CN110853763A - Fusion attribute-based miRNA-disease association identification method and system - Google Patents

Abstract

The invention discloses a miRNA-disease association identification method and system based on fusion attributes. The method comprises the steps of firstly calculating the functional similarity between any two miRNAs in a disease database, constructing an miRNA network undirected graph according to the functional similarity, calculating the aggregation coefficient between any two different miRNAs, and fusing the functional similarity and the aggregation coefficient between the two miRNAs to obtain a combined weight; and calculating the weight of each miRNA vertex according to the combined weight, performing descending sorting on each miRNA according to the weight, and screening out potential miRNAs related to diseases according to the descending sorting result. The method is simple to realize, miRNA nodes are subjected to weighting and descending sequencing on the basis of fusing two attributes of topological attributes and functional similarity, and then the association of potential miRNA and diseases is predicted by means of the disease database related to human miRNA and the sequenced result, so that the accuracy of miRNA-disease association identification is improved, and valuable clues can be provided for medical diagnosis.

Description

Fusion attribute-based miRNA-disease association identification method and system

technical field

The invention relates to the technical field of information biology, in particular to a method and system for identifying miRNA-disease associations based on fusion attributes.

Background technique

miRNAs (microRNAs) are non-coding small RNAs containing about 22 amino acids, which play an important role in the post-transcriptional regulation of gene expression and various biological activities. Studies have demonstrated that miRNA dysfunction is associated with various complex human diseases. Therefore, identifying potential miRNA-disease associations can help to understand the pathogenic mechanism and provide valuable references for medical diagnosis of human diseases. In 2010, Jiang et al. quantified the functional similarity between miRNAs for the first time using the degree of overlap of miRNA target genes, optimized disease-related miRNAs through hypergeometric distribution, and further integrated disease phenotypic similarity and miRNA similarity. to calculate the functional similarity between miRNA pairs.

The researchers propose that miRNAs with similar functions are often associated with similar diseases, and vice versa. Therefore, miRNAs are widely used for disease-miRNA prediction. Professor Chen Xing proposed the RWRMDA (Random Walk with Restart for MiRNA-Disease Association) method, which used the global network information for the first time to discover some candidate disease-related miRNAs through random walks; Xuan et al. used random walks in miRNA functional similarity multithreading. walk model to predict the association between miRNA and disease; based on the functional similarity of miRNA, Professor Luo Jiawei proposed a non-equilibrium bipartite random walk method to predict the association between miRNA and disease in a heterogeneous network in 2017. In 2018, Li et al. used label propagation to predict miRNA-disease associations based on linear neighborhood similarity.

Although various methods have been used to predict the association between miRNAs and diseases, however, some of the existing methods are based only on the functional similarity of miRNA pairs, and some only based on the topological properties of miRNA similarity networks to predict miRNA- associations between diseases. The existing literature shows that it is unrealistic to rely on only one method to construct an absolutely reliable biological network. Existing miRNA-disease association identification methods often predict miRNA-disease associations based on only one attribute, thus leading to inaccurate identification of miRNA-disease associations.

SUMMARY OF THE INVENTION

The purpose of the present invention is to provide a method and system for identifying miRNA-disease associations based on fusion attributes, to predict potential associations between miRNAs and diseases based on topological attributes and functional similarity methods, so as to solve the existing miRNA-disease associations Problems with low accuracy of identification methods.

For achieving the above object, the present invention provides the following scheme:

A fusion attribute-based miRNA-disease association identification method, the method comprising:

Obtain a disease database to be analyzed; the disease database stores multiple disease types and multiple miRNAs;

calculating the functional similarity between any two miRNAs in the disease database;

Constructing an undirected graph of a miRNA network according to the functional similarity between any two miRNAs;

Calculate the aggregation coefficient between any two miRNAs according to the miRNA network undirected graph;

Determine the combined weight between any two miRNAs according to the functional similarity and aggregation coefficient between the any two miRNAs;

Calculate the weight of each miRNA vertex according to the combined weight between the any two miRNAs;

Sort each miRNA in descending order according to the weight of each miRNA vertex;

The potential disease-related miRNAs were screened according to the descending order results.

Optionally, the calculating the functional similarity between any two miRNAs in the disease database specifically includes:

|DT₁|表示与miRNAm1相关联的疾病集的长度，dt_1i表示疾病集DT₁中的第i种疾病；DT₂表示与miRNA m2相关联的疾病集，|DT₂|表示与miRNA m2相关联的疾病集的长度，dt_2j表示疾病集DT₂中的第j种疾病；Sim(dt_1i,DT₂)表示疾病dt_1i与疾病集DT₂之间的相似度，Sim(dt_2j,DT₁)表示疾病dt_2j与疾病集DT₁之间的相似度。using the formula Calculate the functional similarity between any two miRNAs in the disease database; wherein miRNA m1 and miRNA m2 are any two miRNAs in the disease database; MSim(m1, m2) represents the difference between miRNA m1 and miRNA m2. Functional similarity; DT ₁ represents the disease set associated with miRNA m1,

|DT ₁ | represents the length of the disease set associated with miRNAm1, dt _1i represents the ith disease in the disease set DT ₁ ; DT ₂ represents the disease set associated with miRNA m2, |DT ₂ | represents the length of the disease set associated with miRNA m2, dt _2j represents the jth disease in the disease set DT ₂ ; Sim(dt _1i ,DT ₂ ) represents the difference between the disease dt _1i and the disease set DT ₂ Similarity, Sim(dt _2j , DT ₁ ) represents the similarity between the disease dt _2j and the disease set DT ₁ .

Optionally, calculating the aggregation coefficient between any two miRNAs according to the miRNA network undirected graph specifically includes:

Obtain the neighbor node set N _m1 of the miRNA m1 in the undirected graph of the miRNA network, and the neighbor node set N _m2 of the miRNAm2;

using the formula Calculate the aggregation coefficient ECC(m1,m2) between miRNA m1 and miRNA m2; where |N _m1 ∩N _m2 | represents the number of nodes in the intersection of N _m1 and N _m2 ; |N _m1 | represents the number of nodes in N _m1 Number of nodes; |N _m2 | represents the number of nodes in N _m2 .

Optionally, determining the combination weight between any two miRNAs according to the functional similarity and aggregation coefficient between the any two miRNAs specifically includes:

确定所述miRNA m1与miRNA m2之间的组合权重ω(m1,m2)。According to the functional similarity MSim(m1,m2) and the aggregation coefficient ECC(m1,m2) between any two miRNAs, the formula

A combined weight ω(m1, m2) between the miRNA m1 and miRNA m2 is determined.

Optionally, calculating the weight of each miRNA vertex according to the combined weight between any two miRNAs specifically includes:

|V|表示所述加权子图S中miRNA的个数；ω表示所述加权子图S中边的组合权重，即所述加权子图S中任意两个miRNA之间的组合权重。The weight V _ωs of any miRNA vertex V is calculated by the formula V _ωs =km _max ×d _ωs ; where km _max represents the weight of the edge in the weighted subgraph S; the weighted subgraph S is the miRNA vertex V and its direct neighbors a collection of nodes;

|V| represents the number of miRNAs in the weighted subgraph S; ω represents the combined weight of the edges in the weighted subgraph S, that is, the combined weight between any two miRNAs in the weighted subgraph S.

A fusion attribute-based miRNA-disease association identification system, the system includes:

The disease database acquisition module is used to acquire the disease database to be analyzed; the disease database stores multiple disease types and multiple miRNAs;

a functional similarity calculation module for calculating the functional similarity between any two miRNAs in the disease database;

a miRNA network undirected graph building module for constructing a miRNA network undirected graph according to the functional similarity between any two miRNAs;

an aggregation coefficient calculation module, configured to calculate the aggregation coefficient between any two miRNAs according to the miRNA network undirected graph;

an attribute fusion module, configured to determine the combined weight between any two miRNAs according to the functional similarity and aggregation coefficient between the any two miRNAs;

a vertex weight calculation module, configured to calculate the weight of each miRNA vertex according to the combined weight between the any two miRNAs;

a sorting module, configured to sort each miRNA in descending order according to the weight of each miRNA vertex;

Screening module for screening potential disease-related miRNAs according to descending sorting results.

Optionally, the functional similarity calculation module specifically includes:

计算所述疾病数据库中任意两个miRNA之间的功能相似性；其中miRNA m1和miRNA m2为所述疾病数据库中的任意两个miRNA；MSim(m1,m2)表示miRNA m1与miRNA m2之间的功能相似性；DT₁表示与miRNA m1相关联的疾病集，

DT₁表示与miRNA m1相关联的疾病集的长度，dt_1i表示疾病集DT₁中的第i种疾病；DT₂表示与miRNA m2相关联的疾病集，|DT₂|表示与miRNA m2相关联的疾病集的长度，dt_2j表示疾病集DT₂中的第j种疾病；Sim(dt_1i,DT₂)表示疾病dt_1i与疾病集DT₂之间的相似度，Sim(dt_2j,DT₁)表示疾病dt_2j与疾病集DT₁之间的相似度。Functional similarity calculation unit for taking formulas

Calculate the functional similarity between any two miRNAs in the disease database; wherein miRNA m1 and miRNA m2 are any two miRNAs in the disease database; MSim(m1, m2) represents the difference between miRNA m1 and miRNA m2. Functional similarity; DT ₁ represents the disease set associated with miRNA m1,

DT ₁ represents the length of the disease set associated with miRNA m1, dt _1i represents the i-th disease in the disease set DT ₁ ; DT ₂ represents the disease set associated with miRNA m2, |DT ₂ | represents the length of the disease set associated with miRNA m2, dt _2j represents the jth disease in the disease set DT ₂ ; Sim(dt _1i ,DT ₂ ) represents the difference between the disease dt _1i and the disease set DT ₂ Similarity, Sim(dt _2j , DT ₁ ) represents the similarity between the disease dt _2j and the disease set DT ₁ .

Optionally, the aggregation coefficient calculation module specifically includes:

a neighbor node set obtaining unit, configured to obtain the neighbor node set N _m1 of the miRNA m1 and the neighbor node set N _m2 of the miRNA m2 in the undirected graph of the miRNA network;

计算miRNAm1与miRNA m2之间的聚集系数ECC(m1,m2)；其中|N_m1∩N_m2|表示N_m1与N_m2的交集中的结点个数；|N_m1|表示N_m1中的结点个数；|N_m2|表示N_m2中的结点个数。Aggregation coefficient calculation unit for taking formulas

Calculate the aggregation coefficient ECC(m1,m2) between miRNAm1 and miRNA m2; where |N _m1 ∩N _m2 | represents the number of nodes in the intersection of N _m1 and N _m2 ; |N _m1 | represents the nodes in N _m1 The number of points; |N _m2 | represents the number of nodes in N _m2 .

Optionally, the attribute fusion module specifically includes:

确定所述miRNA m1与miRNA m2之间的组合权重ω(m1,m2)。The combined weight calculation unit is used for according to the functional similarity MSim(m1,m2) and the aggregation coefficient ECC(m1,m2) between the any two miRNAs, using the formula

A combined weight ω(m1, m2) between the miRNA m1 and miRNA m2 is determined.

Optionally, the vertex weight calculation module specifically includes:

|V|表示所述加权子图S中miRNA的个数；ω表示所述加权子图S中边的组合权重，即所述加权子图S中任意两个miRNA之间的组合权重。The vertex weight calculation unit is used to calculate the weight V _ωs of any miRNA vertex V by using the formula V _ωs =km _max ×d _ωs ; wherein km _max represents the weight of the edge in the weighted subgraph S; the weighted subgraph S is the The set of miRNA vertices V and its immediate neighbors;

|V| represents the number of miRNAs in the weighted subgraph S; ω represents the combined weight of the edges in the weighted subgraph S, that is, the combined weight between any two miRNAs in the weighted subgraph S.

According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

The present invention provides a method and system for identifying miRNA-disease associations based on fusion attributes. The method first calculates the functional similarity between any two miRNAs in the disease database, and then calculates the functional similarity between any two miRNAs according to the function between any two miRNAs. Similarity constructs a miRNA network undirected graph, calculates the aggregation coefficient between any two miRNAs according to the miRNA network undirected graph, and fuses the functional similarity and aggregation coefficient between the any two miRNAs to obtain the arbitrary The combined weight between the two miRNAs; the weight of each miRNA vertex is calculated according to the combined weight between the any two miRNAs; the respective miRNAs are sorted in descending order according to the weight of each miRNA vertex; according to the descending sorting result Screening potential miRNAs associated with disease. The method of the invention is simple to implement. On the basis of fusing the above two attributes, the miRNA nodes are weighted and sorted in descending order, and then, with the help of the human miRNA-related disease database, the sorted results are used to predict the association between potential miRNAs and diseases , which improves the accuracy of miRNA-disease association identification and can provide valuable clues for medical diagnosis.

Description of drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings required in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some of the present invention. In the embodiments, for those of ordinary skill in the art, other drawings can also be obtained according to these drawings without creative labor.

1 is a flowchart of a fusion attribute-based miRNA-disease association identification method provided by the present invention;

2 is a schematic diagram of a fusion attribute-based miRNA-disease association identification method provided by the present invention;

FIG. 3 is a structural diagram of the fusion attribute-based miRNA-disease association identification system provided by the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

The purpose of the present invention is to provide a method and system for identifying miRNA-disease associations based on fusion attributes, to predict potential associations between miRNAs and diseases based on topological attributes and functional similarity methods, so as to solve the existing miRNA-disease associations Problems with low accuracy of identification methods.

In order to make the above objects, features and advantages of the present invention more clearly understood, the present invention will be described in further detail below with reference to the accompanying drawings and specific embodiments.

FIG. 1 is a flowchart of a fusion attribute-based miRNA-disease association identification method provided by the present invention. FIG. 2 is a schematic diagram of the fusion attribute-based miRNA-disease association identification method provided by the present invention. Referring to FIG. 1 and FIG. 2 , the fusion attribute-based miRNA-disease association identification method provided by the present invention specifically includes:

Step 101: Obtain the disease database to be analyzed.

The disease database stores multiple disease types and multiple miRNAs. Take dbDEMC (Database of Differentially Expressed miRNAs in Tumors) (http://www.picb.ac.cn/dbDEMC) as an example, a comprehensive database designed to detect the presence and display of human cancers by high-throughput methods Differentially expressed miRNAs. The current version contains 2224 differentially expressed miRNAs across 36 cancer types, 49202 miRNA-cancer associations, an enhanced miRNA page is provided to demonstrate basic miRNA descriptions, multiple expression profiles within each analysis type, and Results of relevant analytical experiments and low-throughput validation assays. For a set of miRNAs and multiple cancer types, differential expression profiles are displayed as heatmaps, allowing researchers to explore differences and similarities between cancers.

Step 102: Calculate the functional similarity between any two miRNAs in the disease database.

The functional similarity calculation method is:

|DT₁|表示与miRNA m1相关联的疾病集的长度，dt_1i表示疾病集DT₁中的第i种疾病。DT₂表示与miRNA m2相关联的疾病集，|DT₂|表示与miRNA m2相关联的疾病集的长度，dt_2j表示疾病集DT₂中的第j种疾病。Sim(dt_1i,DT₂)表示疾病dt_1i与疾病集DT₂之间的相似度，Sim(dt_2j,DT₁)表示疾病dt_2j与疾病集DT₁之间的相似度。Formula (1) is used to calculate the functional similarity between any two miRNAs (a pair of miRNAs) in the disease database; wherein miRNA m1 and miRNA m2 are any two different miRNAs in the disease database. MSim(m1,m2) represents the functional similarity between miRNA m1 and miRNA m2. DT ₁ represents the disease set associated with miRNA m1,

|DT ₁ | represents the length of the disease set associated with miRNA m1, and dt _1i represents the ith disease in the disease set DT ₁ . DT ₂ represents the disease set associated with miRNA m2, |DT ₂ | denotes the length of the disease set associated with miRNA m2, and dt _2j denotes the jth disease in the disease set DT ₂ . Sim(dt _1i , DT ₂ ) represents the similarity between the disease dt _1i and the disease set DT ₂ , and Sim(dt _2j , DT ₁ ) represents the similarity between the disease dt _2j and the disease set DT ₁ .

Step 103: Construct an undirected graph of a miRNA network according to the functional similarity between any two miRNAs.

Input the calculated functional similarity network information between each group of miRNA pairs (miRNA m1 and miRNA m2), filter the repeated interactions and self-interactions, and build the miRNA network undirected graph G.

Step 104: Calculate the aggregation coefficient between any two miRNAs according to the miRNA network undirected graph.

Existing miRNA-disease association identification methods often use only one functional similarity calculation to predict the association between miRNA-diseases, resulting in inaccurate identification of miRNA-disease associations. The present invention identifies the association between miRNA and disease based on topological properties and functional similarity, so the identification accuracy is higher. The clustering coefficient calculated in step 104 is the calculated topology attribute.

The aggregation coefficient between miRNA and miRNA can be calculated by the following formula:

ECC(m1,m2) is the edge aggregation coefficient between miRNA m1 and miRNA m2. N _m1 is the set of neighbor nodes of the miRNA m1 in the undirected graph of the miRNA network, and N _m2 is the set of neighbor nodes of the miRNA m2. |N _m1 ∩N _m2 | represents the number of neighbor nodes in the intersection of N _m1 and N _m2 . |N _m1 | represents the number of neighbor nodes in N _m1 ; |N _m2 | represents the number of neighbor nodes in N _m2 . min(N _m1 , N _m2 ) represents the minimum number of neighbor nodes of miRNA m1 and miRNA m2.

Step 105: Determine the combined weight between the any two miRNAs according to the functional similarity and the aggregation coefficient between the any two miRNAs.

The functional similarity and aggregation coefficient of the fusion miRNA pair, the functional similarity and aggregation coefficient of the miRNA pair fusion method can be obtained by the following formula:

where ω(m1,m2) represents the combined weight between miRNA m1 and miRNA m2, which effectively fuses the topological properties and functional similarity of the miRNA functional similarity network. The denominator is increased by 1 to avoid the case of 0.

Step 106: Calculate the weight of each miRNA vertex according to the combined weight between any two miRNAs.

In a weighted subgraph S, the weight of a miRNA vertex V can be calculated by the following formula:

V _ωs =k _max ×d _ωs (4)

表示一个加权子图S的密度。|V|表示所述加权子图S中miRNA的个数。ω表示所述加权子图S中边的组合权重，即所述加权子图S中任意两个miRNA之间的组合权重。∑ω表示对所述加权子图S中所有边的组合权重求和。Among them, V _ωs is the weight of any miRNA vertex V. _kmx represents the weight of the edge in the subgraph S, the weighted subgraph S is the set of the miRNA vertex V and its direct neighbor nodes.

represents the density of a weighted subgraph S. |V| represents the number of miRNAs in the weighted submap S. ω represents the combined weight of the edges in the weighted subgraph S, that is, the combined weight between any two miRNAs in the weighted subgraph S. Σω represents the summation of the combined weights of all edges in the weighted subgraph S.

The calculation of the weight of each miRNA vertex V is the fusion of the previous two topological properties, that is, the weight of each miRNA vertex V is calculated by combining the weights ω(m1, m2).

Step 107: Sort each miRNA in descending order according to the weight of each miRNA vertex.

The weight of each miRNA vertex is calculated by formula (4), and then the miRNAs are sorted in descending order according to the weight of each miRNA vertex, and the potential miRNAs related to the disease are screened according to the ranking.

Step 108: Screen potential miRNAs related to diseases according to the descending order results.

With the help of the human miRNA-related disease database, the ranking results are used to predict the association of potential miRNAs with diseases, screen out potential miRNAs related to diseases, and provide valuable clues for medical diagnosis.

Taking lung cancer-related miRNAs in the PhenomiR2.0 database as an example, the screening results obtained by the method of the present invention are shown in Table 1:

Table 1 Verified miRNA and the screening result comparison table of the present invention

The first column in Table 1 is the miRNAs that have been verified in the PhenomiR2.0 database, the second column TOP30 is the top 30 miRNAs screened by the method of the present invention, and the third column sign indicates whether the 30 miRNAs screened by the present invention are related to Disease-related, with "Y" for related and "N" for not related. From the screening results in Table 1, it can be known that among the 30 miRNAs screened by the method of the present invention, 24 are related to diseases, and only 6 are not related to diseases, and the accuracy rate reaches 24/30*100%=80 %.

The pseudo code of the fusion attribute-based miRNA-disease association identification method of the present invention is as follows:

Table 2 Pseudo code of fusion attribute-based miRNA-disease association identification method

Starting from the biological significance of miRNA, the present invention proposes a method for identifying the association between miRNA and disease based on topological attributes and functional similarity by fusing the edge aggregation coefficient and functional similarity of the miRNA similarity network. The method of the invention is simple to implement. On the basis of fusing the above two attributes, the miRNA nodes are weighted and sorted in descending order, and then, with the help of the human miRNA-related disease database, the sorted results are used to predict the association between potential miRNAs and diseases , which improves the accuracy of miRNA-disease association identification and provides valuable clues for medical diagnosis.

Based on a fusion attribute-based miRNA-disease association identification method provided by the present invention, the present invention also provides a fusion attribute-based miRNA-disease association identification system, see FIG. 3 , the system includes:

The disease database acquisition module 301 is used to acquire the disease database to be analyzed; the disease database stores multiple disease types and multiple miRNAs;

a functional similarity calculation module 302, configured to calculate the functional similarity between any two miRNAs in the disease database;

The miRNA network undirected graph building module 303 is configured to construct a miRNA network undirected graph according to the functional similarity between any two miRNAs;

an aggregation coefficient calculation module 304, configured to calculate the aggregation coefficient between any two miRNAs according to the miRNA network undirected graph;

an attribute fusion module 305, configured to determine the combined weight between the any two miRNAs according to the functional similarity and the aggregation coefficient between the any two miRNAs;

a vertex weight calculation module 306, configured to calculate the weight of each miRNA vertex according to the combined weight between the any two miRNAs;

A sorting module 307, configured to sort each miRNA in descending order according to the weight of each miRNA vertex;

The screening module 308 is used for screening potential miRNAs related to the disease according to the descending order results.

Wherein, the functional similarity calculation module 302 specifically includes:

计算所述疾病数据库中任意两个miRNA之间的功能相似性；其中miRNA m1和miRNA m2为所述疾病数据库中的任意两个miRNA；MSim(m1,m2)表示miRNA m1与miRNA m2之间的功能相似性；DT₁表示与miRNA m1相关联的疾病集，

|DT₁|表示与miRNA m1相关联的疾病集的长度，dt_1i表示疾病集DT₁中的第i种疾病；DT₂表示与miRNA m2相关联的疾病集，

|DT₂|表示与miRNA m2相关联的疾病集的长度，dt_2j表示疾病集DT₂中的第j种疾病；Sim(dt_1i,DT₂)表示疾病dt_1i与疾病集DT₂之间的相似度，Sim(dt_2j,DT₁)表示疾病dt_2j与疾病集DT₁之间的相似度。Functional similarity calculation unit for taking formulas

Calculate the functional similarity between any two miRNAs in the disease database; wherein miRNA m1 and miRNA m2 are any two miRNAs in the disease database; MSim(m1, m2) represents the difference between miRNA m1 and miRNA m2. Functional similarity; DT ₁ represents the disease set associated with miRNA m1,

|DT ₁ | represents the length of the disease set associated with miRNA m1, dt _1i represents the ith disease in the disease set DT ₁ ; DT ₂ represents the disease set associated with miRNA m2,

|DT ₂ | represents the length of the disease set associated with miRNA m2, dt _2j represents the jth disease in the disease set DT ₂ ; Sim(dt _1i ,DT ₂ ) represents the difference between the disease dt _1i and the disease set DT ₂ Similarity, Sim(dt _2j , DT ₁ ) represents the similarity between the disease dt _2j and the disease set DT ₁ .

The aggregation coefficient calculation module 304 specifically includes:

a neighbor node set obtaining unit, configured to obtain the neighbor node set N _m1 of the miRNA m1 and the neighbor node set N _m2 of the miRNA m2 in the undirected graph of the miRNA network;

Aggregation coefficient calculation unit for taking formulas Calculate the aggregation coefficient ECC(m1,m2) between miRNAm1 and miRNA m2; where |N _m1 ∩N _m2 | represents the number of nodes in the intersection of N _m1 and N _m2 ; |N _m1 | represents the nodes in N _m1 The number of points; |N _m2 | represents the number of nodes in N _m2 .

The attribute fusion module 305 specifically includes:

The combined weight calculation unit is used for according to the functional similarity MSim(m1,m2) and the aggregation coefficient ECC(m1,m2) between the any two miRNAs, using the formula A combined weight ω(m1, m2) between the miRNA m1 and miRNA m2 is determined.

The vertex weight calculation module 306 specifically includes:

|V|表示所述加权子图S中miRNA的个数；ω表示所述加权子图S中边的组合权重，即所述加权子图S中任意两个miRNA之间的组合权重。The vertex weight calculation unit is used to calculate the weight V _ωs of any miRNA vertex V by adopting the formula V _ωs =km _max ×d _ωs ; where km _max represents the weight of the edge in the weighted subgraph S; the weighted subgraph S is the The set of miRNA vertices V and its immediate neighbors;

|V| represents the number of miRNAs in the weighted subgraph S; ω represents the combined weight of the edges in the weighted subgraph S, that is, the combined weight between any two miRNAs in the weighted subgraph S.

The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the various embodiments can be referred to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant part can be referred to the description of the method.

In this paper, specific examples are used to illustrate the principles and implementations of the present invention. The descriptions of the above embodiments are only used to help understand the methods and core ideas of the present invention; meanwhile, for those skilled in the art, according to the present invention There will be changes in the specific implementation and application scope. In conclusion, the contents of this specification should not be construed as limiting the present invention.

Claims (10)

1. A fusion attribute-based miRNA-disease association identification method, wherein the method comprises: Obtain a disease database to be analyzed; the disease database stores multiple disease types and multiple miRNAs; calculating the functional similarity between any two miRNAs in the disease database; Constructing an undirected graph of a miRNA network according to the functional similarity between any two miRNAs; Calculate the aggregation coefficient between any two miRNAs according to the miRNA network undirected graph; Determine the combined weight between any two miRNAs according to the functional similarity and aggregation coefficient between the any two miRNAs; Calculate the weight of each miRNA vertex according to the combined weight between the any two miRNAs; Sort each miRNA in descending order according to the weight of each miRNA vertex; Potential disease-related miRNAs were screened according to the results in descending order. 2. The miRNA-disease association identification method according to claim 1, wherein the calculating the functional similarity between any two miRNAs in the disease database specifically comprises: using the formula

Calculate the functional similarity between any two miRNAs in the disease database; wherein miRNA m1 and miRNA m2 are any two miRNAs in the disease database; MSim(m1, m2) represents the difference between miRNA m1 and miRNA m2. Functional similarity; DT ₁ represents the disease set associated with miRNA m1,

|DT ₁ | represents the length of the disease set associated with miRNAm1, dt _1i represents the ith disease in the disease set DT ₁ ; DT ₂ represents the disease set associated with miRNA m2,

|DT ₂ | represents the length of the disease set associated with miRNA m2, dt _2j represents the jth disease in the disease set DT ₂ ; Sim(dt _1i ,DT ₂ ) represents the difference between the disease dt _1i and the disease set DT ₂ Similarity, Sim(dt _2j , DT ₁ ) represents the similarity between the disease dt _2j and the disease set DT ₁ . 3. The miRNA-disease association identification method according to claim 2, wherein the calculation of the aggregation coefficient between any two miRNAs according to the miRNA network undirected graph specifically comprises: obtaining the neighbor node set N _m1 of the miRNA m1 in the undirected graph of the miRNA network, and the neighbor node set N _{m2 of the miRNA m2} ; using the formula

Calculate the aggregation coefficient ECC(m1,m2) between miRNA m1 and miRNA m2; where |N _m1 ∩N _m2 | represents the number of nodes in the intersection of N _m1 and N _m2 ; |N _m1 | represents the number of nodes in N _m1 Number of nodes; |N _m2 | represents the number of nodes in N _m2 . 4. The miRNA-disease association identification method according to claim 3, wherein the combination weight between any two miRNAs is determined according to the functional similarity and aggregation coefficient between the any two miRNAs , including: According to the functional similarity MSim(m1,m2) and the aggregation coefficient ECC(m1,m2) between any two miRNAs, the formula

A combined weight ω(m1, m2) between the miRNA m1 and miRNA m2 is determined. 5. The miRNA-disease association identification method according to claim 4, wherein the calculation of the weight of each miRNA vertex according to the combined weight between the any two miRNAs specifically includes: The weight V _ωs of any miRNA vertex V is calculated by the formula V _ωs =km _max ×d _ωs ; where km _max represents the weight of the edge in the weighted subgraph S; the weighted subgraph S is the miRNA vertex V and its direct neighbors a collection of nodes;

|V| represents the number of miRNAs in the weighted subgraph S; ω represents the combined weight of the edges in the weighted subgraph S, that is, the combined weight between any two miRNAs in the weighted subgraph S. 6. A fusion attribute-based miRNA-disease association identification system, wherein the system comprises: The disease database acquisition module is used to acquire the disease database to be analyzed; the disease database stores multiple disease types and multiple miRNAs; a functional similarity calculation module for calculating the functional similarity between any two miRNAs in the disease database; a miRNA network undirected graph building module for constructing a miRNA network undirected graph according to the functional similarity between any two miRNAs; an aggregation coefficient calculation module, configured to calculate the aggregation coefficient between any two miRNAs according to the miRNA network undirected graph; an attribute fusion module, configured to determine the combined weight between any two miRNAs according to the functional similarity and aggregation coefficient between the any two miRNAs; a vertex weight calculation module, configured to calculate the weight of each miRNA vertex according to the combined weight between the any two miRNAs; a sorting module, configured to sort each miRNA in descending order according to the weight of each miRNA vertex; Screening module for screening potential disease-related miRNAs according to descending sorting results. 7. The miRNA-disease association identification system according to claim 6, wherein the functional similarity calculation module specifically comprises: Functional similarity calculation unit for taking formulas Calculate the functional similarity between any two miRNAs in the disease database; wherein miRNA m1 and miRNA m2 are any two miRNAs in the disease database; MSim(m1, m2) represents the difference between miRNA m1 and miRNA m2. Functional similarity; DT ₁ represents the disease set associated with miRNA m1,

|DT ₁ | represents the length of the disease set associated with miRNA m1, dt _1i represents the ith disease in the disease set DT ₁ ; DT ₂ represents the disease set associated with miRNA m2,

|DT ₂ | represents the length of the disease set associated with miRNA m2, dt _2j represents the jth disease in the disease set DT ₂ ; Sim(dt _1i ,DT ₂ ) represents the difference between the disease dt _1i and the disease set DT ₂ Similarity, Sim(dt _2j , DT ₁ ) represents the similarity between the disease dt _2j and the disease set DT ₁ . 8. The miRNA-disease association identification system according to claim 7, wherein the aggregation coefficient calculation module specifically comprises: a neighbor node set obtaining unit, configured to obtain the neighbor node set N _m1 of the miRNA m1 and the neighbor node set N _m2 of the miRNA m2 in the undirected graph of the miRNA network; Aggregation coefficient calculation unit for taking formulas

Calculate the aggregation coefficient ECC(m1,m2) between miRNA m1 and miRNA m2; where |N _m1 ∩N _m2 | represents the number of nodes in the intersection of N _m1 and N _m2 ; |N _m1 | represents the number of nodes in N _m1 Number of nodes; |N _m2 | represents the number of nodes in N _m2 . 9. The miRNA-disease association identification system according to claim 8, wherein the attribute fusion module specifically comprises: The combined weight calculation unit is used for according to the functional similarity MSim(m1,m2) and the aggregation coefficient ECC(m1,m2) between the any two miRNAs, using the formula A combined weight ω(m1, m2) between the miRNA m1 and miRNA m2 is determined. 10. The miRNA-disease association identification system according to claim 9, wherein the vertex weight calculation module specifically comprises: The vertex weight calculation unit is used to calculate the weight V _ωs of any miRNA vertex V by adopting the formula V _ωs =km _max ×d _ωs ; where km _max represents the weight of the edge in the weighted subgraph S; the weighted subgraph S is the The set of miRNA vertices V and its immediate neighbors;

|V| represents the number of miRNAs in the weighted subgraph S; ω represents the combined weight of the edges in the weighted subgraph S, that is, the combined weight between any two miRNAs in the weighted subgraph S.

Images