Cancer assessment model based on interpretable generative deep learning and its application

Abstract

The present invention relates to a cancer assessment model based on interpretable generative deep learning and its application, and relates to the technical field of cancer prognosis prediction. The cancer assessment model includes a Cox proportional hazards model combined with an L2 regularization term. This cancer assessment model can accurately assess cancer prognosis risk.

Description

Technical Field

[0001] The present invention relates to the technical field of cancer prognosis prediction, and in particular to a cancer assessment model based on explainable generative deep learning and its application. Background Art

[0002] Cancer is a complex disease that involves a series of interactions between genes and the environment. Although the medical community has made great progress in cancer research and treatment, there are still significant differences in the treatment outcomes of patients with the same type of cancer in clinical studies. This difference is because each patient's cancer has unique genomic characteristics and environmental exposure history. Therefore, developing effective cancer therapies has always been a huge challenge. To meet this challenge, researchers are increasingly relying on genomic information to accurately distinguish between high-risk and low-risk patients. Currently, many studies are based on gene expression (mRNA) data to assess cancer prognostic risk, which is usually measured by microarray technology. Gene expression profiles can provide important information about the biological characteristics of cancer and help predict disease progression and treatment response. Summary of the Invention

[0003] To address the above problems, the present invention provides a cancer assessment model based on interpretable generative deep learning, which can accurately assess the prognosis risk of cancer.

[0004] To achieve the above objectives, the present invention provides a cancer assessment model based on interpretable generative deep learning, including a Cox proportional hazard model combined with an L2 regularization term.

[0005] The Cox regression model, a semiparametric regression model, is widely used to assess the impact of a small number of clinical features on patient prognosis. However, the traditional Cox model suffers from long computational time and low prediction accuracy. Regularization methods are widely used to address this issue. However, the accuracy of such methods when processing high-dimensional, nonlinear data still needs to be improved. Compared to these methods, deep neural networks offer certain advantages when processing high-dimensional, nonlinear data. The DeepSurv model integrates these functions into a single deep neural network for cancer prognostic analysis, significantly outperforming both random survival forests and the Cox proportional hazards model. However, deep neural networks based solely on a risk prediction loss function cannot guarantee effective feature compression. Therefore, autoencoders are used to reduce the dimensionality of multi-omics expression data and then incorporate the reconstructed low-dimensional features into a proportional hazards model to predict survival risk in patients with liver cancer. Building on this, the variational autoencoder (VAE) regularizes the latent space to conform to a known prior distribution (typically a standard normal distribution), enabling it to better learn the spatial properties of high-dimensional features than autoencoders. However, while variational autoencoders (VAEs) have shown great potential in processing high-dimensional and complex genomic data, they still suffer from several drawbacks in feature extraction. The way VAEs generate data is limited to a defined data distribution, and their ability to learn the unique spatial distribution of the data is limited. In contrast, adversarial autoencoders (AAEs) can utilize arbitrary prior distributions, rather than being restricted to simple normal distributions, through a generative-adversarial strategy. This makes them more flexible and particularly suitable for scenarios requiring complex distributions.

[0006] On the other hand, the black box properties of most existing deep learning technologies result in a lack of feature interpretability in the established models. The black box properties of neural networks have caused certain difficulties for researchers to identify relevant genes that affect patient prognosis. Improving the interpretability of such models is of great significance for exploring new targets for subsequent anticancer drugs. Therefore, the inventors proposed the above-mentioned cancer assessment model. AAE combines the advantages of generative adversarial networks (GANs) and autoencoders. By introducing an adversarial training mechanism, it can more effectively learn the distribution of data, thereby extracting features with stronger discriminative power. This improvement helps to improve the accuracy of cancer prognosis risk assessment based on genomic information, and provides a more reliable basis for the formulation of personalized treatment plans. The feature interpretability of its framework can help us better find potential markers related to liver cancer prognosis.

[0007] This cancer assessment model, built using deep learning and generative adversarial networks, applies cutting-edge artificial intelligence technologies to bioinformatics and cancer research, promoting the integration of scientific research and clinical applications. This model is not only effective for liver cancer but also has potential applications in prognosis assessment and target identification for other types of cancer, with broad prospects for widespread adoption. Compared to traditional methods such as the Cox regression model, random survival forest (RSF), Cox-elastic net, and deep neural networks (DNN), it significantly improves the C-index value for liver cancer prognosis assessment, reaching an average C-index of 0.634, approximately 3.55% higher than other methods.

[0008] In one embodiment, the method for constructing the L2-regularized Cox regression model includes the following steps: inputting sample data into an unsupervised adversarial autoencoder, training the unsupervised adversarial autoencoder, outputting features, calculating the partial likelihood function using the Cox regression model based on the features, adding an L2 regularization term to the logarithmic partial likelihood function to maximize the regularized logarithmic partial likelihood function, determining the regression coefficient of the Cox regression model, and obtaining the L2-regularized Cox regression model.

[0009] The above-mentioned unsupervised adversarial autoencoder can integrate sample data of cancer cells (such as high-dimensional input data such as mRNA) and more effectively extract discriminative features for cancer prognosis assessment.

[0010] In one embodiment, the sample data includes gene expression data.

[0011] In one embodiment, the gene expression data is mRNA data.

[0012] In one embodiment, the training includes autoencoder training and adversarial training, and the autoencoder training includes the following steps: mapping sample data to a latent space through an encoder, the encoder outputting latent variables, reconstructing through a decoder to obtain a reconstruction result, calculating a reconstruction error, backpropagating to minimize the reconstruction error, and updating the parameters of the encoder and decoder;

[0013] The adversarial training includes training a discriminator and training an encoder, wherein the training of the discriminator includes the following steps: sampling a prior distribution latent variable from a prior distribution, sampling an encoder latent variable from a latent variable output by the encoder, the discriminator distinguishing the prior distribution latent variable and the encoder latent variable, calculating the adversarial loss of the discriminator, back-propagating to minimize the adversarial loss of the discriminator, and updating the parameters of the discriminator;

[0014] The training encoder includes the following steps: calculating the adversarial loss of the encoder, back-propagating to minimize the adversarial loss of the encoder, and updating the parameters of the encoder until the model converges.

[0015] In one embodiment, the total loss function of the unsupervised adversarial autoencoder is the multiplication of the reconstruction error and the adversarial loss The weighted sum of .

[0016] above

[0017] In one embodiment, the Cox regression model is as follows: h(t|X)=h0(t)exp(Xβ);

[0018] Where h(t|X) is the hazard function under a given covariate X, h0(t) is the baseline hazard function that describes the change in risk at time t, X is the covariate vector, and β is the regression coefficient;

[0019] The log partial likelihood function after adding the L2 regularization term is as follows: Where: λ is the hyperparameter of regularization strength, ∥β∥ 2 is the L2 norm of the regression coefficient vector.

[0020] In one embodiment, the log partial likelihood function is as follows: Where n is the number of observations, X is the covariate vector, and R(t i ) is at time t i The set of individuals that have not died before, j represents the number of individuals at time t j Individuals who have died, β is the regression coefficient.

[0021] The present invention also provides a method for constructing the cancer assessment model, comprising the following steps:

[0022] Data processing: Obtain gene expression data, perform preprocessing, and obtain sample data;

[0023] Obtain features: Input sample data into the unsupervised adversarial autoencoder, train the unsupervised adversarial autoencoder, and output features;

[0024] Constructing a cancer assessment model: Based on the features, the Cox regression model is used to calculate the partial likelihood function. An L2 regularization term is added to the logarithmic partial likelihood function to maximize the regularized logarithmic partial likelihood function. The regression coefficient of the Cox regression model is determined to obtain the L2 regularized Cox regression model.

[0025] In one embodiment, the preprocessing includes the following steps: deleting missing samples and features in the gene expression data, filling in the remaining missing items, and standardizing to obtain sample data;

[0026] The training includes autoencoder training and adversarial training. The autoencoder training includes the following steps: mapping sample data to a latent space through an encoder, the encoder outputting latent variables, reconstructing the latent variables through a decoder to obtain a reconstruction result, calculating the reconstruction error, backpropagating to minimize the reconstruction error, and updating the parameters of the encoder and decoder;

[0027] The adversarial training includes training a discriminator and training an encoder, wherein the training of the discriminator includes the following steps: sampling a prior distribution latent variable from a prior distribution, sampling an encoder latent variable from a latent variable output by the encoder, the discriminator distinguishing the prior distribution latent variable and the encoder latent variable, calculating the adversarial loss of the discriminator, back-propagating to minimize the adversarial loss of the discriminator, and updating the parameters of the discriminator;

[0028] The training encoder includes the following steps: calculating the adversarial loss of the encoder, back-propagating to minimize the adversarial loss of the encoder, and updating the parameters of the encoder until the model converges.

[0029] In one embodiment, the preprocessing includes the following steps: deleting samples and features with more than 20% missing in the gene expression data, filling the remaining missing items with the median, and normalizing the gene expression data to obtain sample data.

[0030] In one embodiment, the Cox regression model is as follows: h(t|X)=h0(t)exp(Xβ); wherein h(t|X) is the hazard function under a given covariate X, h0(t) is the baseline hazard function, X is the covariate vector, and β is the regression coefficient;

[0031] The log partial likelihood function is as follows: Where n is the number of observations, X is the covariate vector, and R(t i ) is at time t i The set of individuals that have not died before, j represents the number of individuals at time t j Individuals who have experienced a death event, β is the regression coefficient;

[0032] The log partial likelihood function after adding the L2 regularization term is as follows: Where: λ is the hyperparameter of regularization strength, ∥β∥ 2 is the L2 norm of the regression coefficient vector.

[0033] The present invention also provides a method for assessing cancer prognosis risk, comprising the following steps: inputting the gene expression data of the person to be assessed into an unsupervised adversarial autoencoder, outputting features, substituting the features into the cancer assessment model to obtain a hazard function h(t|X); if the hazard function h(t|X) is greater than 0, it is judged that the person to be assessed has a high cancer prognosis risk.

[0034] The cancer assessment model of this invention provides a more reliable gene expression signature, enabling the aforementioned method to help differentiate high-risk from low-risk patients, providing a basis for developing personalized treatment plans. By accurately identifying high-risk patients, clinicians can develop more precise treatment plans for these patients, improving treatment outcomes.

[0035] The present invention also provides a method for screening cancer prognostic targets, comprising the following steps: inputting sample data into a random forest model to obtain an importance coefficient; analyzing the sample data using the cancer assessment model to obtain a hazard function; performing differential expression analysis on the hazard function to obtain differentially expressed genes; and finding the intersection of the differentially expressed genes and the importance coefficient to obtain cancer prognostic targets;

[0036] The random forest model is shown below: in, is the predicted risk value of the i-th sample, K is the number of decision trees in the random forest, and f k is the prediction function of the kth decision tree.

[0037] This method can identify potential targets for liver cancer prognosis, facilitating the development of new drugs and targeted therapies. In target identification, a random forest model was constructed using gene expression data to further screen key genes (such as AKR1B10 and ALDOB). These genes may become new targets for liver cancer treatment, providing important clues for subsequent research.

[0038] In one embodiment, each decision tree f k can be expressed as: f k (x) = w qk(x) , where q k (x) is the function that maps the feature vector x to the leaf node of the kth decision tree, and w is the weight of the leaf node.

[0039] The present invention also provides a system for assessing cancer prognosis risk, comprising:

[0040] A data storage module, used to store the gene expression data of the person to be evaluated and the cancer assessment model;

[0041] A data analysis module, configured to perform analysis according to the method described; and

[0042] The data display module is used to display the cancer prognosis risk of the person to be evaluated.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] The present invention provides a cancer assessment model based on interpretable generative deep learning, which can accurately assess the risk of cancer prognosis and then evaluate the prognosis of cancer. This cancer assessment model applies cutting-edge artificial intelligence technology to the fields of bioinformatics and cancer research, promoting the integration of scientific research and clinical applications. This model is not only effective for liver cancer, but also has potential application value in prognosis assessment and target identification of other types of cancer, and has broad promotion prospects. Compared with traditional methods such as Cox regression model, random survival forest (RSF), Cox-elastic net and deep neural network (DNN), there is a significant improvement in the C index value of liver cancer prognosis assessment, with an average C index value of 0.634, which is about 3.55% higher than other methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A process for evaluating liver cancer prognosis and identifying potential targets based on the cancer assessment model of Example 1;

[0046] Figure 2 This is a comparison chart of the differential expression of liver cancer prognostic targets identified in Example 2. DETAILED DESCRIPTION

[0047] To facilitate understanding of the present invention, the present invention will be described more fully below with reference to the accompanying drawings. Preferred embodiments of the present invention are shown in the accompanying drawings. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and comprehensive understanding of the present disclosure.

[0048] It should be noted that when an element is referred to as being “fixed to” another element, it may be directly on the other element or there may be an intermediate element. When an element is referred to as being “connected to” another element, it may be directly connected to the other element or there may be an intermediate element at the same time.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this invention pertains. The terms used herein in the specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0050] source:

[0051] Unless otherwise specified, the reagents, materials, and equipment used in this example are all commercially available; and the experimental methods, unless otherwise specified, are all conventional experimental methods in the art.

[0052] Example 1

[0053] A cancer assessment model based on explainable generative deep learning.

[0054] In this embodiment, cancer assessment is cancer prognosis risk assessment, and the method for constructing the cancer assessment model is as follows:

[0055] 1. Data processing

[0056] Step 1: Obtain mRNA data of liver cancer patients from public datasets (TCGA, gse10186, gse14520).

[0057] Step 2: Remove samples and features with more than 20% missing in the data to ensure data quality.

[0058] Step 3: Use the median to fill in the remaining missing data to reduce the impact of missing data on the model.

[0059] Step 4: Standardize the gene expression data to eliminate the impact of different dimensions and magnitudes on the model and obtain sample data for model training.

[0060] 2. Obtain features.

[0061] The sample data is input into the unsupervised adversarial autoencoder, the unsupervised adversarial autoencoder is trained, and features are output.

[0062] The training process of an unsupervised adversarial autoencoder consists of two main stages: autoencoder training and adversarial training.

[0063] 1. During the autoencoder training phase.

[0064] First, forward propagation is performed to map the input data x to the latent space through the encoder E to obtain the latent variable z, and then the input data is reconstructed through the decoder D to obtain the reconstruction result x'. Next, the reconstruction error is calculated The reconstruction error is then minimized through backpropagation to update the parameters of the encoder and decoder.

[0065] 2. During the confrontation training phase.

[0066] First, the discriminator is trained. The discriminator samples a batch of latent variables z from the prior distribution p(z) prior , and at the same time sample another batch of latent variables from the latent variables z=E(x) output by the encoder. The discriminator tries to distinguish these two batches of latent variables and calculates the adversarial loss of the discriminator The discriminator’s parameters are updated by minimizing the adversarial loss of the discriminator through backpropagation.

[0067] Next, train the encoder. The goal of the encoder is to generate latent variables z that can deceive the discriminator. Calculate the adversarial loss of the encoder The encoder’s adversarial loss is minimized through backpropagation, and the encoder’s parameters are updated. This process is repeated until the model converges.

[0068] The total loss function of the adversarial autoencoder can be expressed as a weighted sum of the reconstruction error and the adversarial loss: Where λ is a hyperparameter that balances the two losses, In this way, the adversarial autoencoder can not only reconstruct the input data, but also generate high-quality data whose latent variable distribution matches the prior distribution.

[0069] 3. Build a cancer assessment model.

[0070] The features learned from the hidden layer of the adversarial autoencoder are used to construct a Cox proportional hazards model combined with L2 regularization to estimate cancer prognostic risk assessment.

[0071] The basic form of the Cox regression model is: h(t|X)=h0(t)exp(Xβ), where h(t|X) is the hazard function under a given covariate X, h0(t) is the baseline hazard function, X is the covariate vector, and β is the regression coefficient vector.

[0072] The Cox regression model estimates the regression coefficient β by maximizing the partial likelihood function. The logarithmic form of the partial likelihood function is: Where: n is the number of observations, R(t i ) is at time t i A collection of individuals for whom no previous death event has occurred.

[0073] L2 regularization prevents overfitting by adding a penalty term to the objective function. The penalty term is a multiple of the L2 norm (i.e., the sum of squares) of the regression coefficients. The log partial likelihood function after adding L2 regularization is: Where: λ is the hyperparameter of regularization strength, ∥β∥ 2 is the L2 norm of the regression coefficient vector.

[0074] Based on the collected data (i.e., the features output by the unsupervised adversarial autoencoder described above), a partial likelihood function is calculated based on the Cox regression model formula. An L2 regularization term is then added to the log partial likelihood function. This term is calculated by subtracting half the L2 norm (sum of squares) of the regression coefficients from the log partial likelihood function and multiplying it by the regularization strength hyperparameter. An objective function that includes the regularization term is then constructed, which aims to maximize the regularized log partial likelihood function. To achieve this optimization goal, numerical optimization methods can be used to find the maximum value of the regularized log partial likelihood function, thereby obtaining the regression coefficients.

[0075] Finally, the accuracy of the liver cancer prognosis prediction model constructed by our algorithm was evaluated by calculating the C-index.

[0076] In this step, we input the data (i.e., the features output by the unsupervised adversarial autoencoder) into the Cox, RSF, Cox-elastic net, and DNN methods for computational evaluation and comparison of their accuracy. The results are shown in Table 1.

[0077] Table 1 Confidence C-index scores of liver cancer public dataset

[0078]

[0079] Example 2

[0080] Random forest model construction and feature selection.

[0081] To address the feature interpretability issue of deep learning frameworks, random forests were used to select a small number of key genomic features to build prediction models.

[0082] Given a dataset where x i is the eigenvector, y i is the corresponding risk value. Dataset D is the sample data obtained after data processing in step 1 of Example 1. We want to build an integrated random forest model to select a small number of key genomic features and predict the patient's risk. The random forest model can be expressed as the following formula: in, is the predicted risk value of the i-th sample, K is the number of decision trees in the random forest, and f k Is the prediction function of the kth decision tree. Each decision tree f k can be expressed as: f k (x) = w qk(x) , where q k (x) is the function that maps the feature vector x to the leaf node of the kth decision tree, and w is the weight of the leaf node. Therefore, the prediction value of the random forest model is It is obtained by averaging the predictions of each decision tree. The training process of random forest involves constructing multiple decision trees through random sampling and random feature selection, and training each tree to minimize the model error. During the prediction process, random forest averages or votes the predictions of each tree to obtain the final prediction result (i.e., the importance coefficient). The results are shown in Table 2.

[0083] The liver cancer prognosis assessment and potential target identification process based on the cancer assessment model of Example 1 is as follows: Figure 1 As shown, differential expression analysis was then performed based on the obtained prognostic risk assessment results (i.e., hazard function) for liver cancer patients ( Figure 2 Differential expression analysis compares the expression levels of genes, proteins, or metabolites in biological samples under different conditions (e.g., disease and health, treated and untreated, at different time points) to identify molecules that exhibit significant differences between these conditions. By intersecting the differentially expressed genes identified with the importance coefficients screened by random forests, potential gene targets influencing liver cancer prognosis are identified, addressing the lack of feature interpretability inherent in deep learning frameworks.

[0084] Table 2 Identification of potential prognostic targets for liver cancer

[0085]

[0086] In summary, to evaluate the performance of our proposed adversarial autoencoder method for integrating patient mRNA data for liver cancer prognosis assessment and target identification, we compared our method with other commonly used methods for liver cancer prognosis assessment using liver cancer cell mRNA data. As shown in Table 1, the C-index values ​​of our method ranged from 0.611 to 0.665, with an average of 0.634. Compared to other methods, our method achieved an average C-index improvement of 3.55%. Among the other methods, the Cox method achieved the lowest C-index, with an average of 0.575. The other three methods, RSF, Cox-elastic net, and DNN, achieved average C-index values ​​of 0.596, 0.602, and 0.621, respectively, which were lower than those of deep learning-based methods. Cox-elastic net outperformed Cox but not our method. We performed t-tests on the results obtained with our method and the other methods, and the p-values ​​showed that our method significantly improved over the other methods. In addition, in Table 2, we list the potential targets that may affect the prognosis of liver cancer found based on our method. Among them, 14 have been proven to be related to liver cancer in other literature, which proves that our method can find key genes for liver cancer with high accuracy, while the rest may be potential targets for liver cancer that have not yet been proven.

[0087] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0088] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the patent for this invention shall be determined by the appended claims.

Claims

1. A cancer assessment model based on interpretable generative deep learning, characterized by: A Cox proportional hazards model incorporating an L2 regularization term is included; the Cox regression model is shown below: ; in, is a given covariate The hazard function under is the baseline hazard function, describing the risk change at time t, is the covariate vector, is the regression coefficient; The method for constructing the L2-regularized Cox regression model comprises the following steps: inputting sample data into an unsupervised adversarial autoencoder, training the unsupervised adversarial autoencoder, outputting features, calculating a partial likelihood function using a Cox regression model based on the features, adding an L2 regularization term to the logarithmic partial likelihood function to maximize the regularized logarithmic partial likelihood function, determining the regression coefficient of the Cox regression model, and obtaining the L2-regularized Cox regression model; The log partial likelihood function after adding the L2 regularization term is as follows: ,in: is a hyperparameter of the regularization strength, is the L2 norm of the regression coefficient vector; The sample data is mRNA data; the hazard function of the L2 regularized Cox regression model is used to determine cancer prognosis risk and / or screen cancer prognosis targets.

2. The cancer assessment model according to claim 1, characterized in that The training includes autoencoder training and adversarial training. The autoencoder training includes the following steps: mapping sample data to a latent space through an encoder, the encoder outputting latent variables, reconstructing the latent variables through a decoder to obtain a reconstruction result, calculating the reconstruction error, backpropagating to minimize the reconstruction error, and updating the parameters of the encoder and decoder; The adversarial training includes training a discriminator and training an encoder, wherein the training of the discriminator includes the following steps: sampling a prior distribution latent variable from a prior distribution, sampling an encoder latent variable from a latent variable output by the encoder, the discriminator distinguishing the prior distribution latent variable and the encoder latent variable, calculating the adversarial loss of the discriminator, back-propagating to minimize the adversarial loss of the discriminator, and updating the parameters of the discriminator; The training encoder includes the following steps: calculating the adversarial loss of the encoder, back-propagating to minimize the adversarial loss of the encoder, and updating the parameters of the encoder until the model converges.

3. The method for constructing a cancer assessment model according to any one of claims 1 to 2, characterized in that: The following steps are involved: Data processing: Obtain gene expression data, perform preprocessing, and obtain sample data; Obtain features: Input sample data into the unsupervised adversarial autoencoder, train the unsupervised adversarial autoencoder, and output features; Constructing a cancer assessment model: Based on the features, the Cox regression model is used to calculate the partial likelihood function. An L2 regularization term is added to the logarithmic partial likelihood function to maximize the regularized logarithmic partial likelihood function. The regression coefficient of the Cox regression model is determined to obtain the L2 regularized Cox regression model.

4. The construction method according to claim 3, characterized in that The preprocessing includes the following steps: deleting missing samples and features in the gene expression data, filling in the remaining missing items, and standardizing to obtain sample data; The training includes autoencoder training and adversarial training. The autoencoder training includes the following steps: mapping sample data to a latent space through an encoder, the encoder outputting latent variables, reconstructing the latent variables through a decoder to obtain a reconstruction result, calculating the reconstruction error, backpropagating to minimize the reconstruction error, and updating the parameters of the encoder and decoder; The adversarial training includes training a discriminator and training an encoder, wherein the training of the discriminator includes the following steps: sampling a prior distribution latent variable from a prior distribution, sampling an encoder latent variable from a latent variable output by the encoder, the discriminator distinguishing the prior distribution latent variable and the encoder latent variable, calculating the adversarial loss of the discriminator, back-propagating to minimize the adversarial loss of the discriminator, and updating the parameters of the discriminator; The training encoder includes the following steps: calculating the adversarial loss of the encoder, back-propagating to minimize the adversarial loss of the encoder, and updating the parameters of the encoder until the model converges.

5. The construction method according to claim 4, characterized in that: The Cox regression model is as follows: ;in, is a given covariate The hazard function under is the baseline hazard function, is the covariate vector, is the regression coefficient; The log partial likelihood function is as follows: ;in, is the number of observations, is the covariate vector, It's in time The set of individuals who have not died before, j Indicates time Individuals who died, is the regression coefficient; The log partial likelihood function after adding the L2 regularization term is as follows: ,in: is a hyperparameter of the regularization strength, is the L2 norm of the regression coefficient vector.

6. A method for assessing cancer prognosis risk, characterized in that: The following steps are involved: The gene expression data of the person to be evaluated is input into an unsupervised adversarial autoencoder, and features are output. The features are substituted into the cancer assessment model described in any one of claims 1-2 to obtain a hazard function. , if the hazard function If it is >0, the person being evaluated is judged to have a high risk of cancer prognosis.

7. A method for screening cancer prognosis targets, characterized in that: The method comprises the following steps: inputting sample data into a random forest model to obtain an importance coefficient; analyzing the sample data using the cancer assessment model described in any one of claims 1 to 2 to obtain a hazard function; performing differential expression analysis on the hazard function to obtain differentially expressed genes; and finding the intersection of the differentially expressed genes and the importance coefficient to obtain cancer prognosis targets; The random forest model is shown below: in, It is the The predicted risk value of samples is is the number of decision trees in the random forest, It is The prediction function of a decision tree.

8. A system for assessing cancer prognosis risk, characterized in that: include: A data storage module, configured to store gene expression data of the person to be evaluated and the cancer assessment model according to any one of claims 1 to 2; a data analysis module, configured to perform analysis according to the method of claim 6; and The data display module is used to display the cancer prognosis risk of the person to be evaluated.

Images