect of the present invention, using body fluid exosomes as samples, liquid chromatography tandem mass spectrometry is used to obtain the protein phenotype of breast cancer metastasis patients and establish a metastasis diagnosis model.

[0007] Furthermore, the metastatic body fluid protein markers are used as a data set to construct a breast cancer metastasis detection and / or prediction model, and whether metastasis occurs is determined based on the output results of the model.

[0008] Furthermore, based on the exosome samples of breast cancer patients, a training set and a validation set were established. The protein markers in the training set were divided into a metastasis group and a non-metastasis group, and a training detection and / or prediction model was constructed using a machine learning method.

[0009] Furthermore, internal validation outputs the transition probability of the training set samples, draws the ROC curve, and evaluates the model prediction results by the area under the ROC curve. External validation outputs the transition probability of the validation set samples, draws the ROC curve, and evaluates the model prediction results by the area under the ROC curve.

[0010] Furthermore, the body fluid exosomes are blood, saliva, urine or cerebrospinal fluid exosomes of breast cancer patients. Preferably, the blood exosomes are serum exosomes or plasma exosomes.

[0011] Furthermore, the breast cancer is invasive ductal carcinoma of the breast or invasive lobular carcinoma of the breast according to the World Health Organization Classification of Breast Tumors; according to molecular classification, it is luminal A type (ER and / or PR+, HER2-, Ki-67<20%), luminal B type (HER2 negative type (B1 type): ER+ and / or PR<20%, HER2-, Ki-67≥20%; B2: HER2 positive type (B2 type): ER+ and / or PR+, HER2 overexpression); HER2 positive type (HER2+, ER- and PR-) or basal type / triple negative type (HER2-, ER- and PR-).

[0012] Further, the breast cancer metastasis is breast cancer lymph node metastasis, chest wall metastasis, bone metastasis, liver metastasis, lung metastasis, brain metastasis or pleural metastasis. Preferably, the lymph node metastasis is axillary lymph node metastasis, clavicular lymph node metastasis or distal lymph node metastasis.

[0013] Furthermore, provided is the use of any one or more of the following protein markers of breast cancer lymph node metastasis in the preparation of a kit and / or chip for detecting breast cancer lymph node metastasis: ACADVL, ACTA1, ACTA2, ACTC1, ACTG2, PARP1, ALOX5, ANXA5, APOA2, APOC2, APOC3, ATP12A, B2M, CCT6A, SEPTIN7, CEL, CES1, CKB, COL15A1, CS, DAG1, DDB1, DDX5, DSG1, EI F5, FBP1, FCGRT, FLNA, GBA, GOT1, GP1BA, GPD2, HBA1, HBD, HP, HSP90AA2P, IGHE, IK, ITPR3, KIF5B, KRT16, LCP1, LDHA, LP A. MCAM, ND1, NCL, NDUFS3, P4HB, PRDX1, PEPD, PLGLB1, PPP1R10, PRKACB, PRKCSH, PSMA1, PSMA3, PSMA4, PSMB1, PVR, RDX, R PS9, RPS24, RPS27A, SEMG1, SGTA, SPTBN1, TALDO1, TBCA, PRDX2, TGFBI, UBA52, UBB, UBC, EZR, H4C1, SUCLG2, INA, SEC16A , WDR1, RAD50, PDIA6, PGRMC2, CAP1, PRDX4, CFHR3, STIP1, TMED10, MST1L, NID2, LIMCH1, ESYT1, TNS2, MTREX, CASP14, SUN 2, SAMHD1, SEZ6L2, VPS4A, COQ6, LIMA1, KRT20, DHX29, SYTL2, PSPC1, OTUB1, DPEP2, FTO, CFHR5, LMAN2L, RAB1B, ZFYVE19, NT5C3B, STXBP5, PLGLA, MSL1, IGHV2-70D, FAH, RPSA, RANBP2, RRBP1, STX7, GTF3C4, SARM1, IGKV1D-8, IGKV1-16, and NOP58.

[0014] Furthermore, the use of 10 protein markers of breast cancer lymph node metastasis in combination in the preparation of a kit and / or chip for detecting breast cancer lymph node metastasis: ACTA1, ACTA2, P4HB, LDHA, CFHR3, CS, ANXA5, PDIA6, PRDX2 and HBD.

[0015] Furthermore, the kit and / or chip also includes a control, and the expression level of any one or more of the following protein markers of breast cancer lymph node metastasis in the exosomes of patients with breast cancer lymph node metastasis is significantly higher than the expression level in the control for detecting breast cancer lymph node metastasis: ACADVL, ACTA1, ACTA2, ACTC1, ACTG2, PARP1, ALOX5, ANXA5, APOA2, APOC2, APOC3, ATP12A, B2M, CCT6A, SEPTIN7, CEL, C ES1, CKB, COL15A1, CS, DAG1, DDB1, DDX5, DSG1, EIF5, FBP1, FCGRT, FLNA, GBA, GOT1, GP1BA, GPD2, HBA1, HBD, HP, HSP 90AA2P, IGHE, IK, ITPR3, KIF5B, KRT16, LCP1, LDHA, LPA, MCAM, ND1, NCL, NDUFS3, P4HB, PRDX1, PEPD, PLGLB1, PPP1R1 0. PRKACB, PRKCSH, PSMA1, PSMA3, PSMA4, PSMB1, PVR, RDX, RPS9, RPS24, RPS27A, SEMG1, SGTA, SPTBN1, TALDO1, TBCA , PRDX2, TGFBI, UBA52, UBB, UBC, EZR, H4C1, SUCLG2, INA, SEC16A, WDR1, RAD50, PDIA6, PGRMC2, CAP1, PRDX4, CFHR3, S TIP1, TMED10, MST1L, NID2, LIMCH1, ESYT1, TNS2, MTREX, CASP14, SUN2, SAMHD1, SEZ6L2, VPS4A, COQ6, LIMA1, KRT20, DHX29, SYTL2, PSPC1, OTUB1, DPEP2, FTO, CFHR5, LMAN2L, RAB1B, ZFYVE19, NT5C3B, STXBP5, PLGLA, MSL1 and IGHV2-70D.

[0016] Furthermore, the kit and / or chip also includes a control, and the expression level of any one or more of the following protein markers of breast cancer lymph node metastasis in the blood exosomes of patients with breast cancer lymph node metastasis is significantly lower than the expression level in the control for detecting breast cancer lymph node metastasis: FAH, RPSA, RANBP2, RRBP1, STX7, GTF3C4, SARM1, IGKV1D-8, IGKV1-16 and NOP58.

[0017] Furthermore, the exosomes are blood exosomes from patients with breast cancer accompanied by lymph node metastasis and blood exosomes from patients with breast cancer without metastasis. Preferably, the breast cancer is invasive ductal carcinoma of the breast and invasive lobular carcinoma of the breast according to the World Health Organization Classification of Breast Tumors.

[0018] Furthermore, the expression level is the expression level at the gene level, the expression level at the transcription level or the expression level at the protein level. Preferably, the expression level at the protein level is detected by one or more of mass spectrometry, Western blotting and ELISA.

[0019] Furthermore, the breast cancer is of Luminal A type (ER and / or PR+, HER2-, Ki-67<20%), Luminal B type (HER2 negative type (B1 type): ER+ and / or) PR<20%, HER2-, Ki-67≥20%; B2: HER2 positive type (B2 type): ER+ and / or) PR+, HER2 overexpression); HER2 positive type (HER2+, ER- and PR-) or basal type / triple negative type (HER2-, ER- and PR-).

[0020] Furthermore, the kit includes reagents for identifying any one or more of the following protein markers for breast cancer lymph node metastasis: ACADVL, ACTA1, ACTA2, ACTC1, ACTG2, PARP1, ALOX5, ANXA5, APOA2, APOC2, APOC3, ATP12A, B2M, CCT6A, SEPTIN7, CEL, CES1, CKB, COL15A1, CS, DAG1, DDB1, DDX5, DSG1, EIF5, FBP1, FCGRT, F LNA, GBA, GOT1, GP1BA, GPD2, HBA1, HBD, HP, HSP90AA2P, IGHE, IK, ITPR3, KIF5B, KRT16, LCP1, LDHA, LPA, MCAM, ND1, NC L, NDUFS3, P4HB, PRDX1, PEPD, PLGLB1, PPP1R10, PRKACB, PRKCSH, PSMA1, PSMA3, PSMA4, PSMB1, PVR, RDX, RPS9, RPS24, RPS27A, SEMG1, SGTA, SPTBN1, TALDO1, TBCA, PRDX2, TGFBI, UBA52, UBB, UBC, EZR, H4C1, SUCLG2, INA, SEC16A, WDR1, RA D50, PDIA6, PGRMC2, CAP1, PRDX4, CFHR3, STIP1, TMED10, MST1L, NID2, LIMCH1, ESYT1, TNS2, MTREX, CASP14, SUN2, SAM HD1, SEZ6L2, VPS4A, COQ6, LIMA1, KRT20, DHX29, SYTL2, PSPC1, OTUB1, DPEP2, FTO, CFHR5, LMAN2L, RAB1B, ZFYVE19, NT5C3B, STXBP5, PLGLA, MSL1, IGHV2-70D, FAH, RPSA, RANBP2, RRBP1, STX7, GTF3C4, SARM1, IGKV1D-8, IGKV1-16, and NOP58.

[0021] Furthermore, the kit includes reagents for jointly identifying 10 protein markers of breast cancer lymph node metastasis: ACTA1, ACTA2, P4HB, LDHA, CFHR3, CS, ANXA5, PDIA6, PRDX2 and HBD.

[0022] Furthermore, the reagent is a mass spectrometry detection reagent or an antibody detection reagent for identifying the protein marker of breast cancer lymph node metastasis; preferably, the antibody detection reagent is a monoclonal antibody.

[0023] Furthermore, the chip is provided with reagents for identifying any one or more of the following protein markers for breast cancer lymph node metastasis: ACADVL, ACTA1, ACTA2, ACTC1, ACTG2, PARP1, ALOX5, ANXA5, APOA2, APOC2, APOC3, ATP12A, B2M, CCT6A, SEPTIN7, CEL, CES1, CKB, COL15A1, CS, DAG1, DDB1, DDX5, DSG1, EIF5, FBP1, FCGRT, FLNA, GBA, GOT1, GP1BA, GPD2, HBA1, HBD, HP, HSP90AA2P, IGHE, IK, ITPR3, KIF5B, KRT16, LCP1, LDHA, LPA, MCAM, ND1, N CL, NDUFS3, P4HB, PRDX1, PEPD, PLGLB1, PPP1R10, PRKACB, PRKCSH, PSMA1, PSMA3, PSMA4, PSMB1, PVR, RDX, RPS9, RPS24 , RPS27A, SEMG1, SGTA, SPTBN1, TALDO1, TBCA, PRDX2, TGFBI, UBA52, UBB, UBC, EZR, H4C1, SUCLG2, INA, SEC16A, WDR1, R AD50, PDIA6, PGRMC2, CAP1, PRDX4, CFHR3, STIP1, TMED10, MST1L, NID2, LIMCH1, ESYT1, TNS2, MTREX, CASP14, SUN2, SA MHD1, SEZ6L2, VPS4A, COQ6, LIMA1, KRT20, DHX29, SYTL2, PSPC1, OTUB1, DPEP2, FTO, CFHR5, LMAN2L, RAB1B, ZFYVE19, NT5C3B, STXBP5, PLGLA, MSL1, IGHV2-70D, FAH, RPSA, RANBP2, RRBP1, STX7, GTF3C4, SARM1, IGKV1D-8, IGKV1-16, and NOP58.

[0024] Furthermore, the chip is provided with reagents for jointly identifying 10 protein markers of breast cancer lymph node metastasis: ACTA1, ACTA2, P4HB, LDHA, CFHR3, CS, ANXA5, PDIA6, PRDX2 and HBD.

[0025] Furthermore, the reagent is a mass spectrometry detection reagent or an antibody detection reagent for identifying the breast cancer lymph node metastasis protein marker; preferably, the antibody detection reagent is a monoclonal antibody.

[0026] Furthermore, the present invention also provides a system for detecting breast cancer metastasis, the system comprising:

[0027] 1. A marker combination verification module, which receives input data and judges the input data. When the input data meets the judgment condition, the module outputs the judgment result; the marker combination is a combination of all 127 protein markers of breast cancer lymph node metastasis mentioned above. Preferably, the marker combination is ACTA1, ACTA2, P4HB, LDHA, CFHR3, CS, ANXA5, PDIA6, PRDX2 and HBD.

[0028] 2. A result judgment module, which predicts breast cancer metastasis according to the judgment result and outputs the prediction result.

[0029] Wherein, in the marker combination verification module, when the input data meets the judgment condition, the output judgment result is "yes"; when the input data does not meet the judgment condition, the output judgment result is "no";

[0030] In the result judgment module, when the judgment result is "yes", the output prediction result is "breast cancer metastasis"; when the judgment result is "no", the output prediction result is "breast cancer has not metastasized".

[0031] Furthermore, the system also includes a sample extraction module, which extracts sample data and transmits it to the marker combination verification module.

[0032] Furthermore, the present invention also provides the use of the system in preparing a product for detecting breast cancer metastasis.

[0033] Furthermore, the present invention also provides a device including a machine learning model, which includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the functions of the system can be realized.

[0034] Furthermore, the present invention also provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the functions of the system can be realized. Based on the common sense in the art, the above-mentioned preferred conditions can be arbitrarily combined to obtain the preferred embodiments of the present invention.

[0035] The reagents and raw materials used in the present invention are commercially available.

[0036] The positive and progressive effects of the present invention are:

[0037] The present invention provides a method and application for predicting breast cancer metastasis. The present invention uses body fluid exosomes as samples, utilizes liquid chromatography tandem mass spectrometry, obtains the protein phenotype of patients with breast cancer metastasis, establishes a metastasis diagnosis model based on proteomics, and provides a kit or chip for detecting breast cancer lymph node metastasis, and the application of breast cancer lymph node metastasis protein markers in the preparation of kits and / or chips. Compared with traditional diagnostic methods such as axillary lymph node dissection and tissue biopsy, the present invention has the characteristics of non-invasive and convenient detection, and can accurately determine whether the sample to be tested is a breast cancer metastasis sample. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0039] Figure 1 The present invention is a flowchart of a method for predicting lymph node metastasis of breast cancer according to an embodiment of the present invention.

[0040] Figure 2 This is a cumulative curve diagram of the proteomic identification of blood exosomes according to an embodiment of the present invention.

[0041] Figure 3 This is a volcano plot of differential proteins in blood exosomes according to an embodiment of the present invention.

[0042] Figure 4 Confusion matrix of lymph node metastasis probability for internal validation.

[0043] Figure 5 Schematic diagram of the area under the ROC curve for internal validation.

[0044] Figure 6 Confusion matrix of lymph node metastasis probability for external validation.

[0045] Figure 7 Schematic diagram of the area under the ROC curve for external validation. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0049] The present invention provides a method and application for predicting breast cancer metastasis. The present invention uses exosomes in body fluids as samples, utilizes liquid chromatography tandem mass spectrometry, obtains the protein phenotype of patients with breast cancer metastasis, establishes a metastasis diagnosis model based on proteomics, and provides a kit or chip for detecting breast cancer lymph node metastasis, and the application of breast cancer lymph node metastasis protein markers in the preparation of kits and / or chips.

[0050] Figure 1 FIG. 1 is a flow chart of a method for predicting breast cancer metastasis according to an embodiment of the present invention. Figure 1 As shown, a method for predicting breast cancer metastasis according to an embodiment of the present invention comprises the following steps:

[0051] (1) Sample selection: Based on exosome samples from the blood of breast cancer patients, a training set and a validation set were established for proteomic analysis.

[0052] In one embodiment, the present invention selects 105 exosome samples derived from the blood of patients with invasive breast cancer, establishes a training set and a validation set, and performs proteomic analysis.

[0053] Specifically, 70% of the samples were used as training sets and 30% of the samples were used as validation sets. The training set included 73 breast cancer patients and the validation set included 32 breast cancer patients.

[0054] (2) Sample preparation and mass spectrometry analysis: Exosome extraction, exosome protein extraction, mass spectrometry analysis, peptide identification and protein quantification, and protein identification through retrieval and comparison.

[0055] In one embodiment, a blood sample is drawn from each patient for serum separation. First, serum exosomes are extracted. 1) 1 mL of serum is centrifuged at 10,000 g for 30 minutes at 4°C, the supernatant is diluted with 20 mL of PBS, and filtered with a 0.2 μm diameter filter membrane. 2) The filtered serum is placed in an ultracentrifuge tube and centrifuged at 150,000 g for 4 hours. Resuspend in PBS and continue to centrifuge at 4°C, 150,000 g for 2 hours. 3) The supernatant is discarded, and about 200 μL of PBS is retained.

[0056] Secondly, extraction and trypsin digestion of exosome proteins. Exosome samples (usually 5 μg, adjusted according to BCA measurement) were dried by vacuum centrifugation and re-dissolved with 30-50 μL 8M urea / 50mM ammonium bicarbonate / 10mM DTT. After lysis and reduction, the proteins were alkylated with 20 or 30mM iodoacetamide (Sigma). The proteins were digested with trypsin (Promega) at an enzyme mass ratio of 1:50 at 37°C overnight, and then the peptides were extracted and dried (SpeedVac, Eppendorf).

[0057] Again, mass spectrometry analysis. We used an EASY-nLC 1200 ultra-high pressure system liquid chromatography system (ThermoFisher Scientific). Peptides were separated in 75 min, with a flow rate of 600 nL / min, on a 150 μm ID×15 cm column, with a laser-pulled electrospray emitter packed with 1.9 μm ReproSil-Pur 120C18-AQ particles. Mobile phases A and B were water and acetonitrile (0.1 vol% FA), respectively. %B was linearly increased from 15 to 30% in 75 min. Samples were analyzed on a Q-EX-HF mass spectrometer (MS) with a nano-electrospray ion source (Thermo Fisher Scientific). For the generation of ion mobility enhanced spectral libraries, the mass spectrometer was run in data-independent mode. Generally, 75% of the samples were injected. The peptide was dissolved in 12 μL (0.1% formic acid) buffer and 9 μL was loaded onto a 100 μm I.D. × 2.5 cm C18 trapping column with a maximum pressure of 280 bar and 14 μL of solvent A (0.1% formic acid). The DIA method consisted of an MS1 ​​scan from 300-1400 m / z at 60k resolution (AGC target 4e5 or 50ms). 30 DIA fragments were then acquired at 15k resolution with an AGC target of 5e4 and a maximum injection time of 22ms. The setting "Inject all available parallel time" was enabled. HCD fragmentation was set to a normalized collision energy of 30%. Spectra were recorded in profile mode. The default charge state for MS2 was set to 3.

[0058] Finally, peptide identification and protein quantification. All data were processed using the Firmiana one-stop proteomics cloud platform independently developed by the laboratory. FragPipe (v.12.1) and MSFragger (2.2) were used to search the UniProt human protein database (updated on 2019.12.17, 20406 entries). The mass tolerance of the precursor is 20ppm, and the mass tolerance of the product ion is 50mmu. A maximum of two gaps are allowed. The search engine uses cysteine ​​carbamidomethylation as a fixed modification and N-acetylation and oxidation of methionine as variable modifications. The charge limit of the precursor ion score is

[0059] +2, +3 and +4. The results of DIA data were combined into spectral libraries using SpectraST software. All libraries were used as reference libraries. DIA data were analyzed using DIANN (v.1.7.0). DIA-NN was used with default settings: Precursor FDR: 5%, Loglev: 1, Mass accuracy: 20ppm, MS1accuracy: 10ppm, Scan window: 30, Implicit proteingroup: genes, Quantification strategy: robust LC (high accuracy). The quantification of identified peptides was calculated as the average of the peak areas of chromatographic fragment ions in all reference libraries. Label-free protein quantification was calculated using the label-free, intensity-based absolute quantification (iBAQ) method. We calculated the peak area values ​​of the corresponding proteins. The fraction of total protein (FOT) was used to represent the normalized abundance of a specific protein in a sample. FOT is defined as the iBAQ of a protein divided by the total iBAQ of all identified proteins in the sample. For ease of representation, FOT values ​​were multiplied by 10e5 and missing values ​​were calculated as 10e-5.

[0060] (3) Screening for transferred protein markers: Analyze the expression of protein markers and select effective identification proteins.

[0061] In one embodiment, the number of proteins identified in each of the 105 samples is 1,000-2,500. Figure 2 The cumulative curve shown in Figure 1 shows that a total of 8,973 proteins were identified in 105 samples. The present invention uses the ratio of the expression level of each protein in a specific sample to the expression level of all proteins in the sample (fraction of total, FOT) as its normalized expression level. The FOT value is multiplied by 10e5 and then logarithmized to base 10.

[0062] (4) Establishing a prediction model: The protein markers in the training set were divided into a lymph node metastasis group and a non-lymph node metastasis group, and a prediction model was trained based on machine learning.

[0063] In one embodiment, the training set is first divided into a lymph node metastasis group and a non-lymph node metastasis group, and the protein differences between the two groups are compared. In order to improve the accuracy and universality of the prediction, proteins whose expression frequency in either group is less than 30% are removed from the training set, and the remaining 1,500 proteins enter the second step of screening, such as Figure 3In the second step of screening, proteins with a rank sum test p value less than 0.05 between the lymph node metastasis and non-metastasis groups and a fold difference of more than two times in expression between the two groups were selected. A total of 127 proteins were screened as candidate markers (ACADVL, ACTA1, ACTA2, ACTC1, ACTG2, PARP1, ALOX5, ANXA5, APOA2, APOC2, APOC3, ATP12A, B2M, CCT6A, SEPTIN7, CEL, CES1, CKB, COL15A1, CS, DAG1, DDB1, DDX5, DSG1, EIF5, FBP1, FCGRT, FLNA, GBA, GOT1, GP1BA, GPD2, HBA1, HBD, HP, HSP90AA2P, IGHE, IK, ITPR3, KIF5B, KRT16, LCP1, LDHA, LPA, MCAM, ND1, NCL, NDUFS3, P4HB, PRDX1, PEPD, PLGLB1, PPP1R10, PRKACB, PRKCSH, PSMA1, PSMA3, PSMA4, PSMB1, PVR, RDX, RPS9, RP S24, RPS27A, SEMG1, SGTA, SPTBN1, TALDO1, TBCA, PRDX2, TGFBI, UBA52, UBB, UBC, EZR, H4C1, SUCLG2, INA, SEC16A, WDR1 , RAD50, PDIA6, PGRMC2, CAP1, PRDX4, CFHR3, STIP1, TMED10, MST1L, NID2, LIMCH1, ESYT1, TNS2, MTREX, CASP14, SUN2, S , AMHD1, SEZ6L2, VPS4A, COQ6, LIMA1, KRT20, DHX29, SYTL2, PSPC1, OTUB1, DPEP2, FTO, CFHR5, LMAN2L, RAB1B, ZFYVE19, NT5C3B, STXBP5, PLGLA, MSL1, IGHV2-70D, FAH, RPSA, RANBP2, RRBP1, STX7, GTF3C4, SARM1, IGKV1D-8, IGKV1-16, and NOP58).

[0064] Specifically, the prediction model was established based on the machine learning method. The Random Forest algorithm was used to screen out 10 important features (ACTA1, ACTA2, P4HB, LDHA, CFHR3, CS, ANXA5, PDIA6, PRDX2 and HBD), and the XGBoost algorithm was used to build a model for the 10 selected features.

[0065] Table 1 shows the 10 important features in the protein prediction model.

[0066] Table 1

[0067]

[0068] In one embodiment of the present invention, during the validation process of the model, the training set samples are first used as internal validation. Figure 4 The confusion matrix for lymph node metastasis was validated internally. Figure 5 Figure 2 is a schematic diagram of the area under the ROC curve for internal validation. Figure 4 As shown in Figure 2, the internal validation model included 73 samples. The specificity of the diagnostic model was 88.6%, the sensitivity was 89.5%, the positive predictive value was 88.6%, and the negative predictive value was 89.5%. Figure 5 As shown, the ordinate represents the sensitivity value of the diagnostic model; the abscissa represents the specificity value of the diagnostic model, and the area under the ROC curve is 0.944.

[0069] External validation uses validation set samples. Figure 6 The lymph node metastasis confusion matrix for external validation, Figure 7 Schematic diagram of the area under the ROC curve for external validation. Figure 6 As shown, the model included 32 samples. The specificity of the diagnostic model was 89.5%, the sensitivity was 76.9%, the positive predictive value was 85.0%, and the negative predictive value was 83.3%. Figure 5 As shown in the figure, the area under the ROC curve is 0.743. This result suggests that the protein prediction model has high sensitivity and specificity and has potential application value in the clinical diagnosis of breast cancer lymph node metastasis.

[0070] Although the embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and cannot be understood as limiting the present invention. A person of ordinary skill in the art can change, modify, replace and modify the above embodiments within the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. Use of a reagent for detecting the following 10 protein markers for breast cancer lymph node metastasis in the preparation of a kit and / or chip for detecting breast cancer lymph node metastasis, characterized in that: The protein markers are the following 10 protein markers for breast cancer lymph node metastasis: ACTA1, ACTA2, P4HB, LDHA, CFHR3, CS, ANXA5, PDIA6, PRDX2 and HBD; Among them, the expression level of the protein marker in the exosomes of patients with breast cancer lymph node metastasis is significantly higher than the expression level in the control group of breast cancer without lymph node metastasis; the exosomes are blood exosomes of patients with breast cancer accompanied by lymph node metastasis or blood exosomes of patients with breast cancer without metastasis.

2. The use according to claim 1, characterized in that: The expression level is the expression level at the gene level, the expression level at the transcription level or the expression level at the protein level; wherein the expression level at the protein level is detected by one or more of mass spectrometry, Western blotting and ELISA methods.

3. The use according to any one of claims 1 to 2, characterized in that The breast cancer is invasive ductal carcinoma of the breast or invasive lobular carcinoma of the breast.

4. A kit for detecting lymph node metastasis of breast cancer, characterized in that: The kit includes reagents for jointly detecting the following 10 protein markers for breast cancer lymph node metastasis: ACTA1, ACTA2, P4HB, LDHA, CFHR3, CS, ANXA5, PDIA6, PRDX2 and HBD; Among them, the expression level of the protein marker in the exosomes of patients with breast cancer lymph node metastasis is significantly higher than the expression level in the control group of breast cancer without lymph node metastasis; the exosomes are blood exosomes of patients with breast cancer accompanied by lymph node metastasis or blood exosomes of patients with breast cancer without metastasis.

5. The kit according to claim 4, characterized in that The reagent is a mass spectrometry detection reagent or an antibody detection reagent for detecting the protein marker of breast cancer lymph node metastasis.

6. The kit according to claim 5, characterized in that The antibody detection reagent is a monoclonal antibody.

7. A chip for detecting lymph node metastasis of breast cancer, characterized in that: The chip is provided with reagents for jointly detecting the following 10 protein markers for breast cancer lymph node metastasis: ACTA1, ACTA2, P4HB, LDHA, CFHR3, CS, ANXA5, PDIA6, PRDX2 and HBD; Among them, the expression level of the protein marker in the exosomes of patients with breast cancer lymph node metastasis is significantly higher than the expression level in the control group of breast cancer without lymph node metastasis; the exosomes are blood exosomes of patients with breast cancer accompanied by lymph node metastasis or blood exosomes of patients with breast cancer without metastasis.

8. The chip according to claim 7, characterized in that: The reagent is a mass spectrometry detection reagent or an antibody detection reagent for detecting the breast cancer lymph node metastasis protein marker.

9. The chip according to claim 8, characterized in that: The antibody detection reagent is a monoclonal antibody.

Images