CN115762792A - A lncRNA-based optimization model for predicting survival and prognosis of bladder cancer patients - Google Patents

Abstract

The invention relates to the technical field of bladder cancer prediction, and discloses a method for predicting the survival prognosis of a bladder cancer patient based on an lncRNA optimization model, which comprises the following steps: s1: data collection and pre-processing, analysis of bladder cancer lncRNA data from TCGA using FPKM data, analysis of mRNA data from tcgalvel 3 using RSEM normalized count class data and further log2 transformed expression matrix, TCGA clinical data with corrected phenotype data, pre-processing of the data, quality control, normalization and transformation to obtain a uniform expression matrix. In research, incomplete data or missing data are common problems limiting the application of the model, and the model is constructed on the basis of relatively complete data, so that the generation can be predicted in multiple dimensions, and the model performance is more stable.

Description

A lncRNA-based optimization model for predicting survival and prognosis of bladder cancer patients

technical field

The invention relates to the technical field of prognosis prediction of bladder cancer, in particular to a method for predicting survival and prognosis of bladder cancer patients based on an lncRNA optimization model.

Background technique

Bladder cancer (Bladder Cancer, BC) is one of the most common malignant tumors worldwide, with significant tumor heterogeneity. Muscle-invasive bladder cancer (Muscle-invasive Bladder Cancer, MIBC) usually has a poor prognosis, while non-muscle-invasive bladder cancer (Non-muscle-invasive Bladder Cancer, NMIBC) has a relatively better prognosis. Prognosis prediction of bladder cancer is of great significance for the selection of clinical treatment options. However, accurate assessment of a patient's risk for adverse prognosis remains a challenge.

Several bladder cancer prediction models have been established. For non-muscle-invasive bladder cancer, these models mainly focus on predicting disease recurrence and progression, patient response to neoadjuvant chemotherapy, lymph node metastasis, and survival prognosis. However, for muscle-invasive bladder cancer, these models are less effective in predicting patient survival outcomes, which may be related to tumor heterogeneity, patient response to treatment, and other as-yet-unrecognized risk factors related to bladder cancer development. mechanism of action, etc.

As for the models of lymph node metastasis, several models such as KNN51, RF15 and LN20 have been reported so far. The AUC of KNN51 for predicting lymph node positive cases was reported to be 0.82 (range 0.71–0.93). In addition, a preoperative lymph node metastasis prediction model was proposed that utilized genomic as well as clinicopathological features to identify patients at risk of lymph node metastasis from bladder cancer , showing good discriminative ability. Our study shows that the composite model is effective in predicting lymph node metastasis. However, the prediction model for lymph node metastasis of urothelial carcinoma in previous studies is still not available for clinical application, and it is still a formidable challenge to accurately predict the prognosis of bladder cancer.

Previous studies have shown that long noncoding RNA (Long-noncoding-RNA, lncRNA) has significant tissue specificity and is widely involved in epigenetic regulation in cells. Multiple studies have shown that lncRNA plays an important regulatory role in bladder cancer, affecting tumor treatment response, tumor metastasis and progression. Multiple long non-coding RNAs are related to the metastasis of bladder cancer, such as H19, DLX6-AS1 and BLACAT2. However, most of these studies focus on analyzing the biological function of a single long non-coding RNA in tumors and its correlation with prognosis. There is still little research on models based on multiple lncRNAs to predict the prognosis of bladder cancer, and there is a lack of validation and systematic research. We intend to build an lncRNA model based on statistical and unbiased methods, and compare its prognostic performance with models established based on lncRNAs discovered on the basis of functional studies.

Due to the marked tumor heterogeneity in bladder cancer, similar patients with urothelial carcinoma may have different outcomes after treatment. Recent studies have revealed that different molecular subtypes of bladder cancer have different clinical prognosis, and different molecular subtypes of bladder cancer present specific tumor microenvironmental characteristics, which are significantly correlated with patient prognosis. Among them, tumor fibroblasts (Cancer-associated fibroblast, CAF) in the tumor microenvironment are closely related to specific tumor cell differentiation subtypes, and subgroups rich in mesenchymal cells are usually associated with poor prognosis of bladder cancer, and these subgroups are also Accompanied by abundant lymphocyte infiltration, suggesting the presence of immunosuppression in bladder cancer tissue. In addition, several studies have evaluated the role of immune molecules as cancer prognostic biomarkers, suggesting that immune status may affect bladder cancer prognosis. We hypothesize that constructing a bladder cancer prognosis prediction model by integrating the immune and stromal characteristics of the tumor microenvironment may improve the accuracy of prediction and help guide clinical treatment plans.

Based on this, in this study, we constructed and optimized a long non-coding RNA fusion model. The model incorporates clinical risk factors, tumor microenvironmental stromal cells, and gene expression information of immune cell subtypes to predict the prognosis of bladder cancer patients. The model performs well in accurately predicting bladder cancer prognosis and is scalable.

Contents of the invention

(1) Solved technical problems

Aiming at the deficiencies of the prior art, the present invention provides a method for predicting the survival and prognosis of bladder cancer patients based on an lncRNA-based optimization model.

(2) Technical solution

In order to achieve the above object, the present invention provides the following technical scheme: a method for predicting the survival and prognosis of bladder cancer patients based on an lncRNA-based optimization model, comprising the following steps:

S1: Data collection and preprocessing

Use FPKM data to analyze lncRNA data from TCGA, use RSEM normalized count data and further log2 transformation expression matrix to analyze mRNA data from TCGA Level 3, TCGA clinical data uses corrected phenotype data, preprocesses the data, Through quality control, normalization and transformation to obtain a unified expression matrix;

S2: Statistical Analysis

The 394 patients included in the analysis were randomly divided into a training set and a validation set at a ratio of 7:3. First, the data in the training set was used to find independent prognostic factors, and lasso regression and stepwise method were used to further reduce the variables to build a multivariate Cox risk model. , and then applied the model to a validation cohort to assess the specificity, sensitivity, and clinical validity of the predictive model. For model optimization, construct a model in the mRNA data set for a given gene expression label, calculate the risk score, and use it to optimize the fusion model. The model after fusion and optimization is displayed in a nomogram, and the predictive value and clinical effectiveness of the model The evaluation adopts receiver operating characteristic curve and decision curve analysis respectively;

S3: framework design and data preprocessing

After data preprocessing and lasso dimensionality reduction screening, the lncRNA prognosis prediction model was constructed, and then clinical risk factors affecting the prognosis of bladder cancer were incorporated into the model, including clinically meaningful indicators such as T stage, N stage and tumor grade, to construct The clinical factor-lncRNA composite model, and then based on the specific expression tags of tumor-associated fibroblast stromal cells (CAF) in the microenvironment, together with the cell information of immune cell subsets, the risk scores were calculated respectively, as an optimization variable for the clinical factor-lncRNA Optimize the composite model, and then compare this optimized model with published, tumor-associated lncRNA models;

S4: Construction of lncRNA-based prognosis prediction model

Using the combination of lasso algorithm and multiple Cox regression analysis, a lncRNA model containing 12 molecules was obtained. The ROC curve showed that the lncRNA model performed well in predicting the prognosis of bladder cancer, and the AUC of the 5-year survival prediction of the training data set was 0.894. , the risk score calculated by the model can be used to distinguish patients into two groups with significant differences. Compared with patients with low risk scores, the risk of death increased by 7.5 times. The AUC of the 5-year survival prediction of the validation data set was 0.755, and the death risk of patients with high-risk scores was 2.7 times that of patients with low-risk scores;

S5: Integration of lncRNA-based models and clinical risk factors

Integrating clinical risk factors, including bladder cancer T stage, N stage, tumor grade, constructing a clinical risk factor-lncRNA composite model, a separate clinical risk factor model and a single lncRNA model, the prognosis prediction performance of bladder cancer is good, but the performance is not yet Reaching an excellent level, the AUC of the 5-year survival prediction of the clinical risk factor model in the verification set is 0.774, and the AUC of the lncRNA model is 0.764. In contrast, after the lncRNA model is integrated into the clinical risk factors (clinical risk factor-lncRNA composite model) In the verification set, the AUC of 5-year survival prediction is 0.882, and the performance of the model has reached an excellent level. The fusion model constructed by combining lncRNA and clinical risk factors can greatly improve the performance of the prediction model;

S6: The predictive effect of tumor microenvironment stromal cell signature genes and immune cell subsets on the prognosis of bladder cancer

We built a model for the characteristic gene expression signature of mesenchymal cells, calculated the risk score and integrated it into the lncRNA model. The results show that characteristic gene expression risk scores of mesenchymal cells can improve the performance of the model. In the validation dataset, the prognostic prediction AUC for 5-year survival was 0.789. Using CYBERSORT to calculate immune cell components from mRNA data by deconvolution, it was shown that immune cell components alone can predict the prognosis of bladder cancer, and then the risk score of immune cell components was calculated and integrated into the lncRNA-CAF composite model , the results show that the performance of the lncRNA-CAF-Immune composite model is excellent in the training set (AUC of 5-year survival prediction=0.924), and the prediction value of the composite model in the verification set of 5-year survival is also better than that of the simple lncRNA model (AUC =0.787);

S7: Performance of optimized lncRNA fusion model in predicting survival and prognosis of bladder cancer patients

Predictive models that combine multidimensional biological information may improve predictive performance, so we established a fusion model based on the lncRNA model and integrated with clinical risk factors and gene expression information of stromal cells/immune cell subtypes in the tumor microenvironment , the results show that the ROC curve of the fusion model performs well in both the training set and the verification data set. In the verification data set, the prognosis prediction AUC of 5-year survival is 0.913;

S8: Clinical application exploration of the optimized lncRNA fusion model

Based on the constructed fusion model, a nomogram was drawn. The nomogram visually shows the most feasible lncRNA markers, CAF risk score, Immune risk score and the impact of clinical risk factors on the generated prognosis in the optimized fusion model. In addition, the DCA curve we drew shows that the fusion model we constructed has clinical application value.

Preferably, in said S3, the model of data processing and model construction starts from the obtained public data TCGA-bladder cancer level 3 data, and obtains a unified data matrix through quality control, standardization and conversion operations, and the data matrix is according to The ratio of 7:3 is randomly divided into training data set and verification data set, and the lasso regression method is used to reduce the dimension and screen the data, and construct the lncRNA prognosis prediction model; after the model is built, first add clinical risk factors, and then explore Impact of microenvironmental stromal/immune cell signature gene expression signatures on model performance.

Preferably, in said S6, a model is constructed for the characteristic gene expression signature of the mesenchymal cells, and the risk score is calculated and integrated into the lncRNA model. The results show that the characteristic gene expression risk score of the mesenchymal cells can improve the prognosis prediction of the model Performance, in the validation dataset, the prognostic prediction AUC for 5-year survival was 0.789.

Preferably, in the S6, the risk score of the characteristic gene of the mesenchymal cell and the risk score of the immune cell component are further integrated into the model, and the performance of the composite model of lncRNA and tumor microenvironment mesenchymal/immunity is close to excellent.

Preferably, in said S8, the scoring method includes variables of the most feasible lncRNA markers and clinical risk factors, and also provides CAF risk scores that can be used for further optimization and risk scores calculated by immune cell subsets, the column The line graph can be used for potential validation and diagnosis in the future. In addition, the drawn DCA curve shows that the constructed fusion model has clinical application value.

Preferably, in said S3, said lncRNA model includes 12 lncRNA molecules.

(3) Beneficial effects

Compared with the prior art, the present invention provides a method for predicting the survival and prognosis of bladder cancer patients based on an lncRNA-based optimized model, which has the following beneficial effects:

1. The method for predicting survival and prognosis of bladder cancer patients based on an optimized model of lncRNA, constructs an lncRNA model that can be used for prognosis prediction of bladder cancer through this method. By incorporating clinical risk factors, gene expression information of tumor microenvironmental stromal cells, and immune cell subtypes, the performance of the lncRNA model in predicting long-term survival of bladder cancer patients was optimized. The optimized fusion model has excellent performance, is scalable, and has certain clinical application value.

2. The method for predicting survival and prognosis of bladder cancer patients with an optimized model based on lncRNA, through this method, firstly, molecular features from multi-omics data can be included. In research, incomplete data or missing data is usually a common problem that limits the application of the model. The model of the present invention is built on the basis of relatively complete data, which makes it possible to predict survival in multiple dimensions, and the performance of the model will be more stable . Second, the framework of the present invention is scalable and can be adjusted according to the availability of clinical and genetic data at different centers. Third, the framework in the research of the present invention is also applicable to various cancer types, and the availability of multi-omics data makes this framework very useful for model construction of other cancers. The same framework can be developed for prognostic prediction of other cancer types, ultimately making the conceptually constructed models of the present invention suitable for clinical application.

3. This lncRNA-based optimization model predicts the survival and prognosis of bladder cancer patients. Through the model in this method, the model combines molecular features, which makes the model more biologically explanatory. Studies have shown that these molecular characteristics of the tumor microenvironment can also affect the efficacy, and may also be used to construct models to predict treatment response, which is worth further research in the future. Highlights the advantages of systematically synthesizing functional signaling networks from multi-omics data in computational models for predicting cancer prognosis. Previous studies have shown that multiple signaling pathways are involved in the pathogenesis of bladder cancer, including MAPK signaling and ERBB signaling. In this study, only the role of immune/stromal cells in the microenvironment of bladder cancer was investigated, and there are other genetic factors that may also explain bladder cancer prognosis. This multi-dimensional comprehensive model achieves better performance in prognosis prediction, and is easy to explain from a biological perspective, making the model more interpretable.

4. The method for predicting survival and prognosis of patients with bladder cancer based on an optimized model of lncRNA is helpful to predict the survival rate of MIBC patients, and is also helpful for predicting the prognosis of early bladder cancer.

Description of drawings

The accompanying drawings are used to provide a further understanding of the present invention, and constitute a part of the description, and are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation to the present invention. In the attached picture:

Fig. 1 is the flow chart of data processing and lncRNA model construction of the present invention;

Fig. 2 is the ROC curve and the survival curve (A: the AUC curve that the lncRNA model predicts the prognosis in the training set based on the lncRNA model of the present invention in the training data set and the verification data set; B: the survival curve that the lncRNA model predicts the prognosis in the training set; C: verification The AUC curve of the lncRNA model predicting the prognosis in the data set; D: the survival curve of the lncRNA model predicting the prognosis in the validation data set)

Fig. 3 is the figure of the effect of the lncRNA model integrating clinical risk factors of the present invention on bladder cancer prognosis prediction; (A: the AUC curve of predicting prognosis (36 months) after the lncRNA model integrates clinical risk factors in the training set; B: clinical risk in the training set Factors integrated into lncRNA model to predict prognosis (60 months) AUC curve; C: AUC curve of lncRNA model integrated clinical risk factors in validation data set to predict prognosis (36 months); D: Validation data set clinical risk factors integrated into lncRNA AUC curve of model prediction (60 months) prognosis)

Fig. 4 is the optimal lncRNA prediction model diagram of the interstitial/immune cell characteristic gene expression label based on the tumor microenvironment of the present invention; The risk scores calculated by the expression labels were integrated into the lncRNA model to predict the AUC curve of 3-year survival; B: The risk scores calculated by the expression labels of the immune cell characteristic genes in the training set, and the risk calculated by the expression labels of the mesenchymal cell characteristic genes The scores are integrated into the lncRNA model to predict the AUC curve of 5-year survival; C: The risk score calculated by the expression signature of the immune cell characteristic gene in the verification set, and the risk score calculated by the expression signature of the mesenchymal cell characteristic gene are respectively integrated into lncRNA model, predicting the AUC curve of 3-year survival; D: The risk score calculated by the expression signature of the immune cell signature gene in the validation set, and the risk score calculated by the expression signature of the mesenchymal cell signature gene were integrated into the lncRNA model, predicting 5 AUC curve of annual survival)

Fig. 5 is the performance diagram of predicting the prognosis of the lncRNA fusion model of the present invention integrating clinical risk factors and tumor microenvironmental gene expression labels; (A: the AUC curve of the lncRNA fusion model predicting prognosis (36 months) in the training set; B: the lncRNA in the training set AUC curve of fusion model predicting prognosis (60 months); C: AUC curve of lncRNA fusion model predicting prognosis (36 months) in validation set; D: AUC curve of lncRNA fusion model predicting prognosis (60 months) in validation set)

Fig. 6 is a nomogram for predicting the prognosis of bladder cancer patients based on lncRNA-based optimization model of the present invention

Fig. 7 is the DCA curve diagram of the lncRNA optimization fusion model of the present invention (A: drawing in the training data set; B: drawing 12, 24, 36, 48 and 60 months in the verification data set)

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention.

Examples of the described embodiments are shown in the drawings, wherein like or similar reference numerals designate like or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

In describing the present invention, it should be understood that the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", " Back", "Left", "Right", "Vertical", "Horizontal", "Top", "Bottom", "Inner", "Outer", "Clockwise", "Counterclockwise", "Axial" , "radial", "circumferential" and other indicated orientations or positional relationships are based on the orientations or positional relationships shown in the drawings, which are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying the referred device or Elements must have certain orientations, be constructed and operate in certain orientations, and therefore should not be construed as limitations on the invention.

In the present invention, unless otherwise clearly specified and limited, terms such as "installation", "connection", "connection" and "fixation" should be understood in a broad sense, for example, it can be a fixed connection or a detachable connection , or integrated; it can be mechanically connected or electrically connected; it can be directly connected or indirectly connected through an intermediary, and it can be the internal communication of two components or the interaction relationship between two components. Those of ordinary skill in the art can understand the specific meanings of the above terms in the present invention according to specific situations.

The present invention provides a method for predicting the survival and prognosis of bladder cancer patients based on an lncRNA-based optimization model, comprising the following steps:

S1: Data collection and preprocessing

Use FPKM data to analyze lncRNA data from TCGA, use RSEM to normalize count data and further log2 transform expression matrix, analyze mRNA data from TCGA Level 3, and use corrected phenotype data for TCGA clinical data to preprocess the data , through quality control, normalization and transformation to obtain a unified expression matrix;

S2: Statistical analysis

The 394 bladder cancer patients included in the analysis were randomly divided into a training set and a validation set at a ratio of 7:3. First, the data in the training set was used to find independent prognostic factors, and lasso regression and stepwise method were used to further reduce the dimensionality of variables to construct a multivariate Cox The risk model was then applied to the validation cohort to assess the specificity, sensitivity, and clinical validity of the predictive model. For model optimization, construct a model in the mRNA data set for a given gene expression label, calculate the risk score, and use it to optimize the fusion model. The model after fusion and optimization is displayed in a nomogram, and the predictive value and clinical effectiveness of the model The evaluation adopts receiver operating characteristic curve and decision curve analysis respectively;

S3: framework design and data preprocessing

After data preprocessing and lasso dimensionality reduction screening, the lncRNA prognosis prediction model was constructed. The lncRNA model included 12 lncRNA molecules. Then, the clinical risk factors affecting the prognosis of bladder cancer were incorporated into the model, including T stage, N stage and tumor grade. These clinically meaningful indicators are used to construct a clinical factor-lncRNA composite model, and then calculate the risk score based on the specific expression tags of tumor-associated fibroblast-stromal cells (CAF) in the microenvironment, together with the cell information of immune cell subsets , as an optimization variable to optimize the clinical factor-gene composite model, and then compare this optimized model with published, tumor-related lncRNA models;

In the model of data processing and model construction, starting from the obtained public data TCGA-bladder cancer level 3 data, through quality control, standardization and conversion operations, a unified data matrix is obtained, and the data matrix is randomized at a ratio of 7:3 Divided into a training data set and a verification data set, the lasso regression method was used to reduce the dimensionality and screen the data, and construct the lncRNA prognosis prediction model; after the model was constructed, firstly, clinical risk factors were added, and then, the tumor microenvironment stromal cells/ The impact of risk scores calculated from immune cell signature gene expression signatures on model performance;

S4: Construction of lncRNA-based prognosis prediction model

Using the combination of lasso algorithm and multiple Cox regression analysis, a lncRNA model containing 12 molecules was obtained. The ROC curve showed that the lncRNA model performed well in predicting the prognosis of bladder cancer, and the AUC of the 5-year survival prediction of the training data set was 0.894. , the risk score calculated by the model can be used to distinguish patients into two groups with significant differences. Compared with patients with low risk scores, the risk of death increased by 7.5 times. The AUC of the 5-year survival prediction of the validation data set was 0.755, and the death risk of patients with high-risk scores was 2.7 times that of patients with low-risk scores;

S5: Integration of lncRNA-based models and clinical risk factors

Integrating clinical risk factors, including bladder cancer T stage, N stage, tumor grade, constructing a clinical risk factor-lncRNA composite model, a separate clinical risk factor model and a single lncRNA model, the prognosis prediction performance of bladder cancer is good, but the performance is not yet Reaching an excellent level, the AUC of the 5-year survival prediction of the clinical risk factor model in the verification set is 0.774, and the AUC of the lncRNA model is 0.764. In contrast, after the lncRNA model is integrated into the clinical risk factors (clinical risk factor-lncRNA composite model) In the verification set, the AUC of 5-year survival prediction is 0.882, and the performance of the model reaches an excellent level. The combination of lncRNA and clinical risk factors can greatly improve the performance of the model;

S6: The predictive effect of tumor microenvironment stromal cell signature genes and immune cell subsets on the prognosis of bladder cancer

We built a model for the characteristic gene expression signature of mesenchymal cells, calculated the risk score and integrated it into the lncRNA model. The results show that characteristic gene expression risk scores of mesenchymal cells can improve the performance of the model. In the validation dataset, the prognostic prediction AUC for 5-year survival was 0.789. Using CYBERSORT to calculate immune cell components from mRNA data by deconvolution, it was shown that immune cell components alone can predict the prognosis of bladder cancer, and then the risk score of immune cell components was calculated and integrated into the lncRNA-CAF composite model , the results show that the performance of the lncRNA-CAF-Immune composite model is excellent in the training set (AUC of 5-year survival prediction=0.924), and the prediction value of the composite model in the verification set of 5-year survival is also better than that of the simple lncRNA model (AUC =0.787);

S7: Performance of optimized lncRNA fusion model in predicting survival and prognosis of bladder cancer patients

The prediction model combined with multi-dimensional biological information may improve the prediction performance. Therefore, a fusion model based on the lncRNA model and integrated with clinical risk factors and tumor microenvironment stromal cells/immune cell subtype gene expression information was established. The results showed that the ROC curve of the fusion model performed well in the verification data set, and in the verification data set, the prognosis prediction AUC of 5-year survival was 0.913;

S8: Clinical application exploration of the optimized lncRNA fusion model

Based on the constructed fusion model, draw a nomogram;

The scoring method includes variables of the most feasible lncRNA markers and clinical risk factors, and also provides risk scores for CAF and immune cell subsets that can be used for further optimization. After verification, it can be used to predict the survival and prognosis of bladder cancer patients. In addition, the drawn DCA curve shows that the constructed fusion model has good clinical application value.

It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is a relationship between these entities or operations. There is no such actual relationship or order between them. Furthermore, the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus comprising a set of elements includes not only those elements, but also includes elements not expressly listed. other elements of or also include elements inherent in such a process, method, article, or device. Without further limitations, an element defined by the phrase "comprising a referenced structure" does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising said element.

Claims (6)

1. A method for predicting the survival prognosis of a patient with bladder cancer based on an lncRNA optimization model is characterized by comprising the following steps:

s1: data collection and pre-processing

Analyzing bladder cancer lncRNA data from TCGA using FPKM data, analyzing mRNA data from TCGA Level3 using RSEM normalized count-class data and further log2 transformed expression matrices, TCGA clinical data using corrected phenotype data, pre-processing the data, quality control, normalization and transformation to obtain a unified expression matrix;

s2: statistical analysis

394 patients who are included in the analysis are randomly divided into a training set and a verification set according to the proportion of 7:3, firstly, data in the training set are used for searching for independent prognostic factors, a multivariate Cox risk model is constructed by further reducing dimensions of variables by adopting lasso regression and a step-by-step method, and then the model is applied to a verification queue to evaluate the specificity, sensitivity and clinical effectiveness of the prediction model. For the optimization of the model, a model is constructed in an mRNA data set for a given gene expression label related to a tumor microenvironment, a risk score is calculated and used for optimizing a fusion model, the fused and optimized model is displayed by a nomogram, and the evaluation of the prediction value and the clinical effectiveness of the model are respectively analyzed by adopting a subject working characteristic curve and a decision curve;

s3: framework design and data pre-processing

After data preprocessing and lasso dimension reduction screening, constructing an lncRNA prognosis prediction model, then bringing clinical risk factors influencing bladder cancer prognosis into the model, including T stage, N stage and tumor grading which have clinical significance indexes, so as to construct a clinical factor-lncRNA composite model, then respectively calculating risk scores based on tumor-related fibroblast interstitial Cell (CAF) specific expression labels in a microenvironment and immune cell subgroup cell information, optimizing the clinical factor-lncRNA composite model as an optimization variable, and then comparing the optimized model with a published tumor-related lncRNA model;

s4: construction of prognosis prediction model based on lncRNA

The method combining the lasso algorithm and the multivariate Cox regression analysis is adopted to obtain an lncRNA model containing 12 molecules, an ROC curve indicates that the lncRNA model is good in predicting bladder cancer prognosis, the AUC of survival prediction in 5 years of a training data set is 0.894, the risk score calculated by the model can be used for distinguishing patients into two types with significant difference, the death risk of patients with high risk score is increased by 7.5 times compared with the patients with low risk score, the AUC of survival prediction in 5 years of the training data set is verified to be 0.755, and the death risk of the patients with high risk score is 2.7 times that of the patients with low risk score;

s5: integration of lncRNA-based model with clinical risk factors

The clinical risk factors are integrated, including the T stage, the N stage and the tumor stage of the bladder cancer, a clinical risk factor-lncRNA composite model is constructed, the single clinical risk factor model and the single lncRNA model have good performance on prognosis prediction of the bladder cancer, but the performance does not reach an excellent level, the AUC of 5-year survival prediction in a centralized clinical risk factor model is 0.774, and the AUC of the lncRNA model is 0.764, compared with the AUC of 5-year survival prediction in a centralized clinical risk factor model after the lncRNA model is fused into the clinical risk factors (the clinical risk factor-lncRNA composite model), the AUC of the model performance reaches an excellent level, and the fusion model constructed by combining the lncRNA and the clinical risk factors can greatly improve the performance of the prediction model;

s6: prognosis prediction effect of tumor microenvironment interstitial cell characteristic genes and immune cell subsets on bladder cancer

We constructed models for the characteristic gene expression signatures of mesenchymal cells, calculated the risk score and integrated into the lncRNA model. The results indicate that the characteristic gene expression risk score of mesenchymal cells can improve the performance of the model. In the validation dataset, the prognostic prediction AUC for 5-year survival was 0.789. The research of Immune cell components obtained by deconvolution calculation from mRNA data by using CYBERSORT shows that the single Immune cell components can predict the prognosis of bladder cancer, then the risk scores of the Immune cell components are calculated and integrated into an lncRNA-CAF composite model, and the result shows that the lncRNA-CAF-Immune composite model is excellent in performance in a training set (AUC =0.924 of 5-year survival prediction), and the prediction value of the composite model in a verification set for 5 years is also superior to that of a pure lncRNA model (AUC = 0.787);

s7: optimized lncRNA fusion model for predicting performance of bladder cancer patient prognosis

The prediction performance can be improved by combining a prediction model of multidimensional biological information, so that a fusion model which takes an lncRNA model as a framework and is fused with clinical risk factors and interstitial cells/immune cell subtype gene expression information of a tumor microenvironment is established, the result shows that an ROC curve of the fusion model is excellent in a training set and a verification data set, and the prognosis prediction AUC for 5-year survival is 0.913 in the verification data set;

s8: clinical application exploration of optimized lncRNA fusion model

And drawing a nomogram based on the constructed fusion model. The nomogram visually demonstrates the impact of the most feasible lncRNA markers, CAF risk scores, immune risk scores and clinical risk factors on the outcome of the generated fusion model. In addition, the DCA curve drawn by the user shows that the fusion model constructed by the user has clinical application value.

2. The method for predicting the survival prognosis of the patient with bladder cancer based on the lncRNA optimization model as claimed in claim 1, wherein in S3, the model for data processing and model construction is obtained by performing quality control, standardization and transformation operations on the obtained public data TCGA-bladder cancer level3 to obtain a uniform data matrix, the data matrix is randomly divided into a training data set and a verification data set according to the proportion of 7:3, and dimension reduction and screening are performed on the data by using a lasso regression method to construct the lncRNA prognosis prediction model; after the model is constructed, clinical risk factors are added firstly, and then the influence of the risk score calculated by the tumor microenvironment interstitial cell/immune cell characteristic gene expression label on the model expression is explored.

3. The method for predicting survival prognosis of bladder cancer patient by using the incrna-based optimization model according to claim 1, wherein in S6, the characteristic gene expression label of the mesenchymal cells is modeled, the risk score is calculated and integrated into the incrna model, and the result shows that the characteristic gene expression risk score of the mesenchymal cells can improve the prognosis prediction performance of the model, and the prognosis prediction AUC for 5-year survival in the validation dataset is 0.789.

4. The method for predicting survival prognosis of bladder cancer patient according to the lncRNA-based optimization model of claim 1, wherein in S6, the risk score of characteristic genes of mesenchymal cells and the risk score of immune cell components are further fused into the model, and the performance of the lncRNA and the composite model of tumor microenvironment stroma/immunity is close to optimal.

5. The method for predicting the survival prognosis of the patient with bladder cancer based on the lncRNA optimized model of claim 1, wherein in S8, the scoring method comprises the lncRNA markers with the highest feasibility and the variables of clinical risk factors, and also provides CAF risk scores and risk scores calculated by immune cell subsets, which can be used for further optimization, and the nomogram can be used for potential future verification and diagnosis, and in addition, the constructed fused model is shown to have clinical application value through drawn DCA curves.

6. The method for predicting survival prognosis of a patient with bladder cancer based on an lncRNA optimization model of claim 1, wherein in S3, the lncRNA model comprises 12 lncRNA molecules.

Images