Biomarker screening method and system based on genomics

Abstract

The invention discloses a genomics-based biomarker screening method and system, and relates to the technical field of biological detection.The method comprises the steps that biomarker expression data related to significant genes are determined according to transcriptome sequencing data of a biological sample of a cancer disease, the posterior distribution of the biomarker associated with the cancer disease is estimated through a logistic regression model; determining significant interaction genes according to the posterior distribution and the interaction network between the genes; and based on the significant interaction genes, screening to obtain a biomarker list related to cancer diseases. According to the application, the posterior distribution and significant interaction genes are screened through the transcriptome sequencing data of the biological sample of the cancer disease, so that the situation of missing detection caused by low biomarker specificity in the traditional biomarker screening process is avoided, and a biomarker list highly related to the cancer disease can be obtained; and the sensitivity of the biomarker screening process is improved.

Description

Technical Field

[0001] The present application relates to the field of biological detection technology, and in particular to a genomics-based biomarker screening method and system. Background Art

[0002] Cancer (malignant tumor) is a major disease that threatens human life and health. The incidence and mortality rates are increasing year by year around the world, and the situation is very serious. Cancer biomarkers have strong disease specificity, which helps in early diagnosis of the disease and evaluation of treatment effects. Researchers generally use a variety of methods to search and discover biomarkers of cancer diseases, such as immunology, molecular biology, genomics and other technologies.

[0003] However, due to the interactions between biomarkers, differences in disease samples, differences in biomarker levels between individuals, and the fact that the expression levels of some biomarkers do not change significantly in the early stages of the disease or when the condition is mild, the biomarker screening process has a low sensitivity. At the same time, some biomarkers cross-react with other diseases, which can reduce the specificity of the biomarkers and make it easy for them to miss detections, leading to missed or delayed diagnosis of patients. Summary of the invention

[0004] The main purpose of this application is to provide a genomics-based biomarker screening method and system, which aims to solve the shortcomings of low biomarker specificity and low screening sensitivity in the traditional biomarker screening process, which easily leads to missed detection, resulting in missed diagnosis or delayed diagnosis of patients.

[0005] To achieve the above objectives, the present application proposes a biomarker screening method based on genomics, the method comprising: Determining biomarker expression data associated with significant genes based on transcriptome sequencing data of cancer disease biological samples, wherein the transcriptome sequencing data is obtained based on functional genomics and clinical genomics; Based on the biomarker expression data of the significant genes, estimating the posterior distribution of the association between the biomarker and the cancer disease through a logistic regression model; According to the posterior distribution and the gene-gene interaction network, determining the significant interacting genes in the cancer disease biological sample; Based on the significantly interacting genes, a list of biomarkers associated with cancer diseases was screened and obtained.

[0006] In one embodiment, the step of determining biomarker expression data associated with significant genes based on transcriptome sequencing data of a cancer disease biological sample comprises: Obtain biospecimens for various types of cancer diseases; Performing transcription amplification on the cancer disease biological sample, and sequencing to obtain transcriptome sequencing data based on functional genomics and clinical genomics; The transcriptome sequencing data are clustered and screened to obtain biomarker expression data associated with significant genes.

[0007] In one embodiment, the step of performing cluster screening on the transcriptome sequencing data to obtain biomarker expression data associated with significant genes comprises: Preliminarily screening the transcriptome sequencing data according to gene expression levels to obtain gene difference data; Performing an association test based on the gene difference data to obtain the gene difference data after the association test; Performing feature screening on the gene difference data after the association test by a hierarchical clustering algorithm to obtain hierarchical association results between genes and cancer diseases; According to the hierarchical association results, biomarker expression data associated with significant genes are determined.

[0008] In one embodiment, the step of estimating the posterior distribution of the association between the biomarker and the cancer disease by a logistic regression model based on the biomarker expression data of the significant gene comprises: Based on the biomarker expression data of the significant genes, using a logistic regression model to describe the association between the biomarker and the cancer disease; The posterior distribution of the association between biomarkers and cancer diseases was obtained by unnormalizing the association between biomarkers and cancer diseases through Bayesian methods.

[0009] In one embodiment, the step of determining the significant interacting genes in the cancer disease biological sample according to the posterior distribution and the gene interaction network comprises: According to the posterior distribution and the gene-gene interaction network, determining the significant interactions of genes in the cancer disease state and the normal state; According to the significant interactions, the significantly interacting genes in the cancer disease biological sample are determined.

[0010] In one embodiment, the step of screening and obtaining a list of biomarkers associated with cancer diseases based on the significantly interacting genes comprises: Performing feature importance evaluation on the significantly interacting genes to obtain importance scores; Sorting the importance scores to obtain a score list; The significantly interacting genes are screened based on the score list to obtain a list of biomarkers associated with cancer diseases.

[0011] In one embodiment, the step of performing feature importance assessment on the significantly interacting genes to obtain importance scores comprises: Initialize the gradient boosting decision tree model; Training the gradient boosting decision tree model using a cancer gene database; The feature importance of the significantly interacting genes was evaluated according to the trained gradient boosting decision tree model to obtain importance scores.

[0012] In addition, to achieve the above objectives, the present application also proposes a genomics-based biomarker screening system, the system comprising: A sequencing data module, used to determine biomarker expression data associated with significant genes based on transcriptome sequencing data of cancer disease biological samples, wherein the transcriptome sequencing data is obtained based on functional genomics and clinical genomics; A posterior distribution module, for estimating the posterior distribution of the association between the biomarker and the cancer disease through a logistic regression model based on the biomarker expression data of the significant gene; An interaction module, for determining significant interacting genes in a cancer disease biological sample based on the posterior distribution and the gene-gene interaction network; The marker screening module is used to screen and obtain a list of biomarkers related to cancer diseases based on the significantly interacting genes.

[0013] In one embodiment, the sequencing data module is also used to obtain various types of cancer disease biological samples; The sequencing data module is also used to perform transcription amplification on the cancer disease biological sample, and to sequence and obtain transcriptome sequencing data based on functional genomics and clinical genomics; The sequencing data module is also used to perform cluster screening on the transcriptome sequencing data to obtain biomarker expression data related to significant genes.

[0014] In one embodiment, the sequencing data module is further used to perform preliminary screening on the transcriptome sequencing data according to gene expression levels to obtain gene difference data; The sequencing data module is further used to perform an association test based on the gene difference data to obtain the gene difference data after the association test; The sequencing data module is also used to perform feature screening on the gene difference data after the association test by a hierarchical clustering algorithm to obtain a hierarchical association result between genes and cancer diseases; The sequencing data module is also used to determine biomarker expression data associated with significant genes based on the hierarchical association results.

[0015] One or more technical solutions proposed in this application have at least the following technical effects: this application first determines the biomarker expression data associated with significant genes based on the transcriptome sequencing data of cancer disease biological samples, and the transcriptome sequencing data is obtained based on functional genomics and clinical genomics; then, based on the biomarker expression data of the significant genes, the posterior distribution of the association between the biomarker and the cancer disease is estimated through a logistic regression model; then, based on the posterior distribution and the gene-gene interaction network, the significant interaction genes in the cancer disease biological sample are determined; finally, based on the significant interaction genes, a list of biomarkers associated with the cancer disease is screened. Since this application screens the posterior distribution and significant interaction genes associated with the biomarker and the cancer disease through the transcriptome sequencing data of the cancer disease biological sample, it avoids the situation of missed detection due to the low specificity of the biomarker in the traditional biomarker screening process, thereby obtaining a list of biomarkers with high correlation with the cancer disease, and improving the sensitivity of the biomarker screening process. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0018] Figure 1 A schematic diagram of the process provided for Example 1 of the genomics-based biomarker screening method of the present application; Figure 2 A schematic diagram of the process provided for Example 2 of the genomics-based biomarker screening method of the present application; Figure 3 A schematic diagram of the process provided for Example 3 of the genomics-based biomarker screening method of this application; Figure 4 This is a schematic diagram of the functional modules of the genomics-based biomarker screening system according to an embodiment of the present application.

[0019] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0020] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0021] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0022] It should be noted that the execution subject of this embodiment can be a computing service device with transcription sequencing, posterior distribution calculation and marker screening functions, such as a personal computer, server, etc., or an electronic device capable of realizing the above functions, a genomics-based biomarker screening system (screening system) that executes the genomics-based biomarker screening method of this application, etc., and this embodiment does not limit this. The following takes the screening system as an example to illustrate this embodiment and the following embodiments.

[0023] Example 1: Based on this, the present application embodiment provides a biomarker screening method based on genomics, referring to Figure 1 , Figure 1 A schematic diagram of the process provided for Example 1 of the genomics-based biomarker screening method of the present application.

[0024] In this embodiment, the genomics-based biomarker screening method includes steps S10 to S40: Step S10: Determine biomarker expression data associated with significant genes based on transcriptome sequencing data of cancer disease biological samples, wherein the transcriptome sequencing data is obtained based on functional genomics and clinical genomics.

[0025] It should be noted that cancer disease biological samples are various biological materials related to cancer.

[0026] Exemplarily, biological samples of cancer diseases may include tissue specimens (such as tumor tissue, adjacent cancer tissue), blood (such as whole blood, plasma, serum), body fluids (such as urine, cerebrospinal fluid, pleural effusion, etc.), and cells (such as circulating tumor cells, etc.) obtained from cancer patients.

[0027] It should be noted that transcriptome sequencing data is data obtained by sequencing RNA transcribed from cancer disease biological samples under specific conditions.

[0028] For example, the transcription process may include messenger RNA (mRNA), ribosomal RNA (rRNA), transfer RNA (tRNA) and other non-coding RNAs, etc. Transcription sequencing can be used to comprehensively and quantitatively analyze the expression of genes in biological samples of cancer diseases.

[0029] It should be noted that biomarker expression data refers to gene data in transcriptome sequencing data that is closely related to cancer diseases and can significantly express biomarkers.

[0030] It should be noted that functional genomics is the study of gene functions, including gene expression regulation, the function of gene products, and the interaction between genes.

[0031] Clinical genomics is the application of genomics technology and research results to clinical practice, involving the use of genomic information to diagnose diseases, predict disease prognosis, etc.

[0032] Constructing transcriptome sequencing data through the standards of functional genomics and clinical genomics can better understand the molecular mechanisms and individual differences of cancer diseases, provide important support for the screening of biomarkers for cancer diseases and their application in medical treatment, and achieve more accurate and effective screening of biomarkers.

[0033] In one embodiment, transcription amplification can be performed on cancer disease biological samples first, and then transcriptome sequencing data can be obtained based on the standards of functional genomics and clinical genomics. The screening system can screen the associated features of the cancer disease based on these data to obtain biomarker expression data of significant genes that are closely related to the cancer disease.

[0034] Step S20: Based on the biomarker expression data of the significant genes, the posterior distribution of the association between the biomarker and the cancer disease is estimated by a logistic regression model.

[0035] It should be noted that the logistic regression model is a statistical analysis model used to solve binary (or multi-classification) problems. The logistic regression model can be used to describe the association between biomarkers and cancer diseases to determine the association between biomarkers and cancer diseases.

[0036] It should be noted that biomarkers are biochemical molecules that can mark changes or possible changes in systems, organs, tissues, cells, subcellular and genetic structures. Biomarkers can help to diagnose cancer diseases more accurately.

[0037] It should be noted that the posterior distribution is a probability distribution of the association between biomarkers and cancer diseases. Through the posterior distribution, we can deeply understand the role of biomarkers in cancer occurrence and its uncertainty.

[0038] In one embodiment, the biomarker expression data can be used as an input variable and combined with relevant information of the cancer disease. The degree of association between the biomarker and the cancer disease is probabilistically described through a logistic regression model to obtain the posterior distribution of the association between the biomarker and the cancer disease.

[0039] Step S30: Determine the significant interacting genes in the cancer disease biological sample according to the posterior distribution and the gene interaction network.

[0040] It should be noted that the gene interaction network is a complex network structure formed by various interaction relationships between numerous genes.

[0041] In organisms, genes do not exist and function in isolation. The expression and function of a gene may be affected by other genes, and there may be multiple interactions between them, such as synergy and antagonism. These interactions are intertwined to form a huge network.

[0042] It should be noted that significantly interacting genes are genes that have particularly prominent interaction relationships in biological samples of cancer diseases and may play a key role in the occurrence and development of cancer.

[0043] For example, in cancer samples, the interactions of certain genes may change significantly, such as the synergistic or antagonistic effects between them being enhanced or weakened in the cancer state, and these genes can be considered to have significant interactions in the cancer. Through the gene interaction network, we can better understand the interactions between genes and reveal the associations and synergistic patterns between genes that play a key role in the occurrence and development of cancer.

[0044] In one embodiment, based on the posterior distribution of the association between biomarkers and cancer diseases, combined with the gene interaction network, genes with particularly prominent interaction relationships and key roles in the occurrence and development of cancer can be found. This provides an important basis for accurately screening biomarkers related to cancer diseases and helps discover new biomarkers.

[0045] Step S40: Based on the significantly interacting genes, a list of biomarkers related to cancer diseases is screened and obtained.

[0046] It should be noted that the biomarker list is a list of biomarkers related to cancer diseases. Through the biomarker list, we can better understand the relationship between biomarkers and cancer diseases, which is helpful for the diagnosis of diseases.

[0047] In one embodiment, the significantly interacting genes obtained above can be arranged in the order of interaction degree or classified according to different physiological functions, and a list of biomarkers related to cancer diseases can be obtained by screening.

[0048] In this embodiment, the cancer disease biological sample can first be transcribed and amplified, and then the transcriptome sequencing data can be obtained according to the standards of functional genomics and clinical genomics. The screening system can screen the associated features of the cancer disease based on these data to obtain the biomarker expression data of the significant genes closely associated with the cancer disease. Then the biomarker expression data can be used as an input variable, and the relevant information of the cancer disease can be combined. The degree of association between the biomarker and the cancer disease can be described probabilistically through a logistic regression model to obtain the posterior distribution of the association between the biomarker and the cancer disease. Then, according to the posterior distribution of the association between the biomarker and the cancer disease, combined with the gene interaction network, those genes with particularly prominent interaction relationships and key roles in the occurrence and development of cancer can be found. This provides an important basis for accurately screening biomarkers related to cancer diseases and helps to discover new biomarkers. Finally, the above-mentioned significantly interacting genes can be arranged in the order of the degree of interaction or the classification of different physiological functions to screen and obtain a list of biomarkers related to cancer diseases.

[0049] In a feasible implementation, step S40 of this embodiment may include the steps of: performing feature importance evaluation on the significantly interacting genes to obtain importance scores; sorting the importance scores to obtain a score list; and screening the significantly interacting genes based on the score list to obtain a list of biomarkers associated with cancer diseases.

[0050] It should be noted that the importance score is a score expressed in numerical form, which evaluates the importance of each of the significantly interacting genes based on the degree of association with cancer diseases.

[0051] In this embodiment, the characteristic importance of the significantly interacting genes can be evaluated based on the degree of association with the cancer disease to obtain the importance score; then the importance score is sorted to obtain a score list. Finally, the biomolecules corresponding to the significantly interacting genes ranked in the top columns (e.g., the top ten or dozens) in the score list are used as biomarkers to obtain a list of biomarkers related to the cancer disease. Thus, using genes with higher scores as biomarkers helps to further focus on key genes.

[0052] In a feasible implementation, the step of performing feature importance evaluation on the significantly interacting genes and obtaining importance scores described in this embodiment includes: initializing a gradient boosting decision tree model; training the gradient boosting decision tree model through a cancer gene database; and performing feature importance evaluation on the significantly interacting genes according to the trained gradient boosting decision tree model to obtain importance scores.

[0053] It should be noted that the gradient boosting decision tree model is a model that combines multiple decision trees through an ensemble learning method to predict and evaluate the feature importance of significantly interacting genes. During the construction process, different decision trees can be generated through random feature selection and sample sampling. These decision trees together form a "forest" that can evaluate and classify significantly interacting genes.

[0054] It should be noted that the cancer gene database is a database that collects, organizes and stores cancer-related gene information, such as gene sequences, mutations, expression levels, associations with cancer occurrence and development, and related clinical information.

[0055] In this embodiment, the gradient boosting decision tree model can be initialized first. Then, the gradient boosting decision tree model is trained through the cancer gene database to obtain a model that has learned various cancer-related gene information. Finally, the feature importance of the significantly interacting genes is predicted and evaluated according to the trained gradient boosting decision tree model to obtain an importance score. Thus, the cancer gene database can be used to further provide an important basis for finding biomarkers related to cancer diseases, so as to improve the accuracy of the biomarker list.

[0056] This embodiment provides a biomarker screening method based on genomics. First, transcription amplification can be performed on a biological sample of a cancer disease, and then transcriptome sequencing data can be obtained according to the standards of functional genomics and clinical genomics. The screening system can screen the associated features of the cancer disease based on these data to obtain the biomarker expression data of significant genes closely associated with the cancer disease. Then, the biomarker expression data can be used as an input variable, and the relevant information of the cancer disease can be combined. The degree of association between the biomarker and the cancer disease is described probabilistically through a logistic regression model to obtain the posterior distribution of the association between the biomarker and the cancer disease. Then, according to the posterior distribution of the association between the biomarker and the cancer disease, combined with the gene interaction network, genes with particularly prominent interaction relationships and key roles in the occurrence and development of cancer can be found. This provides an important basis for accurately screening biomarkers related to cancer diseases and helps to discover new biomarkers. Finally, the above-obtained significantly interacting genes can be arranged in the order of the degree of interaction or the classification of different physiological functions to screen and obtain a list of biomarkers related to cancer diseases. Since this embodiment uses transcriptome sequencing data of cancer disease biological samples to screen out the posterior distribution of biomarkers associated with cancer diseases and significantly interacting genes, it avoids the situation of missed detection due to low specificity of biomarkers in the traditional biomarker screening process, thereby obtaining a list of biomarkers with high correlation with cancer diseases, thereby improving the sensitivity of the biomarker screening process.

[0057] Embodiment 2: Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those of the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 1 and Figure 2 , Figure 2 A schematic diagram of the process provided for Example 2 of the genomics-based biomarker screening method of the present application.

[0058] In this example, step S10 includes steps S11 to S13: Step S11: Acquire various types of cancer disease biological samples.

[0059] Step S12: performing transcription amplification on the cancer disease biological sample, and sequencing to obtain transcriptome sequencing data based on functional genomics and clinical genomics.

[0060] It should be noted that transcription amplification is the process of increasing the number of RNA transcripts in a sample through specific technical means, and then sequencing and analyzing the samples after transcription amplification. The sequencing process is to determine the sequence information of these RNA molecules, and then screen the sequence information based on functional genomics and clinical genomics to obtain transcriptome sequencing data.

[0061] Step S13: cluster screening is performed on the transcriptome sequencing data to obtain biomarker expression data associated with significant genes.

[0062] In this embodiment, biological samples related to cancer diseases (such as cancer cells, cancer tissues, etc.) can be subjected to transcription amplification. Then, the samples after transcription amplification are sequenced and analyzed to determine the sequence information of RNA molecules in the samples. Then, screening is performed based on functional genomics and clinical genomics to obtain transcriptome sequencing data. In this way, through the standards of functional genomics and clinical genomics, the molecular mechanisms and individual differences of cancer diseases can be better understood, and important support can be provided for the screening of biomarkers for cancer diseases and their application in medical treatment, so as to achieve more accurate and effective screening of biomarkers.

[0063] In a feasible implementation, step S13 of this embodiment may include the steps of: preliminarily screening the transcriptome sequencing data according to gene expression levels to obtain gene difference data; performing association tests based on the gene difference data to obtain gene difference data after the association tests; performing feature screening on the gene difference data after the association tests by a hierarchical clustering algorithm to obtain hierarchical association results between genes and cancer diseases; and determining biomarker expression data associated with significant genes based on the hierarchical association results.

[0064] It should be noted that the genetic difference data are obtained by preliminary difference screening based on gene expression levels (for example, comparing the gene expression levels of diseased and healthy individuals).

[0065] Specifically, by comparing the differences in gene expression levels under different conditions (such as normal tissue and cancer tissue), genes with significant changes (increased or decreased) in expression levels are screened out, and these genes form gene difference data.

[0066] It should be noted that the association test is a process of testing based on the criteria of significant association with cancer disease after preliminary difference screening.

[0067] It should be noted that the hierarchical clustering algorithm is a clustering analysis method, and its basic idea is to form a hierarchical clustering result by gradually merging or splitting samples or data points. The hierarchical clustering algorithm can further hierarchically aggregate the data that are strongly associated with the cancer disease state in the genetic difference data after the association test, construct a hierarchical clustering tree structure, and intuitively display the hierarchical relationship between samples and genes in the genetic difference data after the association test, and obtain a hierarchical association result.

[0068] In this embodiment, the transcriptome sequencing data can be preliminarily screened for differences based on gene expression levels (e.g., comparing the gene expression levels of diseased and healthy individuals) to obtain gene difference data. Then, after the preliminary difference screening, an association test is performed based on the standard that is significantly associated with cancer disease to obtain gene difference data after the association test. Finally, the gene difference data after the association test is feature screened by a hierarchical clustering algorithm, and the data that is strongly associated with the cancer disease state in the gene difference data after the association test is further hierarchically aggregated to construct a hierarchical clustering tree structure, intuitively displaying the hierarchical relationship between samples and genes in the gene difference data after the association test, and obtaining hierarchical association results to determine the biomarker expression data associated with significant genes. Thus, the distribution and structural characteristics of the hierarchical relationship between cancer samples and genes can be better understood through the hierarchical clustering algorithm to improve the accuracy of obtaining biomarker expression data.

[0069] In another feasible implementation, step S30 of this embodiment may include the steps of: determining the significant interactivity of genes in the cancer disease state and the normal state based on the posterior distribution and the gene interaction network; and determining the significant interacting genes in the cancer disease biological sample based on the significant interactivity.

[0070] It should be noted that significant interaction refers to the obvious correlation between genes in the disease state of cancer and in the normal state.

[0071] Specifically, it is to determine how the relationship between genes in cancer is different from that in normal conditions. For example, some genes may cooperate or restrict each other in a relatively peaceful and stable way under normal conditions, but in cancer conditions, the interaction between them may become abnormally active or inhibited. This significant change in interaction may play a key role in the occurrence of cancer. By determining this significant interaction, we can deeply understand the molecular mechanism of cancer and provide an important basis for the screening of biomarkers.

[0072] In this embodiment, the significant interactions between genes in the disease state of cancer and the normal state can be determined based on the posterior distribution of the association between biomarkers and cancer diseases, combined with the gene interaction network. Then, based on the significant interactions, genes with particularly prominent interactions that play a key role in the occurrence and development of cancer are found. Thus, by determining the significant interactions, the molecular mechanism of cancer can be deeply understood, providing an important basis for the screening of biomarkers.

[0073] This embodiment can perform transcription amplification processing on biological samples (such as cancer cells, cancer tissues, etc.) related to cancer diseases. Then, the samples after transcription amplification are sequenced and analyzed to determine the sequence information of RNA molecules in the samples. Then, screening is performed based on functional genomics and clinical genomics to obtain transcriptome sequencing data. In this way, through the standards of functional genomics and clinical genomics, the molecular mechanisms and individual differences of cancer diseases can be better understood, and important support can be provided for the screening of biomarkers for cancer diseases for medical treatment, so as to achieve more accurate and effective screening of biomarkers. Furthermore, according to the posterior distribution of the association between biomarkers and cancer diseases, combined with the gene interaction network, the significant interaction between genes in the disease state of cancer and the normal state can be determined. Then, according to the significant interaction, genes with particularly prominent interaction relationships and key roles in the occurrence and development of cancer are found. Thus, by determining the significant interaction, the molecular mechanism of cancer can be deeply understood, providing an important basis for the screening of biomarkers.

[0074] Embodiment 3: Based on the first and second embodiments of the present application, in the third embodiment of the present application, the same or similar contents as those of the above-mentioned embodiments 1 and 2 can be referred to the above introduction, and will not be repeated in the following. Figure 3 , Figure 3 A schematic diagram of the process provided for Example 3 of the genomics-based biomarker screening method of the present application.

[0075] In this example, step S20 includes steps S21-S22: Step S21: Based on the biomarker expression data of the significant genes, a logistic regression model is used to describe the association between the biomarker and the cancer disease.

[0076] Step S22: Using a Bayesian method, the non-normalized combination of the associations between the biomarkers and cancer diseases is performed to obtain the posterior distribution of the associations between the biomarkers and cancer diseases.

[0077] It should be noted that the Bayesian method is a statistical inference method based on Bayes' theorem. Bayes' theorem describes how to update the estimate of the probability of an event based on new observational data when certain prior information is known. That is, the posterior distribution of the association between biomarkers and cancer diseases is calculated through the prior information of the association between biomarkers and cancer diseases.

[0078] Specifically, for ease of understanding, the specific processing process is as follows: 1. First, build a model for binary outcomes.

[0079] set up Indicates research indicators (i.e., biomarker expression data) that facilitate aggregation. A single , represents a binary disease outcome, represents a biomarker exposure measurement from a reference laboratory (reference measurement), represents biomarker measurements from study-specific local laboratories (local measurements), A vector representing other covariates. It is assumed that for all samples in the study, the local measurement of the biomarker is available, but only a subset of samples have reference measurements For research A single , indicates that the reference measurement value is available, otherwise .

[0080] Assuming reference measurement value The distribution of The distribution of was heterogeneous across studies. In addition, it can be assumed that the results and local measurements are conditionally independent, given a reference measurement , which means the probability: ; For convenience, it was assumed that the covariates had no effect on study-specific measurement bias, i.e. In addition, the likelihood function containing all samples can be expressed as follows: ; in, ; For convenience, Represents the set of all parameters, which are introduced below. It is research The total number of samples. Further referring to the assumption of conditional independence 1, we can derive the following equation: ; It can be observed that the likelihood function consists of three components, namely, the biomarker-disease association , reference-local measurement correlation , and the reference prior .

[0081] A logistic regression model with a random intercept term was used to describe the association between biomarkers and disease as follows: ; in, To study the specific intercept, is the inverse of the logit function. Our main purpose is to estimate , which is the logarithm of the odds ratio (OR), describes the relationship between the biomarker and the disease.

[0082] The model used to describe the reference-local measurement relationship is called the calibration model. and local measurements There is a linear correlation between and All obey normal distribution, then: ; and, ; , , , , , , and Can be seen as Now, the likelihood function can be fully expressed.

[0083] Since the likelihood function involves the unknown , the use of maximum likelihood estimation introduces challenging integral calculations. In addition, the hierarchical structure of biological specimens is not incorporated into the estimation of parameters. Therefore, a Bayesian approach is chosen to obtain The posterior distribution of . In the Bayesian method, Treated as a latent variable, it can be transformed into an estimable quantity by constructing an appropriate prior distribution. Similarly, the hierarchical structure can also be reflected in The pre-setting of parameters such as can improve the efficiency of estimation.

[0084] 2. Then perform prior distribution.

[0085] Simply put, assuming and The joint prior distribution of is factorized and independent of ,Right now: ; Since the reference measurements are assumed to be consistent across studies, and should be identically distributed. Therefore, and are not independent. Based on the assumption of normal distribution, the prior distribution of these three variables can be expressed as: ; and It can be set according to the reference measurement value in the actual scene, or a conjugate prior (normal and inverse gamma distribution) can be used. In our study, a non-informative prior is placed, specifically: ; for and , it is recommended to use informative priors or weakly informative priors to preserve power and avoid severe instability. For example, using a standard normal distribution, as follows: ; in, and is the number of covariates.

[0086] For specific study parameters , , and , assuming that any vectors between them are sampled from a common distribution. This corresponds to a "random effects" model. However, in a Bayesian framework, there is no need to assume that the trials are sampled from a superpopulation. Instead, it is replaced by the qualitative assumption of "exchangeability", which means that there is no reason to believe that the studies are systematically different. Here, we continue with the simplest assumption that the parameters of each study are independent samples from a superpopulation distribution controlled by some unknown hyperparameter. For and , the population distribution is normal distribution, as follows:

[0087] And for , which is an inverse gamma distribution, as follows: ; in, , , , , , , and is the corresponding hyperparameter, which is also considered to be part of the unknown parameters. express Follows the inverse gamma distribution, as follows: ; and and Similar to the prior distribution of , we propose to assign an appropriate weakly informative prior to these hyperparameters. and A standard normal distribution can be used, as follows: ; for , , , , you can use the semi-Cauchy distribution version as follows: .

[0088] 3. Finally, perform parameter estimation.

[0089] According to the Bayesian formula, the unnormalized joint posterior distribution of the unknown parameters and the reference measurement values ​​can be obtained as follows: ; Using Markov Chain Monte Carlo (MCMC) methods, such as NUT (without U-type sampler)6, it is possible to sample from this distribution. Based on the MCMC sampler, the sample mean can be calculated as a point estimate of the parameter, and the 95% highest posterior density interval can be calculated as an interval estimate. Thus, the posterior distribution of the association between the biomarker and the cancer disease can be obtained.

[0090] This example uses Bayesian techniques to aggregate biomarker data from multiple research sources, treating reference measurements of biospecimens that have not been reanalyzed as unobservable latent variables. A two-level study-biospecimen model is built to describe the relationship between reference measurements, local measurements, and outcomes. Through this model, the posterior distribution of biomarker-disease associations is estimated, providing a powerful framework for integrating biomarker data for cancer diseases.

[0091] Reference Figure 4 The genomics-based biomarker screening method of the present application is implemented by a genomics-based biomarker screening system. Figure 4 This is a schematic diagram of the functional modules of the genomics-based biomarker screening system of the present application embodiment. The system includes: The sequencing data module 10 is used to determine the biomarker expression data related to the significant genes according to the transcriptome sequencing data of the cancer disease biological sample, wherein the transcriptome sequencing data is obtained based on functional genomics and clinical genomics.

[0092] It should be noted that cancer disease biological samples are various biological materials related to cancer.

[0093] Exemplarily, biological samples of cancer diseases may include tissue specimens (such as tumor tissue, adjacent cancer tissue), blood (such as whole blood, plasma, serum), body fluids (such as urine, cerebrospinal fluid, pleural effusion, etc.), and cells (such as circulating tumor cells, etc.) obtained from cancer patients.

[0094] It should be noted that transcriptome sequencing data is data obtained by sequencing RNA transcribed from cancer disease biological samples under specific conditions.

[0095] For example, the transcription process may include messenger RNA (mRNA), ribosomal RNA (rRNA), transfer RNA (tRNA) and other non-coding RNAs, etc. Transcription sequencing can be used to comprehensively and quantitatively analyze the expression of genes in biological samples of cancer diseases.

[0096] It should be noted that biomarker expression data refers to gene data in transcriptome sequencing data that is closely related to cancer diseases and can significantly express biomarkers.

[0097] It should be noted that functional genomics is the study of gene functions, including gene expression regulation, the function of gene products, and the interaction between genes.

[0098] Clinical genomics is the application of genomics technology and research results to clinical practice, involving the use of genomic information to diagnose diseases, predict disease prognosis, etc.

[0099] Constructing transcriptome sequencing data through the standards of functional genomics and clinical genomics can better understand the molecular mechanisms and individual differences of cancer diseases, provide important support for the screening of biomarkers for cancer diseases and their application in medical treatment, and achieve more accurate and effective screening of biomarkers.

[0100] In one embodiment, transcription amplification can be performed on cancer disease biological samples first, and then transcriptome sequencing data can be obtained based on the standards of functional genomics and clinical genomics. The screening system can screen the associated features of the cancer disease based on these data to obtain biomarker expression data of significant genes that are closely related to the cancer disease.

[0101] The posterior distribution module 20 is used to estimate the posterior distribution of the association between the biomarker and the cancer disease through a logistic regression model based on the biomarker expression data of the significant gene.

[0102] It should be noted that the logistic regression model is a statistical analysis model used to solve binary (or multi-classification) problems. The logistic regression model can be used to describe the association between biomarkers and cancer diseases to determine the association between biomarkers and cancer diseases.

[0103] It should be noted that biomarkers are biochemical molecules that can mark changes or possible changes in systems, organs, tissues, cells, subcellular and genetic structures. Biomarkers can help to diagnose cancer diseases more accurately.

[0104] It should be noted that the posterior distribution is a probability distribution of the association between biomarkers and cancer diseases. Through the posterior distribution, we can deeply understand the role of biomarkers in cancer occurrence and its uncertainty.

[0105] In one embodiment, the biomarker expression data can be used as an input variable and combined with relevant information of the cancer disease. The degree of association between the biomarker and the cancer disease is probabilistically described through a logistic regression model to obtain the posterior distribution of the association between the biomarker and the cancer disease.

[0106] The interaction module 30 is used to determine the significant interacting genes in the cancer disease biological sample according to the posterior distribution and the gene interaction network.

[0107] It should be noted that the gene interaction network is a complex network structure formed by various interaction relationships between numerous genes.

[0108] In organisms, genes do not exist and function in isolation. The expression and function of a gene may be affected by other genes, and there may be multiple interactions between them, such as synergy and antagonism. These interactions are intertwined to form a huge network.

[0109] It should be noted that significantly interacting genes are genes that have particularly prominent interaction relationships in biological samples of cancer diseases and may play a key role in the occurrence and development of cancer.

[0110] For example, in cancer samples, the interactions of certain genes may change significantly, such as the synergistic or antagonistic effects between them being enhanced or weakened in the cancer state, and these genes can be considered to have significant interactions in the cancer. Through the gene interaction network, we can better understand the interactions between genes and reveal the associations and synergistic patterns between genes that play a key role in the occurrence and development of cancer.

[0111] In one embodiment, based on the posterior distribution of the association between biomarkers and cancer diseases, combined with the gene interaction network, genes with particularly prominent interaction relationships and key roles in the occurrence and development of cancer can be found. This provides an important basis for accurately screening biomarkers related to cancer diseases and helps discover new biomarkers.

[0112] The marker screening module 40 is used to screen and obtain a list of biomarkers related to cancer diseases based on the significantly interacting genes.

[0113] It should be noted that the biomarker list is a list of biomarkers related to cancer diseases. Through the biomarker list, we can better understand the relationship between biomarkers and cancer diseases, which is helpful for the diagnosis of diseases.

[0114] In one embodiment, the significantly interacting genes obtained above can be arranged in the order of interaction degree or classified according to different physiological functions, and a list of biomarkers related to cancer diseases can be obtained by screening.

[0115] This embodiment provides a biomarker screening system based on genomics. First, transcription amplification can be performed on biological samples of cancer diseases, and then transcriptome sequencing data can be obtained according to the standards of functional genomics and clinical genomics. The screening system can screen the associated features of cancer diseases based on these data to obtain biomarker expression data of significant genes closely associated with cancer diseases. Then, the biomarker expression data can be used as an input variable, combined with relevant information of cancer diseases, and the degree of association between biomarkers and cancer diseases can be probabilistically described through a logistic regression model to obtain the posterior distribution of the association between biomarkers and cancer diseases. Then, based on the posterior distribution of the association between biomarkers and cancer diseases, combined with the gene interaction network, genes with particularly prominent interaction relationships and key roles in the occurrence and development of cancer can be found. This provides an important basis for accurately screening biomarkers related to cancer diseases and helps to discover new biomarkers. Finally, the above-mentioned significantly interacting genes can be arranged in the order of the degree of interaction or the classification of different physiological functions to screen and obtain a list of biomarkers related to cancer diseases. Since this embodiment uses transcriptome sequencing data of cancer disease biological samples to screen out the posterior distribution of biomarkers associated with cancer diseases and significantly interacting genes, it avoids the situation of missed detection due to low specificity of biomarkers in the traditional biomarker screening process, thereby obtaining a list of biomarkers with high correlation with cancer diseases, thereby improving the sensitivity of the biomarker screening process.

[0116] Based on the first embodiment of the system of the present application, a second embodiment of the system of the present application is proposed. In the second embodiment of the present application, the same or similar contents as those of the above-mentioned embodiment 1 can be referred to the above introduction and will not be repeated in the following.

[0117] The sequencing data module 10 in this example is also used to obtain various types of cancer disease biological samples.

[0118] The sequencing data module 10 is also used to perform transcription amplification on the cancer disease biological sample, and to obtain transcriptome sequencing data by sequencing based on functional genomics and clinical genomics.

[0119] It should be noted that transcription amplification is the process of increasing the number of RNA transcripts in a sample through specific technical means, and then sequencing and analyzing the samples after transcription amplification. The sequencing process is to determine the sequence information of these RNA molecules, and then screen the sequence information based on functional genomics and clinical genomics to obtain transcriptome sequencing data.

[0120] The sequencing data module 10 is also used to perform cluster screening on the transcriptome sequencing data to obtain biomarker expression data related to significant genes.

[0121] In this embodiment, biological samples related to cancer diseases (such as cancer cells, cancer tissues, etc.) can be subjected to transcription amplification. Then, the samples after transcription amplification are sequenced and analyzed to determine the sequence information of RNA molecules in the samples. Then, screening is performed based on functional genomics and clinical genomics to obtain transcriptome sequencing data. In this way, through the standards of functional genomics and clinical genomics, the molecular mechanisms and individual differences of cancer diseases can be better understood, and important support can be provided for the screening of biomarkers for cancer diseases and their application in medical treatment, so as to achieve more accurate and effective screening of biomarkers.

[0122] In another feasible implementation, the sequencing data module 10 described in this embodiment is also used to perform preliminary screening of the transcriptome sequencing data according to the gene expression level to obtain gene difference data; the sequencing data module 10 is also used to perform association test based on the gene difference data to obtain the gene difference data after the association test; the sequencing data module 10 is also used to perform feature screening on the gene difference data after the association test through a hierarchical clustering algorithm to obtain the hierarchical association results between genes and cancer diseases; the sequencing data module 10 is also used to determine the biomarker expression data related to the significant genes based on the hierarchical association results.

[0123] It should be noted that the genetic difference data are obtained by preliminary difference screening based on gene expression levels (for example, comparing the gene expression levels of diseased and healthy individuals).

[0124] Specifically, by comparing the differences in gene expression levels under different conditions (such as normal tissue and cancer tissue), genes with significant changes (increased or decreased) in expression levels are screened out, and these genes form gene difference data.

[0125] It should be noted that the association test is a process of testing based on the criteria of significant association with cancer disease after preliminary difference screening.

[0126] It should be noted that the hierarchical clustering algorithm is a clustering analysis method, and its basic idea is to form a hierarchical clustering result by gradually merging or splitting samples or data points. The hierarchical clustering algorithm can further hierarchically aggregate the data that are strongly associated with the cancer disease state in the genetic difference data after the association test, construct a hierarchical clustering tree structure, and intuitively display the hierarchical relationship between samples and genes in the genetic difference data after the association test, and obtain a hierarchical association result.

[0127] In this embodiment, the transcriptome sequencing data can be preliminarily screened for differences based on gene expression levels (e.g., comparing the gene expression levels of diseased and healthy individuals) to obtain gene difference data. Then, after the preliminary difference screening, an association test is performed based on the standard that is significantly associated with cancer disease to obtain gene difference data after the association test. Finally, the gene difference data after the association test is feature screened by a hierarchical clustering algorithm, and the data that is strongly associated with the cancer disease state in the gene difference data after the association test is further hierarchically aggregated to construct a hierarchical clustering tree structure, intuitively displaying the hierarchical relationship between samples and genes in the gene difference data after the association test, and obtaining hierarchical association results to determine the biomarker expression data associated with significant genes. Thus, the distribution and structural characteristics of the hierarchical relationship between cancer samples and genes can be better understood through the hierarchical clustering algorithm to improve the accuracy of obtaining biomarker expression data.

[0128] The genomics-based biomarker screening system provided by the present application adopts the genomics-based biomarker screening method in the above-mentioned embodiment, which can solve the shortcomings of low biomarker specificity and low screening sensitivity in the traditional biomarker screening process, which easily leads to missed detection and technical problems such as missed diagnosis or delayed diagnosis of patients. Compared with the prior art, the beneficial effects of the genomics-based biomarker screening system provided by the present application are the same as the beneficial effects of the genomics-based biomarker screening method provided by the above-mentioned embodiment, and the other technical features of the genomics-based biomarker screening system are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0129] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the genomics-based biomarker screening method and system of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0130] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A biomarker screening method based on genomics, characterized in that: The method includes: Determining biomarker expression data associated with significant genes based on transcriptome sequencing data of cancer disease biological samples, wherein the transcriptome sequencing data is obtained based on functional genomics and clinical genomics; Based on the biomarker expression data of the significant genes, estimating the posterior distribution of the association between the biomarker and the cancer disease through a logistic regression model; According to the posterior distribution and the gene-gene interaction network, determining the significant interacting genes in the cancer disease biological sample; Based on the significantly interacting genes, a list of biomarkers associated with cancer diseases was screened and obtained.

2. The method according to claim 1, characterized in that The step of determining biomarker expression data associated with significant genes based on transcriptome sequencing data of cancer disease biological samples comprises: Obtain biospecimens for various types of cancer diseases; Performing transcription amplification on the cancer disease biological sample, and sequencing to obtain transcriptome sequencing data based on functional genomics and clinical genomics; The transcriptome sequencing data are clustered and screened to obtain biomarker expression data associated with significant genes.

3. The method according to claim 2, characterized in that The step of clustering and screening the transcriptome sequencing data to obtain biomarker expression data associated with significant genes comprises: Preliminarily screening the transcriptome sequencing data according to gene expression levels to obtain gene difference data; Performing an association test based on the gene difference data to obtain the gene difference data after the association test; Performing feature screening on the gene difference data after the association test by a hierarchical clustering algorithm to obtain hierarchical association results between genes and cancer diseases; According to the hierarchical association results, biomarker expression data associated with significant genes are determined.

4. The method according to claim 1, characterized in that The step of estimating the posterior distribution of the association between the biomarker and the cancer disease by a logistic regression model based on the biomarker expression data of the significant genes comprises: Based on the biomarker expression data of the significant genes, using a logistic regression model to describe the association between the biomarker and the cancer disease; The posterior distribution of the association between biomarkers and cancer diseases was obtained by unnormalizing the association between biomarkers and cancer diseases through Bayesian methods.

5. The method according to any one of claims 1 to 4, characterized in that The step of determining the significant interacting genes in the cancer disease biological sample according to the posterior distribution and the gene interaction network comprises: According to the posterior distribution and the gene-gene interaction network, determining the significant interactions of genes in the cancer disease state and the normal state; According to the significant interactions, the significantly interacting genes in the cancer disease biological sample are determined.

6. The method according to any one of claims 1 to 4, characterized in that The step of screening and obtaining a list of biomarkers associated with cancer diseases based on the significantly interacting genes comprises: Performing feature importance evaluation on the significantly interacting genes to obtain importance scores; Sorting the importance scores to obtain a score list; The significantly interacting genes are screened based on the score list to obtain a list of biomarkers associated with cancer diseases.

7. The method according to claim 6, characterized in that The step of evaluating the feature importance of the significantly interacting genes to obtain importance scores comprises: Initialize the gradient boosting decision tree model; Training the gradient boosting decision tree model using a cancer gene database; The feature importance of the significantly interacting genes was evaluated according to the trained gradient boosting decision tree model to obtain importance scores.

8. A genomics-based biomarker screening system, characterized in that: The system comprises: A sequencing data module, used to determine biomarker expression data associated with significant genes based on transcriptome sequencing data of cancer disease biological samples, wherein the transcriptome sequencing data is obtained based on functional genomics and clinical genomics; A posterior distribution module, for estimating the posterior distribution of the association between the biomarker and the cancer disease through a logistic regression model based on the biomarker expression data of the significant gene; An interaction module, for determining significant interacting genes in a cancer disease biological sample based on the posterior distribution and the gene-gene interaction network; The marker screening module is used to screen and obtain a list of biomarkers related to cancer diseases based on the significantly interacting genes.

9. The system according to claim 8, characterized in that The sequencing data module is also used to obtain various types of cancer disease biological samples; The sequencing data module is also used to perform transcription amplification on the cancer disease biological sample, and to sequence and obtain transcriptome sequencing data based on functional genomics and clinical genomics; The sequencing data module is also used to perform cluster screening on the transcriptome sequencing data to obtain biomarker expression data related to significant genes.

10. The system according to claim 9, characterized in that The sequencing data module is also used to perform preliminary screening on the transcriptome sequencing data according to gene expression levels to obtain gene difference data; The sequencing data module is further used to perform an association test based on the gene difference data to obtain the gene difference data after the association test; The sequencing data module is also used to perform feature screening on the gene difference data after the association test by a hierarchical clustering algorithm to obtain a hierarchical association result between genes and cancer diseases; The sequencing data module is also used to determine biomarker expression data associated with significant genes based on the hierarchical association results.

Images