Comprehensive analysis platform for tumor marker detection data

Abstract

The invention belongs to the technical field of biomedicine, and discloses a comprehensive analysis platform for tumor marker detection data. Comprising a data collection module used for collecting marker detection data of candidate markers; the data coding module is used for coding the marker detection data to obtain marker coding data; the model construction module is used for constructing a tumor prognosis model according to the marker coding data; the potential evaluation module is used for evaluating the potential of the marker according to the marker coding data and the tumor prognosis model; the marker determination module is used for determining whether the candidate marker can be used as a tumor marker or not according to the potential of the marker, and if yes, quantitative calculation of clinical practicability is carried out; the detection and verification efficiency of the tumor marker is improved, important support is provided for personalized medicine and precise treatment, and the prognosis evaluation and treatment effect of a patient can be remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of biomedical technology, and more specifically, to a comprehensive analysis platform for tumor marker detection data. Background Art

[0002] With the advancement of medical technology, the detection of tumor markers has become an important means for early diagnosis, prognosis assessment and treatment monitoring of tumors. Tumor markers refer to biomarkers in tumor cells or patients, and their changes can reflect the existence, development and treatment response of tumors. Traditional detection methods often rely on a single marker. However, the complexity and heterogeneity of tumors make the detection effect of a single marker limited. In recent years, with the development of multi-omics technologies such as genomics, transcriptomics and proteomics, researchers have gradually realized the importance of combining multiple tumor markers for comprehensive analysis. Therefore, how to effectively identify more tumor markers has become the key to promoting personalized medicine and precision treatment.

[0003] The patent application with publication number CN118186086A discloses a comprehensive analysis device for head and neck tumor marker detection data; it includes a data acquisition module, which uses high-throughput sequencing technology to obtain gene expression data, and combines mass spectrometry or immunoassay to obtain serum marker data; a data preprocessing module, which screens out genes and markers related to head and neck tumors; a feature extraction module, which extracts biological process and pathway information related to head and neck tumors, and obtains protein markers; a model training module, which uses machine learning methods to establish a head and neck tumor marker data analysis model; a result analysis module, which uses biostatistics methods to verify and evaluate the model output; this invention can efficiently and accurately analyze patients' head and neck tumor marker detection data and provide valuable clinical information.

[0004] However, although the above-mentioned technology can realize the comprehensive analysis of tumor marker detection data, it can only perform comprehensive analysis of existing tumor markers and cannot identify new tumor markers; this leads to deviations in diagnostic results and inability to comprehensively assess the tumor status, thus resulting in insufficient prognosis assessment and poor treatment effects, and at the same time missing the opportunity to discover new therapeutic targets.

[0005] In view of this, the present invention proposes a comprehensive analysis platform for tumor marker detection data to solve the above problems. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solution: a comprehensive analysis platform for tumor marker detection data, comprising: A data collection module, used to collect marker detection data of candidate markers; A data encoding module, used to encode the marker detection data and obtain the marker encoding data; A model building module is used to build a tumor prognosis model based on marker coding data; A potential assessment module, used to assess the potential of a marker based on marker coding data and a tumor prognosis model; The marker determination module is used to determine whether the candidate marker can be used as a tumor marker based on the marker potential, and if so, to perform quantitative calculations of clinical practicality.

[0007] Furthermore, the marker detection data includes single nucleotide polymorphism detection data, clinical detection data, protein expression data, pathological detection data and postoperative follow-up data; the clinical detection data includes laboratory detection data and intraoperative tumor data; the pathological detection data includes cytological data and histological data; the postoperative follow-up data includes the patient's survival and recurrence; the survival status includes overall survival and disease-free survival; The method for obtaining marker coding data comprises: The single nucleotide polymorphism detection data, clinical detection data, protein expression data and pathological detection data in the marker detection data are used as analysis detection data; the data that is not a numerical value in the analysis detection data is marked as data to be encoded; the number of each different data in the data to be encoded is counted and marked as the data number; the number of data of each different data in the data to be encoded is used as the corresponding data frequency; all data frequencies are compared in turn, and the data to be encoded whose data frequency is different from all other data frequencies is marked as direct data, and the data to be encoded with the same data frequency is marked as combined data; the data frequency of the direct data is used as the corresponding data code; the data corresponding to the same group of analysis detection data in the combined data is divided into a combined set, and the combined set corresponds to the analysis detection data one by one; the data frequency corresponding to each data in each combined set is merged as the set code corresponding to the corresponding combined set; In the group marker detection data, each combined set is replaced by the corresponding set code, each direct data is replaced by the corresponding data code, and the replaced marker detection data is marked as marker code data.

[0008] Furthermore, the step of constructing a tumor prognosis model includes: Step S101: Using a search optimization algorithm to set the number of training samples ; Step S102: Random selection The group marker encoding data is used as training samples; Step S103: constructing a tumor prognosis model according to the training samples, where the tumor prognosis model is a random forest regression model; In step S101, the number of training samples is set The steps include: Step S201: Setting the search range And search accuracy ; Step S202: Determine the search sequence ; Step S203: From the search sequence Determine the partition coefficient ; Step S204: Based on the division coefficient Divide the search interval and obtain the division points and ; Step S205: Calculate the division points respectively and The corresponding training accuracy; Step S206: updating the search interval according to the training accuracy; Step S207: Calculate the search interval width ; Step S208: Set the interval width With search precision For comparison, if ,but ,like , then jump back to step S203.

[0009] Furthermore, in step S202, the search sequence ; In step S203, from the search sequence Determine the partition coefficient The methods include: Calculate the initial partition coefficient based on the search interval ; Search the sequence Subtract the initial partition coefficient from each value in to obtain the coefficient difference; sort each coefficient difference from small to large, mark the coefficient difference at the front as the most recent difference; and search the corresponding sequence of the most recent difference. The value in is used as the partition coefficient ; Initial partition coefficient The expression is: ; In the formula, is the maximum value of the search interval, is the minimum value of the search interval; In step S204, the division point ; In the formula, To search for the partition coefficient in the sequence The value of the first two digits; Divide point ; In the formula, To search for the partition coefficient in the sequence The value of the previous digit.

[0010] Furthermore, in step S205, the division points are calculated and The corresponding training accuracy methods include: The number of different types of data in the marker detection data is counted and marked as the number of types; the number of groups of the marker detection data is obtained and marked as the number of data groups; the number of types, the number of data groups and the numerical values ​​of the dividing points are used as analysis data, and the analysis data is input into the trained accuracy assessment model to evaluate the corresponding training accuracy; the training process of the accuracy assessment model includes: Pre-collection Group analysis data, The corresponding training precision is set for each group of analysis data. is an integer greater than 1, converting the analysis data and the corresponding training accuracy into a corresponding set of feature vectors; taking each set of feature vectors as the input of the accuracy assessment model, the accuracy assessment model takes a set of predicted training accuracy corresponding to each set of analysis data as the output, and takes the actual training accuracy corresponding to each set of analysis data as the prediction target, and the actual training accuracy is the pre-set training accuracy corresponding to the analysis data; minimizing the sum of the prediction errors of all analysis data is taken as the training target; training the accuracy assessment model until the sum of the prediction errors reaches convergence and the training is stopped; the accuracy assessment model is a deep neural network model; In step S206, the method for updating the search interval according to the training accuracy includes: Divide the points The corresponding training accuracy is marked as the first accuracy , divide the points The corresponding training accuracy is marked as the second accuracy ; Set the first precision and second precision For comparison; if , then update the minimum value of the search interval to , the maximum value is not updated; if , then update the maximum value of the search interval to , the minimum value is not updated; In step S207, the width of the search interval is calculated. The method is: subtract the corresponding minimum value from the maximum value of the search interval to obtain the interval width of the search interval .

[0011] Furthermore, in step S103, the method of constructing a tumor prognosis model according to training samples includes: Initialize the model parameters, including the maximum depth of the decision tree and the minimum number of samples of the internal nodes; delete the postoperative follow-up data in each group of training samples and mark them as training data; set different digital labels for different groups of postoperative follow-up data and mark them as postoperative labels; Sampling from the training data tree subsets, each tree subset includes Group training data, where , ;according to Each subset of trees is trained separately decision trees, where the training process of each decision tree is independent and the same, and finally a decision tree containing A random forest regression model with 1 decision tree; Input each set of training data into each decision tree in turn, record the decision output, which is the postoperative label output by each decision tree and marked as the predicted label; calculate the mean of the predicted labels corresponding to the same training data and use it as the predicted value; calculate the mean square error between each predicted value and the true value and use it as the loss function value, where the true value is the postoperative label corresponding to the training data input into the decision tree; use random search method or Bayesian optimization method to tune the model hyperparameters, and select the model hyperparameters with the smallest loss function value as the model hyperparameters of the tumor prognosis model.

[0012] Further, the method of training a decision tree using a tree subset includes: Subset a tree Divide the training data into training sets and validation set , the training set The training data in is labeled , , For the training set The number of groups of training data in; using features represents the data in the training data, , is the number of different types of data in the training data; calculate each feature Information gain rate ; Select the maximum information gain rate The corresponding features As an internal node, and according to the maximum information gain rate The corresponding features The training set Divide into decision subsets; for each according to the maximum information gain rate The algorithm recursive process is repeated for the divided decision subsets until the number of training data in the decision subset is less than or equal to the minimum number of samples in the internal node, or the number of recursions is greater than or equal to the maximum depth of the decision tree, and the recursion ends; the trained decision tree model is used as the validation set. Perform evaluation and finally complete the training of the decision tree.

[0013] Furthermore, the information gain rate The expression is: ; In the formula, For the training set According to the characteristics The decision subsets divided into , is the number of decision subsets, for The information entropy of For the training set Information entropy of The expression is: ; The expression is: ; In the formula, Represents a decision subset Middle The postoperative labels corresponding to the group training data.

[0014] Furthermore, the method for evaluating the potential of a marker comprises: The marker coding data that is not marked as training samples is used as evaluation samples, and the postoperative follow-up data in the evaluation samples is marked as real data; the postoperative follow-up data in each evaluation sample is deleted and marked as evaluation data; each group of evaluation data is input into the trained tumor prognosis model to predict the corresponding postoperative label; according to the predicted postoperative label, the corresponding postoperative follow-up data is obtained and marked as predicted data; each real data and the corresponding predicted data are used as a set of analysis sets, and the analysis sets correspond to the real data one by one; each value in each real data is subtracted from the corresponding value in the corresponding predicted data, and the absolute value is taken to obtain the numerical difference; A weight set is preset, and the weight set includes a weight coefficient corresponding to each data in the postoperative follow-up data; each numerical difference is multiplied by the corresponding weight coefficient to obtain a weight difference; the weight differences corresponding to each group of analysis sets are added in turn to obtain a total numerical difference; the number of statistical analysis sets is analyzed and marked as the number of sets; each total numerical difference is added in turn, and then divided by the number of sets to obtain a total difference mean, and the reciprocal of the total difference mean is used as the marker potential.

[0015] Furthermore, the method for determining whether a candidate marker can be used as a tumor marker comprises: A potential threshold is preset, and the potential of the marker is compared with the potential threshold; if the potential of the marker is greater than or equal to the potential threshold, the candidate marker is determined to be a tumor marker; if the potential of the marker is less than the potential threshold, the candidate marker is determined not to be a tumor marker; The method for quantitative calculation of clinical practicality includes: calculate The protein expression data in the group marker detection data is correlated with each data in the postoperative follow-up data; each correlation is multiplied by the corresponding weight coefficient to obtain the weight correlation degree; the absolute value of each weight correlation degree is taken and added in sequence to obtain the clinical practicality corresponding to the candidate marker; The expression of correlation is: ; In the formula, For relevance, For the Protein expression data in group marker detection data, For the A data within the postoperative follow-up data in the group marker detection data.

[0016] Technical effects and advantages of a comprehensive analysis platform for tumor marker detection data of the present invention: By comprehensively analyzing multiple omics data such as genome, transcriptome, proteome, clinical pathology data, and postoperative follow-up data, and using optimized machine learning algorithms to build tumor prognosis models, it is possible to accurately predict patients' survival and recurrence risk, accurately evaluate the potential of markers, and effectively identify new potential tumor markers, promote the discovery of new therapeutic targets, and further promote early diagnosis and personalized treatment. At the same time, correlation algorithms are used to objectively quantify the clinical value of candidate markers, providing a basis for selecting the most appropriate tumor markers for clinical applications. This not only improves the detection and verification efficiency of tumor markers, but also provides important support for personalized medicine and precision treatment, and can significantly improve patients' prognosis evaluation and treatment effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a schematic diagram of a comprehensive analysis platform for tumor marker detection data according to Example 1 of the present invention; Figure 2 This is a flow chart of the method for constructing a tumor prognosis model in Example 1 of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] Example 1 See also Figure 1 As shown, the comprehensive analysis platform for tumor marker detection data described in this embodiment includes a data collection module, a data encoding module, a model building module, a potential assessment module and a marker determination module; each module is connected by wired and / or wireless means to achieve data transmission between modules.

[0020] The data collection module is used to collect marker detection data of candidate markers.

[0021] Candidate markers are biomarkers that have been identified as potentially tumor-related in research but have not yet been confirmed for clinical application, such as HLA-DRA, HLA-DRB1, etc.; marker detection data include single nucleotide polymorphism detection data, clinical detection data, protein expression data, pathological detection data, and postoperative follow-up data; marker detection data are collected in total Group, is an integer greater than 1.

[0022] Single nucleotide polymorphism detection data provides genetic variation information of gene loci, such as single nucleotide polymorphism identifiers, single nucleotide polymorphism positions, allele information, etc., which are obtained through whole genome sequencing or high-throughput SNP chip technology; single nucleotide polymorphism detection data are used to identify genetic variations that affect tumor susceptibility or tumor progression, and help screen tumor-related biomarkers.

[0023] Clinical test data include laboratory test data and intraoperative tumor data; laboratory test data include blood test data (such as blood cell count, biochemical indicators, etc.), imaging test data, etc.; imaging test data include CT scan data (such as tumor size, tumor shape, etc.), MRI data (such as tumor boundaries and infiltration conditions), ultrasound examination data (such as tumor echo characteristics, blood flow dynamics, etc.); laboratory test data are obtained through the hospital laboratory; intraoperative tumor data such as tumor location, tumor size, tumor stage, etc. are obtained through doctor observation during tumor surgery; clinical test data are used to comprehensively analyze tumor characteristics and provide an important basis for the subsequent clinical verification of candidate markers.

[0024] Protein expression data is the protein expression level of the candidate marker, obtained by immunohistochemistry or Western blotting; protein expression data is used to verify whether it is upregulated or downregulated in tumor tissue and to further understand the role of the candidate marker in tumor development.

[0025] Pathological detection data include cytological data and histological data; cytological data such as cell size and cell shape are obtained through flow cytometry or microscopic imaging; histological data such as tumor type, tumor grade, tumor stage, etc. are obtained through tissue sections or immunohistochemistry; pathological detection data are used to evaluate the expression of candidate markers in tumor tissues and help verify their potential as tumor markers.

[0026] Postoperative follow-up data include the patient's survival and recurrence, which are obtained through telephone interviews or outpatient follow-up; survival status includes overall survival and disease-free survival. Overall survival is the time span from the start of treatment to death, and disease-free survival is the time span from the start of treatment to the first progression of the disease (such as tumor enlargement or the emergence of new diseases); recurrence is the time span from the reappearance of the tumor after treatment; postoperative follow-up data are used to judge the effectiveness of tumor treatment and the long-term survival rate of patients, and to verify the correlation between candidate markers and patient prognosis. For example, some markers may be closely related to the patient's survival and recurrence rate.

[0027] The data encoding module is used to encode the marker detection data and obtain the marker encoding data.

[0028] Methods for obtaining marker encoding data include: The single nucleotide polymorphism detection data, clinical detection data, protein expression data and pathological detection data in the marker detection data are used as analysis detection data; the data that is not a numerical value in the analysis detection data is marked as data to be encoded; the number corresponding to each different data in the data to be encoded is counted and marked as the data number; for example, the number corresponding to a circular tumor shape, the number corresponding to a multi-knot tumor shape, etc.; the data number of each different data in the data to be encoded is used as the corresponding data frequency; all data frequencies are compared in turn, and the data to be encoded whose data frequency is different from all other data frequencies is marked as direct data, and the data to be encoded with the same data frequency is marked as combined data; the data frequency of the direct data is used as the corresponding data code; the data corresponding to the same group of analysis detection data in the combined data is divided into a combined set, and the combined set corresponds to the analysis detection data one by one; the data frequency corresponding to each data in each combined set is merged as the set code corresponding to the corresponding combined set; In the group marker detection data, each combined set is replaced by the corresponding set code, each direct data is replaced by the corresponding data code, and the replaced marker detection data is marked as marker code data.

[0029] Exemplarily, there are a combination set A and a combination set B, the combination set A includes tumor shape A and single nucleotide polymorphism position B, and the combination set B includes tumor shape B, tumor type C and tumor grade D; the data frequency corresponding to tumor shape A and tumor shape B is 10, and the data frequency corresponding to single nucleotide polymorphism position B, tumor type C and tumor grade D is 20; therefore, the set code corresponding to the combination set A is 1020, and the set code corresponding to the combination set B is 102020.

[0030] The model building module is used to build a tumor prognosis model based on marker encoding data.

[0031] like Figure 2 As shown, the steps of constructing a tumor prognosis model include: Step S101: Using a search optimization algorithm to set the number of training samples ; Step S102: Random selection The group marker encoding data is used as training samples; Step S103: constructing a tumor prognosis model according to the training samples, where the tumor prognosis model is a random forest regression model.

[0032] In the above step S101, the number of training samples is set The steps include: Step S201: Setting the search range And search accuracy ; Step S202: Determine the search sequence ; Step S203: From the search sequence Determine the partition coefficient ; Step S204: Based on the division coefficient Divide the search interval and obtain the division points and ; Step S205: Calculate the division points respectively and The corresponding training accuracy; Step S206: Update the search interval according to the training accuracy; Step S207: Calculate the interval width of the search interval ; Step S208: Set the interval width With search precision For comparison, if ,but ,like , then jump back to step S203.

[0033] In the above step S201, the search accuracy It is preset by those skilled in the art according to actual conditions.

[0034] In the above step S202, the search sequence .

[0035] In the above step S203, from the search sequence Determine the partition coefficient The methods include: Calculate the initial partition coefficient based on the search interval ; Search the sequence Subtract the initial partition coefficient from each value in to obtain the coefficient difference; sort each coefficient difference from small to large, mark the coefficient difference at the front as the most recent difference; and search the corresponding sequence of the most recent difference. The value in is used as the partition coefficient ; Initial partition coefficient The expression is: ; In the formula, is the maximum value of the search interval, is the minimum value of the search interval.

[0036] In the above step S204, the division point ; In the formula, To search for the partition coefficient in the sequence The value of the first two digits; Divide point ; In the formula, To search for the partition coefficient in the sequence The value of the previous digit.

[0037] In the above step S205, the division point is calculated and The corresponding training accuracy methods include: The number of different types of data in the marker detection data is counted and marked as the number of types; the number of groups of the marker detection data is obtained and marked as the number of data groups; the number of types, the number of data groups and the numerical values ​​of the dividing points are used as analysis data, and the analysis data is input into the trained accuracy assessment model to evaluate the corresponding training accuracy; the training process of the accuracy assessment model includes: Pre-collection Group analysis data, The corresponding training precision is set for each group of analysis data. is an integer greater than 1, and the analysis data and the corresponding training accuracy are converted into a corresponding set of feature vectors; the training accuracy corresponding to the analysis data is collected by technicians in the process of historical training of random forest regression model. The random forest regression model was trained by selecting the corresponding number of marker coding data as training samples according to the values ​​of the dividing points in each group of analysis data. After the model training was completed, the model accuracy of each random forest regression model was evaluated in turn according to the actual situation, and used as the training accuracy of the corresponding analysis data. The group analysis data sets the corresponding training precision in turn; Each set of feature vectors is used as the input of the accuracy assessment model. The accuracy assessment model uses a set of predicted training accuracy corresponding to each set of analysis data as output, and uses the actual training accuracy corresponding to each set of analysis data as the prediction target. The actual training accuracy is the pre-set training accuracy corresponding to the analysis data; the training target is to minimize the sum of the prediction errors of all analysis data; where the calculation formula for the prediction error is: ,in is the prediction error, is the group number of the eigenvector corresponding to the analyzed data, For the The prediction training accuracy corresponding to the group analysis data, For the The actual training accuracy corresponding to the group analysis data; the accuracy evaluation model is trained until the sum of the prediction errors reaches convergence and the training is stopped.

[0038] The above-mentioned accuracy assessment model is specifically a deep neural network model; it includes an input layer, a hidden layer and an output layer; each hidden layer includes multiple neurons, each neuron is connected to the neurons in the next layer, and the connection contains weights, which determine the importance and influence of data transmission in the neural network; an activation function is applied to each neuron between the hidden layer and the output layer, and the activation function introduces nonlinearity, allowing the network to learn more complex patterns and features.

[0039] In the above step S206, the method for updating the search interval according to the training accuracy includes: Divide the points The corresponding training accuracy is marked as the first accuracy , divide the points The corresponding training accuracy is marked as the second accuracy ; Set the first precision and second precision For comparison; if , then update the minimum value of the search interval to , the maximum value is not updated; if , then update the maximum value of the search interval to , the minimum value is not updated; illustratively, the search interval is ,like , then the search interval is updated to ,like , then the search interval is updated to .

[0040] In the above step S207, the width of the search interval is calculated The method is: subtract the corresponding minimum value from the maximum value of the search interval to obtain the interval width of the search interval .

[0041] In the above step S103, the method for constructing a tumor prognosis model according to the training samples includes: Initialize model parameters, including the maximum depth of the decision tree and the minimum number of samples of internal nodes; the model parameters are preset by technicians in this field according to actual conditions; delete the postoperative follow-up data in each group of training samples and mark them as training data; Sampling from the training data tree subsets, each tree subset contains Group training data, according to Each subset of trees is trained separately decision trees; among them, , .

[0042] Methods for training a decision tree using a subset of trees include: Subset a tree Divide the training data into training sets and validation set , the training set The training data in is labeled , , For the training set The number of groups of training data in; using features represents the data in the training data, , is the number of different types of data in the training data; calculate each feature Information gain rate ; Information gain rate The expression is: ; In the formula, For the training set According to the characteristics The decision subsets divided into , is the number of decision subsets, for The information entropy of For the training set Information entropy of The expression is: ; The expression is: ; In the formula, Represents a decision subset Middle The postoperative labels are the numerical labels corresponding to the postoperative follow-up data of the group training data. The numerical labels corresponding to the postoperative follow-up data of different groups are different. Select the maximum information gain rate The corresponding features As an internal node, and according to the maximum information gain rate The corresponding features The training set Divide into decision subsets; for each according to the maximum information gain rate The algorithm recursive process is repeated for the divided decision subsets until the number of training data in the decision subset is less than or equal to the minimum number of samples in the internal node, or the number of recursions is greater than or equal to the maximum depth of the decision tree, and the recursion ends; the trained decision tree model is used as the validation set. Perform evaluation and finally complete the training of the decision tree.

[0043] Use the rest in turn A subset of trees is trained decision trees, where the training process of each decision tree is independent and the same, and finally a decision tree containing A random forest regression model with 2 decision trees.

[0044] Input each group of training data into each decision tree in turn, and record the decision output, which is the postoperative label output by each decision tree and marked as the predicted label; calculate the mean of the predicted labels corresponding to the same training data and use it as the predicted value; calculate the mean square error between each predicted value and the true value and use it as the loss function value, and the true value is the postoperative label corresponding to the training data input into the decision tree; use the random search method or the Bayesian optimization method to tune the model hyperparameters, reduce the loss function value, and select the model hyperparameters with the smallest loss function value as the model hyperparameters of the tumor prognosis model; it should be noted that the random search method and the Bayesian optimization method are both existing technologies and will not be elaborated on here.

[0045] The potential assessment module is used to assess the potential of markers based on marker coding data and tumor prognosis models.

[0046] Methods for evaluating the potential of a marker include: The marker coding data that is not marked as training samples is used as evaluation samples, and the postoperative follow-up data in the evaluation samples is marked as real data; the postoperative follow-up data in each evaluation sample is deleted and marked as evaluation data; each group of evaluation data is input into the trained tumor prognosis model to predict the corresponding postoperative label; according to the predicted postoperative label, the corresponding postoperative follow-up data is obtained and marked as predicted data; each real data and the corresponding predicted data are used as a set of analysis sets, and the analysis sets correspond to the real data one by one; each value in each real data is subtracted from the corresponding value in the corresponding predicted data, and the absolute value is taken to obtain the numerical difference; A weight set is preset, and the weight set includes a weight coefficient corresponding to each data in the postoperative follow-up data. The weight set is preset by technical personnel in this field according to actual conditions; each numerical difference is multiplied by the corresponding weight coefficient to obtain a weight difference; the weight differences corresponding to each group of analysis sets are added in turn to obtain a total numerical difference; the number of statistical analysis sets is analyzed and marked as the number of sets; each total numerical difference is added in turn, and then divided by the number of sets to obtain a total difference mean, and the inverse of the total difference mean is used as the marker potential.

[0047] The marker determination module is used to determine whether the candidate marker can be used as a tumor marker based on the marker potential, and if so, to perform quantitative calculations of clinical practicality.

[0048] Methods for determining whether a candidate marker can be used as a tumor marker include: A potential threshold is preset, and the potential threshold is pre-set by a technician in this field according to actual conditions; the marker potential is compared with the potential threshold; if the marker potential is greater than or equal to the potential threshold, the candidate marker is determined to be a tumor marker; if the marker potential is less than the potential threshold, the candidate marker is determined not to be a tumor marker.

[0049] Methods for quantifying clinical utility include: calculate The protein expression data in the group marker detection data is correlated with each data in the postoperative follow-up data; each correlation is multiplied by the corresponding weight coefficient to obtain the weight correlation degree; the absolute value of each weight correlation degree is taken and added in sequence to obtain the clinical practicality corresponding to the candidate marker; The expression of correlation is: ; In the formula, For relevance, For the Protein expression data in group marker detection data, For the A data within the postoperative follow-up data in the group marker detection data.

[0050] This embodiment comprehensively analyzes multiple omics data such as genome, transcriptome, proteome, clinical pathological data and postoperative follow-up data, and uses an optimized machine learning algorithm to build a tumor prognosis model, which can accurately predict the patient's survival and recurrence risk, accurately evaluate the potential of markers, and effectively identify new potential tumor markers, promote the discovery of new therapeutic targets, and further promote the realization of early diagnosis and personalized treatment; at the same time, a correlation algorithm is used to objectively quantify the clinical value of candidate markers, providing a basis for selecting the most appropriate tumor markers for clinical applications; it not only improves the detection and verification efficiency of tumor markers, but also provides important support for personalized medicine and precision treatment, and can significantly improve the patient's prognosis evaluation and treatment effect.

[0051] Example 2 The present application also provides an electronic device. The electronic device may include one or more processors and one or more memories. The memories store computer-readable codes, and when the computer-readable codes are executed by one or more processors, the integrated analysis platform for tumor marker detection data as described above may be executed.

[0052] The method or system according to the implementation mode of the present application can also be implemented with the help of the architecture of the electronic device shown in the present application. The electronic device may include a bus, one or more CPUs, ROM, RAM, a communication port connected to a network, input / output, a hard disk, etc. A storage device in the electronic device, such as a ROM or a hard disk, can store a comprehensive analysis platform for tumor marker detection data provided by the present application. Furthermore, the electronic device may also include a user interface. Of course, the architecture shown in the present application is only exemplary. When implementing different devices, one or more components in the electronic device shown in the present application may be omitted according to actual needs.

[0053] Example 3 One embodiment of the present application discloses a computer-readable storage medium. Computer-readable instructions are stored on the computer-readable storage medium. When the computer-readable instructions are executed by the processor, a comprehensive analysis platform for tumor marker detection data according to the embodiment of the present application described with reference to the above figures can be executed. The storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0054] In addition, according to the embodiments of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium, which stores machine-readable instructions, and the machine-readable instructions can be executed by a processor to execute instructions corresponding to the method steps provided in the present application, for example: a comprehensive analysis platform for tumor marker detection data. When the computer program is executed by a central processing unit (CPU), the above functions defined in the method of the present application are executed.

[0055] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0056] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A comprehensive analysis platform for tumor marker detection data, characterized in that: include: A data collection module, used to collect marker detection data of candidate markers; A data encoding module, used to encode the marker detection data and obtain the marker encoding data; A model building module is used to build a tumor prognosis model based on marker coding data; A potential assessment module, used to assess the potential of a marker based on marker coding data and a tumor prognosis model; The marker determination module is used to determine whether the candidate marker can be used as a tumor marker based on the marker potential, and if so, to perform quantitative calculations of clinical practicality.

2. A comprehensive analysis platform for tumor marker detection data according to claim 1, characterized in that: The marker detection data include single nucleotide polymorphism detection data, clinical detection data, protein expression data, pathological detection data and postoperative follow-up data; the clinical detection data include laboratory detection data and intraoperative tumor data; the pathological detection data include cytological data and histological data; the postoperative follow-up data include the patient's survival and recurrence; the survival status includes overall survival and disease-free survival; The method for obtaining marker coding data comprises: The single nucleotide polymorphism detection data, clinical detection data, protein expression data and pathological detection data in the marker detection data are used as analysis detection data; the data that is not a numerical value in the analysis detection data is marked as data to be encoded; the number of each different data in the data to be encoded is counted and marked as the data number; the number of data of each different data in the data to be encoded is used as the corresponding data frequency; all data frequencies are compared in turn, and the data to be encoded whose data frequency is different from all other data frequencies is marked as direct data, and the data to be encoded with the same data frequency is marked as combined data; the data frequency of the direct data is used as the corresponding data code; the data corresponding to the same group of analysis detection data in the combined data is divided into a combined set, and the combined set corresponds to the analysis detection data one by one; the data frequency corresponding to each data in each combined set is merged as the set code corresponding to the corresponding combined set; In the group marker detection data, each combined set is replaced by the corresponding set code, each direct data is replaced by the corresponding data code, and the replaced marker detection data is marked as marker code data.

3. A comprehensive analysis platform for tumor marker detection data according to claim 2, characterized in that: The step of constructing a tumor prognosis model comprises: Step S101: Using a search optimization algorithm to set the number of training samples ; Step S102: Random selection The group marker encoding data is used as training samples; Step S103: constructing a tumor prognosis model according to the training samples, where the tumor prognosis model is a random forest regression model; In step S101, the number of training samples is set The steps include: Step S201: Setting the search range And search accuracy ; Step S202: Determine the search sequence ; Step S203: From the search sequence Determine the partition coefficient ; Step S204: Based on the division coefficient Divide the search interval and obtain the division points and ; Step S205: Calculate the division points respectively and The corresponding training accuracy; Step S206: updating the search interval according to the training accuracy; Step S207: Calculate the width of the search interval ; Step S208: Set the interval width With search precision For comparison, if ,but ,like , then jump back to step S203.

4. A comprehensive analysis platform for tumor marker detection data according to claim 3, characterized in that: In step S202, the search sequence ; In step S203, from the search sequence Determine the partition coefficient The methods include: Calculate the initial partition coefficient based on the search interval ; Search the sequence Subtract the initial partition coefficient from each value in to obtain the coefficient difference; sort each coefficient difference from small to large, mark the coefficient difference at the front as the most recent difference; and search the corresponding sequence of the most recent difference. The value in is used as the partition coefficient ; Initial partition coefficient The expression is: ; In the formula, is the maximum value of the search interval, is the minimum value of the search interval; In step S204, the division point ; In the formula, To search for the partition coefficient in the sequence The value of the first two digits; Divide point ; In the formula, To search for the partition coefficient in the sequence The value of the previous digit.

5. A comprehensive analysis platform for tumor marker detection data according to claim 4, characterized in that: In step S205, the division points are calculated. and The corresponding training accuracy methods include: The number of different types of data in the marker detection data is counted and marked as the number of types; the number of groups of the marker detection data is obtained and marked as the number of data groups; the number of types, the number of data groups and the numerical values ​​of the dividing points are used as analysis data, and the analysis data is input into the trained accuracy assessment model to evaluate the corresponding training accuracy; the training process of the accuracy assessment model includes: Pre-collection Group analysis data, The corresponding training precision is set for each group of analysis data. is an integer greater than 1, converting the analysis data and the corresponding training accuracy into a corresponding set of feature vectors; taking each set of feature vectors as the input of the accuracy assessment model, the accuracy assessment model takes a set of predicted training accuracy corresponding to each set of analysis data as the output, and takes the actual training accuracy corresponding to each set of analysis data as the prediction target, and the actual training accuracy is the pre-set training accuracy corresponding to the analysis data; minimizing the sum of the prediction errors of all analysis data is taken as the training target; training the accuracy assessment model until the sum of the prediction errors reaches convergence and the training is stopped; the accuracy assessment model is a deep neural network model; In step S206, the method for updating the search interval according to the training accuracy includes: Divide the points The corresponding training accuracy is marked as the first accuracy , divide the points The corresponding training accuracy is marked as the second accuracy ; Set the first precision and second precision For comparison; if , then update the minimum value of the search interval to , the maximum value is not updated; if , then update the maximum value of the search interval to , the minimum value is not updated; In step S207, the width of the search interval is calculated. The method is: subtract the corresponding minimum value from the maximum value of the search interval to obtain the interval width of the search interval .

6. A comprehensive analysis platform for tumor marker detection data according to claim 5, characterized in that: In step S103, the method for constructing a tumor prognosis model according to training samples includes: Initialize the model parameters, including the maximum depth of the decision tree and the minimum number of samples of the internal nodes; delete the postoperative follow-up data in each group of training samples and mark them as training data; set different digital labels for different groups of postoperative follow-up data and mark them as postoperative labels; Sampling from the training data tree subsets, each tree subset includes Group training data, where , ;according to Each subset of trees is trained separately decision trees, where the training process of each decision tree is independent and the same, and finally a decision tree containing A random forest regression model with 1 decision tree; Input each set of training data into each decision tree in turn, record the decision output, which is the postoperative label output by each decision tree and marked as the predicted label; calculate the mean of the predicted labels corresponding to the same training data and use it as the predicted value; calculate the mean square error between each predicted value and the true value and use it as the loss function value, where the true value is the postoperative label corresponding to the training data input into the decision tree; use random search method or Bayesian optimization method to tune the model hyperparameters, and select the model hyperparameters with the smallest loss function value as the model hyperparameters of the tumor prognosis model.

7. A comprehensive analysis platform for tumor marker detection data according to claim 6, characterized in that: Methods for training a decision tree using a subset of trees include: Subset a tree Divide the training data into training sets and validation set , the training set The training data in is labeled , , For the training set The number of groups of training data in; using features represents the data in the training data, , is the number of different types of data in the training data; calculate each feature Information gain rate ; Select the maximum information gain rate The corresponding features As an internal node, and according to the maximum information gain rate The corresponding features The training set Divide into decision subsets; for each according to the maximum information gain rate The algorithm recursive process is repeated for the divided decision subsets until the number of training data in the decision subset is less than or equal to the minimum number of samples in the internal node, or the number of recursions is greater than or equal to the maximum depth of the decision tree, and the recursion ends; the trained decision tree model is used as the validation set. Perform evaluation and finally complete the training of the decision tree.

8. A comprehensive analysis platform for tumor marker detection data according to claim 7, characterized in that: Information gain rate The expression is: ; In the formula, For the training set According to the characteristics The decision subsets divided into , is the number of decision subsets, for The information entropy of For the training set Information entropy of The expression is: ; The expression is: ; In the formula, Represents a decision subset Middle The postoperative labels corresponding to the group training data.

9. A comprehensive analysis platform for tumor marker detection data according to claim 8, characterized in that: The method for evaluating the potential of a marker comprises: The marker coding data that is not marked as training samples is used as evaluation samples, and the postoperative follow-up data in the evaluation samples is marked as real data; the postoperative follow-up data in each evaluation sample is deleted and marked as evaluation data; each group of evaluation data is input into the trained tumor prognosis model to predict the corresponding postoperative label; according to the predicted postoperative label, the corresponding postoperative follow-up data is obtained and marked as predicted data; each real data and the corresponding predicted data are used as a set of analysis sets, and the analysis sets correspond to the real data one by one; each value in each real data is subtracted from the corresponding value in the corresponding predicted data, and the absolute value is taken to obtain the numerical difference; A weight set is preset, and the weight set includes a weight coefficient corresponding to each data in the postoperative follow-up data; each numerical difference is multiplied by the corresponding weight coefficient to obtain a weight difference; the weight differences corresponding to each group of analysis sets are added in turn to obtain a total numerical difference; the number of statistical analysis sets is analyzed and marked as the number of sets; each total numerical difference is added in turn, and then divided by the number of sets to obtain a total difference mean, and the reciprocal of the total difference mean is used as the marker potential.

10. A comprehensive analysis platform for tumor marker detection data according to claim 9, characterized in that: The method for determining whether a candidate marker can be used as a tumor marker comprises: A potential threshold is preset, and the potential of the marker is compared with the potential threshold; if the potential of the marker is greater than or equal to the potential threshold, the candidate marker is determined to be a tumor marker; if the potential of the marker is less than the potential threshold, the candidate marker is determined not to be a tumor marker; The method for quantitative calculation of clinical practicality includes: calculate The protein expression data in the group marker detection data is correlated with each data in the postoperative follow-up data; each correlation is multiplied by the corresponding weight coefficient to obtain the weight correlation degree; the absolute value of each weight correlation degree is taken and added in sequence to obtain the clinical practicality corresponding to the candidate marker; The expression of correlation is: ; In the formula, For relevance, For the Protein expression data in group marker detection data, For the A data within the postoperative follow-up data in the group marker detection data.

Images