Predisease state detection method and device, electronic equipment and readable storage medium

Abstract

The invention provides a pre-disease state detection method and device, electronic equipment and a readable storage medium, and relates to the field of analysis and detection.The method comprises the steps that dynamic network markers related to the disease state of a target disease are obtained, the dynamic network markers comprise the size of a regulation and control network between a transcription factor and messenger RNA in each disease state, and the size of the regulation and control network is obtained; the disease state is used for representing the development stage of the target disease; and obtaining an effective information value of the dynamic network marker corresponding to each disease state, and determining whether the disease state is a pre-disease state of the target disease based on the effective information value. According to the method, samples of other states are utilized to construct a gene regulation and control network, and effective information numerical values in a causal emergence theory are used as standards for judging whether the disease state is the pre-disease state, so that the pre-disease state is identified more stably and more accurately.

Description

Technical Field

[0001] The present invention relates to the field of analysis and detection, and in particular to a method, device, electronic device and readable storage medium for detecting a pre-disease state. Background Art

[0002] Complex diseases are the result of the combined effects of genetic and environmental factors that lead to an imbalance in the body. A large number of clinical studies have found that complex diseases do not occur in a gradual manner, but in a mutational manner. That is to say, a relatively stable state (such as a normal state) will quickly enter another relatively stable state (disease state) after passing a critical point (such as a pre-disease state). Therefore, the evolution of complex diseases can be divided into three states: a relatively stable normal state, a pre-disease state characterized by decreased recovery ability and increased susceptibility, and a relatively stable disease state. Among them, the pre-disease state is a reversible state. If it is well treated early, the state will return to the normal state, otherwise it will deteriorate into a disease state.

[0003] Currently, pre-disease states can be detected through dynamic network biomarkers (DNBs) from a single sample of a specific state.

[0004] However, only a single sample of a specific state will result in a lack of reference to control samples or samples of other states when testing the previous disease state, which in turn leads to insufficient stability and accuracy in testing the previous disease state. Summary of the invention

[0005] The object of the present invention is to address the deficiencies in the above-mentioned prior art and provide a detection method, device, electronic device and readable storage medium for a pre-disease state, which can determine whether a disease state is a pre-disease state through valid information values ​​corresponding to dynamic network markers related to multiple disease states.

[0006] To achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0007] In a first aspect, the present invention provides a method for detecting a pre-disease state, comprising: obtaining dynamic network markers associated with the disease state of a target disease, the dynamic network markers including the size of a regulatory network between transcription factors and messenger RNA in each disease state, the disease state being used to indicate the development stage of the target disease; obtaining an effective information value of the dynamic network marker corresponding to each disease state, and determining whether the disease state is a pre-disease state of the target disease based on the effective information value.

[0008] In some embodiments, obtaining a dynamic network marker associated with a disease state of a target disease includes: obtaining first sample data associated with the disease state of the target disease, the first sample data including expression spectrum data of a transcription factor and expression spectrum data of a messenger RNA; identifying, based on the first sample data, a regulatory relationship between the transcription factor and the messenger RNA in each disease state; obtaining a state-specific network between the transcription factor and the messenger RNA based on the identified multiple regulatory relationships, the state-specific network being used to represent the regulatory relationship between the transcription factor and the messenger RNA corresponding to each disease state; and obtaining a dynamic network marker based on the state-specific network.

[0009] In some embodiments, the first sample data includes disease states corresponding to transcription factors and messenger RNAs; based on the first sample data, identifying the regulatory relationship between the transcription factors and messenger RNAs in each disease state, including: obtaining the second sample data based on the first sample data, the disease states corresponding to the transcription factors and messenger RNAs being removed from the second sample data; obtaining a first correlation matrix and a second correlation matrix of the transcription factors and messenger RNAs between the first sample data and the second sample data, the first correlation matrix being used to represent the strength of the correlation between the transcription factors and messenger RNAs before the disease states are removed, and the first correlation matrix being used to represent the strength of the correlation between the transcription factors and messenger RNAs after the disease states are removed; obtaining a third correlation matrix between the transcription factors and messenger RNAs and each disease state based on the first correlation matrix and the second correlation matrix, the third correlation matrix being used to represent the strength of the correlation between each disease state and the transcription factors and messenger RNAs; and determining whether there is a regulatory relationship between the transcription factors and messenger RNAs in each disease state based on the third correlation matrix.

[0010] In some embodiments, based on the third correlation matrix, determining whether there is a regulatory relationship between the transcription factor and the messenger RNA in each disease state includes: normalizing the third correlation matrix to obtain a fourth correlation matrix, the fourth correlation matrix being used to represent the normalized correlation strength between each disease state and the transcription factor and the messenger RNA; determining in the fourth correlation matrix that the normalized correlation strength that meets a preset condition corresponds to the existence of a regulatory relationship between the transcription factor and the messenger RNA in the corresponding disease state.

[0011] In some embodiments, the preset condition includes: a significance value corresponding to the normalized correlation strength is less than a preset threshold.

[0012] In some embodiments, dynamic network markers are obtained based on state-specific networks, including: determining whether the transcription factors and messenger RNAs in the state-specific network are target transcription factors or target messenger RNAs through the cumulative probability of Poisson distribution; extracting the regulatory network between the transcription factors and messenger RNAs of each disease state from the state-specific network based on the target transcription factors and target messenger RNAs; and obtaining dynamic network markers based on the size of the regulatory network.

[0013] In some embodiments, effective information values ​​of dynamic network markers corresponding to each disease state are obtained, and based on the effective information values, it is determined whether the disease state is a pre-disease state of the target disease, including: calculating the effective information values ​​of the regulatory network between transcription factors and messenger RNA corresponding to each disease state through causal emergence theory according to the dynamic network markers; obtaining normalized effectiveness parameters of the regulatory network between transcription factors and messenger RNA according to the effective information values; and determining that the disease state corresponding to the maximum value of multiple effectiveness parameters is the pre-disease state of the target disease.

[0014] In the first aspect, whether a disease state is a pre-disease state is determined by valid information values ​​corresponding to dynamic network markers related to multiple disease states. By using samples of other states to construct a gene regulatory network, and using the valid information values ​​in the causal emergence theory as the standard for judging whether a disease state is a pre-disease state, a more stable and accurate identification of pre-disease states is achieved.

[0015] In a second aspect, the present invention provides a detection device for a pre-disease state, which features include: an acquisition module for acquiring dynamic network markers related to the disease state of a target disease, the dynamic network markers including a regulatory network between transcription factors and messenger RNA of each disease state, and the disease state is used to indicate the development stage of the target disease; a determination module for acquiring a valid information value of the dynamic network marker corresponding to each disease state, and determining whether the disease state is a pre-disease state of the target disease based on the valid information value.

[0016] In some embodiments, the acquisition module is specifically used to obtain first sample data related to the disease state of the target disease, the first sample data including expression spectrum data of transcription factors and expression spectrum data of messenger RNA; according to the first sample data, the regulatory relationship between the transcription factor and the messenger RNA in each disease state is identified; based on the identified multiple regulatory relationships, a state-specific network between the transcription factor and the messenger RNA is obtained, the state-specific network is used to represent the regulatory relationship between the transcription factor and the messenger RNA corresponding to each disease state; and dynamic network markers are obtained according to the state-specific network.

[0017] In some embodiments, the first sample data includes disease states corresponding to transcription factors and messenger RNAs; an acquisition module is specifically used to acquire second sample data based on the first sample data, wherein the disease states corresponding to the transcription factors and messenger RNAs are removed from the second sample data; a first correlation matrix and a second correlation matrix of transcription factors and messenger RNAs are acquired between the first sample data and the second sample data, the first correlation matrix being used to represent the strength of the correlation between the transcription factors and messenger RNAs before the disease states are removed, and the first correlation matrix being used to represent the strength of the correlation between the transcription factors and messenger RNAs after the disease states are removed; a third correlation matrix between the transcription factors and messenger RNAs and each disease state is acquired based on the first correlation matrix and the second correlation matrix, the third correlation matrix being used to represent the strength of the correlation between each disease state and the transcription factors and messenger RNAs; and based on the third correlation matrix, determining whether there is a regulatory relationship between the transcription factors and messenger RNAs in each disease state.

[0018] In some embodiments, the acquisition module is specifically used to normalize the third correlation matrix to obtain a fourth correlation matrix, and the fourth correlation matrix is ​​used to represent the normalized correlation strength between each disease state and the transcription factor and the messenger RNA; determine in the fourth correlation matrix, the transcription factor and the messenger RNA corresponding to the normalized correlation strength that meets the preset conditions have a regulatory relationship under the corresponding disease state.

[0019] In some embodiments, the preset condition includes: a significance value corresponding to the normalized correlation strength is less than a preset threshold.

[0020] In some embodiments, dynamic network markers are obtained based on state-specific networks, including: determining whether the transcription factors and messenger RNAs in the state-specific network are target transcription factors or target messenger RNAs through the cumulative probability of Poisson distribution; extracting the regulatory network between the transcription factors and messenger RNAs of each disease state from the state-specific network based on the target transcription factors and target messenger RNAs; and obtaining dynamic network markers based on the size of the regulatory network.

[0021] In some embodiments, the determination module is specifically used to calculate the effective information value of the regulatory network between transcription factors and messenger RNA corresponding to each disease state according to dynamic network markers through causal emergence theory; according to the effective information value, obtain the normalized effectiveness parameter of the regulatory network between transcription factors and messenger RNA; determine the disease state corresponding to the maximum value among multiple effectiveness parameters as the pre-disease state of the target disease.

[0022] In a third aspect, the present invention provides an electronic device comprising a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the storage medium communicate via the bus, and the processor executes the machine-readable instructions to execute the method provided in the first aspect.

[0023] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method provided in the first aspect is executed.

[0024] The beneficial effects of the second to fourth aspects can be referred to the first aspect and will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 A schematic flow chart of a method for detecting a pre-disease state provided in an embodiment of the present application is shown;

[0027] Figure 2 A schematic diagram of a process for obtaining dynamic network markers related to the disease state of a target disease in a pre-disease state detection method provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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.

[0029] Complex diseases are the result of the combined effects of genetic and environmental factors that lead to an imbalance in the body. A large number of clinical studies have found that complex diseases do not occur in a gradual manner, but in a mutational manner. That is to say, a relatively stable state (such as a normal state) will quickly enter another relatively stable state (disease state) after passing a critical point (such as a pre-disease state). Therefore, the evolution of complex diseases can be divided into three states: a relatively stable normal state, a pre-disease state characterized by decreased recovery ability and increased susceptibility, and a relatively stable disease state. Among them, the pre-disease state is a reversible state. If it receives good early treatment, the state will return to the normal state, otherwise it will deteriorate into a disease state. Therefore, identifying the critical point (i.e., the pre-disease state) in the evolution process of complex diseases is of great scientific significance for the prevention and treatment of complex diseases.

[0030] However, accurately detecting the pre-disease state or critical point of complex diseases is a challenging task. Because before entering the disease state, the changes in the molecular level of different phenotypes (such as molecular biomarkers) are often not obvious or even negligible. As the research continues to deepen, researchers have found that dynamic network biomarkers (DNB) are helpful in detecting pre-disease states and have great advantages over traditional markers (molecular biomarkers and network markers).

[0031] Previous research methods were mainly based on specific state samples, without making full use of control samples or other state sample information to construct gene regulatory networks. Therefore, the constructed gene regulatory networks have limited robustness and accuracy. In addition, the gene regulatory network is essentially a causal regulatory network. However, at the network level, existing research methods do not consider the causal emergence of dynamic networks. Therefore, there is an urgent need to develop new detection methods suitable for single-sample and multi-sample transcriptome data. This detection method needs to be able to simultaneously predict gene regulatory networks at the single-sample and multi-sample levels, as well as consider the causal emergence of gene regulatory networks, which will ultimately help to accurately detect the pre-disease state of complex diseases.

[0032] Based on this, an embodiment of the present invention provides a method for detecting a pre-disease state, comprising: obtaining dynamic network markers related to the disease state of a target disease, the dynamic network markers including the size of a regulatory network between transcription factors and messenger RNA in each disease state, and the disease state is used to indicate the development stage of the target disease; obtaining a valid information value of the dynamic network marker corresponding to each disease state, and determining whether the disease state is a pre-disease state of the target disease based on the valid information value.

[0033] Whether a disease state is a pre-disease state is determined by the effective information values ​​corresponding to the dynamic network markers related to multiple disease states. By using samples of other states to construct a gene regulatory network and using the effective information values ​​in the causal emergence theory as the standard for judging whether a disease state is a pre-disease state, a more stable and accurate identification of pre-disease states is achieved.

[0034] The following is an introduction to the detection method of the flavonoid compounds provided in the embodiments of the present invention for the scavenging effect of active oxygen in living cells in conjunction with the accompanying drawings.

[0035] Figure 1 FIG. 1 is a flow chart of a method for detecting a pre-disease state provided in an embodiment of the present application. Figure 1 As shown, the method may include S101 and S102.

[0036] S101. Obtain dynamic network markers related to the disease state of the target disease. The dynamic network markers include the size of the regulatory network between transcription factors and messenger RNA in each disease state. The disease state is used to indicate the development stage of the target disease.

[0037] Figure 2 A schematic diagram of a process for obtaining dynamic network markers related to the disease state of a target disease in a pre-disease state detection method provided in an embodiment of the present application is shown.

[0038] In some embodiments, reference Figure 2 , obtain dynamic network markers related to the disease state of the target disease, including:

[0039] S1011. Acquire first sample data related to the disease state of the target disease, wherein the first sample data includes expression profile data of transcription factors and expression profile data of messenger RNA.

[0040] In some embodiments, the first sample data may be obtained by preprocessing the transcriptome data of a given target disease. For example, the given transcriptome data may be first subjected to logarithmic transformation, duplicate gene removal, and protein coding retention. Then, according to the prior annotation information, the processed transcriptome data is segmented into transcription factor (TF) expression profile data and messenger RNA (mRNA) expression profile data.

[0041] As an example, the expression profile data corresponding to TF can be expressed by the following formula:

[0042]

[0043] The expression profile data corresponding to mRNA can be expressed by the following formula:

[0044]

[0045] Where s represents the number of samples, q represents the number of TFs in each sample, and p represents the number of mRNAs in each sample. Assuming that there are m disease states k in s samples of TF and mRNA transcriptome data, the m disease states k can be recorded as k∈{s1,s2,…,s k ,…s m}.

[0046] S1012. Based on the first sample data, identify the regulatory relationship between transcription factors and messenger RNA in each disease state.

[0047] S1013. Based on the identified multiple regulatory relationships, a state-specific network between transcription factors and messenger RNA is obtained, and the state-specific network is used to represent the regulatory relationship between the transcription factors and messenger RNA corresponding to each disease state.

[0048] In some embodiments, the first sample data includes disease states corresponding to transcription factors and messenger RNAs. Based on the first sample data, identifying the regulatory relationship between transcription factors and messenger RNAs in each disease state includes: obtaining second sample data based on the first sample data, wherein the disease states corresponding to transcription factors and messenger RNAs are removed from the second sample data. Obtaining a first correlation matrix and a second correlation matrix of transcription factors and messenger RNAs between the first sample data and the second sample data, wherein the first correlation matrix is ​​used to represent the strength of the correlation between transcription factors and messenger RNAs before the disease states are removed, and the first correlation matrix is ​​used to represent the strength of the correlation between transcription factors and messenger RNAs after the disease states are removed. Obtaining a third correlation matrix between transcription factors and messenger RNAs and each disease state based on the first correlation matrix and the second correlation matrix, wherein the third correlation matrix is ​​used to represent the strength of the correlation between each disease state and transcription factors and messenger RNAs. According to the third correlation matrix, determining whether there is a regulatory relationship between transcription factors and messenger RNAs in each disease state.

[0049] In some embodiments, the first correlation matrix and the second correlation matrix of the transcription factor and the messenger RNA between the first sample data and the second sample data are obtained, and the first correlation matrix and the second correlation matrix between the first sample data and the second sample data can be calculated by a network identification method. For example, the network identification method can include at least one of the following three ratio analysis methods: φ(Phit), φ s (Phis) and ρ p (Rhop).

[0050] In some embodiments, a ratio analysis method is used to calculate a metric between two given variables. For example, φ(Phit) and φ s (Phis) can use the distance indicator as a metric, ρ p (Rhop) can use similarity index as a metric.

[0051] In some embodiments, assuming that the two given variables are V i and V j , the three ratio analysis methods are defined as follows:

[0052]

[0053]

[0054] Among them, var is the variance function. Similar to the Pearson correlation coefficient, ρ p The metric is a similarity metric and is naturally symmetric, with a value range of [-1,1]. s The index is a distance index with a value range of [0,∞].

[0055] As an example, the first correlation matrix X (k) It can be expressed by the following formula:

[0056]

[0057] The second correlation matrix Y (k) It can be expressed by the following formula:

[0058]

[0059] in, and They respectively represent the correlation strength between TF(j) and mRNA(i) before and after removing the state k sample. and The larger the absolute value of , the stronger the correlation between TF(j) and mRNA(i).

[0060] In some embodiments, for state k, the correlation strength U between TF(j) and mRNA(i) is (k) (i.e., the strength of the correlation between each disease state k and the transcription factor and messenger RNA) can be represented by a third correlation matrix. For example, the third correlation matrix can be represented by the following formula:

[0061]

[0062] In some embodiments, according to the third correlation matrix, whether there is a regulatory relationship between the transcription factor and the messenger RNA in each disease state can be determined, and the third correlation matrix can be normalized to obtain a fourth correlation matrix, and the fourth correlation matrix is ​​used to represent the normalized correlation strength between each disease state and the transcription factor and the messenger RNA. It is determined in the fourth correlation matrix that the transcription factor and the messenger RNA corresponding to the normalized correlation strength that meets the preset conditions exist a regulatory relationship in the corresponding disease state. As an example, the preset condition may include: the significance value corresponding to the normalized correlation strength is less than a preset threshold.

[0063] In some embodiments, Basically obey the normal distribution. As an example, the normalized correlation strength It can be expressed by the following formula:

[0064]

[0065] Among them, μ (k) and σ (k) Represent the third correlation matrix U (k) The mean and standard deviation of . Then the fourth correlation matrix Z (k) It can be expressed by the following formula:

[0066]

[0067] Among them, each normalized correlation strength Corresponding to a significant p-value, The corresponding significance p value It can be calculated by the following formula:

[0068]

[0069] in, express The pnorm() function is used to calculate the absolute value of a standard normal distribution random number less than The probability p-value. The smaller the p, the more likely it is that there is a regulatory relationship between TF(j) and mRNA(i) in disease state k. As an example, the preset threshold of p can be 0.05.

[0070] In some embodiments, the regulatory relationship between the transcription factor and the messenger RNA corresponding to each identified disease state is integrated to obtain a state-specific network between the transcription factor and the messenger RNA.

[0071] S1014. Acquire dynamic network markers according to the state-specific network.

[0072] In some embodiments, dynamic network markers are obtained based on state-specific networks, including: determining whether the transcription factors and messenger RNAs in the state-specific network are target transcription factors or target messenger RNAs through the cumulative probability of Poisson distribution; extracting the regulatory network between the transcription factors and messenger RNAs of each disease state from the state-specific network based on the target transcription factors and target messenger RNAs; and obtaining dynamic network markers based on the size of the regulatory network.

[0073] In some embodiments, the target transcription factor and the target messenger RNA can be the hub TF and the hub mRNA in the state-specific network. The cumulative probability of Poisson distribution is used to evaluate whether the TF or mRNA is a hub, which can be obtained by the following formula:

[0074]

[0075] Where λ = np, n is the number of genes (including TF and mRNA), t is the number of predicted TF-mRNA regulatory relationships, and C is the number of all possible TF-mRNA regulatory relationships. The smaller the p-value of a gene, the more likely it is to be a hub. As an example, a gene with a p-value less than 0.05 can be determined as a hub.

[0076] In some embodiments, based on the target transcription factor and the target messenger RNA, the regulatory network between the transcription factor and the messenger RNA of each disease state is extracted from the state-specific network, and the following method can be adopted:

[0077] For the state-specific network of m disease state indicators, only the hub TFs and mRNAs that are also the hubs of m state-specific networks are retained. These hub TFs and mRNAs are the conserved hub TFs and mRNAs of m state-specific networks. Based on these conserved hub TFs and mRNAs, the TF-mRNA regulatory network of each state is extracted (the size of each regulatory network is used as a dynamic network marker). For the TF-mRNA regulatory network of each state, the number of TFs and mRNAs is the same, but the TF-mRNA regulatory relationship is different.

[0078] S102, obtaining valid information values ​​of dynamic network markers corresponding to each disease state, and determining whether the disease state is a pre-disease state of the target disease based on the valid information values.

[0079] In some embodiments, the effective information value of the regulatory network between transcription factors and messenger RNA corresponding to each disease state can be calculated based on dynamic network markers through causal emergence theory; based on the effective information value, the normalized effectiveness parameter of the regulatory network between transcription factors and messenger RNA is obtained; and the disease state corresponding to the maximum value among multiple effectiveness parameters is determined as the pre-disease state of the target disease.

[0080] In some embodiments, according to the dynamic network markers, the effective information (EI) value of the regulatory network between the transcription factor and the messenger RNA corresponding to each disease state is calculated by the causal emergence theory, which can be achieved by the following formula:

[0081] EI=H( <W i out >)- <H(W i out )> (Formula 10)

[0082] Among them, W i out Represents a regulatory network, which includes multiple network nodes. The parameter in <> refers to the average value from node i to all nodes, and H refers to entropy, that is, H( <W i out >) represents the entropy of the average value from node i to all nodes in the regulatory network, <H(W i out )> represents the average value of entropy from node i to all nodes in the regulatory network. EI varies with the size of the network, so the effectiveness parameter can be a standardized metric, Effectiveness, which can be used to characterize the causal emergence of the network. As an example, Effectiveness can be obtained by the following formula:

[0083]

[0084] Among them, Effectiveness is the result of normalizing EI by the logarithm of the number of network nodes n.

[0085] In some embodiments, through network causal emergence analysis, the critical point or pre-disease state of the target disease often has an Effectiveness peak. Therefore, the disease state corresponding to the maximum Effectiveness value is the critical point or pre-disease state of the target disease.

[0086] The method provided in this application is further described below through two examples.

[0087] Embodiment 1:

[0088] This embodiment takes the identification of human liver precancerous disease states as an example to illustrate the method provided by the present application.

[0089] In this embodiment, the target disease is liver cancer, and the transcriptome data can be human liver cancer transcriptome data caused by hepatitis C virus collected from the public database GEO (Gene Expression Omnibus, https: / / www.ncbi.nlm.nih.gov / geo / ) (data set number is GSE6764). And human TF prior information is obtained from the CollecTRI database (https: / / github.com / saezlab / CollecTRI).

[0090] After preprocessing the transcriptome data (such as logarithmic transformation, removal of duplicate genes, and retention of protein-coding genes), 1138 TF and 15,140 mRNA expression profile data of 75 liver cancer samples were obtained. and These 75 liver cancer samples included 13 control samples and 62 case samples. The 62 case samples were divided into 7 disease states: cirrhotic liver tissue (10 samples), low-grade dysplastic liver tissue (10 samples), high-grade dysplastic liver tissue (7 samples), very early HCC (8 samples), early HCC (10 samples), advanced HCC (7 samples) and very advanced HCC (10 samples).

[0091] According to the method provided in the present application, the state-specific network of human liver cancer is obtained based on 1138 TFs and 15,140 mRNA transcriptome data R and T of 75 liver cancer samples. In this embodiment, three proportional analysis methods (Phit, Phis and Rhop) are applied to calculate the relationship strength between TF and mRNA before and after removing human liver cancer state k samples. In each human liver cancer state, the significance p threshold of the relationship strength between TF and mRNA is set to 0.05. In each human liver cancer state k, all TF-mRNA regulatory relationships are fused to obtain 7 state-specific networks of human liver cancer, and the number of gene regulatory relationships of human liver cancer in Example 1 is shown in Table 1.

[0092] Table 1

[0093]

[0094] In this embodiment, dynamic network markers of 7 human liver cancer states (cirrhosis liver tissue, low-grade dysplasia liver tissue, high-grade dysplasia liver tissue, very early liver cancer, early liver cancer, intermediate liver cancer, and late liver cancer) were obtained by three ratio analysis methods (Phit, Phis, and Rhop). For example, for the Phit method, the dynamic network markers of the 7 human liver cancer states are 39,292, 37,502, 38,622, 29,928, 30,893, 28,375, and 30,167, respectively. For the Phis method, the dynamic network markers of the 7 human liver cancer states are 53,819, 51,946, 61,331, 42,564, 41,720, 46,228, and 49,151, respectively. For the Rhop method, the dynamic network markers of the seven human liver cancer states were 3137, 4198, 3876, 2719, 1810, 2473 and 1847. The causal emergence efficiency of these dynamic networks (i.e., TF-mRNA regulatory networks) is shown in Table 2.

[0095] Table 2

[0096]

[0097] As shown in Table 2, for the Phit and Phis methods, the very early liver cancer state is predicted to be the critical state of human liver cancer; for the Rhop method, the early liver cancer state is predicted to be the critical state of human liver cancer. This result shows that the critical or pre-disease state of human liver cancer predicted by the dynamic network constructed by most ratio analysis methods (including the Phit and Phis methods) is completely consistent with the research results of previous experimental observations.

[0098] Embodiment 2:

[0099] This example uses the identification of the pre-lymphoma disease state of mice as an example to illustrate the method provided by the present application.

[0100] In this embodiment, the target disease is lymphoma, and the transcriptome data can be mouse lymphoma transcriptome data collected from the public database GEO (Gene Expression Omnibus, https: / / www.ncbi.nlm.nih.gov / geo / ) (dataset number is GSE6136). And the mouse TF prior information is obtained from the CollecTRI database (https: / / github.com / saezlab / CollecTRI).

[0101] After preprocessing the transcriptome data (such as logarithmic transformation, removal of duplicate genes, and retention of protein-coding genes), 934 TF and 12,545 mRNA expression profile data of 26 lymphoma samples were obtained.

[0102] Therefore, in this embodiment, and These 26 lymphoma samples were divided into five states: resting (5 samples), activated (3 samples), lymphoma marginal (6 samples), lymphoma transitional (5 samples) and lymphoma aggressive (7 samples).

[0103] According to the method provided in the present application, a mouse lymphoma state-specific network is obtained based on 934 TFs and 12,545 mRNA transcriptome data R and T of 26 lymphoma samples. In this embodiment, three proportional analysis methods (Phit, Phis and Rhop) are also applied to calculate the relationship strength between TF and mRNA before and after removing the mouse lymphoma state k sample. In each mouse lymphoma state, the significance p threshold of the relationship strength between TF and mRNA is set to 0.05. In each mouse lymphoma state k, all TF-mRNA regulatory relationships are fused to obtain the state-specific network of 5 mouse lymphomas, and the number of mouse lymphoma state-specific gene regulatory relationships in Example 2 is shown in Table 3.

[0104] Table 3

[0105]

[0106] In this embodiment, dynamic network markers of 5 mouse lymphoma states (resting, activated, lymphoma margin, lymphoma transition, lymphoma invasion) were obtained by three ratio analysis methods (Phit, Phis and Rhop). For the Phit method, the dynamic network markers of 5 mouse lymphoma states were 180,758, 239,734, 146,729, 205,938 and 189,554, respectively. For the Phis method, the dynamic network markers of 5 mouse lymphoma states were 218,673, 270,865, 201,766, 237,132 and 211,230, respectively. For the Rhop method, the dynamic network markers of 5 mouse lymphoma states were 26,861, 28,108, 26,534, 24,110 and 27,749, respectively. The causal emergence efficiency of these dynamic networks (i.e., TF-mRNA regulatory networks) is shown in Table 4.

[0107] Table 4

[0108]

[0109]

[0110] As shown in Table 4, for the Phit, Phis, and Rhop methods, the lymphoma edge state was predicted to be the mouse lymphoma critical state. This result shows that the mouse lymphoma critical or pre-disease state predicted by the dynamic network constructed by all proportional analysis methods (including the Phit, Phis, and Rhop methods) is completely consistent with the results of previous experimental observations.

[0111] The results in Example 1 and Example 2 show that the three ratio analysis methods can basically accurately predict the critical or pre-disease state of human liver cancer and mouse lymphoma, which shows that the method proposed in this application can effectively predict the pre-disease state. In summary, the pre-disease state detection method proposed in this application can accurately detect the critical or pre-disease state of the disease, provide technical support for the early intervention treatment of complex human diseases, and have important biological significance.

[0112] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A method for detecting a pre-disease state, characterized in that: include: Acquire a dynamic network marker associated with the disease state of the target disease, wherein the dynamic network marker is used to indicate the size of the regulatory network between transcription factors and messenger RNA in each disease state, and the disease state is used to indicate the development stage of the target disease; The effective information value of the dynamic network marker corresponding to each disease state is obtained, and based on the effective information value, it is determined whether the disease state is a pre-disease state of the target disease.

2. The method according to claim 1, characterized in that The step of obtaining dynamic network markers related to the disease state of the target disease includes: Acquiring first sample data related to the disease state of the target disease, wherein the first sample data includes expression profile data of transcription factors and expression profile data of the messenger RNA; identifying, according to the first sample data, the regulatory relationship between the transcription factor and the messenger RNA in each of the disease states; Based on the identified multiple regulatory relationships, a state-specific network between the transcription factor and the messenger RNA is obtained, wherein the state-specific network is used to represent the regulatory relationship between the transcription factor and the messenger RNA corresponding to each disease state; The dynamic network marker is obtained according to the state-specific network.

3. The method according to claim 2, characterized in that The first sample data includes the disease status corresponding to the transcription factor and the messenger RNA; The step of identifying the regulatory relationship between the transcription factor and the messenger RNA in each disease state according to the first sample data includes: Acquire second sample data according to the first sample data, wherein the disease state corresponding to the transcription factor and the messenger RNA is removed from the second sample data; Obtaining a first correlation matrix and a second correlation matrix between the transcription factor and the messenger RNA between the first sample data and the second sample data, wherein the first correlation matrix is ​​used to represent the strength of the correlation between the transcription factor and the messenger RNA before the disease state is removed, and the first correlation matrix is ​​used to represent the strength of the correlation between the transcription factor and the messenger RNA after the disease state is removed; Obtaining a third correlation matrix between the transcription factor and the messenger RNA and each of the disease states according to the first correlation matrix and the second correlation matrix, wherein the third correlation matrix is ​​used to represent the strength of the correlation relationship between each of the disease states and the transcription factor and the messenger RNA; According to the third correlation matrix, it is determined whether there is a regulatory relationship between the transcription factor and the messenger RNA in each of the disease states.

4. The method according to claim 3, characterized in that: Determining whether there is a regulatory relationship between the transcription factor and the messenger RNA in each of the disease states according to the third correlation matrix includes: Normalizing the third correlation matrix to obtain a fourth correlation matrix, wherein the fourth correlation matrix is ​​used to represent the normalized correlation strength between each of the disease states and the transcription factors and the messenger RNA; Determine in the fourth correlation matrix that the normalized correlation strength that meets the preset conditions corresponds to a regulatory relationship between the transcription factor and the messenger RNA under the corresponding disease state.

5. The method according to claim 4, characterized in that The preset conditions include: The significance value corresponding to the normalized correlation strength is less than a preset threshold.

6. The method according to any one of claims 2 to 5, characterized in that: The acquiring the dynamic network marker according to the state-specific network comprises: Determining whether the transcription factor and the messenger RNA in the state-specific network are target transcription factors or target messenger RNAs by using the cumulative probability of Poisson distribution; According to the target transcription factor and the target messenger RNA, extracting the regulatory network between the transcription factor and the messenger RNA of each disease state from the state-specific network; The dynamic network marker is obtained according to the size of the regulatory network.

7. The method according to any one of claims 1 to 5, characterized in that: The obtaining of the effective information value of the dynamic network marker corresponding to each disease state, and determining whether the disease state is a pre-disease state of the target disease based on the effective information value, includes: According to the dynamic network markers, the effective information value of the regulatory network between the transcription factor and the messenger RNA corresponding to each disease state is calculated by causal emergence theory; According to the effective information value, obtaining a normalized effective parameter of the regulatory network between the transcription factor and the messenger RNA; The disease state corresponding to the maximum value among the plurality of effectiveness parameters is determined as the pre-disease state of the target disease.

8. A device for detecting a pre-disease state, comprising: An acquisition module, used to acquire dynamic network markers related to the disease state of the target disease, wherein the dynamic network markers include a regulatory network between transcription factors and messenger RNAs of each disease state, and the disease state is used to indicate the development stage of the target disease; The determination module is used to obtain the effective information value of the dynamic network marker corresponding to each disease state, and determine whether the disease state is a pre-disease state of the target disease based on the effective information value.

9. An electronic device, characterized in that: The electronic device comprises a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the storage medium communicate via the bus, and the processor executes the machine-readable instructions to execute any one of the methods of claims 1-7.

10. A computer-readable storage medium, characterized in that: A computer program is stored on a computer-readable storage medium, and when the computer program is executed by a processor, the method of any one of claims 1 to 7 is executed.

Images