Syndrome gene relationship prediction method fusing meta-path semantic dependence and transfer learning

Abstract

The invention provides a syndrome gene relationship prediction method fusing meta-path semantic dependence and transfer learning, and belongs to the technical field of biological information processing based on deep learning, the method takes a double-flow fine tuning structure in deep transfer learning as a core framework, and two transfer learning tasks are established: 1) a source domain is disease gene prediction; the target domain is syndrome gene prediction; 2) predicting a source domain as a symptom gene; and the target domain is syndrome gene prediction, and through training on a source domain task, migration to a syndrome gene prediction problem of the target domain is carried out, so that syndrome gene relationship prediction in a target domain zero sample scene is realized. In a subject network of transfer learning, through designed syndrome knowledge graph embedding learning, semantic embedding learning of meta-paths and embedding aggregation of multi-order meta-paths, semantic dependency learning of relation meta-paths is realized, and meanwhile, predictive scoring of a relation based on tensor decomposition is designed, so that predictive scoring of syndrome genes is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of biological information processing based on deep learning, and in particular to a syndrome-gene relationship prediction method integrating meta-path semantic dependency and transfer learning. Background Art

[0002] Analysis of the molecular mechanism of syndromes is one of the important topics in TCM research. In recent years, relevant scholars have carried out biological basic research on kidney yang deficiency syndrome, spleen qi deficiency syndrome and blood stasis syndrome. These studies mainly use experimental methods to discover the molecular relationship of syndromes. These experimental methods are mainly based on systems biology, including functional genomics, proteomics and metabolomics. For example, Zhao Xiaoshan et al. used modern molecular biology technology to screen differential genes in patients with kidney deficiency syndrome and studied the intrinsic relationship between these genes and the phenotype of kidney deficiency syndrome; Jiang et al. analyzed the lncRNA expression profiles of patients with pulmonary tuberculosis with different syndromes and found that there were significant differences in the expression of lncRNA in different syndromes; Li Jing et al. conducted control experiments on patients with different TCM syndromes to explore the relationship between TCM syndromes and molecular biology in patients with chronic atrophic gastritis, and found that the EGF content and EGFRmRNA level of patients in the qi and yin deficiency group were upregulated, which was significantly different from other syndrome groups.

[0003] Some scholars have conducted research on combining data mining with artificial intelligence algorithms to achieve syndrome gene prediction, but the number is relatively small. For example, Zhou Xuezhong et al. proposed a gene relationship mining method to achieve effective mining of syndrome gene relationships. Dong Hanyang used Fisher's test to generate some syndrome-gene relationships, and used consistency analysis and other methods to verify the reliability of the quality of syndrome-gene data, and proposed a syndrome-gene relationship prediction method PSGene that combines pre-training and knowledge completion.

[0004] The system biology research method based on syndrome animal model experiments has high requirements for technology, methods and equipment, and also consumes a lot of manpower and material costs, which limits the further development of syndrome molecular research. Syndrome gene methods based on machine learning and deep learning usually require high-quality syndrome gene relationship data to train the model. However, there is currently no high-quality syndrome gene relationship data, which also limits the performance of such methods. Summary of the invention

[0005] The purpose of the present invention is to provide a syndrome-gene relationship prediction method that integrates meta-path semantic dependency and transfer learning to solve at least one technical problem existing in the above-mentioned background technology.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides a syndrome-gene relationship prediction method integrating meta-path semantic dependency and transfer learning, comprising:

[0008] Obtain the syndrome to be predicted;

[0009] The syndromes are processed based on a pre-trained relationship prediction model to obtain the syndrome-gene relationship; wherein, the training of the pre-trained relationship prediction model includes: for source domain entity pairs and target domain entity pairs, the multi-order meta-paths of the entity pairs are found from the pre-obtained multi-order meta-path dictionary, and the embedded representations of the entities in the meta-paths are obtained, wherein the source domain entity pairs include disease-gene entity pairs and symptom-gene entity pairs, and the target domain entity pairs include syndrome-gene entity pairs; the entity representations in the multi-order meta-paths are input into the shared weight layer to realize the sharing of neural network parameters in the source domain and the target domain; in the bottleneck layer of the neural network, a more compact feature expression is obtained, and the bottleneck layer is followed by an adaptive layer, which is used to calculate the distance loss between the source domain and the target domain as a migration regularization term; and the classification task is completed in the output layer.

[0010] Furthermore, the multi-order meta-path of the entity pair is found from the pre-obtained multi-order meta-path dictionary, including: referring to the attention mechanism to adaptively learn the weights of different meta-paths to obtain the quantitative attention degree of each path; wherein the key K and value V in the attention mechanism are both semantic representation vectors of the meta-path, and Q is the first-order embedding representation of the sample entity pair; in the calculation process of the attention mechanism, the similarity between the query Q and each path representation K is first calculated, and then the score value with the value V is calculated, and the weight of each meta-path is obtained through the Softmax activation function, and then the semantic embedding representations of all meta-paths are weighted summed to obtain the final embedding representation of the sample entity pair.

[0011] Furthermore, the set of all entities is denoted as E * ={e s ,e p ,e d ,e g}, where e s Represents all syndrome entities, e p Represents all symptom entities, e d represents all disease entities, e g Represents all gene entities; the set of all relationship types is denoted as R * = {r s-p ,r s-d ,r p-d ,r p-g ,r d-g ,r g-g}, r s -p 、r s-d 、r p-d 、rp-g 、r d-g 、r g-g They represent syndrome-symptom, syndrome-disease, symptom-disease, symptom-gene, disease-gene, and gene-gene relationships respectively; after obtaining the embedded representation of the meta-path, the contextual semantic learning of the meta-path is performed, that is, the recurrent neural network RNN ​​is used to learn the deep semantic embedding representation of the meta-path.

[0012] Furthermore, symptom-disease, symptom-gene, and disease-gene relationship data were obtained from the SympGAN website, syndrome-symptom and syndrome-disease relationship data were obtained from traditional Chinese medicine books, and protein interaction data were obtained from the STRING11 database; the syndrome knowledge graph was obtained by integrating the above six relationships and performing normative checks, removing duplicate data, encoding correspondence and unification, etc.; the knowledge graph embedding learning algorithm TransE was used to learn the complex relationship between the four entities of disease, symptom, syndrome, and gene in the syndrome knowledge graph, and finally the syndrome, disease, symptom, and gene were mapped into a 50-dimensional embedding vector for downstream prediction tasks.

[0013] Furthermore, the loss function of the migration neural network is:

[0014] L u =L c (D s )+λL(D s ,d t )

[0015] Among them, L c (D s ) is the classification loss of the source domain dataset for disease gene prediction, λL(D s ,D t ) is the migration regularization term, λ is an adjustable parameter, L(D s ,D t ) is the loss of the adaptive layer.

[0016] Furthermore, the tensor decomposition algorithm is used to predict and score the relationship:

[0017]

[0018] in, is the head entity embedding of the first-order path, For its tail entity embedding, e r is the meta-path embedding representation after multi-order meta-path aggregation, × n Represents a tensor product.

[0019] In a second aspect, the present invention provides a syndrome-gene relationship prediction system integrating meta-path semantic dependency and transfer learning, comprising:

[0020] An acquisition module, used to acquire the syndrome to be predicted;

[0021] A processing module is used to process the syndrome based on a pre-trained relationship prediction model to obtain the syndrome-gene relationship; wherein the training of the pre-trained relationship prediction model includes: for source domain entity pairs and target domain entity pairs, finding the multi-order meta-path of the entity pair from the pre-obtained multi-order meta-path dictionary, and obtaining the embedded representation of the entity in the meta-path, wherein the source domain entity pair includes disease-gene entity pair and symptom-gene entity pair, and the target domain entity pair includes syndrome-gene entity pair; inputting the entity representation in the multi-order meta-path into the shared weight layer to realize the sharing of neural network parameters in the source domain and the target domain; obtaining a more compact feature expression in the bottleneck layer of the neural network, and the adaptive layer after the bottleneck layer is used to calculate the distance loss between the source domain and the target domain as a migration regularization term; and completing the classification task in the output layer.

[0022] In a third aspect, the present invention provides a non-transitory computer-readable storage medium, which is used to store computer instructions. When the computer instructions are executed by a processor, the syndrome-gene relationship prediction method that integrates meta-path semantic dependency and transfer learning as described in the first aspect is implemented.

[0023] In a fourth aspect, the present invention provides a computer device comprising a memory and a processor, wherein the processor and the memory communicate with each other, the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the syndrome-gene relationship prediction method that integrates meta-path semantic dependency and transfer learning as described in the first aspect.

[0024] In a fifth aspect, the present invention provides an electronic device, comprising: a processor, a memory, and a computer program; wherein the processor is connected to the memory, and the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device executes instructions for implementing the syndrome-gene relationship prediction method that integrates meta-path semantic dependency and transfer learning as described in the first aspect.

[0025] The beneficial effects of the present invention are as follows: a syndrome gene prediction method integrating meta-path semantic dependency and transfer learning is proposed, and the models trained on source domain tasks such as disease gene prediction and symptom gene prediction are migrated to the target domain, so as to realize syndrome gene relationship prediction in the target domain zero-sample scenario; a method including syndrome knowledge graph embedding learning, meta-path semantic embedding learning and multi-order meta-path embedding aggregation is designed, and a transfer learning neural network framework for syndrome gene prediction is constructed, so as to realize the semantic dependency learning of relational meta-paths.

[0026] Additional advantages of the present invention will be more clearly given in the following description or learned through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0028] Figure 1 This is a flow chart of the syndrome gene prediction method integrating meta-path semantic dependency and transfer learning described in an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The embodiments described below by the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be interpreted as limiting the present invention.

[0030] It should be understood by those skilled in the art that unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those skilled in the art to which this invention belongs.

[0031] It should also be understood that terms, such as those defined in commonly used dictionaries, should be understood to have a meaning consistent with that in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless as defined herein.

[0032] Those skilled in the art will appreciate that, unless otherwise stated, the singular forms "a", "an", "said" and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements and / or groups thereof.

[0033] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. Different embodiments or examples described in this specification and features of different embodiments or examples may be combined and combined by those skilled in the art without contradiction.

[0034] To facilitate understanding of the present invention, the present invention is further explained below with reference to specific embodiments in conjunction with the accompanying drawings, and the specific embodiments do not constitute a limitation on the embodiments of the present invention.

[0035] Those skilled in the art should understand that the drawings are merely schematic diagrams of embodiments, and the components in the drawings are not necessarily necessary for implementing the present invention.

[0036] The system biology research method based on syndrome animal model experiments has high requirements for technology, methods and equipment, and also consumes a large amount of manpower and material costs, which limits the further development of syndrome molecular research. Syndrome gene methods based on machine learning and deep learning usually require high-quality syndrome gene relationship data to train the model. However, there is currently no high-quality syndrome gene relationship data, which also limits the performance of this type of method. The purpose of the present invention is to establish a syndrome gene prediction method that integrates meta-path semantic dependency and transfer learning, that is, using the dual-stream fine-tuning structure in deep transfer learning as the core framework, by establishing two transfer learning tasks, the model trained on source domain tasks such as disease gene prediction and symptom gene prediction is migrated to the target domain, and the syndrome gene relationship prediction in the target domain zero-sample scenario is realized. That is, without syndrome gene relationship data, the training of the model and the prediction of syndrome genes can be realized, solving the zero-sample problem of syndrome gene prediction.

[0037] Example 1

[0038] In this embodiment 1, a syndrome-gene relationship prediction system integrating meta-path semantic dependency and transfer learning is first provided, including: an acquisition module, used to acquire the syndrome to be predicted; a processing module, used to process the syndrome based on a pre-trained relationship prediction model to obtain the syndrome-gene relationship; wherein the training of the pre-trained relationship prediction model includes: for source domain entity pairs and target domain entity pairs, finding the multi-order meta-path of the entity pair from a pre-obtained multi-order meta-path dictionary, and obtaining the embedded representation of the entity in the meta-path, wherein the source domain entity pair includes a disease-gene entity pair and a symptom-gene entity pair, and the target domain entity pair includes a syndrome-gene entity pair; the entity representation in the multi-order meta-path is input into a shared weight layer to realize the sharing of neural network parameters in the source domain and the target domain; in the bottleneck layer of the neural network, a more compact feature expression is obtained, and the bottleneck layer is followed by an adaptive layer for calculating the distance loss between the source domain and the target domain as a transfer regularization term; and the classification task is completed in the output layer.

[0039] In this embodiment, the above system is used to realize the syndrome gene relationship prediction method that integrates meta-path semantic dependency and transfer learning, that is, taking the dual-stream fine-tuning structure in deep transfer learning as the core framework, by establishing two transfer learning tasks, the model trained on source domain tasks such as disease gene prediction and symptom gene prediction is migrated to the target domain, and the syndrome gene relationship prediction in the target domain zero-sample scenario is realized. At the same time, when constructing the main network of transfer learning, the syndrome knowledge graph embedding learning, the semantic embedding learning of meta-path, and the embedding aggregation of multi-order meta-path are designed, the semantic dependency learning of the relational meta-path is realized, and the prediction scoring of syndrome genes based on tensor decomposition is designed.

[0040] like Figure 1 As shown, in this embodiment, a syndrome gene prediction method is integrated with meta-path semantic dependency and transfer learning. With the dual-stream fine-tuning structure in deep transfer learning as the core framework, two transfer learning tasks are established: 1) the source domain is disease gene prediction; the target domain is syndrome gene prediction; 2) the source domain is symptom gene prediction; the target domain is syndrome gene prediction. Through the training on the source domain task, it is transferred to the syndrome gene prediction problem in the target domain, and the syndrome gene relationship prediction in the zero-sample scenario of the target domain is realized. In the main network of transfer learning, through the syndrome knowledge graph embedding learning designed by us, the semantic embedding learning of meta-paths, and the embedding aggregation of multi-order meta-paths, the semantic dependency learning of relational meta-paths is realized. At the same time, the prediction scoring of the relationship based on tensor decomposition is designed to realize the prediction scoring of syndrome genes. The details are as follows.

[0041] (1) Syndrome Knowledge Graph Embedding Learning

[0042] First, we obtain symptom-disease, symptom-gene, and disease-gene relationship data from the SympGAN website, syndrome-symptom and syndrome-disease relationship data from TCM books, and protein interaction data from the STRING11 database. We integrate the above six relationships and perform standardization checks, remove duplicate data, and encode corresponding and unified processes to obtain the syndrome knowledge graph. Then, we use the knowledge graph embedding learning algorithm TransE to learn the complex relationship between the four entities in the syndrome knowledge graph, and finally map syndrome, disease, symptom, and gene into a 50-dimensional embedding vector for downstream prediction tasks.

[0043] (2) Semantic Embedding Learning of Meta-paths

[0044] The semantic embedding learning module of meta-path includes multi-order meta-path embedding and meta-path semantic learning. For each entity pair sample, its multi-order meta-path needs to be obtained as the supplementary information of the entity pair. 1 first-order paths (entity to itself), a 2 second-order paths and a 3 Formally, the set of all entities is denoted by E * ={e s ,e p ,e d ,e g}, where e s Represents all syndrome entities, e p Represents all symptom entities, e d represents all disease entities, e g represents all gene entities. At the same time, the set of all relationship types is recorded as R * = {r s-p ,r s-d ,r p-d ,r p-g ,r d-g ,r g-g}, where the elements represent the syndrome-symptom, syndrome-disease, symptom-disease, symptom-gene, disease-gene, and gene-gene relationships from left to right. Taking the disease-gene relationship as an example, for the input triple (d 1 ,r d-g ,g 1 ), d 1 ∈e d , g 1 ∈e g , the path set corresponding to its first-order element path is itself, that is, S 1 ={(d 1 ,g 1 )}, the set of second-order meta-paths includes disease-symptom-gene, disease-gene-gene, as follows.

[0045] S 2 ={(d 1 ,p i ,g 1 )∪(d 1 ,g j ,g 1 )|p i ∈e p ,g j ∈e g}

[0046] The set of third-order meta-paths includes relationships such as disease-syndrome-symptom-gene, disease-syndrome-disease-gene, etc. Here, disease-syndrome-symptom-gene and disease-syndrome-disease-gene are taken as examples and expressed as follows.

[0047] S 3 ={(d 1 ,s i ,p j ,g 1 )∪(d 1 , s m,d n ,g 1 )|s i ∈e s ,p j ∈e p ,d n ∈e d}

[0048] In addition, S i The path in is represented as The kth entity in the path is represented as Where k = {1, 2, 3, 4}. After obtaining the embedded representation of the meta-path, the contextual semantic learning of the meta-path is performed, that is, the deep semantic embedding representation of the meta-path is learned using a recurrent neural network (RNN). Specifically, for the set S 2 , S 3 Each path element in And their embedded representations are used as the input of RNN, and after passing through the recurrent neural network module of RNN, the contextual semantic embedding representation of each meta-path is obtained.

[0049] (3) Embedded Aggregation of Multi-Order Meta-Paths

[0050] The embedding aggregation part of the multi-order meta-path uses the attention mechanism to adaptively learn the weights of different meta-paths and obtain the quantitative attention level of each path. Specifically, the key K and value V in the attention mechanism are both semantic representation vectors of meta-paths, and Q is the first-order embedding representation of the sample entity pair. In the calculation process of the attention mechanism, the similarity between the query Q and each path representation K is first calculated, and then the score value with the value V is calculated. The weight of each meta-path is obtained through the Softmax activation function, and then the semantic embedding representations of all meta-paths are weighted and summed to obtain the final embedding representation of the sample entity pair.

[0051] (4) Prediction and scoring of relationships

[0052] In the prediction and scoring part of the relationship, it is necessary to score the relationship to be predicted. Here, the tensor decomposition algorithm is used to predict and score the relationship. The calculation method of the scoring function can be expressed as follows.

[0053]

[0054] in, is the head entity embedding of the first-order path, For its tail entity embedding, e r is the meta-path embedding representation after multi-order meta-path aggregation, × n Represents tensor product (shorthand notation along mode n).

[0055] (5) Deep Transfer Learning

[0056] In the deep transfer learning stage, the source domain is disease-gene data and the target domain is syndrome-gene data. First, the entity pairs in the source domain and the target domain need to find the multi-order meta-path of the entity pair from the pre-obtained multi-order meta-path dictionary, and obtain the embedded representation of the entity in the meta-path. Then, the entity representation in the multi-order meta-path is input into the backbone network that needs to be fine-tuned in the pre-trained model, that is, the shared weight layer of the source domain data and the target domain data in the transfer network. The shared weight layer is only fine-tuned at a small learning rate during transfer training. The shared weight means that the source domain and the target domain completely share the parameters of this part of the neural network. After that, the bottleneck layer of the neural network is entered to obtain a more compact feature expression and improve the training speed, and finally the output layer is entered to complete the classification task. The parameters of the bottleneck layer and the output layer are retrained in a randomly initialized manner and updated at a large learning rate. In particular, an adaptive layer is added after the bottleneck layer to calculate the distance loss between the source domain and the target domain as a transfer regularization term. The loss function of the transfer neural network can be expressed as follows.

[0057] L u =L c (D s )+λL(D s ,D t )

[0058] Among them, L c (D s) is the classification loss of the source domain dataset for disease gene prediction, λL(D s ,D t ) is the migration regularization term, λ is an adjustable parameter, L(D s ,D t ) is the loss of the adaptive layer.

[0059] Example 2

[0060] This embodiment 2 provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the syndrome-gene relationship prediction method integrating meta-path semantic dependency and transfer learning as described above is implemented. The method includes:

[0061] Obtain the syndrome to be predicted;

[0062] The syndromes are processed based on a pre-trained relationship prediction model to obtain the syndrome-gene relationship; wherein, the training of the pre-trained relationship prediction model includes: for source domain entity pairs and target domain entity pairs, the multi-order meta-paths of the entity pairs are found from the pre-obtained multi-order meta-path dictionary, and the embedded representations of the entities in the meta-paths are obtained, wherein the source domain entity pairs include disease-gene entity pairs and symptom-gene entity pairs, and the target domain entity pairs include syndrome-gene entity pairs; the entity representations in the multi-order meta-paths are input into the shared weight layer to realize the sharing of neural network parameters in the source domain and the target domain; in the bottleneck layer of the neural network, a more compact feature expression is obtained, and the bottleneck layer is followed by an adaptive layer, which is used to calculate the distance loss between the source domain and the target domain as a migration regularization term; and the classification task is completed in the output layer.

[0063] Example 3

[0064] This embodiment 3 provides a computer device, including a memory and a processor, the processor and the memory communicate with each other, the memory stores program instructions executable by the processor, the processor calls the program instructions to execute the syndrome gene relationship prediction method integrating meta-path semantic dependency and transfer learning as described above, the method comprising:

[0065] Obtain the syndrome to be predicted;

[0066] The syndromes are processed based on a pre-trained relationship prediction model to obtain the syndrome-gene relationship; wherein, the training of the pre-trained relationship prediction model includes: for source domain entity pairs and target domain entity pairs, the multi-order meta-paths of the entity pairs are found from the pre-obtained multi-order meta-path dictionary, and the embedded representations of the entities in the meta-paths are obtained, wherein the source domain entity pairs include disease-gene entity pairs and symptom-gene entity pairs, and the target domain entity pairs include syndrome-gene entity pairs; the entity representations in the multi-order meta-paths are input into the shared weight layer to realize the sharing of neural network parameters in the source domain and the target domain; in the bottleneck layer of the neural network, a more compact feature expression is obtained, and the bottleneck layer is followed by an adaptive layer, which is used to calculate the distance loss between the source domain and the target domain as a migration regularization term; and the classification task is completed in the output layer.

[0067] Example 4

[0068] This embodiment 4 provides an electronic device, including: a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device executes instructions for implementing the syndrome gene relationship prediction method integrating meta-path semantic dependency and transfer learning as described above, the method comprising:

[0069] Obtain the syndrome to be predicted;

[0070] The syndromes are processed based on a pre-trained relationship prediction model to obtain the syndrome-gene relationship; wherein, the training of the pre-trained relationship prediction model includes: for source domain entity pairs and target domain entity pairs, the multi-order meta-paths of the entity pairs are found from the pre-obtained multi-order meta-path dictionary, and the embedded representations of the entities in the meta-paths are obtained, wherein the source domain entity pairs include disease-gene entity pairs and symptom-gene entity pairs, and the target domain entity pairs include syndrome-gene entity pairs; the entity representations in the multi-order meta-paths are input into the shared weight layer to realize the sharing of neural network parameters in the source domain and the target domain; in the bottleneck layer of the neural network, a more compact feature expression is obtained, and the bottleneck layer is followed by an adaptive layer, which is used to calculate the distance loss between the source domain and the target domain as a migration regularization term; and the classification task is completed in the output layer.

[0071] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0072] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0073] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0074] These computer program instructions can also be loaded onto a computer or other programmable data processing device, and a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0075] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative work on the basis of the technical solution disclosed in the present invention should be included in the scope of protection of the present invention.

Claims

1. A syndrome-gene relationship prediction method integrating meta-path semantic dependency and transfer learning, characterized in that: include: Obtain the syndrome to be predicted; The syndromes are processed based on a pre-trained relationship prediction model to obtain the syndrome-gene relationship; wherein, the training of the pre-trained relationship prediction model includes: for source domain entity pairs and target domain entity pairs, the multi-order meta-paths of the entity pairs are found from the pre-obtained multi-order meta-path dictionary, and the embedded representations of the entities in the meta-paths are obtained, wherein the source domain entity pairs include disease-gene entity pairs and symptom-gene entity pairs, and the target domain entity pairs include syndrome-gene entity pairs; the entity representations in the multi-order meta-paths are input into the shared weight layer to realize the sharing of neural network parameters in the source domain and the target domain; in the bottleneck layer of the neural network, a more compact feature expression is obtained, and the bottleneck layer is followed by an adaptive layer, which is used to calculate the distance loss between the source domain and the target domain as a migration regularization term; and the classification task is completed in the output layer.

2. The syndrome-gene relationship prediction method integrating meta-path semantic dependency and transfer learning according to claim 1, characterized in that: The multi-order meta-path of the entity pair is found from the pre-obtained multi-order meta-path dictionary, including: referring to the attention mechanism to adaptively learn the weights of different meta-paths to obtain the quantitative attention degree of each path; wherein the key K and the value V in the attention mechanism are both semantic representation vectors of the meta-path, and Q is the first-order embedding representation using the sample entity pair; in the calculation process of the attention mechanism, the similarity between the query Q and each path representation K is first calculated, and then the score value with the value V is calculated, and the weight of each meta-path is obtained through the Softmax activation function, and then the semantic embedding representations of all meta-paths are weighted summed to obtain the final embedding representation of the sample entity pair.

3. The syndrome-gene relationship prediction method integrating meta-path semantic dependency and transfer learning according to claim 2, characterized in that: The set of all entities is denoted by E * ={e s ,e p ,e d ,e g }, where e s Represents all syndrome entities, e p Represents all symptom entities, e d represents all disease entities, e g Represents all gene entities; the set of all relationship types is denoted as R * = {r s-p ,r s-d ,r p-d ,r p-g ,r d-g ,r g-g }, r s-p 、r s-d 、r p-d 、r p-g 、r d-g 、r g-g They represent syndrome-symptom, syndrome-disease, symptom-disease, symptom-gene, disease-gene, and gene-gene relationships respectively; after obtaining the embedded representation of the meta-path, the contextual semantic learning of the meta-path is performed, that is, the recurrent neural network RNN ​​is used to learn the deep semantic embedding representation of the meta-path.

4. The syndrome-gene relationship prediction method integrating meta-path semantic dependency and transfer learning according to claim 3, characterized in that: The symptom-disease, symptom-gene, and disease-gene relationship data were obtained from the SympGAN website, the syndrome-symptom and syndrome-disease relationship data were obtained from traditional Chinese medicine books, and the protein interaction data were obtained from the STRING11 database. The syndrome knowledge graph was obtained by integrating the above six relationships and performing normative checks, removing duplicate data, encoding correspondence and unification. The knowledge graph embedding learning algorithm TransE was used to learn the complex relationships between the four entities of disease, symptom, syndrome, and gene in the syndrome knowledge graph, and finally the syndrome, disease, symptom, and gene were mapped into a 50-dimensional embedding vector for downstream prediction tasks.

5. The syndrome-gene relationship prediction method integrating meta-path semantic dependency and transfer learning according to claim 1, characterized in that: The loss function of the transfer neural network is: L u =L c (D s )+λL(D s ,D t ) Among them, L c (D s ) is the classification loss of the source domain dataset for disease gene prediction, λL(D s ,D t ) is the migration regularization term, λ is an adjustable parameter, L(D s ,D t ) is the loss of the adaptive layer.

6. The syndrome-gene relationship prediction method integrating meta-path semantic dependency and transfer learning according to claim 1, characterized in that: Use the tensor decomposition algorithm to predict and score relationships: in, is the head entity embedding of the first-order path, For its tail entity embedding, e r is the meta-path embedding representation after multi-order meta-path aggregation, × n Represents a tensor product.

7. A syndrome-gene relationship prediction system integrating meta-path semantic dependency and transfer learning, characterized in that: include: An acquisition module, used to acquire the syndrome to be predicted; A processing module is used to process the syndrome based on a pre-trained relationship prediction model to obtain the syndrome-gene relationship; wherein the training of the pre-trained relationship prediction model includes: for source domain entity pairs and target domain entity pairs, finding the multi-order meta-path of the entity pair from the pre-obtained multi-order meta-path dictionary, and obtaining the embedded representation of the entity in the meta-path, wherein the source domain entity pair includes disease-gene entity pair and symptom-gene entity pair, and the target domain entity pair includes syndrome-gene entity pair; inputting the entity representation in the multi-order meta-path into the shared weight layer to realize the sharing of neural network parameters in the source domain and the target domain; obtaining a more compact feature expression in the bottleneck layer of the neural network, and the adaptive layer after the bottleneck layer is used to calculate the distance loss between the source domain and the target domain as a migration regularization term; and completing the classification task in the output layer.

8. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by the processor, the syndrome-gene relationship prediction method integrating meta-path semantic dependency and transfer learning as described in any one of claims 1-6 is implemented.

9. A computer device, characterized in that: It includes a memory and a processor, the processor and the memory communicate with each other, the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the syndrome-gene relationship prediction method integrating meta-path semantic dependency and transfer learning as described in any one of claims 1-6.

10. An electronic device, characterized in that: include: A processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory so that the electronic device executes instructions for implementing the syndrome-gene relationship prediction method integrating meta-path semantic dependency and transfer learning as described in any one of claims 1-6.

Images