A prognostic assessment method and system for diffuse large B-cell lymphoma

Abstract

This invention discloses a prognostic assessment method and system for diffuse large B-cell lymphoma (DLBCL). The method first uses weighted gene co-expression network analysis (WGCNA) to screen gene modules closely related to lipid metabolism from DLBCL transcriptome data. Then, multi-step regression analysis (univariate Cox, LASSO, and multivariate Cox) identifies eight key prognostic genes from these modules: FNDC1, IL22RA2, C15orf48, OMD, MFAP2, BC017398, CXCL6, and TNFAIP6. Based on the expression levels and regression coefficients of these genes, a risk scoring model is constructed, which can classify DLBCL patients into high-risk and low-risk groups with significant survival differences. Further integration of the risk score with clinicopathological factors to construct a nomogram enables individualized survival probability prediction. This invention also provides a corresponding prognostic assessment system, electronic device, and storage medium. Validated with independent datasets, the prognostic model of this invention exhibits excellent predictive performance and clinical practical value.

Description

Technical Field

[0001] This invention relates to the fields of bioinformatics and medical prognostic assessment, and in particular to a prognostic assessment method and system for diffuse large B-cell lymphoma. Background Technology

[0002] Diffuse large B-cell lymphoma (DLBCL) is the most common aggressive non-Hodgkin lymphoma, accounting for approximately 40% of adult cases. Although first-line R-CHOP therapy and novel therapies such as CAR-T have improved patient outcomes, about one-third of patients still develop resistance or relapse, and some patients do not respond well to CAR-T therapy; the underlying mechanisms are not fully understood. Therefore, developing tools that can accurately assess the prognosis of DLBCL patients and identify high-risk individuals is of great significance for achieving personalized treatment.

[0003] Lipid metabolism plays a crucial role in tumorigenesis, development, and treatment response. Studies have shown that lipid metabolism disorders are among the most prominent metabolic alterations in cancer. Cancer cells regulate lipid metabolism to support their proliferation, survival, and metastasis, and also influence the tumor microenvironment. In deep blood lung cancer (DLBCL), lipid metabolism characteristics are associated with treatment resistance and poor prognosis. For example, resistant samples show elevated levels of specific lipid fragments, and dyslipidemia-prone M2 macrophages can induce T cell suppression through cholesterol efflux. These findings suggest that lipid metabolism plays an important role in the prognosis and treatment response of DLBCL, but its specific regulatory mechanisms still require further investigation.

[0004] Currently, several prognostic models for DLBCL based on gene expression characteristics have been developed, as well as models based on other gene features. However, most existing models fail to fully utilize lipid metabolism gene information closely related to the occurrence and development of DLBCL, or the robustness and predictive accuracy of the constructed models need further improvement. Furthermore, many models fail to provide a personalized prognostic prediction tool that can integrate key prognostic factors and directly serve clinical practice, thus limiting their practical application value in precision medicine.

[0005] Therefore, there is an urgent need in this field for a new technology that can fully utilize lipid metabolism-related gene information, construct accurate and reliable prognostic assessment models, and provide personalized prognostic predictions for clinical decision-making. Summary of the Invention

[0006] To address the aforementioned problems, the present invention aims to provide a prognostic assessment method and system for diffuse large B-cell lymphoma.

[0007] To achieve the above-mentioned technical objectives, the technical solution adopted by the present invention is as follows: In a first aspect, the present invention provides a prognostic assessment method for diffuse large B-cell lymphoma, comprising the following steps: S1: Obtain gene expression data from DLBCL patients to be evaluated; S2: Input the gene expression data into the prognostic risk scoring model, which is constructed based on the expression levels of eight genes, FNDC1, IL22RA2, C15orf48, OMD, MFAP2, BC017398, CXCL6 and TNFAIP6, and their respective regression coefficients. S3: Based on the risk score output by the model, patients are divided into different prognostic risk groups.

[0008] Furthermore, the risk score S output by the model is calculated using the following formula:

[0009] in, This indicates the gene expression level of FNDC1. This represents the regression coefficient corresponding to FNDC1. =-1.496; This indicates the gene expression level of IL22RA2. This represents the regression coefficient corresponding to IL22RA2. =-0.559; This indicates the gene expression level of C15orf48. This represents the regression coefficient corresponding to C15orf48. =-1.561; This indicates the gene expression level of OMD. This represents the regression coefficient corresponding to OMD. =-1.053; This indicates the gene expression level of MFAP2. This represents the regression coefficient corresponding to MFAP2. =2.873; This indicates the gene expression level of BC017398. This represents the regression coefficient corresponding to BC017398. =0.973; This indicates the gene expression level of CXCL6. This represents the regression coefficient corresponding to CXCL6. =0.771; This indicates the gene expression level of TNFAIP6. This represents the regression coefficient corresponding to TNFAIP6. =1.451.

[0010] Furthermore, the prognostic assessment method for diffuse large B-cell lymphoma also includes S4: constructing a nomogram for predicting individualized survival probability based on the risk score and in combination with at least one clinicopathological factor.

[0011] Furthermore, the clinicopathological factors include age, sex, and tumor stage.

[0012] Furthermore, the method for constructing the prognostic risk scoring model includes: Based on DLBCL transcriptome data, we identified gene modules related to lipid metabolism phenotypes through weighted gene co-expression network analysis. From the gene module, the eight key genes were screened out and their regression coefficients were determined by combining multiple regression analyses; The method of combining multiple regression analyses includes: performing univariate Cox regression analysis, LASSO regression analysis, and multivariate Cox regression analysis in sequence.

[0013] Furthermore, the method for constructing the prognostic risk scoring model specifically includes the following steps: 1) Data Acquisition and Preprocessing: Training and validation sets were obtained from the GEO database; all gene expression data were standardized, including background correction, quantile normalization and probe annotation, to eliminate batch effects and technical differences. 2) Identification of key gene modules: Weighted gene co-expression network analysis was used to conduct in-depth analysis of the training set. The specific steps are as follows: Data preprocessing: Calculate the expression variation coefficient of all genes, and select the top 5000 genes with the highest variation coefficient for network construction; Network construction: A gene similarity matrix was constructed using Pearson correlation coefficients. The optimal soft threshold β=2 was determined using the pickSoftThreshold function, at which point the scaling topology fit exponent R0 was determined. 2 >0.85, which satisfies the characteristics of scale-free networks; Module identification: Hierarchical clustering is performed based on the topological overlap matrix. The initial modules are divided using a dynamic pruning tree algorithm. The minimum number of genes in a module is set to 30, and the merging threshold is set to 0.25 (i.e., modules with a correlation coefficient greater than 0.75 between feature genes are merged). Finally, several feature modules are obtained. Module-phenotype association: The correlation between characteristic genes of each module and lipid metabolism phenotype is calculated, and the association is verified by correlation analysis between module members and gene characteristics, thereby identifying key modules; 3) Construction of prognostic risk model: Based on key gene modules, a prognostic risk model was constructed using multi-step regression analysis, as detailed below: Genes significantly associated with prognosis were screened using univariate Cox regression; 10-fold cross-validation was used to further compress variables and obtain key prognostic factors; and 8 independent prognostic genes were finally identified through multivariate Cox regression: FNDC1, IL22RA2, C15orf48, OMD, MFAP2, BC017398, CXCL6 and TNFAIP6. A prognostic risk scoring model was constructed based on the expression levels of the above eight genes and their corresponding regression coefficients.

[0014] Furthermore, in step S3, patients are divided into high-risk and low-risk groups based on the median risk score.

[0015] In a second aspect, the present invention provides a system for prognostic assessment of diffuse large B-cell lymphoma, which applies the prognostic assessment method described in the first aspect above, the system comprising: The data acquisition module is used to acquire or receive gene expression data of the sample to be tested; The storage module contains a prognostic risk scoring model built on the expression levels and regression coefficients of eight genes: FNDC1, IL22RA2, C15orf48, OMD, MFAP2, BC017398, CXCL6, and TNFAIP6. The processing module is configured to invoke the prognostic risk scoring model to process the gene expression data in order to calculate a risk score; The output module is used to output the risk score and the prognostic risk assessment results based on the score.

[0016] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the prognostic assessment method as described in the first aspect above.

[0017] In a fourth aspect, an electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the prognostic assessment method as described in the first aspect above.

[0018] In a fifth aspect, the present invention provides a kit for assessing the prognosis of diffuse large B-cell lymphoma; the kit comprises detection reagents for detecting the expression of the eight lipid metabolism-related genes (FNDC1, IL22RA2, C15orf48, OMD, MFAP2, BC017398, CXCL6, and TNFAIP6). The detection reagents may include specific primers, probes, or gene chips targeting these eight genes.

[0019] By adopting the above technical solution, the present invention has the following beneficial effects compared with the prior art: 1. Novel and Mechanistically Relevant Biomarkers: This invention is the first to screen and validate a biomarker set consisting of eight lipid metabolism-related genes (FNDC1, IL22RA2, C15orf48, OMD, MFAP2, BC017398, CXCL6, and TNFAIP6) for prognostic assessment of DLBCL. These genes are closely related to lipid metabolism and immune microenvironment regulation, providing a more reliable basis for prognostic prediction from a biological mechanism perspective.

[0020] 2. Scientific and robust model construction methodology: This invention employs a systematic strategy combining WGCNA with multiple regression analyses (univariate Cox, LASSO, and multivariate Cox) to construct a risk scoring model. This effectively screens out key prognostic factors, avoids overfitting, and ensures the model's stability and generalization ability. The model has been effectively validated on an independent validation set.

[0021] 3. Excellent predictive performance: The risk scoring model based on eight genes provided by this invention demonstrates good prognostic discrimination ability in both the training and validation sets, with the overall survival of patients in the high-risk group being significantly shorter than that in the low-risk group. Time-dependent ROC curve analysis shows that the model has high predictive accuracy (AUC value) at 1 year, 3 years, and 5 years.

[0022] 4. High clinical value: The risk score has been proven to be a prognostic factor independent of age, sex, and stage, possessing independent prognostic value. Further integration of the risk score with clinical factors to construct a nomogram provides an intuitive tool for predicting individualized survival probabilities. Its predicted values ​​are highly consistent with actual observed values ​​(verified by calibration curves), and decision curve analysis (DCA) shows that it provides the greatest net benefit in clinical decision-making. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. 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 effort.

[0024] Figure 1 A simplified flowchart for identifying key gene modules using WGCNA.

[0025] Figure 2 The soft threshold parameter selection plot shows that the network conforms to the scale-free distribution characteristics when power=2.

[0026] Figure 3This is a hierarchical clustering tree diagram of the gene co-expression module.

[0027] Figure 4 A heatmap showing the correlation between characteristic genes of each module and lipid metabolism phenotype.

[0028] Figure 5 This is a scatter plot showing the correlation between module members and gene characteristics in the blue module.

[0029] Figure 6 This is a path diagram of the LASSO regression coefficients.

[0030] Figure 7 This is a graph showing the error curve of 10-fold cross-validation in LASSO regression.

[0031] Figure 8 Forest plot of eight key prognostic genes and their regression coefficients identified by multivariate Cox regression analysis.

[0032] Figure 9 The expression heatmaps of eight key prognostic genes in the validation set samples are shown.

[0033] Figure 10 The results of decision curve analysis (DCA) of the nomogram are shown. Detailed Implementation

[0034] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be particularly noted that the following embodiments are for illustrative purposes only and do not limit the scope of the invention. Similarly, the following embodiments are only some, not all, embodiments of the present invention, and all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0035] This invention provides a prognostic assessment method for diffuse large B-cell lymphoma (DLBCL), the core of which lies in utilizing a set of biomarkers based on eight specific lipid metabolism-related genes. The method mainly includes the following steps: S1: Obtain gene expression data from DLBCL patients to be evaluated; S2: Input the gene expression data into the prognostic risk scoring model, which is constructed based on the expression levels of eight genes, FNDC1, IL22RA2, C15orf48, OMD, MFAP2, BC017398, CXCL6 and TNFAIP6, and their respective regression coefficients. S3: Based on the risk score output by the model, patients are divided into different prognostic risk groups, such as high-risk and low-risk groups, thereby achieving prognostic risk assessment. The risk scoring model is constructed based on the expression levels and regression coefficients of the eight genes mentioned above, and the calculation formula is as follows: Risk score = Σ(gene expression level × corresponding regression coefficient) Next, patients were divided into high-risk and low-risk groups based on the median risk score.

[0036] S4: Based on the risk score and combined with at least one clinicopathological factor (preferably age, sex, and tumor stage), construct a nomogram to predict individualized survival probabilities (such as 1-year, 3-year, and 5-year survival rates).

[0037] The prognostic risk scoring model in this invention was constructed using a systematic bioinformatics process: 1) First, based on DLBCL transcriptome data, weighted gene co-expression network analysis (WGCNA) was used to identify gene modules (such as the blue module) that are significantly associated with lipid metabolism phenotypes. The WGCNA analysis process included data preprocessing and screening for highly variable genes, construction of a co-expression network based on Pearson correlation coefficient and a selected soft threshold (e.g., β=2), hierarchical clustering and dynamic pruning based on topological overlap matrix (TOM) to divide and merge modules (e.g., the merging threshold was set to 0.25), and identification of key modules through association analysis between module characteristic genes and lipid metabolism phenotypes.

[0038] 2) From the key modules, the final eight key genes are screened using a combination of regression analyses, and their regression coefficients are determined. This screening strategy preferably includes, in sequence: initial screening using univariate Cox regression analysis; variable compression and overfitting prevention using LASSO regression analysis (e.g., with 10-fold cross-validation); and determining independent prognostic genes and their weights (regression coefficients) using multivariate Cox regression analysis.

[0039] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments: Example 1 See attached document Figure 1 As shown in this embodiment, a prognostic assessment method for diffuse large B-cell lymphoma is provided, which includes: S1: Obtain gene expression data from DLBCL patients to be evaluated; S2: Input the gene expression data into the prognostic risk scoring model, which is constructed based on the expression levels of eight genes, FNDC1, IL22RA2, C15orf48, OMD, MFAP2, BC017398, CXCL6 and TNFAIP6, and their respective regression coefficients. In this embodiment, the prognostic risk scoring model is constructed as follows: 1) Data Acquisition and Preprocessing Training and validation sets were obtained from the GEO database. All gene expression data underwent normalization, including background correction, quantile normalization, and probe annotation, to eliminate batch effects and technical differences.

[0040] 2) Identification of key gene modules The training set was analyzed in depth using weighted gene co-expression network analysis (WGCNA); the specific steps are as follows: Data preprocessing: Calculate the expression variation coefficient of all genes, and select the top 5000 genes with the highest variation coefficient for network construction; Network construction: A gene similarity matrix was constructed using Pearson correlation coefficients, and the optimal soft threshold β=2 was determined using the pickSoftThreshold function (e.g., ...). Figure 2 At this point, the scale-based topology fit index R² > 0.85, satisfying the characteristics of a scale-free network; Module identification: Hierarchical clustering was performed based on the Topological Overlap Matrix (TOM). A dynamic pruning tree algorithm was used to divide the initial modules. The minimum number of genes per module was set to 30, and the merging threshold was set to 0.25 (i.e., modules with a correlation coefficient greater than 0.75 between their feature genes were merged). Finally, five feature modules were obtained: brown (307 genes), blue (384 genes), yellow (91 genes), green (58 genes), and turquoise (4160 genes). Figure 3 ); Module-phenotype association: The correlation between characteristic genes of each module and lipid metabolism phenotype was calculated, and a significant positive correlation was found between the blue module and lipid metabolism characteristics (cor=0.54, p=1e-32). Figure 4 The correlation analysis between module members and gene characteristics further validated this association (e.g. Figure 5 ).

[0041] 3) Construction and validation of prognostic risk models Based on the blue module gene, a prognostic risk model was constructed using multi-step regression analysis: Univariate Cox regression: 172 genes were identified that were significantly associated with prognosis (p<0.05); LASSO regression: 10-fold cross-validation was used to further compress variables, resulting in 42 key prognostic factors (e.g., Figure 6-7 ); Multivariate Cox regression: ultimately identified 8 independent prognostic genes: FNDC1, IL22RA2, C15orf48, OMD, MFAP2, BC017398, CXCL6, and TNFAIP6 (e.g., Figure 8Among them, CXCL6, BC017398, TNFAIP6, and MFAP2 are risk factors, while C15orf48, FNDC1, OMD, and IL22RA2 are protective factors. The regression coefficients of each gene are as follows: Figure 8 .

[0042] Based on the above gene expression levels and regression coefficients, a prognostic risk scoring model is constructed, and the calculation formula is as follows:

[0043] in, This indicates the gene expression level of FNDC1. This represents the regression coefficient corresponding to FNDC1. =-1.496; This indicates the gene expression level of IL22RA2. This represents the regression coefficient corresponding to IL22RA2. =-0.559; This indicates the gene expression level of C15orf48. This represents the regression coefficient corresponding to C15orf48. =-1.561; This indicates the gene expression level of OMD. This represents the regression coefficient corresponding to OMD. =-1.053; This indicates the gene expression level of MFAP2. This represents the regression coefficient corresponding to MFAP2. =2.873; This indicates the gene expression level of BC017398. This represents the regression coefficient corresponding to BC017398. =0.973; This indicates the gene expression level of CXCL6. This represents the regression coefficient corresponding to CXCL6. =0.771; This indicates the gene expression level of TNFAIP6. This represents the regression coefficient corresponding to TNFAIP6. =1.451.

[0044] Patients were divided into high-risk and low-risk groups based on the median risk score. In the training set, the overall survival of patients in the high-risk group was significantly shorter than that in the low-risk group. Time-dependent ROC curves showed that the model had high predictive accuracy (AUC) at 1, 3, and 5 years. Risk score distribution, survival status distribution, and gene expression heatmaps (e.g.) were also analyzed. Figure 9 Further validate the model's effectiveness.

[0045] The above analysis was repeated on the independent validation set, and the results showed that the model maintained good predictive performance, confirming its good generalization ability.

[0046] 4) Clinical validation and nomogram construction To assess the clinical value of the risk score, the following analysis was performed: Independence verification: Univariate and multivariate Cox regression analyses showed that the risk score was a prognostic factor independent of age, gender, and stage. Clinical characteristics distribution: There were no significant differences between the high-risk group and the low-risk group in basic clinical characteristics such as age, gender, and stage, indicating that the risk stratification was independent; Nodal plot construction: Integrating risk score, age, gender, and stage to construct a prognostic nomal plot for individualized prediction of 1-year, 3-year, and 5-year survival probabilities.

[0047] The nomogram verification results show: The calibration curves show a high degree of consistency between predicted survival rates and actual observations; the ROC curves show that the nomogram's predictive power is significantly better than that of a single variable; and decision curve analysis shows that the nomogram achieves the maximum net benefit at all time points (e.g., ...). Figure 10 ).

[0048] S3: Based on the risk score output by the model, patients are divided into different prognostic risk groups, such as high-risk group and low-risk group, thereby achieving prognostic risk assessment.

[0049] S4: Based on the risk score and combined with at least one clinicopathological factor (preferably age, sex, and tumor stage), construct a nomogram to predict individualized survival probabilities (such as 1-year, 3-year, and 5-year survival rates).

[0050] Example 2 This embodiment provides a system for prognostic assessment of diffuse large B-cell lymphoma, which applies the prognostic assessment method for diffuse large B-cell lymphoma described in Embodiment 1 above. The system includes: The data acquisition module is used to acquire or receive gene expression data of the sample to be tested; The storage module contains a prognostic risk scoring model (such as the prognostic risk scoring model constructed in Example 1) based on the expression levels and regression coefficients of eight genes: FNDC1, IL22RA2, C15orf48, OMD, MFAP2, BC017398, CXCL6 and TNFAIP6. The processing module is configured to invoke the prognostic risk scoring model to process the gene expression data in order to calculate a risk score; The output module is used to output the risk score and the prognostic risk assessment results based on the score.

[0051] Example 3 Based on the same inventive concept, this embodiment provides a computer-readable storage medium storing computer instructions that, when executed on a computer, cause the computer to perform a prognostic assessment method for diffuse large B-cell lymphoma as described in Embodiment 1.

[0052] In specific implementation, computer-readable storage media include: Universal Serial Bus flash drive (USB), portable hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, and other storage media that can store program code.

[0053] The device embodiments described above are merely illustrative. The units / modules described as separate components may or may not be physically separate. The components shown as units / modules may or may not be physical units / modules; that is, they may be located in one place or distributed across multiple network units / modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0054] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.

[0055] Example 4 This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the prognostic assessment method for diffuse large B-cell lymphoma as described in Embodiment 1.

[0056] Example 5 This embodiment describes the preparation of a kit for prognostic assessment of DLBCL based on the eight key genes mentioned above (FNDC1, IL22RA2, C15orf48, OMD, MFAP2, BC017398, CXCL6, and TNFAIP6). The kit contains: Specific primers and probes for the FNDC1, IL22RA2, C15orf48, OMD, MFAP2, BC017398, CXCL6 and TNFAIP6 genes; Various reagents required for RT-PCR reactions; Positive and negative control samples; The instruction manual provides a detailed description of the testing process and risk score calculation method.

[0057] When using this method, RNA is extracted from the sample to be tested, reverse transcribed into cDNA, and the expression levels of eight genes are detected by quantitative PCR. The expression levels are then substituted into the risk scoring formula to calculate the risk score, and the patient's prognostic risk is finally assessed based on the score results.

[0058] The above description is only a part of the embodiments of the present invention and does not limit the scope of protection of the present invention. Any equivalent device or equivalent process transformation made based on the content of the present invention specification and drawings, or direct or indirect application in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A system for prognostic assessment of diffuse large B-cell lymphoma, characterized in that, The system is used to perform a prognostic assessment method for diffuse large B-cell lymphoma, the prognostic assessment method comprising the following steps: S1: Obtain gene expression data from DLBCL patients to be evaluated; S2: The gene expression data is input into a prognostic risk scoring model, which is constructed based on the expression levels of eight key genes—FNDC1, IL22RA2, C15orf48, OMD, MFAP2, BC017398, CXCL6, and TNFAIP6—and their corresponding regression coefficients. The risk score S output by the model is calculated using the following formula: in, This indicates the gene expression level of FNDC1. This represents the regression coefficient corresponding to FNDC1. =-1.496; This indicates the gene expression level of IL22RA2. This represents the regression coefficient corresponding to IL22RA2. =-0.559; This indicates the gene expression level of C15orf48. This represents the regression coefficient corresponding to C15orf48. =-1.561; This indicates the gene expression level of OMD. This represents the regression coefficient corresponding to OMD. =-1.053; This indicates the gene expression level of MFAP2. This represents the regression coefficient corresponding to MFAP2. =2.873; This indicates the gene expression level of BC017398. This represents the regression coefficient corresponding to BC017398. =0.973; This indicates the gene expression level of CXCL6. This represents the regression coefficient corresponding to CXCL6. =0.771; This indicates the gene expression level of TNFAIP6. This represents the regression coefficient corresponding to TNFAIP6. =1.451; S3: Based on the risk score output by the model, patients are divided into different prognostic risk groups; The system for prognostic assessment of diffuse large B-cell lymphoma includes: The data acquisition module is used to acquire or receive gene expression data of the sample to be tested; The storage module contains a prognostic risk scoring model built on the expression levels and regression coefficients of eight genes: FNDC1, IL22RA2, C15orf48, OMD, MFAP2, BC017398, CXCL6, and TNFAIP6. The processing module is configured to invoke the prognostic risk scoring model to process the gene expression data in order to calculate a risk score; The output module is used to output the risk score and the prognostic risk assessment results based on the score.

Images