Methods and apparatus for predicting the stage of disease of a BK virus infection based on gene expression

Abstract

The application belongs to the field of intelligent medical treatment, and particularly relates to a method and device for predicting a BK virus infection disease stage based on gene expression. The method comprises the following steps: obtaining a tissue sample of a to-be-tested person; obtaining an expression amount of a target gene of a region of interest based on the tissue sample, the region of interest being PanCK+, and the target gene comprising one or more of the following: HLA-DPA1 and LYZ; inputting the expression amount of the target gene of the region of interest into a classifier, and predicting a BK virus infection stage of the to-be-tested person according to an output of the classifier, wherein the BK virus infection stage comprises the following: non-infection, BK viremia, and BK nephropathy. The application realizes the differentiation of BK virus infection stages based on gene expression, and helps to realize symptomatic treatment from the gene expression level.

Description

Technical Field

[0001] The present invention relates to the field of intelligent medicine, and more specifically, to a method, device, medium and program product for predicting the stage of BK virus infection disease based on gene expression. Background Art Summary of the Invention

[0002] In view of the above problems, the present invention provides a method for predicting the stage of BK virus infection disease based on gene expression, using data processing and feature extraction to capture information in time series data, and proposes improvements to the parameters of the disease prediction model and performs effective optimization, thereby constructing a disease warning model suitable for clinical use.

[0003] The present application (first aspect) discloses a method for predicting the disease stage of BK virus infection based on gene expression, comprising:

[0004] Obtaining tissue samples from the subject;

[0005] Obtaining the expression level of a target gene in a region of interest based on the tissue sample, wherein the region of interest is PanCK+, and the target gene includes one or more of the following: HLA-DPA1, LYZ;

[0006] The expression level of the target gene in the region of interest is input into a classifier, and the BK virus infection stage of the subject is predicted based on the output of the classifier. The BK virus infection stage includes: uninfected, BK blood, and BK nephropathy.

[0007] Furthermore, the region of interest further includes: CD45+, and the target gene further includes one or more of the following: HLA-DQA2;

[0008] Optionally, the region of interest further includes: SMA, and the target gene further includes: IGHM.

[0009] Furthermore, the target genes of PanCK+ in the region of interest also include one or more of the following: RHCG, CA2, CALB1, C5orf38, DEFB1, ATP6V1B1, HOXD8, SERPINA5, WNK1, IGFBP5, IL4I1, TMEM52B, STC1, DUSP15, SLC4A9, SCPEP1, ATP6V1G3, ATP6V0A4, TMEM213, ATP6V0D2, GGTLC2, FZD4, ADAMTS1, CKMT2, HSD11B2, CLDN8, PVALB, CA12, SLC12A3, RHBG, IDH2, SLC8A1, IL17RB, CLEC3B, CLCNKB, PGGHG, SLC26A4, S100A9, KLK1, SIM2, and ATP1B1;

[0010] Optionally, the target genes of CD45+ in the region of interest further include one or more of the following: APOE, CTSB, LGMN, SUSD2, MS4A4E, SLC1A3, GRAPL, POSTN, FBP1, FCMR, STEAP4, SERPINE1, HLA-DQA1, and GPX3;

[0011] Optionally, the target genes of the SMA region of interest further include one or more of the following: HLA-DQA1, TRAM1, MCCD1, C5orf38, MT1E, PPA1, SERPINE1, ITGA3, and GLUL.

[0012] Furthermore, the number of renal tubular epithelial cells of the subject is obtained at the same time, the expression levels of the target gene in the region of interest and the number of renal tubular epithelial cells are input into a classifier, and the BK virus infection stage of the subject is predicted based on the output of the classifier;

[0013] Optionally, the degree of renal interstitial fibrosis is obtained at the same time, the expression level of the target gene in the region of interest and the degree of renal interstitial fibrosis are input into a classifier, and the BK virus infection stage of the subject is predicted based on the output of the classifier.

[0014] Furthermore, spatial transcriptome technology is used to measure the expression level of the target gene of interest in the subject.

[0015] Furthermore, the target gene of the region of interest is obtained as follows:

[0016] Kidney tissue samples were obtained from the uninfected group, BK blood group, and BK nephropathy group;

[0017] constructing a sequencing library based on the renal tissue section sample to obtain gene expression levels in the region of interest;

[0018] The gene expression differences between different regions of interest at different stages of BK virus infection were examined to obtain differentially expressed genes between different groups;

[0019] The target genes in the region of interest are genes with the same change direction in the intersection of the differentially expressed genes between the non-infected group and the BK blood group, and the differentially expressed genes between the BK blood group and the BK nephropathy group, among the differentially expressed genes between the different groups;

[0020] Optionally, the target genes in the region of interest are the intersection of the differentially expressed genes between the non-infected group progressing to the BK blood group and the differentially expressed genes between the BK blood group progressing to the BK nephropathy group among the differentially expressed genes between different groups;

[0021] Optionally, the method for constructing a sequencing library includes:

[0022] The renal tissue section sample is pretreated and then digested according to the DSP standard method to obtain a sample with RNA target exposure;

[0023] Fixing the sample exposed to the RNA target site, performing in situ hybridization incubation, and then performing nuclear staining to obtain a stained sample;

[0024] Based on the stained sample, a sequencing library is constructed after selecting regions of interest through DSP.

[0025] Furthermore, after the renal tissue sections are incubated with morphologically labeled fluorescent antibodies, fluorescent imaging is performed on the incubated renal tissue sections using a DSP system, and regions of interest are selected based on the morphologically labeled antibodies.

[0026] Further, obtaining the expression level of the target gene in the first region of interest, inputting the expression level of the target gene in the first region of interest into a first classifier, and predicting whether the subject is infected with the BK virus based on the output of the first classifier;

[0027] Optionally, obtaining the expression level of the target gene in the second region of interest, inputting the expression level of the target gene in the second region of interest into a second classifier, and predicting whether the subject suffers from BK nephropathy based on the output of the second classifier;

[0028] Optionally, the expression levels of the target gene in the first region of interest and the expression levels of the target gene in the second region of interest are obtained, and the expression levels of the target gene in the first region of interest are first input into a first classifier. If the output of the first classifier predicts that the subject is infected with BK virus, the expression levels of the target gene in the second region of interest are input into a second classifier to predict whether the subject has BK nephropathy, thereby obtaining the BK virus infection disease stage of the subject;

[0029] Optionally, a method for obtaining the target gene in the first region of interest includes:

[0030] Kidney tissue section samples were obtained from the uninfected group and the BK-infected group;

[0031] constructing a sequencing library based on the renal tissue section sample to obtain gene expression levels in the region of interest;

[0032] Examining the gene expression differences between the uninfected group and the BK infected group to obtain the target genes of the first region of interest;

[0033] Optionally, a method for obtaining the target gene in the second region of interest includes:

[0034] Kidney tissue samples were obtained from the non-BK nephropathy group and the BK nephropathy group;

[0035] constructing a sequencing library based on the renal tissue section sample to obtain gene expression levels in the region of interest;

[0036] The gene expression differences between the non-BK nephropathy group and the BK nephropathy group were examined to obtain the target genes of the second region of interest.

[0037] The second aspect of the present application discloses a system for predicting the stage of BK virus infection based on gene expression, comprising:

[0038] Acquisition module 201: used to obtain tissue samples from the subject;

[0039] Extraction module 202: used to obtain the expression level of the target gene in the region of interest based on the tissue sample, the region of interest is PanCK+, and the target gene includes one or more of the following: HLA-DPA1, LYZ;

[0040] Prediction module 203: used to input the expression level of the target gene in the region of interest into a classifier, and predict the BK virus infection stage of the subject according to the output of the classifier. The BK virus infection stage includes: uninfected, BK blood, and BK nephropathy.

[0041] The third aspect of the present application discloses a computer device, which includes: a memory and a processor; the memory is used to store program instructions; the processor is used to call the program instructions, and when the program instructions are executed, it is used to perform the steps of the above method.

[0042] In a fourth aspect, the present application discloses a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above-mentioned method when the computer program is executed by a processor.

[0043] In a fifth aspect, the present application discloses a computer program product, comprising a computer program, which implements the steps of the above method when executed by a processor.

[0044] This application has the following beneficial effects:

[0045] 1. This application achieves the distinction of BK virus infection stages based on gene expression, which helps to achieve symptomatic treatment at the gene expression level.

[0046] 2. This application demonstrates that the expression of HLA-DPA1 and LYZ genes of PANCK+ is closely related to the stage of BK virus infection.

[0047] 3. This application demonstrates that the expression of the HLA-DQA2 gene in CD45+ is closely related to the stage of BK virus infection.

[0048] 4. This application demonstrates that the expression of the IGHM gene of SMA is closely related to the stage of BK virus infection. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0050] Figure 1 This is a schematic diagram of the method flow provided by the first aspect of the embodiment of the present invention;

[0051] Figure 2 is a schematic diagram of a program product provided by the second aspect of an embodiment of the present invention;

[0052] Figure 3 is a schematic diagram of a computer device provided by an embodiment of the present invention;

[0053] Figure 4 is a schematic diagram of the architecture of an exemplary computing device provided by an embodiment of the present invention;

[0054] Figure 5 is a schematic diagram of a storage medium provided by an embodiment of the present invention;

[0055] Figure 6 This is a PanCK four-color fluorescence result diagram provided by an embodiment of the present invention;

[0056] Figure 7 This is a CD45 four-color fluorescence result diagram provided by an embodiment of the present invention;

[0057] Figure 8 This is a CD45 four-color fluorescence result diagram provided by an embodiment of the present invention;

[0058] Figure 9 This is a SMA four-color fluorescence result diagram provided by an embodiment of the present invention;

[0059] Figure 10 This is a low-expression gene detection map provided by an embodiment of the present invention;

[0060] Figure 11 This is a Target LOQ QC diagram provided by an embodiment of the present invention;

[0061] Figure 12 is a correlation analysis diagram of a standardization method provided by an embodiment of the present invention;

[0062] Figure 13 This is a gene expression profile heat map provided by an embodiment of the present invention;

[0063] Figure 14 This is a principal component analysis diagram provided by an embodiment of the present invention;

[0064] Figure 15 : This is a Panck+ differential gene expression plot provided by an embodiment of the present invention: (A) Panck+ differential gene volcano plot of BKV_vs_Normal; (B) Panck+ differential gene volcano plot of BKVAN_vs_Normal; (C) Panck+ differential gene volcano plot of BKVAN_vs_BKV; (D) Venn diagram of differential genes at different infection stages; (E) Box plot of expression of the progression-related gene HLA-DPA1 in different regions of interest; (F) Box plot of expression of the progression-related gene LYZ in different regions of interest;

[0065] Figure 16 : This is a Panck+ differential gene expression plot provided by an embodiment of the present invention: (A) Panck+ differential gene volcano plot of BKV_vs_Normal; (B) CD45+ differential gene volcano plot of BKVAN_vs_Normal; (C) Panck+ differential gene volcano plot of BKVAN_vs_BKV; (D) Venn diagram of differential genes at different infection stages; (E) expression box plot of the progression-related gene HLA-DPA1 in different regions of interest; (F) expression box plot of the progression-related gene LYZ in different regions of interest;

[0066] Figure 17: This is a Panck+ differential gene expression plot provided by an embodiment of the present invention: (A) SMA differential gene volcano plot of BKV_vs_Normal; (B) Panck+ differential gene volcano plot of BKVAN_vs_Normal; (C) Panck+ differential gene volcano plot of BKVAN_vs_BKV; (D) Venn diagram of differential genes at different infection stages; (E) expression box plot of the progression-related gene HLA-DPA1 in different regions of interest; (F) expression box plot of the progression-related gene LYZ in different regions of interest. DETAILED DESCRIPTION

[0067] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0068] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or may be executed in parallel. The serial numbers of the operations, such as S101, S102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., and do not represent the order of precedence, nor do they limit "first" and "second" to be different types.

[0069] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0070] Figure 1 FIG. 1 is a flow chart of a method for predicting the stage of BK virus infection based on gene expression assessment provided by an embodiment of the present invention. Specifically, the method comprises the following steps:

[0071] S101: Obtaining a kidney tissue sample from a subject;

[0072] S102: Obtaining expression levels of target genes in a region of interest based on the tissue sample, where the region of interest is PanCK+, and the target genes include one or more of the following: HLA-DPA1, LYZ;

[0073] S103: Inputting the expression level of the target gene in the region of interest into a classifier, and predicting the BK virus infection stage of the subject according to the output of the classifier, wherein the BK virus infection stage includes: uninfected, BK blood, and BK nephropathy.

[0074] In some embodiments, the following research steps are used to obtain target genes in the region of interest.

[0075] 1. Recruiting Participants

[0076] Renal tissue paraffin blocks were collected from the normal group, BK blood group, and BK nephropathy group.

[0077] 2. Spatial transcriptome sequencing experiment

[0078] 2.1 Sequencing Experiment Process

[0079] FFPE sections are incubated with morphologically labeled fluorescent antibodies and a mixture of all targets in the WTA Panel. Fluorescence imaging is performed using the DSP system, and regions of interest are selected based on the morphologically labeled antibodies. Oligos within the regions of interest are collected and used as templates for downstream NGS processes.

[0080] 2.1.2 Sample preprocessing

[0081] 1) Sample pretreatment: FFPE samples were dewaxed and hydrated according to DSP standard SOP; immunohistochemical pressure cooker was used for repair according to DSP standard antigen repair method.

[0082] 2) RNA target exposure: Digestion with Proteinase K according to the DSP standard method;

[0083] 3) Tissue Fixation: Take the sample from the previous step, add the fragmentation buffer, and place it in a PCR instrument for heat fragmentation to 140-160 nt;

[0084] 4) In situ hybridization: Incubate FFPE sections with antibodies from the WTA Panel (see [Appendix]) in a hybridization oven overnight in the dark.

[0085] 5) Blocking: Block at room temperature in the dark.

[0086] 6) Nuclear staining: Nuclear staining was completed using DSP standard Nuclear Stain SYTO13 and then tested on the instrument.

[0087] 7) Point of interest selection: Through DSP, complete the scanning of all slices and select the region of interest (ROI).

[0088] 8) Sequencing Library Construction: Seal the Collection Plate with a breathable membrane, dry in a thermal cycler, resuspend in DPEC water, allow to stand, and rapidly centrifuge. Establish a PCR system and perform PCR according to the standard DSP protocol to complete library construction (see figure below). The DSP Plate is the Collection Plate, the Primer Plate contains the primer sequences specifically labeled for each well, and the MasterMix contains the enzymes, dNTPs, and other components required for PCR. Purify the library sample using magnetic beads to obtain a pure library ready for sequencing.

[0089] 9) Library quality control and sequencing: Use QFX to quantify the purified product; use Qsep100 to detect the fragment length of the purified product; sequence the library according to the sequencing requirements of the DSP standard process.

[0090] 2.2DSP four-color fluorescence results

[0091] DSP four-color fluorescence results showed that the number of PanCK-positive epithelial cells increased significantly, indicating that the renal tubular epithelial cells in the BK nephropathy group had significant proliferation, while the BK blood group had mild proliferation ( Figure 6 The results of CD45 showed that some renal interstitial inflammatory cells were focally aggregated in the BK blood group, while most renal interstitial inflammatory cells were significantly infiltrated in the BK nephropathy group ( Figure 7 ), and patients with BK nephropathy showed partial glomerular inflammation ( Figure 8 The results of SMA four-color fluorescence showed that the renal interstitial SMA positive cells increased, and the BK blood group had partial renal interstitial fibrosis, while the BK nephropathy group had an increased degree of fibrosis ( Figure 9 ).

[0092] 3. Data Analysis Results of the Spatial Transcriptome Sequencing Project

[0093] 3.1 Data quality inspection results

[0094] NanoString recommended thresholds (Raw Reads > 1000, Aligned Reads Percentage > 80%, Sequencing Saturation > 50%, NTC > 1000, Nuclei Counts > 200, Surface Area > 16,000 μm², Target LOQ > 2.0) were used. Only ROIs that passed QC were included in downstream analysis. Probes that failed QC were removed from all ROIs.

[0095] 3.1.1Segment QC

[0096] Segment QC is a QC performed on AOIs / ROIs, as detailed below. If an AOI / ROI fails any of these QC steps, it will be removed and not included in the final result analysis.

[0097] 3.1.1.1Technical signal QC

[0098] Technical signal QC is an evaluation of the sequencing quality of each AOI / ROI. It has three indicators: Raw Reads, Aligned Reads Percentage, and Sequencing Saturation. Raw Reads: All read sequences of the AOI / ROI during sequencing. Aligned Reads Percentage: The proportion of read sequences in the AOI / ROI that are aligned to the template sequence. Sequencing Saturation: Sequencing reads of an AOI / ROI can be measured once or multiple times. Sequencing saturation refers to the proportion of reads detected at least twice in the raw reads, and it is recommended to be greater than 50%.

[0099] 3.1.1.2Technical background QC

[0100] Technical background QC is a running control set by the GeoMx DSP. It consists of two indicators: No Template Control Count (NTC Count) and Negative Probe Count. The NTC Count is a negative control experiment set during each WTA experiment. It contains no template and is used to detect template contamination during library construction. The NTC value for this WTA experiment was 3000.

[0101] The Negative Probe Count is the number of negative probe counts within each AOI / ROI and is used to measure the technical noise level of this WTA experiment. If the technical noise is too low, consider whether the AOI / ROI area is too small, library construction is unsuccessful, and sequencing depth is too low. Based on empirical values ​​for negative probe measurements, the technical noise level for each WTA experiment should be at least 5.

[0102] 3.1.1.3DSP parameters

[0103] GeoMx DSP limits the Nuclei Counts and Surface Area of ​​each AOI / ROI. Too low Nuclei Counts or Surface Area are not recommended.

[0104] 3.1.1.4low expression probe QC

[0105] The probes designed by GeoMx DSP are used to capture 18,676 target genes. Due to differences in gene expression, some genes will not be captured or the captured expression levels are very low (the default value is 1 as the indicator of low expression). If the vast majority (90% by default) of genes in a ROI are not captured or the expression levels are very low, then it is necessary to consider whether the data of this ROI should be included in the analysis. Otherwise, after the data is normalized, its expression levels will change significantly, and abnormal data trends will often appear in the cluster heat map or PCA map ( Figure 10 ).

[0106] 3.1.2Target LOQ QC

[0107] LOQ represents the limit of expression of a target and is calculated as follows:

[0108] LOQ=GeoMean(NegProbe)×GeoSD(NegProbe) threshold

[0109] In this WTA experiment, the threshold value is 2.0. The figure below shows the distribution of the ratio of the target signal to the LOQ in this WTA experiment. The y-axis has been log2 transformed ( Figure 11 ).

[0110] 3.1.3Normalization QC

[0111] Normalization methods include the Q3 method, which uses the 75th percentile gene as the benchmark for normalization. There are also HK and NegProbe methods. If the three methods are highly correlated, you can choose any one of them. Otherwise, the Q3 method is recommended. The correlation is shown in the figure below (Nuclei_count and Area are used as references for AOI / ROI uniformity). This study selected the Q3 method ( Figure 12 ).

[0112] 3.2 Gene expression profiling analysis

[0113] To explore the molecular changes during BK virus infection, we used GeoMx DSP technology to analyze eight paraffin-embedded renal tissue samples (3 normal, 2 BK viremia (BKV), and 3 BK virus nephropathy (BKVAN)). A total of 71 ROIs were selected from these samples (18 in Normal, 26 in BKV, and 27 in BKVAN), including smooth muscle actin (SMA), pan-cytokeratin positive (PanCK+), and leukocyte positive (CD45+). The gene expression profiles of each ROI are shown in Figure 2. Figure 13 shown.

[0114] 3.3 Principal component analysis diagram

[0115] Data exploration using principal component analysis ( Figure 14 ), as expected, the AOIs were divided into three groups according to the segment (PanCK+ / CD45+ / SMA). Within PanCK+, the BK virus nephropathy group showed clear separation from the other two groups, while the BK virus nephropathy group, with the exception of two ROIs in the second sample, also showed expression pattern differences from the normal group. In the CD45+ group, the normal group showed slight deviation from the BK virus infection group. In SMA, the normal group samples were significantly clustered together, while the viremia and viral nephropathy group samples were more dispersed, indicating strong heterogeneity between samples. These findings indicate that BK virus infection is associated with changes in the transcriptional profile not only of epithelial cells (PanCK+), but also of other surrounding cells.

[0116] SV40 immunohistochemistry

[0117] We performed SV40 testing on three normal renal transplant recipients, two patients with BK viremia, and three patients with BK nephropathy. The results showed that the renal transplant control group and the BK viremia group were SV40 negative, while the BK nephropathy group showed strong SV40 positivity, with a wide area of ​​positivity. Detailed results are available in: Kidney Transplant Immunohistochemistry Results.pptx. We compared the expression profiles of SV40-positive and SV40-negative samples (see 3.5.1.5, 3.5.2.5, and 3.5.3.5). The results showed that only a small number of genes were altered in CD45+ and SMA, while a large number of genes were significantly altered in the PANCK+-marked epithelium.

[0118] 3.5 Differential expression analysis

[0119] To gain a deeper understanding of gene expression changes following BK virus infection, differential expression analysis between different regions and diseases was performed using the unpaired T test, with Benjamini-Hochberg correction for multiple comparisons and a screening parameter of FDR < 0.05 and |log2foldchange| > 1. As expected, only minor differences were found between BKV and BKVAN in CD45+ and SMA, while more differences were observed between the two groups in PANCK+.

[0120] 3.5.1 PANCK+ differential expression

[0121] 3.5.1.1BKV_vs_Normal Difference Analysis

[0122] 461 differentially expressed genes were screened using the above criteria, of which 262 were up-regulated and 199 were down-regulated. The volcano plot of differentially expressed genes is shown in the figure below. Figure 15 -As shown in A.

[0123] 3.5.1.2BKVAN_vs_Normal Difference Analysis

[0124] 558 differentially expressed genes were screened using the above criteria, of which 332 were up-regulated and 226 were down-regulated. The volcano plot of differentially expressed genes is shown in Figure 2. Figure 15 -B.

[0125] 3.5.1.3BKVAN_vs_BKV Difference Analysis

[0126] 157 differentially expressed genes were screened using the above criteria, of which 94 were up-regulated and 63 were down-regulated. The volcano plot of differentially expressed genes is shown in the figure below. Figure 15 -C shown.

[0127] 3.5.1.4 BK virus infection-related genes in PANCK+

[0128] The differentially expressed intersection genes of the BKV_vs_Normal and BKVAN_vs_Normal groups were selected, and a total of 172 genes were obtained, of which 171 genes had the same expression trend. The intersection Venn diagram is shown as follows: Figure 15-D shows the intersection of the purple circle in the upper left corner and the green circle in the lower corner. Protein interaction network analysis of 171 BK virus infection-related genes using the String database (https: / / string-db.org / ) showed that most of these 171 genes formed a coherent network. WikiPathway and KEGG enrichment analysis were performed on genes in this network. The screening criterion was: pval_adj < 0.05. Therefore, these 172 genes can effectively distinguish whether they are infected with BK virus. Among them, 171 genes with consistent expression trends are: TMA7, OGDHL, SPANXA1, LGALS3, B2M, DHRS1, HLA-B, ELOA2, ELOA3P, HLA-E, CCDC13, TTC33, FAM90A1, XRCC2, HLA-A, OR4F21, BAGE5, H4C4, SPDYE5, DUX4, SPDYE16, CTSB, SPDYE3, USP17L3, DRD5, PIGR, GOLGA6L6, GPR4, ZNF346, SPDYE11, H4C12, FOXD4L5, STX1 B. SPATA2L, GJC2, HLA-C, USP17L15, NACA, PRAMEF6, PTBP1, KRT7, MBD3L2, PCBP1, PRSS3, CD74, ANXA4, IGFBP7, TRIM51, PITX 2. FCF1, TRIM64B, PRAMEF1, USP17L12, ORM2, HNRNPD, HPGDS, MANF, CHRNB4, PRR23D2, POTEG, DTD2, HLA-DRB1, HLA-DPB1, C11 orf96, GBA, MAGEA4, HLA-DRA, ANXA5, LGALS3BP, HLA-F, HLA-DPA1, ACSL4, TRIM49D2, AKR1A1, IFI30, TRIM43, HLA-DQB1, LAP3, OR10H2, HSPA8 , HSPA5, TUBB8, ANXA8, KRTAP5-1, RPL38, TSPY1, TMSB4X, OR4C13, ACR, HSP90AA1, DEFB131A, TP53, RPL4, POMP, H4C15, RPL30, USP17L11, PTH1 R, EIF4A3, RPL29, RAB8A, OR5H15, APOE, BTN3A2, PPDPF, C11 orf54, B4GALT1, RPS4X, OR2A2, PANX3, F11R, COL18A1, C4orf46, CALM2, TP53TG3B, FUCA2, ITM2B, RSRP1, OLFM1, USP17L17, CXCL9, NCOA2, SMIM31, ATP1A4, UCHL1, PPA1, H3C4, CAPG, C12orf75, RHOC, SELENOP, SOX2, S TMN1, LCE3A, PSMA4, ULBP1, PSMB8, RPS14, RPL36A, ADAR, BST2, CALR, RPL19, TMEM47, TMEM123, UBD, PRMT8, RPS12, TFAP2C, UMOD, WWTR1, RPS23, RPL37, STAT1, ZNF664, EEF1 G, KRT19, GDI2, RPL28, IGLL5, ACTR2, LYZ, TUBA1C, SAT1, IL2RG, TMEM243, VTCN1, CTSS, RPS8, EIF4G2, COTL1; those with inconsistent expression trends are RHCG.

[0129] 3.5.1.5 SV40-positive related genes in PANCK+

[0130] The differentially expressed intersection genes of the BKVAN_vs_Normal and BKVAN_vs_BKV groups were selected, and a total of 53 genes were obtained. The expression trends of these 53 genes were consistent. The intersection Venn diagram is shown as the intersection of the upper right yellow circle and the lower green circle in Figure 15-D.

[0131] These 53 genes can effectively distinguish whether BK virus progresses to nephropathy, including: IGHM, LYZ, HLA-DPA1, C1QB, C1QC, IFI27, PTPRC, HLA-DQA2, CD68, IFI6, C1 QA, ATP5MC2, LY6E, TRBC1, LAPTM5, MICALL2, APOC1, ANXA1, TYROBP, ITGB2, PLTP, C3, ZEB2, LTF, IFI44L, FCER1 G, HAVCR1, CAPN6, LSP1, ANPEP, JUN, SAMHD1, RNASE1, TRIM22, IFI44, XAF1, LGALS9C, IFIT1, KLF2, CX CL13, RHCG, VCAN, SLC34A2, ODF3B, TNFAIP2, MX1, SAA2, IRF7, TYMP, ADGRF5, OAS1, HMGCS2, TNFSF10.

[0132] In some embodiments, part or all of the 171 BK infection-related differentially expressed genes of Panck+ are first used to train a first classifier for distinguishing whether a new subject is infected with BK virus, and then part or all of the 53 SV40 positivity-related differentially expressed genes are used to train a second classifier for distinguishing whether the BK infection stage of the infected subject predicted by the first classifier is BKemia or BK nephropathy.

[0133] 3.5.1.6 Panck+ progression-related genes

[0134] The differentially expressed intersection genes between the BKV_vs_Normal and BKVAN_vs_BKV groups were selected, and a total of 43 genes were obtained. The intersection Venn diagram is shown in Figure 15-D, which is the intersection of the upper left purple circle and the upper right yellow circle. Among them, two genes, HLA-DPA1 ( Figure 15 -E middle figure) and LYZ ( Figure 15 -F (middle graph) showed the same expression trend, showing up-regulation when progressing from Normal to BKV and from BKV to BKVAN;

[0135] There were 33 genes that were up-regulated when Normal progressed to BKV, and showed the opposite expression trend when BKV progressed to BKVAN: CA2, CALB1, DEFB1, ATP6V1 B1, HOXD8, SERPINA5, WNK1, IGFBP5, TMEM52B, STC1, DUSP15, SLC4A9, SCPEP1, ATP6V1 G3, ATP6V0A4, TMEM213, ATP6V0D2, FZD4, CKMT2, HSD11 B2, CLDN8, PVALB, CA12, SLC12A3, RHBG, IDH2, SLC8A1, CLEC3B, CLCNKB, SLC26A4, KLK1, ATP1 B1, RHCG;

[0136] There were 8 genes that showed down-regulated expression when Normal progressed to BKV, and showed the opposite expression trend when BKV progressed to BKVAN: C5orf38, IL4I1, GGTLC2, ADAMTS1, IL17RB, PGGHG, S100A9, and SIM2.

[0137] Figure 15 The intersection centers of the three different infection stages of -D are HLA-DPA1, LYZ, and RHCG. Among them, the trends of HLA-DPA1 and LYZ are consistent in the two development processes, and the change trends of RHCG in the two development processes are opposite. The expression of these three genes can more effectively distinguish the three different infection stages of BK virus than the expression of other differential genes.

[0138] 3.5.2 Differential Expression of CD45+

[0139] 3.5.2.1BKV_vs_Normal Difference Analysis

[0140] 744 differentially expressed genes were screened using the above criteria, of which 479 were up-regulated and 265 were down-regulated. The volcano plot of differentially expressed genes is shown in Figure 2. Figure 16 -As shown in A.

[0141] 3.5.2.2BKVAN_vs_Normal Difference Analysis

[0142] 271 differentially expressed genes were screened using the above criteria, of which 258 were up-regulated and 13 were down-regulated. The volcano plot of differentially expressed genes is shown in the figure below. Figure 16 -B.

[0143] 3.5.2.3BKVAN_vs_BKV Difference Analysis

[0144] 34 differentially expressed genes were screened using the above criteria, including 14 up-regulated genes and 20 down-regulated genes. The volcano plot of differentially expressed genes is shown in the figure below. Figure 16 -C shown.

[0145] 3.5.2.4 BK virus infection-related genes in CD45+

[0146] The differentially expressed intersection genes of the BKV_vs_Normal and BKVAN_vs_Normal groups were selected, and a total of 178 genes were obtained, of which 177 genes had the same expression trend. The intersection Venn diagram is shown as follows Figure 16 -D (The intersection of the purple circle in the upper left and the green circle in the lower left) shows that protein interaction network analysis of 171 BK virus infection-related genes using the String database (https: / / string-db.org / ) shows that most of these 178 genes form a coherent network. WikiPathway and KEGG enrichment analysis were performed on genes in this network. The screening criterion was: pval_adj < 0.05.

[0147] 3.5.2.5 SV40-positive related genes in CD45+

[0148] The differentially expressed intersection genes between the BKVAN_vs_Normal and BKVAN_vs_BKV groups were selected, and a total of 4 genes (HLA-DQA2, APOE, HLA-DQA1, CTSB) were obtained. Among them, only 2 genes had the same expression trend (HLA-DQA2 and HLA-DQA1). The intersection Venn diagram is shown in the figure below. Figure 16-D is shown by the purple circle in the upper left and the yellow circle in the upper right.

[0149] 2.5.2.6 Progression-related genes in CD45+

[0150] The differentially expressed intersection genes of the BKV_vs_Normal and BKVAN_vs_BKV groups were selected, and a total of 15 genes were obtained. The intersection Venn diagram is shown in Figure 16-D, which is the intersection of the upper left purple circle and the upper right yellow circle. Among them, one gene HLA-DQA2 ( Figure 16 -E (leftmost panel) showed the same expression trend, showing up-regulation when progressing from Normal to BKV and from BKV to BKVAN;

[0151] There were 12 genes that showed up-regulated expression when Normal progressed to BKV, and showed opposite expression trends when BKV progressed to BKVAN: APOE, CTSB, LGMN, SUSD2, MS4A4E, SLC1A3, POSTN, FBP1, STEAP4, SERPINE1, HLA-DQA1, and GPX3;

[0152] There were two genes that showed down-regulation when Normal progressed to BKV, and showed opposite expression trends when BKV progressed to BKVAN: GRAPL and FCMR.

[0153] Figure 16 -D The intersection centers of the three different infection stages are APOE, HLA-DQA2, CTSB, and HLA-DQA1. Among them, the trends of HLA-DQA2 are consistent in the two development processes, while the change trends of APOE, CTSB, and HLA-DQA1 are opposite in the two development processes. The expression of these four genes can more effectively distinguish the three different infection stages of BK virus than the expression of other differential genes.

[0154] 3.5.3 SMA differential expression

[0155] 3.5.3.1BKV_vs_Normal Difference Analysis

[0156] 620 differentially expressed genes were screened using the above criteria, of which 414 were up-regulated and 206 were down-regulated. The full results are shown in: Differential Expression Analysis, and the volcano plot of differentially expressed genes is shown in: Figure 17 -As shown in A.

[0157] 3.5.3.2BKVAN_vs_Normal Difference Analysis

[0158] Using the above criteria, 241 differentially expressed genes were screened, of which 161 were up-regulated and 80 were down-regulated. The full results are shown in: Differential Expression Analysis, and the volcano plot of differentially expressed genes is shown in: Figure 17 -B.

[0159] 3.5.3.3BKVAN_vs_BKV Difference Analysis

[0160] 33 differentially expressed genes were screened using the above criteria, including 8 up-regulated genes and 25 down-regulated genes. The full results are shown in: Differential Expression Analysis, and the volcano plot of differentially expressed genes is shown in: Figure 17 -C shown.

[0161] 3.5.3.4 BK virus infection-related genes in SMA

[0162] The differentially expressed intersection genes of the BKV_vs_Normal and BKVAN_vs_Normal groups were selected, and a total of 133 genes were obtained. The expression trends of these 133 genes were consistent (box plots of all gene expressions are shown in the folder). The intersection Venn diagram is shown in the figure below. Figure 17 -D: As shown by the intersection of the purple circle in the upper left corner and the green circle in the lower corner, protein interaction network analysis of 171 BK virus infection-related genes using the String database (https: / / string-db.org / ) revealed that most of these 133 genes formed a coherent network. WikiPathway and KEGG enrichment analysis were performed on genes in this network. The screening criterion was: pval_adj < 0.05.

[0163] 3.5.3.5 SV40-positive related genes in SMA

[0164] The differentially expressed intersection genes between the BKVAN_vs_Normal and BKVAN_vs_BKV groups were selected, and a total of 6 genes were obtained: IGHM, ADAM15, HSPB1, HLA-DQA2, SPARCL1, and DSTN. The expression trends of these 6 genes were consistent, and the intersection Venn diagram was shown as follows: Figure 17 -D as shown.

[0165] 2.5.2.6 SMA progression-related genes

[0166] The differentially expressed intersection genes between the BKV_vs_Normal and BKVAN_vs_BKV groups were selected, and a total of 10 genes were obtained. The intersection Venn diagram is shown in Figure 17-D, which is the intersection of the upper left purple circle and the upper right yellow circle. Among them, one gene IGHM ( Figure 16 -E (leftmost panel) showed the same expression trend, showing up-regulation when progressing from Normal to BKV and from BKV to BKVAN;

[0167] There were 7 genes that showed up-regulated expression when Normal progressed to BKV, and showed opposite expression trends when BKV progressed to BKVAN: HLA-DQA1, TRAM1, MT1 E, PPA1, SERPINE1, ITGA3, and GLUL;

[0168] There were two genes whose expression was down-regulated when Normal progressed to BKV, and whose expression trend was reversed when BKV progressed to BKVAN: MCCD1 and C5orf38.

[0169] Figure 17 -DThe intersection center of the three different infection stages is IGHM, which also shows that the expression of this gene can effectively distinguish the three different infection stages of BK virus.

[0170] In some embodiments, after feature selection is completed through the above experimental research, the selected features and the corresponding BK infection stages are input into the machine learning model for training to obtain a classifier that can be used to distinguish different BK infection stages.

[0171] Figure 3 is a schematic diagram of a computer device provided by an embodiment of the present invention, such as Figure 3 As shown, the device may include: one or more processors, and one or more memories; wherein the memories store computer-readable codes, and when the computer-readable codes are run by the one or more processors, the method described above may be executed.

[0172] The processor in this embodiment can be an integrated circuit chip with signal processing capabilities. The above-mentioned processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. It can implement or execute the various methods, operations, and logic block diagrams disclosed in the embodiments of the present disclosure. The general-purpose processor can be a microprocessor or any conventional processor, etc., and can be an X86 architecture or an ARM architecture.

[0173] In general, various example embodiments of the present disclosure may be implemented in hardware or dedicated circuitry, software, firmware, logic, or any combination thereof. Certain aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device. When various aspects of the disclosed embodiments are illustrated or described as block diagrams, flow charts, or using some other graphical representation, it will be understood that the blocks, devices, systems, techniques, or methods described herein may be implemented, as non-limiting examples, in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or a controller or other computing device, or some combination thereof.

[0174] For example, the method or apparatus according to the embodiment of the present disclosure may also be implemented by Figure 4 The architecture of the computing device 3000 shown in FIG. Figure 4 As shown, the computing device 3000 may include a bus 3010, one or more CPUs 3020, a read-only memory (ROM) 3030, a random access memory (RAM) 3040, a communication port 3050 connected to a network, an input / output component 3060, a hard disk 3070, etc. The storage device in the computing device 3000, such as the ROM 3030 or the hard disk 3070, may store various data or files used for processing and / or communication of the method provided in the present disclosure, as well as program instructions executed by the CPU. The computing device 3000 may also include a user interface 3080. Of course, Figure 4 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 4 One or more components of a computing device are shown.

[0175] The embodiment of the present invention further provides a computer-readable storage medium, such as Figure 5As shown, it is a schematic diagram of a storage medium provided in an embodiment of the present invention, and computer-readable instructions 4010 are stored on the computer storage medium 4020. When the computer-readable instructions 4010 are executed by the processor, the method according to the embodiment of the present disclosure described with reference to the above figures can be executed. The computer-readable storage medium in the embodiment of the present disclosure can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. The non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus random access memory (DR RAM). It should be noted that the memory of the methods described herein is intended to include, but is not limited to, these and any other suitable types of memory. It should be noted that the memory of the methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0176] The present disclosure also provides a computer program product or a computer program, which implements the steps of the above method when executed by a processor, such as Figure 2 As shown, the computer program product or computer program includes:

[0177] Acquisition module 201: used to obtain tissue samples from the subject;

[0178] Extraction module 202: used to obtain the expression level of the target gene in the region of interest based on the tissue sample, the region of interest is PanCK+, and the target gene includes one or more of the following: HLA-DPA1, LYZ;

[0179] Prediction module 203: used to input the expression level of the target gene in the region of interest into a classifier, and predict the BK virus infection stage of the subject according to the output of the classifier. The BK virus infection stage includes: uninfected, BK blood, and BK nephropathy.

[0180] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architectures, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified functions or operations, or can be implemented using a combination of dedicated hardware and computer instructions.

[0181] In general, various example embodiments of the present disclosure may be implemented in hardware or dedicated circuitry, software, firmware, logic, or any combination thereof. Certain aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device. When various aspects of the disclosed embodiments are illustrated or described as block diagrams, flow charts, or using some other graphical representation, it will be understood that the blocks, devices, systems, techniques, or methods described herein may be implemented, as non-limiting examples, in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or a controller or other computing device, or some combination thereof.

[0182] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0183] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0184] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0185] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0186] The exemplary embodiments of the present disclosure described in detail above are merely illustrative and not restrictive. Those skilled in the art will appreciate that various modifications and combinations may be made to these embodiments or their features without departing from the principles and spirit of the present disclosure, and such modifications should fall within the scope of the present disclosure.

Claims

1. A method for predicting the stage of BK virus infection based on gene expression, characterized in that: The method comprises: Obtaining tissue samples from the subject; Obtaining the expression level of a target gene in a region of interest based on the tissue sample, wherein the region of interest is PanCK+, and the target gene includes one or more of the following: HLA-DPA1, LYZ; The expression levels of the target genes in the region of interest are input into a classifier, and the BK virus infection stage of the subject is predicted based on the output of the classifier, where the BK virus infection stages include: uninfected, BK blood, and BK nephropathy. The target genes in the region of interest are obtained as follows: renal tissue slice samples are obtained from an uninfected group, a BK blood group, and a BK nephropathy group; a sequencing library is constructed based on the renal tissue slice samples to obtain the gene expression levels in the region of interest; the gene expression differences between different regions of interest at different stages of BK virus infection are examined to obtain differentially expressed genes between different groups; the target genes in the region of interest are genes with the same change direction in the intersection of the differentially expressed genes from the uninfected group to the BK blood group and the differentially expressed genes from the BK blood group to the BK nephropathy group among the differentially expressed genes between different groups.

2. The method for predicting the stage of BK virus infection based on gene expression according to claim 1, characterized in that: The region of interest further includes: CD45+, and the target gene further includes one or more of the following: HLA-DQA2.

3. The method for predicting the stage of BK virus infection based on gene expression according to claim 1, characterized in that: The region of interest further includes: SMA, and the target gene further includes: IGHM.

4. The method for predicting the stage of BK virus infection based on gene expression according to claim 1, characterized in that: The tissue sample is a kidney tissue sample.

5. The method for predicting the stage of BK virus infection based on gene expression according to claim 1, characterized in that: The target genes of PanCK+ in the region of interest also include one or more of the following: RHCG, CA2, CALB1, C5orf38, DEFB1, ATP6V1B1, HOXD8, SERPINA5, WNK1, IGFBP5, IL4I1, TMEM52B, STC1, DUSP15, SLC4A9, SCPEP1, ATP6V1G3, ATP6V0A4, TMEM213, ATP6V0D2, GGTLC2, FZD4, ADAMTS1, CKMT2, HSD11B2, CLDN8, PVALB, CA12, SLC12A3, RHBG, IDH2, SLC8A1, IL17RB, CLEC3B, CLCNKB, PGGHG, SLC26A4, S100A9, KLK1, SIM2, and ATP1B1.

6. The method for predicting the stage of BK virus infection based on gene expression according to claim 2, characterized in that: Target genes of CD45+ in the region of interest also include one or more of the following: APOE, CTSB, LGMN, SUSD2, MS4A4E, SLC1A3, GRAPL, POSTN, FBP1, FCMR, STEAP4, SERPINE1, HLA-DQA1, and GPX3.

7. The method for predicting the stage of BK virus infection based on gene expression according to claim 3, characterized in that: Target genes of SMA in the region of interest also include one or more of the following: HLA-DQA1, TRAM1, MCCD1, C5orf38, MT1E, PPA1, SERPINE1, ITGA3, and GLUL.

8. The method for predicting the stage of BK virus infection based on gene expression according to claim 1, characterized in that: At the same time, the number of renal tubular epithelial cells of the subject is obtained, the expression levels of the target gene of the region of interest and the number of renal tubular epithelial cells are input into a classifier, and the BK virus infection stage of the subject is predicted based on the output of the classifier.

9. The method for predicting the stage of BK virus infection based on gene expression according to claim 1, characterized in that: At the same time, the degree of renal interstitial fibrosis is obtained, the expression level of the target gene in the region of interest and the degree of renal interstitial fibrosis are input into a classifier, and the BK virus infection stage of the subject is predicted based on the output of the classifier.

10. The method for predicting the stage of BK virus infection based on gene expression according to claim 1, characterized in that: Spatial transcriptomics technology is used to measure the expression levels of target genes of interest in the subjects.

11. The method for predicting the stage of BK virus infection based on gene expression according to claim 1, characterized in that: The target genes in the region of interest are the intersection of the differentially expressed genes between the different groups, the differentially expressed genes between the non-infected group and the BK blood group and the differentially expressed genes between the BK blood group and the BK nephropathy group.

12. The method for predicting the stage of BK virus infection based on gene expression according to claim 1, characterized in that: Methods for constructing sequencing libraries include: The renal tissue section sample is pretreated and then digested according to the DSP standard method to obtain a sample with RNA target exposure; Fixing the sample exposed to the RNA target site, performing in situ hybridization incubation, and then performing nuclear staining to obtain a stained sample; Based on the stained sample, a sequencing library is constructed after selecting regions of interest through DSP.

13. The method for predicting the stage of BK virus infection based on gene expression according to claim 12, characterized in that: After the renal tissue sections are incubated with morphologically labeled fluorescent antibodies, fluorescent imaging is performed on the incubated renal tissue sections using a DSP system, and regions of interest are selected based on the morphologically labeled antibodies.

14. The method for predicting the stage of BK virus infection based on gene expression according to claim 1, characterized in that: The expression level of the target gene in the first region of interest is obtained, the expression level of the target gene in the first region of interest is input into a first classifier, and whether the subject is infected with the BK virus is predicted based on the output of the first classifier.

15. The method for predicting the stage of BK virus infection based on gene expression according to claim 14, characterized in that: The expression level of the target gene in the second region of interest is obtained, the expression level of the target gene in the second region of interest is input into a second classifier, and whether the subject suffers from BK nephropathy is predicted based on the output of the second classifier.

16. The method for predicting the stage of BK virus infection based on gene expression according to claim 15, characterized in that: The expression levels of the target genes in the first region of interest and the second region of interest are obtained. The expression levels of the target genes in the first region of interest are first input into the first classifier. If the output of the first classifier predicts that the subject is infected with BK virus, the expression levels of the target genes in the second region of interest are input into the second classifier to predict whether the subject suffers from BK nephropathy, thereby obtaining the BK virus infection disease stage of the subject.

17. The method for predicting the stage of BK virus infection based on gene expression according to claim 14, characterized in that: The method for obtaining the target gene of the first region of interest includes: Kidney tissue section samples were obtained from the uninfected group and the BK-infected group; constructing a sequencing library based on the renal tissue section sample to obtain gene expression levels in the region of interest; The gene expression differences between the uninfected group and the BK infected group were examined to obtain the target genes of the first region of interest.

18. The method for predicting the stage of BK virus infection based on gene expression according to claim 15, characterized in that: The method for obtaining the target gene of the second region of interest includes: Kidney tissue samples were obtained from the non-BK nephropathy group and the BK nephropathy group; constructing a sequencing library based on the renal tissue section sample to obtain gene expression levels in the region of interest; The gene expression differences between the non-BK nephropathy group and the BK nephropathy group were examined to obtain the target genes of the second region of interest.

19. A computer device, characterized in that: The device comprises: a memory and a processor; the memory is used to store a computer program; the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 18.

20. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 18 are implemented.

21. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 18 are implemented.

Images