Biomarker combination and its use in predicting the effect of drug treatment of gastric cancer

Abstract

The application discloses a biomarker combination and application thereof in predicting the effect of drug treatment on gastric cancer. The application discloses a biomarker combination and application thereof in predicting the effect of drug treatment on gastric cancer. The biomarker combination can predict the effect of drug treatment on gastric cancer of a gastric cancer patient receiving platinum plus fluorouracil combined with paclitaxel, has the advantages of high sensitivity and high specificity, and provides favorable technical support for predicting the effect of drug treatment on gastric cancer of a gastric cancer patient receiving platinum plus fluorouracil combined with paclitaxel.

Description

Technical Field

[0001] This invention belongs to the field of bioinformatics, specifically relating to combinations of biomarkers and their application in predicting the efficacy of platinum-based plus fluorouracil-based combined with paclitaxel drugs in the treatment of gastric cancer. Background Technology

[0002] Gastric cancer (GC) is the fourth most common malignant tumor worldwide and the second leading cause of cancer-related death globally. Early detection rates for GC are low, and late-stage cure rates are also low. Surgery is the preferred treatment for patients with advanced GC. For some patients who cannot undergo surgery, medication is the only option to improve their quality of life or even maintain survival. Despite significant progress in recent years in the development of first-line treatments, second-line drugs, and targeted therapies such as Herceptin and Ramucirumab (CYRAMZA), drug tolerance remains a problem, and the overall prognosis for GC treatment remains poor. Clinically, there are significant individual differences in the effectiveness of tumor treatment, but there is insufficient evidence for personalized drug selection. There is an urgent clinical need for biomarkers to guide personalized precision medicine and alleviate the problem of drug tolerance.

[0003] Therefore, to achieve personalized treatment for gastric cancer, it is necessary to identify subtypes based on molecular genetic and pathological characteristics and to discover and apply corresponding target genes. Furthermore, in gastric cancer research, results have been reported demonstrating the ability to classify the prognosis of gastric cancer based on its subtype. Currently, many research patents are based on gene expression levels in the genome and transcriptome to classify gastric cancer, such as systems predicting postoperative prognosis or suitability for anticancer drugs in patients with advanced gastric cancer (patent number CN110168106A), and cluster classification and prognostic prediction systems based on the biological characteristics of gastric cancer (patent number CN110177886A). However, in clinical practice, the first-line treatment for gastric cancer patients is often a triple-drug combination therapy using platinum-based drugs plus fluorouracil and paclitaxel (a common treatment regimen is oxaliplatin 100 mg / m² injected on day 1). 2 and docetaxel 40mg / m 2 Take capecitabine 40 mg / m² orally from day 1 to day 14. 2 (Twice a day, repeated every three weeks) has still not yielded an effective treatment plan.

[0004] Proteomics plays a crucial role in elucidating the complex molecular events of tumorigenesis, such as tumorigenesis, invasion, metastasis, and treatment resistance. Proteomics-based tumor diagnosis boasts advantages such as high sensitivity, strong specificity, and well-defined background mechanisms, and has been increasingly applied to tumor detection in recent years. However, research on these tumor biomarkers is often based on limited experimental data, involving relatively limited cancer types and sample sizes. Therefore, collecting proteomic data and utilizing big data analysis methods to establish models predicting treatment effectiveness can facilitate personalized chemotherapy and has significant clinical implications for recommending appropriate treatment plans to patients. Summary of the Invention

[0005] To address the deficiency in existing technologies regarding the lack of a technical solution for predicting the efficacy of platinum-based plus fluorouracil-based combined paclitaxel therapy for gastric cancer, this invention provides a biomarker combination and its application in predicting the efficacy of this therapy. The biomarker combination includes at least AHR, ATP5S, C11orf31, C20orf26, CDC42SE2, CHGA, and CHP2, achieving 100% prediction accuracy, diagnostic sensitivity, and specificity in the validation set. The biomarker combination can be expanded to include up to 234 protein molecular biomarkers as described in this invention, exhibiting high prediction accuracy, diagnostic sensitivity, and specificity.

[0006] To solve the above-mentioned technical problems, the present invention provides a technical solution as follows: a combination of biomarkers, the combination of biomarkers including the following biomarkers: AHR, ATP5S, C11orf31, C20orf26, CDC42SE2, CHGA and CHP2.

[0007] Preferably, the biomarker combination further includes AQP1.

[0008] More preferably, the biomarker combination further includes one or more of the following biomarkers: A1BG, AAMDC, AARS2, ACLY, ACTL6A, AIF1L, ANAPC4, ANKMY2, APBB1IP, ARAF, ARHGEF11, ARID2, ARPC3, ATP6AP1, BCAS3, BCS1L, BUD13, C11orf58, C12orf57, C2, C3orf37, C5AR1, C7orf50, CARHSP1, CASC3, CBLL1, CCDC86, CDKN2AIP, CEACAM1, CEP170B, CFD, CHCHHD4, CHI3L 1. CHMP2B, CLC, CMC1, CNPY4, CNTNAP1, COL6A5, COMMD1, COMMD4, COTL1, CTDNEP1, CTNNA2, CYBRD1, CYTH4, DCAF16, DCAF7, DCD, DDX28, GPCPD1, DDX43, DF NA5, DHODH, DHRS4, DMBT1, DOK2, DPM1, DRG1, DYNLT1, EHBP1L1, ELMOD2, EPB41L5, EPHX2, ETAA1, ETFDH, FADS3, FAM83G, FRK, FUT4, GGCX, GGH, GNA11, GNG 4. GORAB, GPAM, GPR107, GUK1, HAPLN1, HDGFRP2, HLA-F, HNF1A, IFIT5, IGF2R, INSR, IPO13, ISYNA1, ITGA4, KCMF1, KDSR, KIAA1671, KPNA3, KRT73, LENG8 , LIPA, LOC101059966, LSM7, LYPLAL1, LYSMD2, MAP2K6, MAPK13, MFN1, MPHOSPH6, MPP7, MRPL19, MRPL21, MRPL27, MRPL53, MRPS15, MRPS18A, MRPS36, MRP S6, MRPS9, MSRB2, MTARC2, MTG2, MTM1, NEBL, NEGR1, NEMF, NLN, NOL6, NOLC1, NRK, NUDT12, NUP210, NUPL2, OLFML1, ORAI1, ORM1, OSBPL11, OSBPL1A, PADI 4. PANK4, PAPLN, PARVG, PAWR, PDCD2, PDE5A, PI4KB, PKN1, PLCL2, PLEKHF2, PLVAP, PNKD, PPHLN1, PPM1A, PRELP, PRG2, PRR15L, PSCA, PSMB6, PSMD9, PTMS,PURB, RAB11A, RAB24, REG1A, REG3A, RFC2, RIC8A, RNF121, ROGDI, RPS15A, RPS23, RPS6KB2, RTFDC1, RTN4, RWDD1, SAAL1, SAMD9L, SCAF4, SCAF 8. SERF2, SERPINA12, SERPINA6, SERPINB10, SERPINB9, SETD7, SHROOM3, SLC16A1, SLC27A3, SLC7A1, SMG1, SOS1, SOWAHC, SPHK2, SPIN1, SPINK 1. SRA1, STOML3, SUMO2, TACC3, TADA1, TAF10, TAF5, TARBP1, TBC1D10A, TBCK, TBK1, TBP, TFCP2L1, THNSL1, TIMM22, TJP3, TMED8, TMEM246, TME M63A, TNFAIP8, TP53I11, TRAPPC6B, TTC39A, TTI1, UBL3, UCHL1, URB2, UTP14A, VPS33A, WDR47, WIZ, WLS, XPO4, YIPF5, YKT6, ZFYVE21 and ZRANB2. ,

[0009] To solve the above-mentioned technical problems, the present invention provides a technical solution as follows: a set of biomarkers, comprising combination A, combination B and combination C, wherein combination A comprises the biomarker combination as described herein, combination B comprises DFFB, DYNLRB1, FLG2, FNBP1, GCLC, LMAN2, LPXN, MYCBP, NIT1, NUB1, RAB32, RBBP7, RFC2, RMDN1 and WAS, and combination C comprises BAIAP2, CAPN5, COMMD4, DDX60L, DSC2, IRF6, NPL, SCIN, SEPSECS, SLC39A4, SLC5A5, SRPX2 and TECPR1.

[0010] Specifically, the active ingredients of the B-protein AAAS, ABCD4, ABHD13, ACBD5, AGA, AGPAT5, AKAP9, ANKIB1, AN O6, APBB1IP, APH1A, APTX, ARHGEF6, ARPC5, ASH2L, ASRGL1, ATM, ATP5S, ATP 6AP1, ATP7A, AVL9, BAD, BAG3, BCL10, BCL2, BCL2L13, BLOCK1S6, BRE, C10orf 118 C12orf5, C2CD2, C9orf41, CASC4, CD300A, CD38, CDC40, CDR2, CGREF1, C.S HCHD2, CKS1B, CLCA1, COA4, COG2, COMMD7, COX6B1, CPSF1, CYB5A, CYB5R1C YC1, CYP4F11, CYTH1, CYTH2, DACH1, DAPL1, DCK, DSC1, DSG1, E2F4, EIF4EBP1 、EMP3、ENGASE、EPB41L4B、EPHA6、EPM2AIP1、ERF、ESCO2、ETFDH、F2、FAM105 B, FAM185A, FAM83A, FAM84B, FBXO22, FCN2, FTO, FUT2, GABPA, GALNT10, GATC GC, GDPGP1, GIPC3, GLB1L2, GOLGA1, GPAM, GPD1L, GPHN, GPR56, GSK3B, HDH D1, HDHD3, HELZ, HGS, HMGA1, HNMT, HPGD, HTRA1, ICMT, IL1RAP, IMPA2, INSR. ISCA2, IVD, KDELC1, KDM2A, KDM2B, KIAA0020, KIAA0430, KIAA1324, KPNA7 KRT1, KRT10, KRT2, KRT6A, KRT74, KRT77, KRT80, LIMCH1, LMBRD1, LOC101060 291. LONP2, LRRC25, LRRFIP2, LSM7, LYSMD2, LYST, MAEA, MAN2C1, MAP2K1 B21D2, MCTS1, MFAP4, MICAL3, MLKL, MMADHC, MMP15, MNS1, MNT, MOXD1, MRPL2 8. MRPL3, MRPS24, MRPS5, MRTO4, MSH3, MSRB2, MTPAP, MYH7B, NBPF7, ND2, ND UFB3, NDUFS7, NEU1, NFATC2, NFXL1, NIPSNAP3A, NRAS, NTHL1, NUP50, PALMD.PAPOLA, PARP12, PCMTD2, PFKFB3, PGAM5, PGGT1B, PIGG, PIP, PKNOX2, PLD3 POLR2E, POLR2L, POP1, POTEI, PPIF, PPP3CB, PPP3R1, PRKAG1, PRRC2C, PSMG 4. PTDSS2, RAB27A, RAB44, RBCK1, RBM26, RDH14, REL, RENBP, RHBDD2, RNF14 6. RNF185, RPL31, RPL38, RPS15, RRM2B, RSF1, S100A4, S100P, SBF1, SEPN1 ERPINC1, SGK223, SIRT5, SLC10A7, SLC16A1, SLC35F6, SLC39A7, SMIM7, SNR PA1, SNRPB, SPCS1, SPG20, SRBD1, SRGN, SRRD, STON2, SUPT20H, SUPT6H, SVI P, TCEB3, TEP1, TERF2, THOC5, TJAP1, TK2, TLR3, TMCO4, TMED8, TMEM201, TM UB1, TRABD, TRAPPC6B, TRIP10, TRMT5, TRMU, TRRAP, TSC22D1, TSPYL1, UAP1L 1, UBD, UBXN4, VPS33B, WAPAL, WDR18, WDR46, XPO7, YES1, YPEL5, ZSCAN18, and Z SWIM8: C-protein AATF, ABT1, ACSF2, AGFG2, AKAP9, ATG13, ATP5D, ATR, and ATRN. B3GNT6, B4GALNT3, B4GALT4, BCKDK, BMS1, BRD8, C10orf112, C12orf29, C1o rf198, C4orf33, C9orf114, CA5B, CADM1, CAPN8, CC2D1B, CCDC124, CCNK, CD9 9L2, CDC42BPA, CHTOP, CHURC1, CNEP1R1, COX15, COX7C, CREG1, CSTF2T, DCA F8, DCP1A, DDR1, DDX49, DDX56, DHX38, DNASE2, DOPEY2, DSCR3, DTD1, FAM20 7A, FANCI, FARS2, FKBP11, GEMIN7, GIP, GK, GNA12, GNPTG, GTDC2, HERC2, HG D, HOMER3, IL1RAP, IMPAD1, ISCA2, ITGA9, KRT80, KXD1, LGALS4, LMF2, LRMP.MAATS1, MALT1, MAPK9, MED14, MFSD5, MLF2, MLXIPL, MMP7, MPP1, MRPS16, MRPS23, MRPS26, MRVI1, MTHFR, MTIF2, NAV3, NFYC, NOC4L, NOTCH3, NRCAM, NRIP2, NRP1, NUMB, PCBD2, PCMTD1, PGLYRP2, PHLDB1, PI4K2A, PLAT, PLEKHJ1, PLK1, PNKD, PPM1B, PPP1R1B, PPP2R2D, PSMD9, PTGR1, PTPRF, QSER1, RABIF, RCSD1, RHOC, RIN2, RNASEH2C, RNM TL1, ROBO2, S100A16, SCAF1, SEC16A, SEL1L3, SEMA3C, SEPTIN10, SHOC2, SIDT2, SLC25A35, SLC35D1, SLC44A1, SMARCAD1, SMG5, SPINT2, SRSF4, SZRD1, THG1L, TMEM160 , TMUB1, TNRC6B, TNS4, TPP2, TRAPPC1, TRIM3, TSPAN8, TSPYL1, TTC39A, TTC39C, TTN, TUBB2B, UACA, UBE2S, ULBP2, URB1, WBSCR22, WDR44, WIBG, ZADH2, ZC3H7A, and ZNF706. ,

[0011] To address the aforementioned technical problems, the present invention provides a technical solution as follows: a reagent for detecting the expression level of a combination of biomarkers or a set of biomarkers as described herein, the reagent comprising biomolecules that specifically hybridize with the biomarkers individually or simultaneously, such as primers, probes, and / or antibodies; or, the reagent comprising genomic, transcriptomic, and / or proteomic sequencing reagents for detecting the expression level of a combination of biomarkers or a set of biomarkers as described herein.

[0012] To address the aforementioned technical problems, the present invention provides a technical solution as follows: a reagent kit comprising a combination of biomarkers as described herein, a set of biomarkers as described herein, and / or reagents as described herein.

[0013] To address the aforementioned technical problems, the present invention provides the following technical solution: the application of the biomarker combination, biomarker set, reagent, and / or kit described herein in the preparation of a formulation for predicting the efficacy of platinum-based plus fluorouracil-based combined paclitaxel drugs in the treatment of gastric cancer. Preferably, the formulation is a diagnostic product.

[0014] To address the aforementioned technical problems, the present invention provides a technical solution as follows: a system for predicting the efficacy of platinum-based plus fluorouracil-based combined with paclitaxel drugs in the treatment of gastric cancer, the system comprising:

[0015] The data processing module is used to process the expression data of combinations or sets of biomarkers as described herein from patients with gastric cancer who have been received or input.

[0016] The judgment and output module is used to process the expression data through Firmiana software after the reception or input is completed. The preset algorithm is a machine learning algorithm based on a generalized linear regression model to construct a prediction model, predict the sensitive prediction probability and the insensitive prediction probability of gastric cancer patients respectively, and judge whether the expression data meets the preset judgment conditions to predict the effect of platinum-based plus fluorouracil combined with paclitaxel drugs in the treatment of gastric cancer, and output the prediction results.

[0017] Specifically, in the judgment and output module, when the expressed data meets the judgment condition (the sensitive prediction probability is greater than or equal to the insensitive prediction probability), the output prediction result is "Platinum-based drugs combined with fluorouracil and paclitaxel have a therapeutic effect on gastric cancer"; when the expressed data does not meet the judgment condition (i.e., the sensitive prediction probability is less than the insensitive prediction probability), the output prediction result is "Platinum-based drugs combined with fluorouracil and paclitaxel do not have a therapeutic effect on gastric cancer".

[0018] Preferably, in the preset, the training set parameters are set to 80%, and the validation set parameters are set to 20%.

[0019] Preferably, the system further includes a data collection module for collecting expression data of the combination of biomarkers or the set of biomarkers as described herein in a patient's gastric cancer tissue sample and transmitting it to the data processing module.

[0020] To solve the above-mentioned technical problems, the present invention provides a technical solution as follows: a computer-aided method for predicting the therapeutic effect of platinum-based plus fluorouracil-based combined paclitaxel drugs in gastric cancer, comprising the following steps:

[0021] (1) Receive or input expression data of gastric cancer patients’ biomarker combination or biomarker set as described herein, process the expression data through Firmiana software, pre-set a machine learning algorithm based on generalized linear regression model, construct a prediction model, and predict the sensitive prediction probability and insensitive prediction probability of gastric cancer patients respectively.

[0022] (2) Determine whether the expressed data meets the preset judgment conditions, wherein the judgment conditions are that the sensitive prediction probability is greater than or equal to the non-sensitive prediction probability, so as to predict the effect of platinum-based plus fluorouracil-based combined paclitaxel-based drugs in the treatment of gastric cancer, and output the prediction results;

[0023] In step (2), when the expressed data meets the judgment condition, the output prediction result is "platinum-based drugs plus fluorouracil combined with paclitaxel have a therapeutic effect on gastric cancer"; when the expressed data does not meet the judgment condition, the output prediction result is "platinum-based drugs plus fluorouracil combined with paclitaxel have no therapeutic effect on gastric cancer".

[0024] To solve the above-mentioned technical problems, the present invention provides a technical solution as follows: a computer-readable storage medium storing a computer program, which, when executed by a processor, can realize the functions of the system described herein, or implement the steps of the method described herein.

[0025] To address the aforementioned technical problems, the present invention provides a technical solution as follows: an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the functions of the system described herein, or the steps of the method described herein.

[0026] Based on common knowledge in the field, the above-mentioned preferred conditions can be combined arbitrarily to obtain various preferred embodiments of the present invention.

[0027] The reagents and raw materials used in this invention are all commercially available.

[0028] The positive and progressive effects of this invention are as follows:

[0029] The biomarker combination provided by this invention shows significant changes in expression levels in clinical samples of gastric cancer patients with different treatment responses. Therefore, the biomarker combination provided by this invention can predict the gastric cancer efficacy of patients receiving platinum-based plus fluorouracil combined with paclitaxel therapy. It has the advantages of high sensitivity and high specificity, providing favorable technical support for predicting the efficacy of gastric cancer patients receiving platinum-based plus fluorouracil combined with paclitaxel therapy.

[0030] Based on the biomarker combination of this invention, corresponding systems, computer-readable storage media, electronic devices, and predictive methods have been developed, which have broad scientific research value and provide personalized predictions for gastric cancer patients, recommending whether patients are suitable for receiving this platinum-based plus fluorouracil-based combined paclitaxel treatment regimen. Attached Figure Description

[0031] Figure 1The prediction results for the first group of biomarkers in the training and validation sets, including prediction accuracy, sensitivity, and specificity.

[0032] Figure 2 The prediction results for the second group of biomarkers on the training and validation sets include prediction accuracy, sensitivity, and specificity.

[0033] Figure 3 The prediction results for the third group of biomarkers on the training and validation sets include prediction accuracy, sensitivity, and specificity.

[0034] Figure 4 The prediction results for the fourth group of biomarkers in the training and validation sets include prediction accuracy, sensitivity, and specificity.

[0035] Figure 5 The prediction results for the fifth group of biomarkers in the training and validation sets, including prediction accuracy, sensitivity and specificity.

[0036] Figure 6 The prediction results for the sixth group of biomarkers in the training and validation sets, including prediction accuracy, sensitivity and specificity.

[0037] Figure 7 The prediction results for the 7th biomarker combination on the training and validation sets, including prediction accuracy, sensitivity, and specificity.

[0038] Figure 8 A schematic diagram of the system for predicting the efficacy of platinum-based plus fluorouracil-based combined with paclitaxel drugs in the treatment of gastric cancer;

[0039] Figure 9 This is a schematic diagram of the electronic device. Detailed Implementation

[0040] The present invention is further illustrated below by way of embodiments, but the invention is not limited to the scope of the embodiments described herein. Experimental methods in the following embodiments that do not specify specific conditions were performed according to conventional methods and conditions, or as selected according to the product instructions.

[0041] The clinical sample of 44 gastric cancer patients who received platinum-based combined fluorouracil-based combined paclitaxel therapy required for the examples included 22 patients in the treatment-sensitive group and 22 patients in the non-sensitive group (each accounting for 50% of the total sample) (as shown in Table 1). The design and implementation of this study were approved and supervised by the medical ethics committee through ethical voting, and written informed consent was obtained from all patients.

[0042] Table 1. Case treatment information of clinical samples

[0043] Exp033883 M 64 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 2 Exp033884 M 52 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 2 Exp033890 M 63 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 2 Exp033886 M 54 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 2 Exp033885 F 50 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 2 Exp033887 F 68 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 2 Exp033888 M 56 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 2 Exp033889 M 60 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 2 Exp033895 M 47 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 2 Exp033891 M 71 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 2 Exp033892 F 51 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 2 Exp033893 F 64 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 2 Exp033897 M 53 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 4 Exp033899 M 59 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 4 Exp034528 M 62 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 4 Exp034526 M 62 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 3 Exp034527 M 66 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 2 Exp034529 F 67 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 4 Exp034530 M 61 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 2 Exp034531 M 61 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 3 Exp034532 F 53 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 4 Exp034533 F 33 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 4 Exp034552 M 53 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 3 Exp034541 F 38 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 4 Exp034957 M 72 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 4 Exp034561 M 29 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 4 Exp034562 M 56 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 3 Exp034962 M 57 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 4

[0044] Exp035071 M 71 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 11 Exp035072 M 52 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 2 Exp035073 M 63 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 2 Exp035074 M 66 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 3 Exp035076 M 57 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 8 Exp035077 F 48 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 12 Exp035078 F 44 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 3 Exp035079 M 56 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 13 Exp035080 F 50 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 26 Exp035081 M 75 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 2 Exp035083 M 67 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 6 Exp041349 M 64 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 2 Exp041353 M 51 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 4 Exp041357 F 34 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 4 Exp042810 M 22 Platinum-based plus fluorouracil-based combined with paclitaxel chemotherapy regimen 6

[0045] Example 1: Pretreatment of clinical samples before gastric cancer treatment

[0046] Clinical samples were formalin-fixed paraffin-embedded tissues. Sample pretreatment: 3-10 μm thick sections were taken from the paraffin blocks for macroscopic dissection, dewaxed with xylene, washed with ethanol, and air-dried to obtain white slides. Simultaneously, the 3 μm thick sections were stained with hematoxylin and eosin for microscopic evaluation of tumor cell content and tumor region delineation. Tumor samples from the 10 μm thick sections were collected into centrifuge tubes and stored at -80°C for later use.

[0047] Example 2: Extraction of proteins and peptides from clinical samples

[0048] Equal volumes of FFPE (tumor samples prepared in Example 1) tissue were collected in EP tubes, and lysis buffer (0.1M Tris-HCl pH 8.0, 0.1M DTT, 1mM PMSF) was added. The mixture was then ground for 3 minutes. Sodium dodecyl sulfate (SDS) was added to a final concentration of 4%, and the mixture was incubated at 99°C and 1800 rpm for 2-2.5 hours. The supernatant was collected by centrifugation at 12,000g for 5 minutes and added to an EP tube. Four volumes of acetone were added, and the mixture was incubated at -20°C for 4 hours or overnight. The supernatant was discarded by centrifugation at 4°C for 1 minute, and the precipitate was washed three times with cold acetone. The protein precipitate was then air-dried in a clean bench. The protein precipitate was reconstituted with 8M Urea and 50mM NH4HCO3 and added to a FASP tube. Urea was removed by repeated centrifugation with 50mM NH4HCO3. 50μL of 50mM NH4HCO3 containing 5.5μg of trypsin was added to the EP tube. NH4HCO3 was added to a FASP tube and incubated at 37°C for 18-20 hours for enzymatic digestion. The peptides were collected by centrifugation at 12,800g for 15 minutes. To improve the peptide yield, the peptides were washed twice with 200 μL of MS water and collected together. The peptides were dried under vacuum at 60°C to obtain the peptides required for mass spectrometry detection.

[0049] Example 3: Mass spectrometry detection of clinical samples

[0050] The peptide sample was detected using a Q-Exactive HF-X hybrid quadrupole orbital trap mass spectrometer (Thermo Fisher Scientific, Rockford, IL, USA) and a high-performance liquid chromatography system (EASY nLC 1200, Thermo Fisher), and the corresponding mass spectrometric data were obtained. The specific procedures were as follows:

[0051] The dried peptide sample was redissolved in solvent A (0.1% formic acid aqueous solution) and loaded onto a trap column (100 μm × 2 cm; particle size, 3 μm; pore size, ...). The particles were then separated on an analytical column (150 μm × 12 cm, particle size 1.9 μm; pore size...). The elution gradient was 5-35% mobile phase B (80% acetonitrile and 0.1% formic acid) at a flow rate of 600 nL / min for a total elution time of 75 min. MS analysis of the QE-HFX was performed using a single full scan (300-1400 m / z, resolution = 12000). The maximum number of ions allowed in the ion trap (automatic gain control target, AGC target) was 3E+06 ions, followed by high-energy collision-induced dissociation (isolation window 1.6 m / z, collision energy 27%, AGC target 5E+04 ions, maximum injection time 30 ms, dynamic exclusion set to 18 seconds). Data acquisition was performed using the Xcalibur software (Thermo Scientific) on the liquid chromatography-tandem mass spectrometry system.

[0052] Example 4: Predicting the efficacy of platinum-based drugs plus fluorouracil-based drugs combined with paclitaxel in the treatment of gastric cancer.

[0053] All data were processed using Firmiana (V1.0). Firmiana is a workflow based on the Galaxy system, consisting of multiple functional modules including a user login interface, raw data, identification and quantification, data analysis, and knowledge mining. This embodiment uses a machine learning algorithm based on a generalized linear regression model. The raw files were retrieved from the Refseq protein database of the National Center for Biotechnology Information (NCBI) (04-07-2013, 32,015 entries). Trypsin was selected as the proteolytic enzyme, with a maximum allowable two missed cleavage sites. The fixed modification was carbamidomethyl (C), and the dynamic modification was protein acetyl (protein N-term), oxidation (M). The first search quality tolerance was 20 ppm, and the major search peptide tolerance was 0.5 da. The peptide matching (PSMs) and protein false discovery rate (FDR) were both less than 1%. The quantification results of the identified peptides were recorded as the average of the peak areas of chromatographic fragment ions in all reference libraries. Protein quantification was performed using a label-free intensity-based absolute quantification (iBAQ) method. Peak area values ​​were calculated as a subset of the corresponding proteins. The Total Quantity (FOT) score was used to represent the normalized abundance of a specific protein in the sample. FOT was defined as the protein's iBAQ divided by the total iBAQ of all identified proteins in the sample. Proteins with at least one unique peptide and a 1% FDR were selected. The 44 clinical samples were divided into a training set (80% of the total samples) consisting of 35 samples and an internal validation set (20% of the total samples) consisting of 9 samples. The same training and validation sets were used in all groups below:

[0054] Group 1:

[0055] The predictive accuracy, sensitivity, and specificity of protein expression levels of seven protein biomarkers (AHR, ATP5S, C11orf31, C20orf26, CDC42SE2, CHGA, and CHP2) in clinical samples from gastric cancer patients were calculated. In the training set, the predictive accuracy was 100%, the diagnostic sensitivity was 100.00%, and the specificity was 100.00% (see [link to training set]). Figure 1 In the internal validation set, the predictive accuracy was 100%, the diagnostic sensitivity was 100.00%, and the specificity was 100% (see [link]). Figure 1 For patients with untreated gastric cancer, the output results of different responses to platinum-based combined with fluorouracil therapy were obtained based on the expression levels of protein molecular biomarkers, thereby recommending or not recommending this treatment regimen to the patient (see Table 3).

[0056] Group 2:

[0057] Based on the first group of biomarkers, the protein biomarker AQP1 was added. The predictive accuracy, sensitivity, and specificity of the protein expression levels of the combination of these eight protein biomarkers (AHR, AQP1, ATP5S, C11orf31, C20orf26, CDC42SE2, CHGA, and CHP2) were calculated. In the training set, the predictive accuracy was 100%, the diagnostic sensitivity was 100.00%, and the specificity was 100.00% (see [link to training set]). Figure 2 In the internal validation set, the predictive accuracy was 100%, the diagnostic sensitivity was 100.00%, and the specificity was 100% (see [link]). Figure 2 For patients with untreated gastric cancer, the output results of different responses to platinum-based combined with fluorouracil therapy were obtained based on the expression levels of protein molecular biomarkers, thereby recommending or not recommending this treatment regimen to the patient (see Table 3).

[0058] Group 3:

[0059] Based on the second group, it was expanded to include 234 protein molecular biomarkers (A1BG, AAMDC, AARS2, ACLY, ACTL6A, AHR, AIF1L, ANAPC4, ANKMY2, APBB1IP, AQP1, ARAF, ARHGEF11, ARID2, ARPC3, ATP5S, ATP6AP1, BCAS3, BCS1L, BUD13, C11orf31, C11orf58, C12orf57, C2, C20orf26, C3orf37, C5AR1, C7orf50, CARHSP1, CASC3, CBLL1, CCDC86, CDC42SE2, C...). DKN2AIP, CEACAM1, CEP170B, CFD, CHCHD4, CHGA, CHI3L1, CHMP2B, CHP2, CLC, CMC1, CNPY4, CNTNAP1, COL6A5, COMMD1, COMMD4, COTL1, CTDNEP1, CTNNA2, CYBRD1, CYTH4, DCAF16, DCAF7, DCD, DDX28, GPCPD1, DDX43, DFNA5, DHODH, DHRS4, DMBT1, DOK2, DPM1, DRG1, DYNLT1, EHBP1L1, ELMOD2, EPB41L5, EPHX2, E TAA1, ETFDH, FADS3, FAM83G, FRK, FUT4, GGCX, GGH, GNA11, GNG4, GORAB, GPAM, GPR107, GUK1, HAPLN1, HDGFRP2, HLA-F, HNF1A, IFIT5, IGF2R, INSR, IPO1 3. ISYNA1, ITGA4, KCMF1, KDSR, KIAA1671, KPNA3, KRT73, LENG8, LIPA, LOC101059966, LSM7, LYPLAL1, LYSMD2, MAP2K6, MAPK13, MFN1, MPHOSPH6, MPP7, M RPL19, MRPL21, MRPL27, MRPL53, MRPS15, MRPS18A, MRPS36, MRPS6, MRPS9, MSRB2, MTARC2, MTG2, MTM1, NEBL, NEGR1, NEMF, NLN, NOL6, NOLC1, NRK, NUDT12 , NUP210, NUPL2, OLFML1, ORAI1, ORM1, OSBPL11, OSBPL1A, PADI4, PANK4, PAPLN, PARVG, PAWR, PDCD2, PDE5A, PI4KB, PKN1, PLCL2, PLEKHF2, PLVAP, PNKD,PPHLN1, PPM1A, PRELP, PRG2, PRR15L, PSCA, PSMB6, PSMD9, PTMS, PURB, RAB11A, RAB24, REG1A, REG3A, RFC2, RIC8A, RNF121, ROGDI, RPS15A, RPS23, RPS6KB2, RTFDC1, RTN4, R WDD1, SAAL1, SAMD9L, SCAF4, SCAF8, SERF2, SERPINA12, SERPINA6, SERPINB10, SERPINB9, SETD7, SHROOM3, SLC16A1, SLC27A3, SLC7A1, SMG1, SOS1, SOWAHC, SPHK2, SPIN1, SP The protein expression levels of 234 protein molecular biomarkers (see Table 2) were analyzed, and their predictive accuracy, sensitivity, and specificity were calculated. These biomarkers included INK1, SRA1, STOML3, SUMO2, TACC3, TADA1, TAF10, TAF5, TARBP1, TBC1D10A, TBCK, TBK1, TBP, TFCP2L1, THNSL1, TIMM22, TJP3, TMED8, TMEM246, TMEM63A, TNFAIP8, TP53I11, TRAPPC6B, TTC39A, TTI1, UBL3, UCHL1, URB2, UTP14A, VPS33A, WDR47, WIZ, WLS, XPO4, YIPF5, YKT6, ZFYVE21, and ZRANB2.

[0060] Table 2 List of protein information for all biomarkers

[0061]

[0062]

[0063] In the training set, the prediction accuracy was 100%, the diagnostic sensitivity was 100.00%, and the specificity was 100.00% (see...). Figure 3 In the internal validation set, the predictive accuracy was 100%, the diagnostic sensitivity was 100.00%, and the specificity was 100% (see [link]). Figure 3 For patients with untreated gastric cancer, the output results of different responses to platinum-based combined with fluorouracil therapy were obtained based on the expression levels of protein molecular biomarkers, thereby recommending or not recommending this treatment regimen to the patient (see Table 3).

[0064] The results above indicate that combining seven protein molecular biomarkers (see Group 1) from clinical samples of gastric cancer patients can be used to predict whether gastric cancer patients receiving platinum-based plus fluorouracil-based plus paclitaxel treatment will produce an effective therapeutic effect of tumor regression.

[0065] Based on this, adding protein molecular biomarkers (such as Group 2 and Group 3) can provide a good predictive effect on whether gastric cancer patients receiving platinum-based plus fluorouracil combined with paclitaxel treatment will achieve effective tumor regression.

[0066] Example 5: System for predicting the efficacy of platinum-based plus fluorouracil-based combined with paclitaxel therapy in gastric cancer.

[0067] System 61 for predicting the efficacy of platinum-based plus fluorouracil-based combined with paclitaxel therapy for gastric cancer: Data processing module 52 and judgment and output module 53, and also includes data collection module 51. Figure 8 ).

[0068] The data collection module 51 is used to collect expression data of the biomarker combination in the patient's gastric cancer tissue sample and transmit it to the data processing module.

[0069] The data processing module 52 is used to analyze the expression data of the received or input biomarker combination according to the data analysis method described in Example 4 to obtain calculation results. The expression data of the biomarker combination can be collected by the data collection module 51, or it can be obtained from other sources.

[0070] The judgment and output module 53 is used to judge whether the calculation result meets the preset judgment condition, that is, the sensitive prediction probability is greater than the non-sensitive prediction probability, so as to predict the effect of platinum-based drugs plus fluorouracil combined with paclitaxel in the treatment of gastric cancer, and output the prediction result; wherein, in the judgment and output module, when the expressed data meets the judgment condition that the sensitive prediction probability is greater than or equal to the non-sensitive prediction probability, the output prediction result is "platinum-based drugs plus fluorouracil combined with paclitaxel have a therapeutic effect on gastric cancer"; when the expressed data does not meet the judgment condition that the sensitive prediction probability is less than the non-sensitive prediction probability, the output prediction result is "platinum-based drugs plus fluorouracil combined with paclitaxel have no therapeutic effect on gastric cancer".

[0071] Example 6 Electronic device

[0072] This embodiment provides an electronic device, which can be represented in the form of a computing device (e.g., a server device), including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it can implement the method for predicting the therapeutic effect of platinum-based plus fluorouracil-based combined paclitaxel drugs for gastric cancer as described in Embodiment 4 of this invention.

[0073] Figure 9 This embodiment shows a hardware structure diagram, and the electronic device 9 specifically includes:

[0074] At least one processor 91, at least one memory 92, and a bus 93 for connecting different system components (including processor 91 and memory 92), wherein:

[0075] Bus 93 includes a data bus, an address bus, and a control bus.

[0076] The memory 92 includes volatile memory, such as random access memory (RAM) 921 and / or cache memory 922, and may further include read-only memory (ROM) 923.

[0077] The memory 92 also includes a program / utility 925 having a set (at least one) of program modules 924, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0078] The processor 91 executes various functional applications and data processing by running computer programs stored in the memory 92, such as the data analysis method of Embodiment 4 of the present invention.

[0079] Electronic device 9 can further communicate with one or more external devices 94 (e.g., keyboard, pointing device, etc.). This communication can be performed via input / output (I / O) interface 95. Furthermore, electronic device 9 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public network, such as the Internet) via network adapter 96. Network adapter 96 communicates with other modules of electronic device 9 via bus 93. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 9, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.

[0080] It should be noted that although several units / modules or sub-units / modules of the electronic device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided and embodied by multiple units / modules.

[0081] Example 7: Computer-readable storage medium

[0082] This invention provides a computer-readable storage medium storing a computer program thereon. When the program is executed by a processor, it implements the steps of the method in Embodiment 4 of this invention for predicting the therapeutic effect of platinum-based drugs plus fluorouracil-based drugs combined with paclitaxel in gastric cancer.

[0083] The readable storage medium may be more specifically adopted, including but not limited to: portable disk, hard disk, random access memory, read-only memory, erasable programmable read-only memory, optical storage device, magnetic storage device, or any suitable combination thereof.

[0084] In a possible implementation, the present invention can also be implemented as a program product comprising program code, wherein when the program product is run on a terminal device, the program code is used to cause the terminal device to execute the steps of the method for predicting the therapeutic effect of platinum-based plus fluorouracil-based combined paclitaxel drugs in embodiment 4 of the present invention.

[0085] The program code for executing the present invention can be written in any combination of one or more programming languages. The program code can be executed entirely on the user device, partially on the user device, as a standalone software package, partially on the user device and partially on a remote device, or entirely on a remote device.

[0086] Comparative Example 1: Predictive Performance of Combinations of Fewer Protein Biomarkers

[0087] Based on the seven protein molecular biomarkers in Group 1, the number of protein molecular biomarkers was reduced to form a combination of fewer protein molecular biomarkers. The prediction accuracy of each group was calculated using the same database, analysis methods, training set, and validation set as in Examples 1-4.

[0088] Group 4

[0089] In the absence of CHGA protein, the biomarker combination was AHR, ATP5S, C11orf31, C20orf26, CDC42SE2, and CHP2. In the training set, the accuracy was 94.29%, with sensitivity and specificity of 94.74% and 93.75%, respectively; in the internal validation set, the accuracy was 88.89%, with sensitivity and specificity of 100% and 83.33%, respectively (see [link to relevant documentation]). Figure 4 For patients with untreated gastric cancer, the output results of different responses to platinum-based combined with fluorouracil therapy were obtained based on the expression levels of protein molecular biomarkers, thereby recommending or not recommending this treatment regimen to the patient (see Table 3).

[0090] Group 5

[0091] In the absence of CHP2, CHGA, and C20orf26 proteins, the biomarker combination was AHR, ATP5S, C11orf31, and CDC42SE2. In the training set, the accuracy was 82.86%, with sensitivity and specificity of 84.21% and 81.25%, respectively; in the internal validation set, the accuracy was 88.89%, with sensitivity and specificity of 100% and 83.33%, respectively (see [link to relevant documentation]). Figure 5 For patients with untreated gastric cancer, the output results of different responses to platinum-based combined with fluorouracil therapy were obtained based on the expression levels of protein molecular biomarkers, thereby recommending or not recommending this treatment regimen to the patient (see Table 3).

[0092] Group 6

[0093] In the absence of CHP2, CHGA, C20orf26, and ATP5S proteins, the biomarker combination was AHR, C11orf31, and CDC42SE2. In the training set, the accuracy was 77.14%, with sensitivity and specificity of 78.95% and 75%, respectively; in the internal validation set, the accuracy was 66.67%, with sensitivity and specificity of 66.67% and 66.67%, respectively (see [link to relevant documentation]). Figure 6 For patients with untreated gastric cancer, the output results of different responses to platinum-based combined with fluorouracil therapy were obtained based on the expression levels of protein molecular biomarkers, thereby recommending or not recommending this treatment regimen to the patient (see Table 3).

[0094] Group 7

[0095] In the absence of CHP2, CHGA, C20orf26, ATP5S, and C11orf31 proteins, the biomarker combination was AHR and CDC42SE2. In the training set, the accuracy was 65.71%, with sensitivity and specificity of 57.89% and 75%, respectively; in the internal validation set, the accuracy was 58.67%, with sensitivity and specificity of 58.67% and 58.67%, respectively (see [link to relevant documentation]). Figure 7 For patients with untreated gastric cancer, the output results of different responses to platinum-based combined with fluorouracil therapy were obtained based on the expression levels of protein molecular biomarkers, thereby recommending or not recommending this treatment regimen to the patient (see Table 3).

[0096] Table 3. Predictive probability of sensitivity or insensitivity of each biomarker combination for patients with gastric cancer to receive platinum-based plus fluorouracil combined with paclitaxel therapy.

[0097]

[0098]

[0099] Recommended reference values: If the sensitive predictive probability is greater than the non-sensitive predictive probability and the sensitive predictive probability is greater than 0.8, the treatment plan is recommended to the patient; if the non-sensitive predictive probability is greater than the sensitive predictive probability and the non-sensitive predictive probability is greater than 0.8, the treatment plan is not recommended; if the sensitive predictive probability or the non-sensitive predictive probability is less than or equal to 0.8, the treatment plan is not recommended.

[0100] The above results indicate that as the number of proteins in the minimum biomarker combination is successively lost, the accuracy of the biomarker combination prediction decreases, and the sensitivity and specificity also decrease. Therefore, the proteins in the biomarker combination AHR, ATP5S, C11orf31, C20orf26, CDC42SE2, CHGA, and CHP2 are the minimum necessary biomarkers to ensure the highest prediction accuracy.

[0101] Finally, the above specific implementation methods are only used to illustrate the technical solution of the present invention, and are not intended to limit it.

Claims

1. A combination of protein biomarkers for predicting the efficacy of platinum-based plus fluorouracil-based combined with paclitaxel drugs in the treatment of gastric cancer, characterized in that, The protein biomarker group consists of the following biomarkers: AHR, ATP5S, C11orf31, C20orf26, CDC42SE2, CHGA and CHP2.

2. A combination of protein biomarkers for predicting the efficacy of platinum-based plus fluorouracil-based combined with paclitaxel drugs in the treatment of gastric cancer, characterized in that, The protein biomarker group consists of the following biomarkers: AQP1, AHR, ATP5S, C11orf31, C20orf26, CDC42SE2, CHGA and CHP2.

3. A combination of protein biomarkers for predicting the efficacy of platinum-based plus fluorouracil-based combined with paclitaxel drugs in the treatment of gastric cancer, characterized in that, The protein biomarker combination consists of the following biomarkers: AQP1, AHR, ATP5S, C11orf31, C20orf26, CDC42SE2, CHGA, CHP2, A1BG, AAMDC, AARS2, ACLY, ACTL6A, AIF1L, ANAPC4, ANKMY2, APBB1IP, ARAF, ARHGEF11, ARID2, ARPC3, ATP6AP1, BCAS3, BCS1L, BUD13, C11orf58, C12orf57, C2, C3orf37, C5AR1, C7orf50, CARHSP1, CASC3, CBLL1, CCD C86, CDKN2AIP, CEACAM1, CEP170B, CFD, CHCHD4, CHI3L1, CHMP2B, CLC, CMC1, CNPY4, CNTNAP1, COL6A5, COMMD1, COMMD4, COTL1, CTDNEP1, CTNNA2, CYBRD1 , CYTH4, DCAF16, DCAF7, DCD, DDX28, GPCPD1, DDX43, DFNA5, DHODH, DHRS4, DMBT1, DOK2, DPM1, DRG1, DYNLT1, EHBP1L1, ELMOD2, EPB41L5, EPHX2, ETAA1, E TFDH, FADS3, FAM83G, FRK, FUT4, GGCX, GGH, GNA11, GNG4, GORAB, GPAM, GPR107, GUK1, HAPLN1, HDGFRP2, HLA-F, HNF1A, IFIT5, IGF2R, INSR, IPO13, ISYNA 1. ITGA4, KCMF1, KDSR, KIAA1671, KPNA3, KRT73, LENG8, LIPA, LOC101059966, LSM7, LYPLAL1, LYSMD2, MAP2K6, MAPK13, MFN1, MPHOSPH6, MPP7, MRPL19, M RPL21, MRPL27, MRPL53, MRPS15, MRPS18A, MRPS36, MRPS6, MRPS9, MSRB2, MTARC2, MTG2, MTM1, NEBL, NEGR1, NEMF, NLN, NOL6, NOLC1, NRK, NUDT12, NUP210 , NUPL2, OLFML1, ORAI1, ORM1, OSBPL11, OSBPL1A, PADI4, PANK4, PAPLN, PARVG, PAWR, PDCD2, PDE5A, PI4KB, PKN1, PLCL2, PLEKHF2, PLVAP, PNKD, PPHLN1,PPM1A、PRELP、PRG2、PRR15L、PSCA、PSMB6、PSMD9、PTMS、PURB、RAB11A、RAB24、 REG1A、REG3A、RFC2、RIC8A、RNF121、ROGDI、RPS15A、RPS23、RPS6KB2、RTFDC1、 RTN4、RWDD1、SAAL1、SAMD9L、SCAF4、SCAF8、SERF2、SERPINA12、SERPINA6、SER PINB10、SERPINB9、SETD7、SHROOM3、SLC16A1、SLC27A3、SLC7A1、SMG1、SOS1、SO WAHC、SPHK2、SPIN1、SPINK1、SRA1、STOML3、SUMO2、TACC3、TADA1、TAF10、TAF5 、TARBP1、TBC1D10A、TBCK、TBK1、TBP、TFCP2L1、THNSL1、TIMM22、TJP3、TMED8、 TMEM246、TMEM63A、TNFAIP8、TP53I11、TRAPPC6B、TTC39A、TTI1、UBL3、UCHL1、 URB2、UTP14A、VPS33A、WDR47、WIZ、WLS、XPO4、YIPF5、YKT6、ZFYVE21、ZRANB2。、 4. A reagent for detecting the expression level of a combination of protein biomarkers as described in any one of claims 1-3, characterized in that, The reagent is an antibody that specifically binds to the combination of the protein biomarkers.

5. A reagent kit, characterized in that, Includes the reagent as described in claim 4.

6. The use of reagents for detecting the expression levels of the protein biomarker combination as described in any one of claims 1-3 and / or the kit as described in claim 5 in the preparation of formulations for predicting the efficacy of platinum-based plus fluorouracil-based combined paclitaxel drugs in the treatment of gastric cancer.

7. A system for predicting the efficacy of platinum-based plus fluorouracil-based combined with paclitaxel drugs in the treatment of gastric cancer, characterized in that, The system includes: The data processing module is used to receive or input expression data of the protein biomarker combination as described in any one of claims 1-3 from gastric cancer patients; The judgment and output module is used to process the expression data through Firmiana software after the reception or input is completed. The preset algorithm is a machine learning algorithm based on a generalized linear regression model to construct a prediction model, predict the sensitive prediction probability and the insensitive prediction probability of gastric cancer patients respectively, and judge whether the expression data meets the preset judgment conditions to predict the effect of platinum-based plus fluorouracil combined with paclitaxel drugs in the treatment of gastric cancer, and output the prediction results. Specifically, in the judgment and output module, when the expressed data meets the judgment condition (the sensitive prediction probability is greater than or equal to the insensitive prediction probability), the output prediction result is "Platinum-based drugs combined with fluorouracil and paclitaxel have a therapeutic effect on gastric cancer"; when the expressed data does not meet the judgment condition (i.e., the sensitive prediction probability is less than the insensitive prediction probability), the output prediction result is "Platinum-based drugs combined with fluorouracil and paclitaxel do not have a therapeutic effect on gastric cancer".

8. The system as described in claim 7, characterized in that, In the preset, the training set parameters are set to 80%, and the validation set parameters are set to 20%.

9. The system as described in claim 7 or 8, characterized in that, The system also includes a data collection module for collecting expression data of the protein biomarker combination in gastric cancer tissue samples from patients and transmitting it to the data processing module.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it can realize the function of the system as described in any one of claims 7-9, or realize the steps of a computer-aided method for predicting the efficacy of platinum-based plus fluorouracil-based combined paclitaxel-based drugs in the treatment of gastric cancer. The method includes the following steps: (1) Receive or input the expression data of the combination of protein biomarkers as described in any one of claims 1-3 of a gastric cancer patient, process the expression data through Firmiana software, pre-set a machine learning algorithm based on a generalized linear regression model, construct a prediction model, and predict the sensitive prediction probability and the insensitive prediction probability of the gastric cancer patient respectively. (2) Determine whether the expressed data meets the preset judgment conditions, wherein the judgment conditions are that the sensitive prediction probability is greater than or equal to the non-sensitive prediction probability, so as to predict the effect of platinum-based plus fluorouracil-based combined paclitaxel-based drugs in the treatment of gastric cancer, and output the prediction results; In step (2), when the expressed data meets the judgment condition, the output prediction result is "platinum-based drugs plus fluorouracil combined with paclitaxel have a therapeutic effect on gastric cancer"; when the expressed data does not meet the judgment condition, the output prediction result is "platinum-based drugs plus fluorouracil combined with paclitaxel have no therapeutic effect on gastric cancer".

11. An electronic device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor is used to execute the computer program to implement the functions of the system as described in any one of claims 7-9, or to implement the steps of the computer-aided method for predicting the efficacy of platinum-based plus fluorouracil-based combined paclitaxel-based treatment for gastric cancer as described in claim 10.

Images