Construction method and application of bladder cancer chemotherapy drug sensitivity prediction model

Abstract

The invention relates to the technical field of drug sensitivity prediction, and discloses a building method and application of a bladder cancer chemotherapy drug sensitivity prediction model, and the building method comprises the following steps: building a training set; according to the training set, a plurality of candidate models are obtained through training through a plurality of machine learning algorithms; and screening the plurality of candidate models according to preset model indexes to obtain at least two bladder cancer chemotherapeutic drug sensitivity prediction models. Based on bladder cancer chemotherapy drug type data applied by a target group, immune cell infiltration level data of tumor sample tissues and PTC data, a machine learning algorithm is utilized to train and obtain a plurality of high-precision bladder cancer chemotherapy drug sensitivity prediction models; the method can be used for accurately predicting the bladder cancer chemotherapeutic drug sensitivity in combination with a hard voting method. The method is high in model prediction accuracy, suitable for people, more targeted, simple and clear in prediction result, short in service cycle and low in cost.

Description

Technical Field

[0001] The present invention relates to the technical field of drug sensitivity prediction, and in particular to a method for constructing a bladder cancer chemotherapy drug sensitivity prediction model and its application. Background Art

[0002] Bladder cancer is the most common malignant tumor of the urinary system, and ranks first in the incidence of urogenital tumors in my country. Due to the heterogeneity of bladder cancer and its insensitivity to chemotherapy drugs, the treatment is somewhat blind. Chemotherapy drugs are inherently cytotoxic, and during chemotherapy, the tumor may not be controlled, and adverse reactions may occur, causing unnecessary pain to the patient, affecting the quality of life, and even prognosis.

[0003] With the rapid development of molecular biology, it has been found that gene expression in cancer is closely related to the occurrence, development, metastasis, and prognosis of tumors, and is also related to the chemotherapy efficacy of tumors. In addition, more and more machine learning models are used to predict drug sensitivity. How to use machine learning methods to accurately predict patient drug sensitivity and assist in guiding personalized treatment of tumor patients is of great clinical significance. At present, the data used by most drug sensitivity prediction models mainly come from public databases, and there is a lack of real clinical data for Chinese people, which makes the prediction results inconsistent with the actual clinical effects, and the prediction results of the model are IC50 values, which cannot intuitively show the effect of medication.

[0004] Therefore, there is an urgent need for a method to construct a prediction model for bladder cancer chemotherapy drug sensitivity to assist in intuitively and accurately predicting patient drug sensitivity, guide personalized treatment for cancer patients, and improve patient cure rates. Summary of the invention

[0005] The present invention provides a method for constructing a bladder cancer chemotherapy drug sensitivity prediction model and its application, so as to solve the defects that the prediction results of the existing drug sensitivity prediction models are low in accuracy and the prediction results are IC50 values, which cannot intuitively show the drug effect.

[0006] The present invention provides a method for constructing a training set, comprising:

[0007] Obtaining whole transcriptome sequencing data of tumor sample tissues of the target population, data on the types of bladder cancer chemotherapy drugs administered, and data on sensitivity of bladder cancer chemotherapy drugs, wherein the target population is a bladder cancer patient population, and the bladder cancer chemotherapy drug sensitivity data includes bladder cancer chemotherapy drug response data and bladder cancer chemotherapy drug resistance data;

[0008] Obtaining gene expression data of the tumor sample tissue of the target group based on the whole transcriptome sequencing data of the tumor sample tissue of the target group;

[0009] According to the gene expression data of the tumor sample tissue of the target group, the immune cell infiltration level data of the tumor sample tissue of the target group is obtained;

[0010] The training set is constructed using the data on the types of bladder cancer chemotherapy drugs administered to the target population and the data on the immune cell infiltration levels of tumor sample tissues as sample data, and the data on the sensitivity of bladder cancer chemotherapy drugs to the target population as label data.

[0011] In one embodiment, the data of the type of bladder cancer chemotherapy drugs administered include any one or any combination of the following: gemcitabine data, paclitaxel data, docetaxel data.

[0012] In one embodiment, obtaining gene expression data of tumor sample tissues of the target population based on whole transcriptome sequencing data of tumor sample tissues of the target population includes:

[0013] Obtain reference genome data;

[0014] Perform data quality control on the whole transcriptome sequencing data of tumor sample tissues of the target population;

[0015] Compare the whole transcriptome sequencing data after data quality control with the reference genome data to obtain a bam file;

[0016] The gene expression levels were calculated based on the bam file to obtain the gene expression data of the tumor sample tissues of the target group.

[0017] In one embodiment, the data quality control of the whole transcriptome sequencing data of the tumor sample tissue of the target population includes:

[0018] According to the preset data quality control conditions, the whole transcriptome sequencing data of the tumor sample tissue of the target population is subjected to data quality control, wherein the preset data quality control conditions include:

[0019] Filter out reads whose base N content exceeds the preset content threshold;

[0020] Filter out reads whose sequencing quality values ​​are lower than the preset quality value threshold.

[0021] In one embodiment, the preset quality value threshold is 15.

[0022] In one embodiment, obtaining the immune cell infiltration level data of the tumor sample tissue of the target population based on the gene expression data of the tumor sample tissue of the target population includes:

[0023] According to the gene expression data of the tumor sample tissue of the target population, multiple cell infiltration level assessment results are obtained through multiple cell infiltration level assessment methods, and then the immune cell infiltration level data of the tumor sample tissue of the target population is obtained, wherein the multiple cell infiltration level assessment methods include any one of the following or any combination thereof: CIBERSORT, CIBERSORT-ABS, EPIC, MCPCOUNTER, QUANTISEQ, TIMER, XCELL.

[0024] In one embodiment, the present invention provides a method for constructing a training set further comprising:

[0025] The training set is cleaned according to the preset cleaning rules, wherein the preset cleaning rules include any one of the following or any combination thereof:

[0026] For each piece of immune cell infiltration level data in the immune cell infiltration level data of the tumor sample tissue of the target population, when the value of the immune cell infiltration level evaluation result of >60% is 0, the immune cell infiltration level data is deleted;

[0027] For the immune cell infiltration level data of tumor sample tissues of the target population obtained by multiple cell infiltration level assessment methods, when ≥80% of the values ​​of the immune cell infiltration level assessment results obtained by a certain cell infiltration level assessment method are all 0, the immune cell infiltration level assessment results obtained by this cell infiltration level assessment method are deleted;

[0028] When the data on the type of bladder cancer chemotherapy drugs administered represent the same bladder cancer chemotherapy drug, for the bladder cancer chemotherapy drug sensitivity data of the target population, if the bladder cancer chemotherapy drug sensitivity data indicate that the ratio of bladder cancer chemotherapy drug response to bladder cancer chemotherapy drug resistance is outside a preset ratio range, then some of the bladder cancer chemotherapy drug sensitivity data are randomly deleted until the ratio of bladder cancer chemotherapy drug response to bladder cancer chemotherapy drug resistance is within a preset range.

[0029] The present invention provides a method for constructing a prediction model for chemotherapeutic drug sensitivity of bladder cancer, comprising:

[0030] Obtaining a training set obtained by the training set construction method described in any one of the above items;

[0031] According to the training set, multiple candidate models are trained through multiple machine learning algorithms;

[0032] According to preset model indicators, multiple candidate models are screened to obtain at least two final candidate models as at least two bladder cancer chemotherapy drug sensitivity prediction models.

[0033] In one embodiment, at least two final candidate models include four final candidate models, wherein the four final candidate models are candidate models trained according to the training set by EasyEnsemble Classifier (an integrated classifier based on random undersampling), BalancedRandomForest Classifier (balanced random forest classifier), BalancedBagging Classifier (an integrated classifier based on Bagging technology), and RUSBoost Classifier (a classifier based on random undersampling) machine learning algorithms.

[0034] In one embodiment, the preset model indicators include any one of the following items or any combination thereof: area under the ROC curve (AUC), F1 score (F1-score), accuracy (Accuracy), Matthews Correlation Coefficient (MCC).

[0035] The present invention provides a bladder cancer chemotherapy drug sensitivity prediction system, comprising:

[0036] The data receiving module is used to: receive data on the type of bladder cancer chemotherapy drugs to be administered to a subject and data on the immune cell infiltration level of a tumor sample tissue sent by at least one client, wherein the subject to be tested is a bladder cancer patient;

[0037] A prediction module, for: obtaining a prediction result of the bladder cancer chemotherapy drug sensitivity of the subject according to the data of the type of bladder cancer chemotherapy drug to be administered to the subject and the data of the immune cell infiltration level of the tumor sample tissue, using at least two bladder cancer chemotherapy drug sensitivity prediction models obtained by any of the above-mentioned methods for constructing a bladder cancer chemotherapy drug sensitivity prediction model, and combining with a hard voting method;

[0038] The data sending module is used to send the predicted result of the bladder cancer chemotherapy drug sensitivity of the subject to be tested back to at least one client.

[0039] In one embodiment, the prediction module includes:

[0040] The prediction submodule is used to obtain at least two bladder cancer chemotherapy drug sensitivity prediction results for the subject according to the data on the type of bladder cancer chemotherapy drugs to be administered to the subject and the data on the immune cell infiltration level of the tumor sample tissue, respectively, by using at least two bladder cancer chemotherapy drug sensitivity prediction models obtained by any of the above-mentioned methods for constructing a bladder cancer chemotherapy drug sensitivity prediction model;

[0041] The determination submodule is used to obtain the final bladder cancer chemotherapy drug sensitivity prediction result of the subject according to at least two bladder cancer chemotherapy drug sensitivity prediction results of the subject in combination with a hard voting method, wherein the hard voting method is: when there is a unique bladder cancer chemotherapy drug sensitivity prediction result with the most votes among the at least two bladder cancer chemotherapy drug sensitivity prediction results of the subject, the unique bladder cancer chemotherapy drug sensitivity prediction result with the most votes is used as the final bladder cancer chemotherapy drug sensitivity prediction result of the subject; when there is no unique bladder cancer chemotherapy drug sensitivity prediction result with the most votes among the at least two bladder cancer chemotherapy drug sensitivity prediction results of the subject, when the bladder cancer chemotherapy drug sensitivity prediction model is trained by the construction method of the bladder cancer chemotherapy drug sensitivity prediction model described in any of the above items, the bladder cancer chemotherapy drug sensitivity prediction result of the bladder cancer chemotherapy drug sensitivity prediction model with the highest bladder cancer chemotherapy drug sensitivity prediction accuracy corresponding to the bladder cancer chemotherapy drug type is used as the final bladder cancer chemotherapy drug sensitivity prediction result of the subject.

[0042] The present invention also provides an electronic device, comprising a processor and a memory storing a computer program, wherein when the processor executes the computer program, the method for constructing any of the above-mentioned training set construction methods and the method for constructing a bladder cancer chemotherapy drug sensitivity prediction model is implemented.

[0043] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for constructing any of the above-mentioned training set construction methods and the method for constructing a bladder cancer chemotherapy drug sensitivity prediction model is implemented.

[0044] The present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute any of the above-mentioned methods for constructing a training set and methods for constructing a bladder cancer chemotherapy drug sensitivity prediction model.

[0045] The present invention provides a method for constructing a bladder cancer chemotherapy drug sensitivity prediction model and its application. Based on the type data of bladder cancer chemotherapy drugs used by the target group, the immune cell infiltration level data of tumor sample tissue, and the bladder cancer chemotherapy drug sensitivity data (PTC data), a machine learning algorithm is used to train multiple high-precision bladder cancer chemotherapy drug sensitivity prediction models, which can be used to accurately predict the sensitivity of bladder cancer chemotherapy drugs in combination with the hard voting method. The bladder cancer chemotherapy drug sensitivity prediction model constructed by the present invention has high prediction accuracy, with an average accuracy of more than 80%; the applicable population is more targeted, namely Chinese cancer patients; the prediction results are simple and clear, and are divided into bladder cancer chemotherapy drug response and bladder cancer chemotherapy drug resistance; the use cycle is short, starting from obtaining the tumor sample tissue of the bladder cancer patient, the prediction results can be obtained within 7 days (including sequencing, analysis, and prediction); the cost is low, and the main cost is the cost of second-generation sequencing, which is decreasing year by year. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0047] Figure 1 A schematic flow chart of a method for constructing a bladder cancer chemotherapy drug sensitivity prediction model provided by the present invention.

[0048] Figure 2 This is a schematic diagram of the structure of a bladder cancer chemotherapy drug sensitivity prediction system provided by the present invention.

[0049] Figure 3 This is a schematic structural diagram of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings in the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments, and they should not be understood as limitations on the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. In the description of the present invention, it should be understood that the terms used are only for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0051] Combine the following Figure 1-Figure 3The method for constructing a bladder cancer chemotherapy drug sensitivity prediction model provided by the present invention and its application are described. It should be noted that the execution subject of the method for constructing a bladder cancer chemotherapy drug sensitivity prediction model provided by the present invention and its application can be any network side device / terminal side device that meets the technical requirements, such as a bladder cancer chemotherapy drug sensitivity prediction device, etc.

[0052] Figure 1 It is a schematic flow chart of the method for constructing a bladder cancer chemotherapy drug sensitivity prediction model provided by the present invention.

[0053] Reference Figure 1 The present invention provides a method for constructing a bladder cancer chemotherapy drug sensitivity prediction model, which may include:

[0054] Step S110, constructing a training set, wherein the training set uses the data on the types of bladder cancer chemotherapy drugs used by the target population and the data on the immune cell infiltration levels of tumor sample tissues as sample data, and uses the bladder cancer chemotherapy drug sensitivity data of the target population as label data.

[0055] In this embodiment, step S110 may include:

[0056] S1101. Obtain whole transcriptome sequencing data of tumor sample tissues of a target population, data on the types of bladder cancer chemotherapy drugs used, and data on sensitivity of bladder cancer chemotherapy drugs, wherein the target population is a bladder cancer patient population, the bladder cancer chemotherapy drug sensitivity data include bladder cancer chemotherapy drug response data and bladder cancer chemotherapy drug resistance data, the data on the types of bladder cancer chemotherapy drugs used include any one of the following or any combination thereof: gemcitabine data, paclitaxel data, docetaxel data, and the bladder cancer chemotherapy drug sensitivity data is obtained by detecting tumor sample tissues of the target population based on a microtumor drug sensitivity detection method (PTC).

[0057] S1102. Obtain gene expression data of the tumor sample tissue of the target group based on the whole transcriptome sequencing data of the tumor sample tissue of the target group. Specifically, in this step, data quality control can be first performed on the whole transcriptome sequencing data of the tumor sample tissue of the target group to filter out reads whose base N content exceeds a preset content threshold and reads whose sequencing quality value is lower than a preset quality value threshold (e.g., 15), and then the whole transcriptome sequencing data after data quality control is compared with the reference genome data to obtain a bam file, and then the gene expression amount (TPM) is calculated based on the bam file to obtain the gene expression data of the tumor sample tissue of the target group.

[0058] S1103. Based on the gene expression data of the tumor sample tissue of the target population, multiple cell infiltration level assessment results are obtained by using multiple cell infiltration level assessment methods, and then the immune cell infiltration level data of the tumor sample tissue of the target population is obtained, wherein the multiple cell infiltration level assessment methods include: CIBERSORT, CIBERSORT-ABS, EPIC, MCPCOUNTER, QUANTISEQ, TIMER, and XCELL.

[0059] In this embodiment, the gene expression data (TPM) of the tumor sample tissue of the target group is used to evaluate the immune cell infiltration level of the tumor sample tissue of the target group by seven cell infiltration level evaluation methods, and seven immune cell infiltration level evaluation results of the tumor sample tissue of the target group are obtained. The seven immune cell infiltration level evaluation results are then merged to obtain the final immune cell infiltration level evaluation result of the tumor sample tissue of the target group as the immune cell infiltration level data of the tumor sample tissue of the target group.

[0060] S1104. Perform data cleaning on the training set according to preset cleaning rules, wherein the preset cleaning rules include any one of the following or any combination thereof:

[0061] For each piece of immune cell infiltration level data in the immune cell infiltration level data of the tumor sample tissue of the target population, when >60% of the immune cell infiltration level assessment results have a value of 0, the piece of immune cell infiltration level data is deleted (because one piece of immune cell infiltration level data includes seven immune cell infiltration level assessment results, that is, when >60% of the immune cell infiltration level assessment results have a value of 0 among the seven immune cell infiltration level assessment results, the piece of immune cell infiltration level data is deleted);

[0062] For the immune cell infiltration level data of tumor sample tissues of the target population obtained by multiple cell infiltration level assessment methods, when ≥80% of the values ​​in the immune cell infiltration level assessment results obtained by a certain cell infiltration level assessment method are all 0, the immune cell infiltration level assessment results obtained by this cell infiltration level assessment method are deleted (that is, for all immune cell infiltration level assessment results, if ≥80% of the values ​​in the immune cell infiltration level assessment results obtained by a certain cell infiltration level assessment method are all 0, the immune cell infiltration level assessment results of the tumor sample tissues obtained by this cell infiltration level assessment method are deleted);

[0063] When the data on the type of bladder cancer chemotherapy drugs administered represent the same bladder cancer chemotherapy drug, for the bladder cancer chemotherapy drug sensitivity data of the target population, if the bladder cancer chemotherapy drug sensitivity data indicate that the ratio of bladder cancer chemotherapy drug response to bladder cancer chemotherapy drug resistance is outside a preset ratio range, then some of the bladder cancer chemotherapy drug sensitivity data are randomly deleted until the ratio of bladder cancer chemotherapy drug response to bladder cancer chemotherapy drug resistance is within a preset range.

[0064] S1105. Construct a training set using the data on the types of bladder cancer chemotherapy drugs administered to the target population and the data on the immune cell infiltration levels of tumor sample tissues as sample data, and using the data on the sensitivity of bladder cancer chemotherapy drugs to the target population as label data.

[0065] Step S120: According to the training set, multiple candidate models are trained by multiple machine learning algorithms respectively. The multiple machine learning algorithms may include machine learning algorithms with classification tasks, such as decision tree, naive Bayes, logistic regression, K-nearest neighbor, support vector machine, random forest, adaptive boosting, gradient boosting tree algorithm, etc.

[0066] Step S130: Screen multiple candidate models according to preset model indicators to obtain at least two final candidate models as at least two bladder cancer chemotherapy drug sensitivity prediction models, wherein the preset model indicators include any one of the following items or any combination thereof: area under the ROC curve (AUC), F1 score, accuracy, and Matthews Correlation Coefficient (MCC).

[0067] In this embodiment, four final candidate models are obtained, which are candidate models trained by EasyEnsemble Classifier (an integrated classifier based on random undersampling), BalancedRandomForest Classifier (balanced random forest classifier), BalancedBagging Classifier (an integrated classifier based on Bagging technology), and RUSBoostClassifier (a classifier based on random undersampling) machine learning algorithms. In this embodiment, four bladder cancer chemotherapy drug sensitivity prediction models are obtained.

[0068] Among them, EasyEnsemble Classifier (an ensemble classifier based on random undersampling) performs multiple random sampling on the original data set to obtain multiple sub-data sets. For each sub-data set, a classifier is trained using an algorithm (decision tree, support vector machine, etc.). The prediction results of all classifiers are voted, and the one with the most votes is the classification result. It can effectively reduce the problem of overfitting and improve the generalization ability of the model.

[0069] BalancedRandomForest Classifier is similar to Random Forest in principle, but the difference is that the balance of subset samples is automatically considered during training, and the final result is obtained by voting or taking the average, so that the result of the overall model has higher accuracy and generalization performance. It has higher accuracy and generalization performance; it can process very high-dimensional data without dimensionality reduction; it can process not only discrete data but also continuous data without normalizing the data set; it has fast training speed and can get the importance ranking of variables.

[0070] BalancedBagging Classifier (an integrated classifier based on Bagging technology), also known as the bagging algorithm, uses a sampling method with replacement to generate training data. The initial training set is randomly sampled with replacement for multiple rounds, and multiple training sets are generated in parallel. Multiple base learners can be trained (there is no strong dependency between base learners), and then these base learners are combined to build a strong learner. The BalancedBaggingClassifier resamples each subset of the data set before each estimator in the training set, and the rest is the same as the Bagging algorithm. It increases the randomness of the samples, achieves the purpose of reducing variance, and solves the problem of overfitting.

[0071] RUSBoost Classifier (Random Undersampling Classifier) ​​is an ensemble learning method, the core idea of ​​which is to build a strong learning algorithm by combining weak learning algorithms. The boosting method trains multiple learning algorithms, and each model focuses on samples that the previous model did not handle well. RUSBoostClassifier is an ensemble algorithm that combines random undersampling and boosting methods, and is specifically designed to handle unbalanced data. During the learning process, the class balance problem is alleviated by randomly undersampling the samples in each iteration. It improves the accuracy of weak classification algorithms; the algorithm system has a high detection rate and is not prone to overfitting.

[0072] After the bladder cancer chemotherapy drug sensitivity prediction model is trained, it can be applied to the bladder cancer chemotherapy drug sensitivity prediction system, which can be used to obtain the subject's sensitivity prediction results to different bladder cancer chemotherapy drugs based on the subject's bladder cancer chemotherapy drug type data (there can be multiple types of bladder cancer chemotherapy drugs to be administered) and the immune cell infiltration level data of the tumor sample tissue, combined with the hard voting method, to assist in intuitively and accurately predicting the patient's drug sensitivity, guide personalized treatment of tumor patients, and improve the patient's cure rate.

[0073] The following two embodiments will describe the construction and application of a bladder cancer chemotherapy drug sensitivity prediction model.

[0074] Example 1: Construction of a prediction model for sensitivity of bladder cancer chemotherapy drugs

[0075] Example 1 For the tumor tissue samples of 935 bladder cancer patients (target group) participating in the modeling, the operation steps include:

[0076] 1. Use Illumina's NovaSeq X Plus platform to perform LncRNA (whole transcriptome) sequencing, with a sequencing data volume of 30G for each sample, to obtain the whole transcriptome sequencing data of tumor sample tissues of the target population.

[0077] 2. Bioinformatics analysis of sequencing samples: Fastp (v 0.23.2) was used to perform data quality control on the whole transcriptome sequencing data of tumor sample tissues of the target population to generate cleandata (whole transcriptome sequencing data after data quality control). STAR software (v 2.7.10a) was used to compare the cleandata data with the reference genome data (GRCh38) to obtain a bam file.

[0078] 3. Use RSEM (v 1.3.3) to calculate the gene expression through the generated bam file to obtain the TPM value, that is, to obtain the gene expression data of the tumor sample tissue of the target group.

[0079] 4. Use the gene expression data of the tumor sample tissue of the target group and seven cell infiltration level assessment methods (CIBERSORT, CIBERSORT-ABS, EPIC, MCPCOUNTER, QUANTISEQ, TIMER, XCELL) to assess the immune cell infiltration level of the tumor sample tissue of the target group, and obtain the immune cell infiltration level data of the tumor sample tissue of the target group.

[0080] 5. The PTC drug sensitivity reactions of bladder cancer patients were classified into two categories: bladder cancer chemotherapy drug response (represented by 0) and bladder cancer chemotherapy drug resistance (represented by 1).

[0081] 6. Integrated data set, the data columns include: bladder cancer patient number, bladder cancer chemotherapy drug type number that has been administered, immune cell infiltration level of tumor sample tissue evaluated by different methods, and bladder cancer chemotherapy drug sensitivity classification.

[0082] 7. By dividing the data set into 70% training set and 30% test set, 10-fold cross validation, and using AUC and F1_score indicators, four final candidate models were selected as four bladder cancer chemotherapy drug sensitivity prediction models; during the sampling process, the SMOTEENN method was used to solve the problem of classification (response / resistance) imbalance.

[0083] The optimal key parameters of the model set when training the four final candidate models in Example 1 are shown in Table 1.

[0084] Table 1 Optimal key parameter settings for the model

[0085]

[0086] The training results of the final candidate model in Example 1 are shown in Table 2.

[0087] Table 2 Model training results

[0088] Model Name AUC (%) F1-score Accuracy(%) MCC EasyEnsembleClassifier 87.7 0.81 90.3 0.81 BalancedRandomForestClassifier 85.9 0.76 88 0.74 BalancedBaggingClassifier 85 0.71 87 0.71 RUSBoostClassifier 84.2 0.73 86.5 0.71

[0089] After determining the optimal key parameters of the model, Example 1 uses the test set to verify the generalization ability of each final candidate model. The model test accuracy is shown in Table 3.

[0090] Table 3 Model test accuracy

[0091]

[0092]

[0093] Example 2: The bladder cancer chemotherapy drug sensitivity prediction model constructed in Example 1 was used to predict the drug sensitivity of 251 bladder cancer patients to bladder cancer chemotherapy drugs (gemcitabine, paclitaxel, and docetaxel).

[0094] The specific steps include:

[0095] 1. Obtain LncRNA sequencing data (i.e., whole transcriptome sequencing data) of tumor sample tissues from 251 bladder cancer patients. The sample sequencing volume is guaranteed to be at least 30G. All 251 bladder cancer patients are on a single medication, including: 62 patients with clinical drug response data, and drug response types are divided according to tag classification; 189 patients have drug sensitivity values ​​measured by PTC, and drug response types are divided according to drug sensitivity data.

[0096] 2. Perform bioinformatics analysis on the whole transcriptome sequencing data in 1, including data quality control, comparison with reference genome data, and quantitative gene expression.

[0097] 3. Using the gene expression data of tumor sample tissues from 251 bladder cancer patients, seven methods (CIBERSORT, CIBERSORT-ABS, EPIC, MCPCOUNTER, QUANTISEQ, TIMER, and XCELL) were used to evaluate the immune cell infiltration level of tumor sample tissues.

[0098] 4. Generate model input data d1, where the column names include the bladder cancer patient number, the type number of bladder cancer chemotherapy drugs to be administered, and the immune cell infiltration level of tumor sample tissue evaluated by different methods.

[0099] 5. The model input data d1 is input into the four bladder cancer chemotherapy drug sensitivity prediction models constructed in Example 1, and combined with the hard voting method (the bladder cancer chemotherapy drug sensitivity prediction results of the four bladder cancer chemotherapy drug sensitivity prediction models are integrated, and the voting results of the majority of categories are the final results. If there is a tie, the result of the model with the highest corresponding drug prediction accuracy in the test data is selected as the final result), and the bladder cancer chemotherapy drug sensitivity prediction results of 251 bladder cancer patients are obtained.

[0100] 6. The predicted results of bladder cancer chemotherapy drug sensitivity of 251 bladder cancer patients were compared with their actual drug response types. The comparison results of clinical samples and PTC samples are shown in Table 4 and Table 5 respectively:

[0101] Table 4 Comparison of consistency of clinical samples

[0102] Gemcitabine Paclitaxel Docetaxel answer(%) 86.7 84.9 85 Drug resistance (%) 86 86 84.1 Average accuracy (%) 86.35 85.45 84.55

[0103] Table 5 PTC sample consistency comparison

[0104] Gemcitabine Paclitaxel Docetaxel answer(%) 87.5 85 84 Drug resistance (%) 88.4 82.5 87 Average accuracy (%) 87.95 83.75 85.5

[0105] The accuracy of the prediction model for the sensitivity of bladder cancer chemotherapy drugs was tested by clinical data and PTC drug sensitivity data for a total of 251 cases. After comparison, the prediction effect of bladder cancer chemotherapy drug sensitivity (gemcitabine, paclitaxel, docetaxel) was better. Among them, in clinical samples, the accuracy of gemcitabine was 86.35%, the accuracy of paclitaxel was 85.45%, and the accuracy of docetaxel was 84.55%; in patients undergoing PTC testing, the accuracy of gemcitabine was 87.95%, the accuracy of paclitaxel was 83.75%, and the accuracy of docetaxel was 85.5%.

[0106] The method for constructing a bladder cancer chemotherapy drug sensitivity prediction model and its application provided by the present invention have at least the following beneficial effects:

[0107] (1) High accuracy;

[0108] From the results in Table 4 and Table 5, it can be seen that the prediction accuracy of the bladder cancer chemotherapy drug sensitivity prediction model constructed by the present invention is very high (>80%), whether it is consistent with clinical medication data or drug sensitivity data obtained by PTC.

[0109] (2) Short cycle, more economical and efficient;

[0110] Starting from obtaining the tumor sample tissue from bladder cancer patients, the prediction results can be obtained within 7 days (including sequencing, analysis, and prediction), while it takes 2 weeks to obtain drug sensitivity data through PTC; as the sequencing cost decreases year by year, the cost of drug sensitivity testing based on gene expression data for patients will also decrease year by year.

[0111] (3) The modeling data used is clinical data specifically for Chinese people, which is ethnically specific and has high clinical effect consistency.

[0112] (4) The prediction results are simple and clear, divided into two types: response and resistance, which can be used as an auxiliary guidance for medication.

[0113] The following is a description of the system for predicting the sensitivity of bladder cancer chemotherapy drugs provided by the present invention. The system for predicting the sensitivity of bladder cancer chemotherapy drugs described below and the method for predicting the sensitivity of bladder cancer chemotherapy drugs described above can be referenced to each other.

[0114] Reference Figure 2 The present invention provides a bladder cancer chemotherapy drug sensitivity prediction system, which may include:

[0115] The data receiving module is used to: receive data on the type of bladder cancer chemotherapy drugs to be administered to a subject and data on the immune cell infiltration level of a tumor sample tissue sent by at least one client, wherein the subject to be tested is a bladder cancer patient;

[0116] A prediction module, for: obtaining a prediction result of the bladder cancer chemotherapy drug sensitivity of the subject according to the data of the type of bladder cancer chemotherapy drug to be administered to the subject and the data of the immune cell infiltration level of the tumor sample tissue, using at least two bladder cancer chemotherapy drug sensitivity prediction models obtained by any of the above-mentioned methods for constructing a bladder cancer chemotherapy drug sensitivity prediction model, and combining with a hard voting method;

[0117] The data sending module is used to send the predicted result of the bladder cancer chemotherapy drug sensitivity of the subject to be tested back to at least one client.

[0118] In one embodiment, the prediction module includes:

[0119] The prediction submodule is used to obtain at least two bladder cancer chemotherapy drug sensitivity prediction results for the subject according to the data on the type of bladder cancer chemotherapy drugs to be administered to the subject and the data on the immune cell infiltration level of the tumor sample tissue, respectively, by using at least two bladder cancer chemotherapy drug sensitivity prediction models obtained by any of the above-mentioned methods for constructing a bladder cancer chemotherapy drug sensitivity prediction model;

[0120] The determination submodule is used to obtain the final bladder cancer chemotherapy drug sensitivity prediction result of the subject according to at least two bladder cancer chemotherapy drug sensitivity prediction results of the subject in combination with a hard voting method, wherein the hard voting method is: when there is a unique bladder cancer chemotherapy drug sensitivity prediction result with the most votes among the at least two bladder cancer chemotherapy drug sensitivity prediction results of the subject, the unique bladder cancer chemotherapy drug sensitivity prediction result with the most votes is used as the final bladder cancer chemotherapy drug sensitivity prediction result of the subject; when there is no unique bladder cancer chemotherapy drug sensitivity prediction result with the most votes among the at least two bladder cancer chemotherapy drug sensitivity prediction results of the subject, when the bladder cancer chemotherapy drug sensitivity prediction model is trained by the construction method of the bladder cancer chemotherapy drug sensitivity prediction model described in any of the above items, the bladder cancer chemotherapy drug sensitivity prediction result of the bladder cancer chemotherapy drug sensitivity prediction model with the highest bladder cancer chemotherapy drug sensitivity prediction accuracy corresponding to the bladder cancer chemotherapy drug type is used as the final bladder cancer chemotherapy drug sensitivity prediction result of the subject.

[0121] Figure 3 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 3 As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication interface 820 and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to perform the following steps:

[0122] receiving data on the type of chemotherapy drugs to be administered to a subject for bladder cancer and data on the level of immune cell infiltration in tumor sample tissue sent by at least one client, wherein the subject to be tested is a bladder cancer patient;

[0123] According to the data of the type of bladder cancer chemotherapy drugs to be administered to the subject and the data of the immune cell infiltration level of the tumor sample tissue, at least two bladder cancer chemotherapy drug sensitivity prediction models obtained by any of the above-mentioned methods for constructing a bladder cancer chemotherapy drug sensitivity prediction model are combined with a hard voting method to obtain a bladder cancer chemotherapy drug sensitivity prediction result for the subject;

[0124] The predicted result of the bladder cancer chemotherapy drug sensitivity of the subject is sent back to at least one client.

[0125] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0126] On the other hand, the present invention further provides a computer program product, the computer program product comprising a computer program, the computer program can be stored on a non-transitory computer readable storage medium, and when the computer program is executed by a processor, the computer can perform the following steps:

[0127] receiving data on the type of chemotherapy drugs to be administered to a subject for bladder cancer and data on the level of immune cell infiltration in tumor sample tissue sent by at least one client, wherein the subject to be tested is a bladder cancer patient;

[0128] According to the data of the type of bladder cancer chemotherapy drugs to be administered to the subject and the data of the immune cell infiltration level of the tumor sample tissue, at least two bladder cancer chemotherapy drug sensitivity prediction models obtained by any of the above-mentioned methods for constructing a bladder cancer chemotherapy drug sensitivity prediction model are combined with a hard voting method to obtain a bladder cancer chemotherapy drug sensitivity prediction result for the subject;

[0129] The predicted result of the bladder cancer chemotherapy drug sensitivity of the subject is sent back to at least one client.

[0130] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented to perform the following steps when executed by a processor:

[0131] receiving data on the type of chemotherapy drugs to be administered to a subject for bladder cancer and data on the level of immune cell infiltration in tumor sample tissue sent by at least one client, wherein the subject to be tested is a bladder cancer patient;

[0132] According to the data of the type of bladder cancer chemotherapy drugs to be administered to the subject and the data of the immune cell infiltration level of the tumor sample tissue, at least two bladder cancer chemotherapy drug sensitivity prediction models obtained by any of the above-mentioned methods for constructing a bladder cancer chemotherapy drug sensitivity prediction model are combined with a hard voting method to obtain a bladder cancer chemotherapy drug sensitivity prediction result for the subject;

[0133] The predicted result of the bladder cancer chemotherapy drug sensitivity of the subject is sent back to at least one client.

[0134] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0135] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0136] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for constructing a training set, comprising: Obtaining whole transcriptome sequencing data of tumor sample tissues of the target population, data on the types of bladder cancer chemotherapy drugs administered, and data on sensitivity of bladder cancer chemotherapy drugs, wherein the target population is a bladder cancer patient population, and the bladder cancer chemotherapy drug sensitivity data includes bladder cancer chemotherapy drug response data and bladder cancer chemotherapy drug resistance data; Obtaining gene expression data of the tumor sample tissue of the target group based on the whole transcriptome sequencing data of the tumor sample tissue of the target group; According to the gene expression data of the tumor sample tissue of the target group, the immune cell infiltration level data of the tumor sample tissue of the target group is obtained; The training set is constructed using the data on the types of bladder cancer chemotherapy drugs administered to the target population and the data on the immune cell infiltration levels of tumor sample tissues as sample data, and the data on the sensitivity of bladder cancer chemotherapy drugs to the target population as label data.

2. The method for constructing a training set according to claim 1, characterized in that: The method of obtaining gene expression data of tumor sample tissues of the target population based on the whole transcriptome sequencing data of tumor sample tissues of the target population includes: Obtain reference genome data; Perform data quality control on the whole transcriptome sequencing data of tumor sample tissues of the target population; Compare the whole transcriptome sequencing data after data quality control with the reference genome data to obtain a bam file; The gene expression levels were calculated based on the bam file to obtain the gene expression data of the tumor sample tissues of the target group.

3. The method for constructing a training set according to claim 2, characterized in that: The data quality control of the whole transcriptome sequencing data of the tumor sample tissue of the target population includes: According to the preset data quality control conditions, the whole transcriptome sequencing data of the tumor sample tissue of the target population is subjected to data quality control, wherein the preset data quality control conditions include: Filter out reads whose base N content exceeds the preset content threshold; Filter out reads whose sequencing quality values ​​are lower than the preset quality value threshold.

4. The method for constructing a training set according to claim 3, characterized in that: The step of obtaining the immune cell infiltration level data of the tumor sample tissue of the target group based on the gene expression data of the tumor sample tissue of the target group includes: According to the gene expression data of the tumor sample tissue of the target population, multiple cell infiltration level assessment results are obtained by using multiple cell infiltration level assessment methods, and then the immune cell infiltration level data of the tumor sample tissue of the target population is obtained, wherein the multiple cell infiltration level assessment methods include any one of the following or any combination thereof: CIBERSORT, CIBERSORT-ABS, EPIC, MCPCOUNTER, QUANTISEQ, TIMER, XCELL.

5. The method for constructing a training set according to claim 4, characterized in that: Also includes: The training set is cleaned according to the preset cleaning rules, wherein the preset cleaning rules include any one of the following or any combination thereof: For each piece of immune cell infiltration level data in the immune cell infiltration level data of the tumor sample tissue of the target population, when the value of the immune cell infiltration level evaluation result of >60% is 0, the immune cell infiltration level data is deleted; For the immune cell infiltration level data of tumor sample tissues of the target population obtained by multiple cell infiltration level assessment methods, when ≥80% of the values ​​of the immune cell infiltration level assessment results obtained by a certain cell infiltration level assessment method are all 0, the immune cell infiltration level assessment results obtained by this cell infiltration level assessment method are deleted; When the data on the type of bladder cancer chemotherapy drugs administered represent the same bladder cancer chemotherapy drug, for the bladder cancer chemotherapy drug sensitivity data of the target population, if the bladder cancer chemotherapy drug sensitivity data indicate that the ratio of bladder cancer chemotherapy drug response to bladder cancer chemotherapy drug resistance is outside a preset ratio range, then some of the bladder cancer chemotherapy drug sensitivity data are randomly deleted until the ratio of bladder cancer chemotherapy drug response to bladder cancer chemotherapy drug resistance is within a preset range.

6. A method for constructing a prediction model for bladder cancer chemotherapy drug sensitivity, characterized in that: include: Obtain a training set obtained by the method for constructing a training set according to any one of claims 1 to 5; According to the training set, multiple candidate models are trained through multiple machine learning algorithms; According to preset model indicators, multiple candidate models are screened to obtain at least two final candidate models as at least two bladder cancer chemotherapy drug sensitivity prediction models.

7. The method for constructing a prediction model for bladder cancer chemotherapy drug sensitivity according to claim 6, characterized in that: The at least two final candidate models include four final candidate models, wherein the four final candidate models are candidate models trained by EasyEnsembleClassifier, BalancedRandomForestClassifier, BalancedBaggingClassifier, and RUSBoostClassifier learning algorithms according to the training set.

8. A bladder cancer chemotherapy drug sensitivity prediction system, characterized in that: include: The data receiving module is used to: receive data on the type of bladder cancer chemotherapy drugs to be administered to a subject and data on the immune cell infiltration level of a tumor sample tissue sent by at least one client, wherein the subject to be tested is a bladder cancer patient; A prediction module, used to: obtain a prediction result of the bladder cancer chemotherapy drug sensitivity of the subject according to the data of the type of bladder cancer chemotherapy drug to be administered to the subject and the immune cell infiltration level data of the tumor sample tissue, using at least two bladder cancer chemotherapy drug sensitivity prediction models obtained by the method for constructing a bladder cancer chemotherapy drug sensitivity prediction model according to claim 6 or 7, combined with a hard voting method; The data sending module is used to send the predicted result of the bladder cancer chemotherapy drug sensitivity of the subject to be tested back to at least one client.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: The processor performs the following steps: receiving data on the type of chemotherapy drugs to be administered to a subject for bladder cancer and data on the level of immune cell infiltration in tumor sample tissue sent by at least one client, wherein the subject to be tested is a bladder cancer patient; According to the data of the type of bladder cancer chemotherapy drugs to be administered to the subject and the data of the immune cell infiltration level of the tumor sample tissue, at least two bladder cancer chemotherapy drug sensitivity prediction models obtained by the method for constructing a bladder cancer chemotherapy drug sensitivity prediction model according to claim 6 or 7 are combined with a hard voting method to obtain a bladder cancer chemotherapy drug sensitivity prediction result for the subject; The predicted result of the bladder cancer chemotherapy drug sensitivity of the subject is sent back to at least one client.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: The computer program is executed by the processor to perform the following steps: receiving data on the type of chemotherapy drugs to be administered to a subject for bladder cancer and data on the level of immune cell infiltration in tumor sample tissue sent by at least one client, wherein the subject to be tested is a bladder cancer patient; According to the data of the type of bladder cancer chemotherapy drugs to be administered to the subject and the data of the immune cell infiltration level of the tumor sample tissue, at least two bladder cancer chemotherapy drug sensitivity prediction models obtained by the method for constructing a bladder cancer chemotherapy drug sensitivity prediction model according to claim 6 or 7 are combined with a hard voting method to obtain a bladder cancer chemotherapy drug sensitivity prediction result for the subject; The predicted result of the bladder cancer chemotherapy drug sensitivity of the subject is sent back to at least one client.

Images