CN114429786A - Omics data processing method and device, electronic device and storage medium - Google Patents

Omics data processing method and device, electronic device and storage medium Download PDF

Info

Publication number
CN114429786A
CN114429786A CN202111649901.XA CN202111649901A CN114429786A CN 114429786 A CN114429786 A CN 114429786A CN 202111649901 A CN202111649901 A CN 202111649901A CN 114429786 A CN114429786 A CN 114429786A
Authority
CN
China
Prior art keywords
data
genes
graph
training
omics
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202111649901.XA
Other languages
Chinese (zh)
Inventor
郜杰
赵国栋
王凡
何径舟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN202111649901.XA priority Critical patent/CN114429786A/en
Publication of CN114429786A publication Critical patent/CN114429786A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
    • G16B25/00—ICT specially adapted for hybridisation; ICT specially adapted for gene or protein expression
    • G16B25/10—Gene or protein expression profiling; Expression-ratio estimation or normalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
    • G16B40/00—ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
    • G16B40/20—Supervised data analysis

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Biophysics (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Biology (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Genetics & Genomics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Biotechnology (AREA)
  • General Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Bioethics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Epidemiology (AREA)
  • Public Health (AREA)
  • Apparatus Associated With Microorganisms And Enzymes (AREA)

Abstract

The disclosure provides a method and a device for processing group data, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence, in particular to the technical field of deep learning and intelligent medical treatment. The specific implementation scheme is as follows: obtaining omics data, wherein the omics data comprise a plurality of genes; determining an association relationship between a plurality of said genes; determining map data according to the expression levels of a plurality of genes in the omics data and the incidence relation; determining a characteristic of the omics data based on the map data to perform a target task of the omics data according to the characteristic of the omics data. Therefore, accurate low-dimensional representation of omics data can be obtained, and accuracy of downstream target tasks such as classification tasks for cancer typing and individual survival analysis tasks is improved.

Description

Omics data processing method and device, electronic device and storage medium
Technical Field
The present disclosure relates to the field of artificial intelligence, in particular to the field of deep learning and intelligent medical technology, and more particularly to an omics data processing method, apparatus, electronic device, and storage medium.
Background
With the development of high-throughput sequencing technology, omics data are used more and more in modern medicine, and because the omics data can completely depict the health condition of a patient, the omics data are widely applied to aspects of disease diagnosis, medication and the like.
However, the characteristics of high dimensionality, high noise, batch effect and the like of omics data bring a lot of difficulties for practical application, and the acquisition of accurate low-dimensional representation of omics data is of great significance for improving the accuracy of downstream applications such as classification of cancer typing, individual survival analysis and the like.
Disclosure of Invention
The present disclosure provides a method, apparatus, electronic device and storage medium for omics data processing.
According to an aspect of the present disclosure, there is provided a method of processing histological data, the method including: obtaining omics data, wherein the omics data comprise a plurality of genes; determining an association relationship between a plurality of said genes; determining map data according to the expression levels of a plurality of genes in the omics data and the incidence relation; determining a characteristic of the omics data based on the map data to perform a target task of the omics data according to the characteristic of the omics data.
According to another aspect of the present disclosure, there is provided a model training method for omics data processing, the method comprising: obtaining training omics data, wherein the training omics data comprise a plurality of genes, and at least two genes have an incidence relation; determining an association relationship between the plurality of genes; determining training graph data according to the expression quantity of a plurality of genes in the training omics data and the incidence relation; adjusting the training image data by adopting at least two data enhancement strategies to obtain at least two enhancement image data; encoding the at least two types of enhanced graph data by adopting a graph neural network model to obtain corresponding characteristics; adjusting model parameters of the neural network model to minimize a difference between features of the at least two enhancement map data.
According to another aspect of the present disclosure, there is provided a histology data processing apparatus including: the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring omics data which comprises a plurality of genes; a first determination module for determining an association relationship between a plurality of the genes; a second determination module for determining map data based on the expression levels of the plurality of genes in the omics data and the correlation; a third determination module for determining characteristics of the omics data based on the map data to perform a target task of the omics data based on the characteristics of the omics data.
According to another aspect of the present disclosure, there is provided a model training apparatus for omics data processing, comprising: the second acquisition module is used for acquiring training omics data, and the training omics data comprise a plurality of genes; a fourth determining module, configured to determine an association relationship between the plurality of genes; a fifth determining module, configured to determine training graph data according to the expression levels of the genes in the training omics data and the correlation; the first adjusting module is used for adjusting the training image data by adopting at least two data enhancement strategies to obtain at least two enhancement image data; the encoding module is used for encoding the at least two types of enhanced graph data by adopting a graph neural network model so as to obtain corresponding characteristics; a second adjusting module for adjusting model parameters of the neural network model according to differences between features of the at least two enhancement map data to minimize the differences.
According to another aspect of the present disclosure, there is provided an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the omic data processing method of the present disclosure or to perform the model training method for omic data processing of the present disclosure.
According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform an omics data processing method disclosed in the embodiments of the present disclosure or a model training method for omics data processing disclosed in the embodiments of the present disclosure.
According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the omics data processing method of the present disclosure, or implements the steps of the model training method for omics data processing of the present disclosure.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
figure 1 is a schematic flow diagram of an omics data processing method according to a first embodiment of the present disclosure;
figure 2 is a schematic flow diagram of an omics data processing method according to a second embodiment of the present disclosure;
figure 3 is a schematic flow diagram of a model training method for omics data processing according to a third embodiment of the present disclosure;
figure 4 is an architectural schematic diagram of a model training method for omics data processing according to a third embodiment of the present disclosure;
FIG. 5 is a schematic flow diagram of a model training method for omics data processing according to a fourth embodiment of the present disclosure;
figure 6 is a schematic structural diagram of an omics data processing device according to a fifth embodiment of the present disclosure;
figure 7 is a schematic structural diagram of a model training apparatus for omics data processing according to a sixth embodiment of the present disclosure;
figure 8 is a block diagram of an electronic device for implementing an omics data processing method or a model training method for omics data processing of embodiments of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
The disclosure provides an omics data processing method, a model training method for omics data processing, a device, an electronic device, a non-transitory computer readable storage medium and a computer program product, and relates to the technical field of artificial intelligence, in particular to the technical field of deep learning and intelligent medical treatment.
The artificial intelligence is a subject for researching and enabling a computer to simulate certain thinking process and intelligent behaviors (such as learning, reasoning, thinking, planning and the like) of a human, and has a hardware level technology and a software level technology. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing, and the like; the artificial intelligence software technology mainly comprises computer vision, a voice recognition technology, a natural language processing technology, machine learning/deep learning, a big data processing technology, a knowledge map technology and the like.
Intelligent medical treatment is realized by creating a medical information platform in a health archive area and utilizing the most advanced Internet of things technology, so that the interaction between a patient and medical staff, a medical institution and medical equipment is realized, and informatization is gradually achieved. In the near future, the medical industry will incorporate more high technologies such as artificial intelligence, sensing technology and the like, so that the medical service is intelligent in real meaning, and the prosperity and development of the medical industry are promoted.
At present, the characteristics of high dimensionality, high noise, batch effect and the like of omics data bring many difficulties for practical application, and the accurate low-dimensional representation of the omics data is obtained, so that the method has important significance for improving the accuracy of downstream applications such as cancer type classification, survival analysis and the like.
The invention provides a method for processing omic data, which comprises the steps of obtaining the omic data, wherein the omic data comprises a plurality of genes, determining the incidence relation among the plurality of genes, determining the graph data according to the expression quantity and the incidence relation of the plurality of genes in the omic data, determining the characteristics of the omic data based on the graph data, executing the target task of the omic data according to the characteristics of the omic data, obtaining accurate low-dimensional representation of the omic data, and further improving the accuracy of the downstream target task of cancer typing, survival analysis and the like of patients based on the omic data.
An omics data processing method, a model training method for omics data processing, an apparatus, an electronic device, a non-transitory computer-readable storage medium, and a computer program product of the embodiments of the present disclosure are described below with reference to the drawings.
Figure 1 is a schematic flow diagram of an omics data processing method according to a first embodiment of the present disclosure. It should be noted that, the main implementation body of the omics data processing method of this embodiment is an omics data processing device, the omics data processing device may be implemented by software and/or hardware, the omics data processing device may be configured in an electronic device, and the electronic device may include, but is not limited to, a terminal device, a server, and the like, and the embodiment does not specifically limit the electronic device.
As shown in fig. 1, the omics data processing method may include:
step 101, omics data is obtained, wherein the omics data comprises a plurality of genes.
Wherein, the omics data is to-be-processed omics data, and the omics data comprises a plurality of genes.
Step 102, determining the association relationship among a plurality of genes.
And step 103, determining map data according to the expression quantity of the genes in the omics data and the incidence relation.
The expression of a gene refers to the conversion of genetic information stored in a DNA (deoxyribonucleic acid) sequence into a protein molecule with biological activity through transcription and translation in the life process of a cell. Two or more genes are expressed simultaneously, i.e. the genes are co-expressed, and accordingly, the two or more genes have a co-expression relationship.
The expression level of a gene is a quantitative value of gene expression.
In the embodiment of the disclosure, when determining that two genes have a co-expression relationship, it may be determined that the two genes have an association relationship, and further, graph data may be determined according to the expression amount and the association relationship of a plurality of genes in omics data.
And step 104, determining characteristics of the omics data based on the graph data so as to execute the target task of the omics data according to the characteristics of the omics data.
Wherein, the characteristic of the omics data is the omics characterization of the omics data with low dimension, i.e. low dimension representation.
The target task may be any downstream task such as an individual survival analysis task, a disease diagnosis task, a medication recommendation task, a cancer classification task, and the like, which is not limited in the present disclosure.
In the embodiment of the disclosure, after the graph data is determined according to the expression amounts and the incidence relation of a plurality of genes in the omics data, feature extraction can be performed on the graph data to determine the features of the omics data, so as to execute the target task of the omics data according to the features of the omics data.
Since the map data is determined according to the expression quantities of the plurality of genes in the omics data and the incidence relation between at least two genes, by extracting the features of the map data, the expression quantities of the plurality of genes in the omics data and the correlation features between the plurality of genes can be considered, the features can be fully extracted from the omics data, and accurate low-dimensional representation of the omics data can be obtained. Therefore, the expression capability of the low-dimensional representation of the omics data is improved, so that the state of a patient can be better described, the target task of the omics data is executed based on the obtained low-dimensional representation of the omics data, and the accuracy of the target task can be improved.
The omics data processing method of the embodiment of the disclosure determines the incidence relation among a plurality of genes by obtaining the omics data, wherein the omics data comprises a plurality of genes, determines the graph data according to the expression quantity and the incidence relation of the plurality of genes in the omics data, determines the characteristics of the omics data based on the graph data, executes the target task of the omics data according to the characteristics of the omics data, can obtain accurate low-dimensional representation of the omics data, and further improves the accuracy of downstream target tasks such as classification task of cancer typing, individual survival analysis task and the like.
As can be seen from the above analysis, in the embodiment of the present disclosure, the graph data may be determined according to the expression amounts and the association relationships of the plurality of genes in the omics data, and then the characteristics of the omics data may be determined based on the graph data, so as to perform the target task of the omics data according to the characteristics of the omics data. The graph data may include attributes of a plurality of nodes in the graph and edges connecting the nodes. In the omics data processing method provided by the present disclosure, the process of determining the attributes of the plurality of nodes and the edges connecting the nodes included in the graph data according to the expression levels of the plurality of genes in the omics data and the association relationship, and determining the characteristics of the omics data based on the graph data will be further described with reference to fig. 2.
Figure 2 is a schematic flow diagram of an omics data processing method according to a second embodiment of the present disclosure. As shown in fig. 2, the omics data processing method may include the following steps:
step 201, omics data is obtained, wherein the omics data comprises a plurality of genes.
In step 202, the association relationship between multiple genes is determined.
As a possible implementation, the association between at least two genes in omics data can be determined by: inquiring a protein-protein interaction network (PPI) according to proteins synthesized by a plurality of genes to obtain an interaction relation between the proteins synthesized by at least two genes; and determining the association relationship of the at least two genes according to the interaction relationship between the proteins synthesized by the at least two genes.
It is understood that in the PPI network, each node corresponds to one protein, and a connecting edge is formed between two nodes, which indicates that there is an interaction relationship between the proteins corresponding to the two nodes. In the embodiment of the disclosure, the PPI network may be queried by using multiple formats such as names and sequences of proteins synthesized by multiple genes in omics data, so as to determine a correlation relationship between the proteins corresponding to at least two nodes according to a connecting edge between the at least two nodes in the PPI network, and further determine a correlation relationship between the genes synthesizing the at least two proteins according to an interaction relationship between the proteins corresponding to the at least two nodes.
For example, if the PPI network is queried based on the synthesized proteins of a plurality of genes in omics data, it is determined that a node a corresponding to the synthesized protein of gene a, a node B corresponding to the synthesized protein of gene B, a node C corresponding to the synthesized protein of gene C, and a node D corresponding to the synthesized protein of gene D have connecting edges, that is, there is an interaction relationship between the synthesized protein of gene a and the synthesized protein of gene B, and there is an interaction relationship between the synthesized protein of gene C and the synthesized protein of gene D. The association relationship between gene a and gene B and the association relationship between gene C and gene D can be determined based on the interaction relationship between the protein synthesized by gene a and the protein synthesized by gene B and the interaction relationship between the protein synthesized by gene C and the protein synthesized by gene D.
The incidence relation between at least two genes is determined based on the PPI network, so that the incidence relation between the genes in omics data is accurately determined.
As another possible implementation, the association between at least two genes in omics data can be determined by: counting the times of the N times of comparison that the change trend of the expression quantity of the first gene is the same as that of the expression quantity of the second gene; and under the condition that the times are greater than a preset threshold value, determining that the first gene and the second gene have an association relation, wherein the preset threshold value is smaller than N.
Wherein, the first gene and the second gene are any two genes included in the omics data. N and the preset threshold may be set arbitrarily as required, and the preset threshold is smaller than N, for example, N may be set to 100, and the preset threshold is set to 60, 70, and the like, which is not limited by the present disclosure.
In the embodiment of the disclosure, for any two genes in omics data, such as a first gene and a second gene, N times of comparison can be performed on the variation trend of the expression level of the first gene and the variation trend of the second gene, and in the N times of comparison, when the number of times that the variation trend of the expression level of the first gene is the same as the variation trend of the second gene exceeds a preset threshold, it can be determined that the first gene and the second gene have a co-expression relationship, and accordingly, it can be determined that the first gene and the second gene have an association relationship.
For example, if N is 100 and the preset threshold is 60, in 100 comparisons, if the expression level of the first gene is increased and the expression level of the second gene is also increased 70 times, it can be determined that the first gene and the second gene have a co-expression relationship, and accordingly, it can be determined that the first gene and the second gene have an association relationship.
The incidence relation between the at least two genes is determined based on the expression quantity of the at least two genes, so that the incidence relation between the genes in the omics data can be accurately determined.
In another possible implementation form, the association relationship between at least two genes in the omics data can be determined jointly by combining the two manners, so as to improve the accuracy of the determined association relationship between the genes in the omics data. That is, for any two genes in omics data, whether the two genes have a relationship can be determined by the two methods, and when the two genes have a relationship determined by any one of the two methods, the two genes can be determined to have a relationship.
Step 203, determining the attributes of the nodes of the corresponding genes in the graph according to the expression quantities of the genes in the omics data.
In the embodiments of the present disclosure, the map data may be determined based on the expression amounts and the correlation of a plurality of genes in the omics data. The graph data includes attributes of a plurality of nodes in the graph and edges connecting the nodes. Each node in the graph corresponds to one gene, and the structure of the graph can be determined according to the connecting edges among the nodes. Wherein a connecting edge between two nodes, i.e. an edge connecting the two nodes.
In the embodiment of the present disclosure, the expression level of each gene in the omics data may be used as the attribute of the corresponding node in the graph.
And step 204, determining edges connecting corresponding nodes in the graph according to the incidence relation between at least two genes.
In the embodiment of the present disclosure, when an association relationship exists between any two genes, it may be determined that a connection relationship exists between nodes corresponding to the two genes, so that an edge connecting the two nodes may be determined. According to the connecting edges among all the nodes in the graph, the structure of the graph can be determined.
Step 205, determining characteristics of the omics data based on the attributes of the plurality of nodes in the graph and the edges connecting the nodes, so as to execute the target task of the omics data according to the characteristics of the omics data.
In the embodiment of the disclosure, after determining the attributes of the nodes corresponding to the genes in the graph according to the expression quantities of the genes in the omic data and determining the edges connecting the corresponding nodes in the graph according to the incidence relation between at least two genes, the graph data including the attributes of the nodes and the edges connecting the nodes in the graph can be determined based on the attributes of the nodes and the edges connecting the nodes in the graph, and then feature extraction can be performed on the graph data to determine the features of the omic data, so as to execute the target task of the omic data according to the features of the omic data.
The attributes of the plurality of nodes in the diagram data are determined according to the expression quantity of the corresponding genes in the omics data, and the edges connecting the nodes are determined according to the incidence relation among the corresponding genes, so that the expression quantity of the plurality of genes in the omics data and the correlation characteristics among the plurality of genes can be considered by extracting the characteristics of the diagram data, more effective omics data characteristics can be extracted from the omics data, and accurate low-dimensional expression of the omics data is obtained.
In the embodiment of the present disclosure, determining characteristics of omics data based on graph data may specifically be implemented in the following manner: and encoding the graph data by adopting a graph neural network model so as to obtain the characteristics of the omics data.
The Graph neural Network model may be any Graph neural Network model capable of implementing feature extraction, such as a GCN (Graph Convolutional Network) and a GAT (Graph Attention Network), which is not limited in this disclosure.
In the embodiment of the disclosure, the graph neural network model may be trained in advance by means of contrast learning, the graph data determined according to the expression quantities and the incidence relations of a plurality of genes in the omic data is input to the graph neural network model, and the graph data is output as the features of the omic data, so that after the graph data is obtained, the graph data may be input to the trained graph neural network model, and the graph neural network model is used to perform feature extraction on the omic data to obtain the features of the omic data.
For the training process of the neural network model, reference may be made to the following embodiments, which are not described herein again.
After the graph data are determined according to the expression quantity and the incidence relation of a plurality of genes in the omics data, the graph data are coded by adopting the graph neural network model, so that more effective omics data characteristics are extracted from the omics data by adopting the graph neural network model, and accurate low-dimensional representation of the omics data is obtained.
The omics data processing method of the embodiment of the disclosure determines the incidence relation among a plurality of genes by obtaining the omics data, wherein the omics data comprises a plurality of genes, determines the attribute of the node corresponding to the gene in the graph according to the expression quantity of the plurality of genes in the omics data, determines the edge connecting the corresponding node in the graph according to the incidence relation between at least two genes, determines the characteristics of the omics data based on the attribute of the plurality of nodes in the graph and the edge connecting the nodes, executes the target task of the omics data according to the characteristics of the omics data, can obtain the accurate low-dimensional representation of the omics data, and further improves the accuracy of the downstream target tasks such as the classification task of cancer typing, the individual survival analysis task and the like.
According to an embodiment of the present disclosure, a model training method for omics data processing is also provided.
Figure 3 is a schematic flow diagram of a model training method for omics data processing according to a third embodiment of the present disclosure.
It should be noted that, in the model training method for omics data processing provided in the embodiments of the present disclosure, the execution subject is a model training device for omics data processing, which is hereinafter referred to as a model training device for short. The model training apparatus may be implemented by software and/or hardware, and the model training apparatus may be configured in an electronic device, which may include, but is not limited to, a terminal device, a server, and the like.
As shown in fig. 3, the model training method for omics data processing may include the following steps:
step 301, training omics data are obtained, wherein the training omics data comprise a plurality of genes.
Step 302, determining the association relationship among a plurality of genes.
Step 303, determining training graph data according to the expression levels of a plurality of genes in the training omics data and the incidence relation.
Wherein, two or more genes are expressed simultaneously, that is, the genes are co-expressed, and correspondingly, the two or more genes have co-expression relationship.
The expression level of a gene is a quantitative value of gene expression.
In the embodiment of the disclosure, when determining that two genes have a co-expression relationship, it may be determined that the two genes have an association relationship, and then training graph data may be determined according to the expression amounts and the association relationship of the plurality of genes in the training omics data.
Step 304, adjusting the training image data by adopting at least two data enhancement strategies to obtain at least two enhancement image data.
And the data enhancement strategy is a strategy for performing data enhancement on the training image data. The data enhancement policy may be set as desired, and the disclosure is not limited thereto.
In the embodiment of the present disclosure, at least two data enhancement strategies may be adopted to perform data enhancement on training image data to obtain at least two enhanced image data. And performing data enhancement on the training image data by adopting each data enhancement strategy to correspondingly obtain enhanced image data.
Step 305, encoding at least two kinds of enhanced graph data by using a graph neural network model to obtain corresponding characteristics.
The graph neural network model may be any graph neural network model capable of implementing feature extraction, such as a GCN, a GAT, and the like, which is not limited in this disclosure.
In the embodiment of the disclosure, for each kind of enhancement map data, the enhancement map data may be encoded by using the map neural network model to obtain the corresponding features of the enhancement map data. The features corresponding to the enhanced graph data are omics characterization, namely low-dimensional representation, of the enhanced graph data. The enhanced graph data is coded, namely, the feature extraction is carried out on the enhanced graph data.
In step 306, model parameters of the neural network model are adjusted to minimize the difference based on the difference between the features of the at least two enhancement map data.
In the embodiment of the present disclosure, a contrast learning manner may be adopted for model training. Specifically, after the features corresponding to the at least two types of enhanced graph data are obtained, the comparison learning loss function can be calculated together according to the difference between the features corresponding to the at least two types of enhanced graph data, and the model parameters of the graph neural network model are optimized by adjusting the model parameters of the graph neural network model to minimize the comparison learning loss function. And (4) optimizing the model parameters of the graph neural network model for multiple times by repeating the steps of 304-306 for multiple times to obtain the trained graph neural network model.
The model parameters of the neural network model can be optimized by any optimization method such as SGD (Stochastic Gradient Descent), BGD (Batch Gradient Descent), and the like, which is not limited in the present disclosure.
The comparative learning loss function may be an InfoNCE Noise-comparative estimation loss function, a BARLOW twons (an auto-supervised learning method) loss function, or may also be another loss function, and may be selected according to the used comparative learning method, which is not limited in this disclosure.
Taking the BARLOW TWINS loss function as an example, the difference and correlation between the chemical data samples can be learned in the implicit space by increasing the batch size (batch size) and constructing the loss function based on the correlation matrix. Wherein, an omics data sample can be understood as an enhanced graph data.
Taking the example of using two data enhancement strategies to adjust training image data to obtain two types of enhancement image data and performing model training based on the two types of enhancement image data, referring to the architecture diagram shown in fig. 4, in the embodiment of the present disclosure, a double tower model may be used, and the model includes an image data construction module, a data enhancement module, an image data coding module, and a loss function calculation module. The graph data construction module may determine the association relationship between a plurality of genes in the training omics data 401, and determine the training graph data 402 according to the expression level of the plurality of genes in the training omics data 401 and the association relationship between at least two genes. The data enhancement module may use two data enhancement strategies to perform data enhancement on the input training image data 402, so as to obtain two enhanced image data 403 and 404. The graph data encoding module is implemented by a graph neural network model 405, the enhanced graph data 403 is input into the graph neural network model 405, and feature extraction is performed on the enhanced graph data 403 by using the graph neural network model 405, so that low-dimensional features 406 corresponding to the enhanced graph data 403 can be obtained. Similarly, the enhanced graph data 404 is input into the graph neural network model 405, so that feature extraction is performed on the enhanced graph data 404 by using the graph neural network model 405, and a low-dimensional feature 407 corresponding to the enhanced graph data 404 can be obtained. The loss function calculation module, after obtaining the features 406 and 407 output by the graph data encoding module, may calculate a contrast learning loss function according to a difference between the feature 406 of the enhanced graph data 403 and the feature 407 of the enhanced graph data 404, and optimize model parameters of the graph neural network model 405 by adjusting model parameters of the graph neural network model 405 to minimize the contrast learning loss function. The training graph data 402 is subjected to data enhancement by adopting two data enhancement strategies for multiple times, so that model parameters of the graph neural network model 405 are optimized for multiple times based on the difference between the characteristics of the two enhanced graph data, the optimal parameters of the graph neural network model 405 can be obtained, and the training of the graph neural network model 405 is completed.
It should be noted that the trained graph neural network model in the embodiment of the present disclosure may be used to encode the obtained graph data to obtain the characteristics of the corresponding omics data. The above steps are executed by using the trained neural network model, and the above embodiments of the omics data processing method may be parameterized, which is not described herein again.
By adopting the mode of combining contrast learning and the graph neural network model for simultaneous learning, the difference between at least two types of enhanced graph data and the correlation between genes can be learned, so that the graph neural network model obtained by training can fully extract features from the graph data, accurate low-dimensional representation of omics data is obtained, the expression capacity of the low-dimensional representation of the omics data is improved, the state of a patient can be better described, further, a target task of the omics data is executed based on the obtained low-dimensional representation of the omics data, and the accuracy of the target task can be improved.
In summary, the model training method for omics data processing provided in the embodiments of the present disclosure obtains training omics data, the training omics data includes a plurality of genes, determines an association relationship between the plurality of genes, determines training diagram data according to an expression level and the association relationship of the plurality of genes in the training omics data, adjusts the training diagram data using at least two data enhancement strategies to obtain at least two enhancement diagram data, encodes the at least two enhancement diagram data using a diagram neural network model to obtain corresponding features, adjusts model parameters of the neural network model according to a difference between the features of the at least two enhancement diagram data to minimize the difference, realizes training the diagram neural network model based on the training omics data to obtain the diagram neural network model for omics data processing, processes the diagram data determined based on the omics data using the trained diagram neural network model, the method can fully extract features from the omics data to obtain accurate low-dimensional representation of the omics data, and further improve the accuracy of downstream target tasks such as classification tasks of cancer typing, individual survival analysis tasks and the like.
The model training apparatus for omics data processing provided by the present disclosure is further described below in conjunction with figure 5.
Figure 5 is a schematic flow diagram of a model training method for omics data processing according to a fourth embodiment of the present disclosure.
As shown in fig. 5, the model training method for omics data processing may include the following steps:
step 501, training omics data are obtained, wherein the training omics data comprise a plurality of genes.
At step 502, an association relationship between a plurality of genes is determined.
The method for determining the association relationship between multiple genes in the training omics data can refer to the method for determining the association relationship between multiple genes in the omics data in the above embodiments, and is not described herein again.
Step 503, determining the attributes of the nodes of the corresponding genes in the training graph according to the expression quantities of the genes in the training omics data.
In the embodiment of the present disclosure, the training graph data may be determined according to the expression amounts and the association relationship of a plurality of genes in the training omics data. The training graph data comprises attributes of a plurality of nodes in the training graph and edges connecting the nodes. Each node in the training graph corresponds to one gene, and the structure of the training graph can be determined according to the connecting edges among the nodes. Wherein a connecting edge between two nodes, i.e. an edge connecting the two nodes.
In the embodiment of the present disclosure, the expression level of each gene in the training omics data may be used as the attribute of the corresponding node in the training graph.
Step 504, according to the incidence relation between at least two genes, edges connecting corresponding nodes in the training graph are determined.
In the embodiment of the present disclosure, when an association relationship exists between any two genes, it may be determined that a connection relationship exists between nodes corresponding to the two genes, so that an edge connecting the two nodes may be determined. And determining the structure of the training graph according to the connecting edges among all the nodes in the training graph.
And 505, adjusting the training graph data by adopting at least two data enhancement strategies to obtain at least two enhanced graph data, wherein the training graph data comprises attributes of a plurality of nodes in the training graph and edges connecting the nodes.
In the embodiment of the disclosure, after determining the attributes of the nodes corresponding to the genes in the training graph according to the expression quantities of the genes in the training omics data, and determining the edges connecting the corresponding nodes in the training graph according to the association relationship between at least two genes, the training graph data including the attributes of the nodes and the edges connecting the nodes in the training graph can be determined based on the attributes of the nodes and the edges connecting the nodes in the training graph, and then the training graph data can be adjusted by adopting at least two data enhancement strategies to obtain at least two types of enhancement graph data.
The attributes of a plurality of nodes in the training graph data are determined according to the expression quantity of corresponding genes in the training omic data, and the edges connecting the nodes are determined according to the incidence relation between the corresponding genes, so that at least two types of enhanced graph data are obtained by adjusting the training graph data, and the graph neural network model is trained based on the at least two types of enhanced graph data, so that the graph neural network model can better learn the correlation between the genes in the omic data, and more effective omic data characteristics can be extracted from the graph data when the graph data is encoded by using the trained graph data network model, and accurate low-dimensional representation of the omic data is obtained.
As a possible implementation manner, at least two data enhancement strategies are adopted to perform data enhancement on training graph data, and the data enhancement can be implemented by the following manners: and masking the expression quantity of at least one node in the training graph data by adopting at least two data enhancement strategies to obtain at least two types of enhancement graph data.
The at least two data enhancement strategies may be masking the expression quantity of at least one node in the training graph data, but the mask positions corresponding to the data enhancement strategies are different, that is, different data enhancement strategies are masking the expression quantities of different nodes. Therefore, at least two data enhancement strategies are adopted to mask the expression quantity of at least one node in the training graph data, and at least two types of enhancement graph data can be obtained because different data enhancement strategies are used to mask the expression quantities of different nodes.
As another possible implementation manner, at least two data enhancement strategies are adopted to perform data enhancement on training graph data, which may be implemented by: and adding noise to the expression quantity of at least one node in the training graph data by adopting at least two data enhancement strategies to obtain at least two types of enhancement graph data.
The at least two data enhancement strategies may be both adding noise to the expression quantity of at least one node in the training graph data, but the noise adding modes corresponding to different data enhancement strategies are different. For example, the different data enhancement strategies are to add noise to the expression quantities of different nodes, or the different data enhancement strategies are to add noise with different amplitudes to the expression quantities of the same node, or the different data enhancement strategies are to add noise to the expression quantities of different nodes, and the amplitudes of the added noise are different. Therefore, noise can be added to the expression quantity of at least one node in the training graph data by adopting at least two data enhancement strategies, and at least two types of enhancement graph data can be obtained due to the difference of different data enhancement strategies.
By adopting at least two data enhancement strategies, masking the expression quantity of at least one node in the training graph data, or by adopting at least two data enhancement strategies, adding noise to the expression quantity of at least one node in the training graph data, realizing data enhancement of the training graph data, obtaining at least two types of enhancement graph data, further enabling the enhancement graph data after data enhancement to be adopted for training to obtain a graph neural network model, enhancing the anti-interference capability when coding the graph data corresponding to the mathematical data, and further being capable of obtaining more accurate low-dimensional representation of the omics data through the graph neural network model after training.
Step 506, encoding at least two kinds of enhanced graph data by using the graph neural network model to obtain corresponding characteristics.
In step 507, model parameters of the neural network model are adjusted to minimize the difference according to the difference between the features of the at least two enhancement map data.
The specific implementation process and principle of steps 506-507 may refer to the description of the above embodiments, and will not be described herein again.
In summary, the model training method for omics data processing provided in the embodiments of the present disclosure obtains training omics data, where the training omics data includes a plurality of genes, determines an association relationship between the plurality of genes, determines attributes of nodes corresponding to the genes in a training graph according to expression levels of the plurality of genes in the training omics data, determines edges connecting the corresponding nodes in the training graph according to the association relationship between at least two genes, adjusts the training graph data by using at least two data enhancement strategies to obtain at least two types of enhanced graph data, where the training graph data includes the attributes of the plurality of nodes in the training graph and the edges connecting the nodes, encodes the at least two types of enhanced graph data by using a graph neural network model to obtain corresponding features, and encodes the at least two types of enhanced graph data by using the graph neural network model, the method has the advantages that corresponding characteristics are obtained, training of the graph neural network model based on training graph data is achieved, the graph neural network model for omics data processing is obtained, the graph neural network model determined based on the omics data is processed through the trained graph neural network model, characteristics can be fully extracted from the omics data, accurate low-dimensional representation of the omics data is obtained, and accuracy of downstream target tasks such as classification tasks and individual survival analysis tasks of cancer typing is improved.
The omics data processing device provided by the present disclosure will be described with reference to fig. 6.
Fig. 6 is a schematic structural diagram of an omics data processing device according to a fifth embodiment of the present disclosure.
As shown in fig. 6, the present disclosure provides an omics data processing device 600 comprising: a first obtaining module 601, a first determining module 602, a second determining module 603, and a third determining module 604.
The first obtaining module 601 is configured to obtain omics data, where the omics data includes a plurality of genes;
a first determining module 602, configured to determine an association relationship between a plurality of genes;
a second determining module 603, configured to determine map data according to the expression amounts of the plurality of genes in the omics data and the association relationship;
a third determination module 604 for determining characteristics of the omics data based on the map data to perform a target task of the omics data based on the characteristics of the omics data.
It should be noted that the omics data processing device 600 provided in the present embodiment can execute the omics data processing method of the foregoing embodiment. Wherein, the omics data processing device 600 can be implemented by software and/or hardware, and the omics data processing device 600 can be configured in an electronic device, which can include, but is not limited to, a terminal device, a server, etc., and the embodiment does not specifically limit the electronic device.
As a possible implementation manner of the embodiment of the present disclosure, the graph data includes attributes of a plurality of nodes in the graph and edges connecting the nodes, and the second determining module 603 includes:
a first determination unit configured to determine an attribute of a node of a corresponding gene in the graph based on expression amounts of a plurality of genes in omics data;
and the second determining unit is used for determining the edges connecting the corresponding nodes in the graph according to the incidence relation between at least two genes.
As a possible implementation manner of the embodiment of the present disclosure, the first determining module 602 includes:
the query unit is used for querying the protein interaction PPI network according to the proteins synthesized by the plurality of genes so as to obtain the interaction relation between the proteins synthesized by at least two genes;
and a third determining unit for determining the association relationship of the at least two genes according to the interaction relationship between the proteins synthesized by the at least two genes.
As a possible implementation of the embodiments of the present disclosure, the plurality of genes includes a first gene and a second gene; a first determination module 602, comprising:
a counting unit for counting the number of times that the variation trend of the expression level of the first gene is the same as that of the expression level of the second gene in the N comparisons;
and the fourth determining unit is used for determining that the first gene and the second gene have the association relation under the condition that the times are greater than a preset threshold value, wherein the preset threshold value is less than N.
As a possible implementation manner of the embodiment of the present disclosure, the third determining module 604 includes:
and the coding unit is used for coding the graph data by adopting the graph neural network model so as to obtain the characteristics of the omics data.
It should be noted that the foregoing description of the embodiments of the omics data processing method is also applicable to the omics data processing apparatus provided in the present disclosure, and is not repeated herein.
The omics data processing device provided by the embodiment of the disclosure determines the incidence relation among a plurality of genes by acquiring the omics data, determines the graph data according to the expression quantity and the incidence relation of the plurality of genes in the omics data, determines the characteristics of the omics data based on the graph data, executes the target task of the omics data according to the characteristics of the omics data, can acquire accurate low-dimensional representation of the omics data, and further improves the accuracy of downstream target tasks such as classification task of cancer typing, individual survival analysis task and the like.
According to an embodiment of the present disclosure, there is also provided a model training device for omics data processing.
The model training device for omics data processing provided by the present disclosure is described below with reference to fig. 7.
Fig. 7 is a schematic structural diagram of a model training apparatus for omics data processing according to a sixth embodiment of the present disclosure.
As shown in fig. 7, the present disclosure provides a model training apparatus 700 for omics data processing, comprising: a second obtaining module 701, a fourth determining module 702, a fifth determining module 703, a first adjusting module 704, an encoding module 705, and a second adjusting module 706.
The second obtaining module 701 is configured to obtain training omics data, where the training omics data includes a plurality of genes;
a fourth determining module 702, configured to determine an association relationship between a plurality of genes;
a fifth determining module 703, configured to determine training graph data according to the expression amounts of the multiple genes in the training omics data and the association relationship;
a first adjusting module 704, configured to adjust training image data by using at least two data enhancement strategies to obtain at least two enhancement image data;
the encoding module 705 is configured to encode at least two types of enhancement map data by using a map neural network model to obtain corresponding features;
a second adjusting module 706 for adjusting model parameters of the neural network model based on differences between the features of the at least two enhancement map data to minimize the differences.
It should be noted that the model training device 700 for omics data processing, referred to as a model training device for short, provided in this embodiment may perform the model training method for omics data processing of the foregoing embodiment. The model training apparatus may be implemented by software and/or hardware, and the model training apparatus may be configured in an electronic device, which may include, but is not limited to, a terminal device, a server, and the like.
As a possible implementation manner of the embodiment of the present disclosure, the training diagram data includes attributes of a plurality of nodes in the training diagram and edges connecting the nodes, and the fifth determining module 703 includes:
a fifth determining unit, configured to determine attributes of nodes of corresponding genes in the training graph according to expression levels of a plurality of genes in the training omics data;
and the sixth determining unit is used for determining edges connecting corresponding nodes in the training graph according to the incidence relation between at least two genes.
As a possible implementation manner of the embodiment of the present disclosure, the first adjusting module 704 includes:
and the mask unit is used for masking the expression quantity of at least one node in the training graph data by adopting at least two data enhancement strategies to obtain at least two types of enhancement graph data.
As a possible implementation manner of the embodiment of the present disclosure, the first adjusting module 704 includes:
and the processing unit is used for adding noise to the expression quantity of at least one node in the training graph data by adopting at least two data enhancement strategies to obtain at least two types of enhancement graph data.
It should be noted that the foregoing description of the embodiment of the model training method for omics data processing is also applicable to the model training apparatus for omics data processing provided in the present disclosure, and is not repeated herein.
The model training device for omics data processing provided in the embodiments of the present disclosure obtains training omics data, the training omics data includes a plurality of genes, determines an association relationship between the plurality of genes, determines training map data according to an expression level and the association relationship of the plurality of genes in the training omics data, adjusts the training map data using at least two data enhancement strategies to obtain at least two enhancement map data, encodes the at least two enhancement map data using a map neural network model to obtain corresponding features, adjusts model parameters of the neural network model according to a difference between the features of the at least two enhancement map data to minimize the difference, realizes training the map neural network model based on the training omics data to obtain a map neural network model for omics data processing, processes the map data determined based on the omics data using the trained map neural network model, the method can fully extract features from the omics data to obtain accurate low-dimensional representation of the omics data, and further improve the accuracy of downstream target tasks such as classification tasks of cancer typing, individual survival analysis tasks and the like.
Based on the above embodiment, the present disclosure also provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the omic data processing method of the present disclosure or to perform the model training method for omic data processing of the present disclosure.
Based on the above embodiments, the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute an omics data processing method disclosed in the embodiments of the present disclosure or execute a model training method for omics data processing disclosed in the embodiments of the present disclosure.
Based on the above embodiments, the present disclosure also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the omics data processing method of the present disclosure, or implements the steps of the model training method for omics data processing of the present disclosure.
The present disclosure also provides an electronic device and a readable storage medium and a computer program product according to embodiments of the present disclosure.
FIG. 8 illustrates a schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 8, the electronic device 800 may include a computing unit 801 that may perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)802 or a computer program loaded from a storage unit 808 into a Random Access Memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The calculation unit 801, the ROM 802, and the RAM 803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to bus 804.
A number of components in the device 800 are connected to the I/O interface 805, including: an input unit 806, such as a keyboard, a mouse, or the like; an output unit 807 such as various types of displays, speakers, and the like; a storage unit 808, such as a magnetic disk, optical disk, or the like; and a communication unit 809 such as a network card, modem, wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
Computing unit 801 may be a variety of general and/or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and the like. The calculation unit 801 performs the various methods and processes described above, such as an omic data processing method or a model training method for omic data processing. For example, in some embodiments, the omics data processing method or the model training method for omics data processing can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program can be loaded and/or installed onto device 800 via ROM 802 and/or communications unit 809. When loaded into RAM 803 and executed by computing unit 801, a computer program may perform one or more steps of the omics data processing method or the model training method for omics data processing described above. Alternatively, in other embodiments, the computing unit 801 may be configured to perform an omic data processing method or a model training method for omic data processing by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), the internet, and blockchain networks.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The Server can be a cloud Server, also called a cloud computing Server or a cloud host, and is a host product in a cloud computing service system, so as to solve the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service ("Virtual Private Server", or simply "VPS"). The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims (21)

1. A method of histological data processing, comprising:
obtaining omics data, wherein the omics data comprises a plurality of genes;
determining an association relationship between a plurality of said genes;
determining map data according to the expression levels of a plurality of genes in the omics data and the incidence relation;
determining a characteristic of the omics data based on the map data to perform a target task of the omics data according to the characteristic of the omics data.
2. The method of claim 1, wherein the graph data includes attributes of a plurality of nodes in the graph and edges connecting the nodes; determining map data according to the expression levels of the genes in the omics data and the correlation, wherein the determining map data comprises:
determining attributes of nodes of corresponding genes in the graph according to the expression quantities of a plurality of genes in the omics data;
and determining edges connecting corresponding nodes in the graph according to the incidence relation between at least two genes.
3. The method of claim 1, wherein said determining an associative relationship between a plurality of said genes comprises:
inquiring a protein interaction PPI network according to the proteins synthesized by a plurality of genes so as to obtain an interaction relation between the proteins synthesized by at least two genes;
and determining the association relationship of the at least two genes according to the interaction relationship between the proteins synthesized by the at least two genes.
4. The method of claim 1, wherein the plurality of genes comprises a first gene and a second gene; the determining the association relationship among a plurality of the genes comprises:
counting the times of the N times of comparison that the change trend of the expression quantity of the first gene is the same as that of the expression quantity of the second gene;
and determining that the association relationship exists between the first gene and the second gene under the condition that the times are greater than a preset threshold, wherein the preset threshold is less than N.
5. The method of any of claims 1-4, wherein the determining a characteristic of the omics data based on the map data comprises:
encoding the graph data using a graph neural network model to obtain characteristics of the omics data.
6. A model training method for omics data processing, comprising:
obtaining training omics data, wherein the training omics data comprise a plurality of genes, and at least two genes have an incidence relation;
determining an association relationship between the plurality of genes;
determining training graph data according to the expression quantity of a plurality of genes in the training omics data and the incidence relation;
adjusting the training image data by adopting at least two data enhancement strategies to obtain at least two enhancement image data;
encoding the at least two types of enhanced graph data by adopting a graph neural network model to obtain corresponding characteristics;
adjusting model parameters of the neural network model to minimize a difference between features of the at least two enhancement map data.
7. The method according to claim 6, wherein the training graph data comprises attributes of a plurality of nodes in the training graph and edges connecting the nodes; determining training graph data according to the expression levels of the genes in the training omics data and the incidence relation, wherein the training graph data comprises:
determining attributes of nodes of corresponding genes in the training graph according to the expression quantities of the genes in the training omics data;
and determining edges connecting corresponding nodes in the training graph according to the incidence relation between at least two genes.
8. The method of claim 7, wherein the adapting the training image data with at least two data enhancement strategies to obtain at least two enhancement image data comprises:
and masking the expression quantity of at least one node in the training graph data by adopting at least two data enhancement strategies to obtain at least two types of enhancement graph data.
9. The method of claim 7, wherein the adapting the training image data with at least two data enhancement strategies to obtain at least two enhancement image data comprises:
and adding noise to the expression quantity of at least one node in the training graph data by adopting at least two data enhancement strategies to obtain at least two types of enhancement graph data.
10. A histologic data processing apparatus, comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring omics data which comprises a plurality of genes;
a first determination module for determining an association relationship between a plurality of the genes;
a second determination module for determining map data based on the expression levels of the plurality of genes in the omics data and the correlation;
a third determination module for determining characteristics of the omics data based on the map data to perform a target task of the omics data based on the characteristics of the omics data.
11. The apparatus of claim 10, wherein the graph data comprises attributes of a plurality of nodes in the graph and edges connecting the nodes; the second determining module includes:
a first determination unit configured to determine an attribute of a node of a corresponding gene in the graph based on expression levels of a plurality of genes in the omics data;
a second determining unit, configured to determine, according to the association relationship between at least two of the genes, an edge connecting corresponding nodes in the graph.
12. The apparatus of claim 10, wherein the first determining means comprises:
the query unit is used for querying the protein interaction PPI network according to the proteins synthesized by a plurality of genes so as to obtain the interaction relation between the proteins synthesized by at least two genes;
a third determining unit configured to determine the correlation between the at least two genes based on an interaction relationship between the proteins synthesized by the at least two genes.
13. The apparatus of claim 10, wherein the plurality of genes comprises a first gene and a second gene; the first determining module includes:
a counting unit for counting the number of times that the variation trend of the expression level of the first gene is the same as that of the expression level of the second gene in the N comparisons;
a fourth determining unit, configured to determine that the first gene and the second gene have the association relationship when the number of times is greater than a preset threshold, where the preset threshold is smaller than N.
14. The apparatus of any of claims 10-13, wherein the third determining means comprises:
and the coding unit is used for coding the graph data by adopting a graph neural network model so as to obtain the characteristics of the omics data.
15. A model training apparatus for omics data processing, comprising:
the second acquisition module is used for acquiring training omics data, and the training omics data comprise a plurality of genes;
a fourth determining module, configured to determine an association relationship between the plurality of genes;
a fifth determining module, configured to determine training graph data according to the expression levels of the genes in the training omics data and the association relationship;
the first adjusting module is used for adjusting the training image data by adopting at least two data enhancement strategies to obtain at least two enhancement image data;
the encoding module is used for encoding the at least two types of enhanced graph data by adopting a graph neural network model so as to obtain corresponding characteristics;
a second adjusting module for adjusting model parameters of the neural network model according to differences between features of the at least two enhancement map data to minimize the differences.
16. The apparatus according to claim 15, wherein the training graph data comprises attributes of a plurality of nodes in the training graph and edges connecting the nodes; the fifth determining module includes:
a fifth determining unit, configured to determine an attribute of a node of a corresponding gene in the training graph according to expression amounts of the genes in the training omics data;
a sixth determining unit, configured to determine, according to the association relationship between at least two of the genes, an edge connecting corresponding nodes in the training graph.
17. The apparatus of claim 16, wherein the first adjusting module comprises:
and the mask unit is used for masking the expression quantity of at least one node in the training graph data by adopting at least two data enhancement strategies to obtain at least two types of enhancement graph data.
18. The apparatus of claim 16, wherein the first adjustment module comprises:
and the processing unit is used for adding noise to the expression quantity of at least one node in the training graph data by adopting at least two data enhancement strategies to obtain at least two types of enhancement graph data.
19. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5 or to perform the method of any one of claims 6-9.
20. A non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method of any one of claims 1-5 or to perform the method of any one of claims 6-9.
21. A computer program product comprising a computer program which, when executed by a processor, implements the steps of the method of any one of claims 1-5 or implements the steps of the method of any one of claims 6-9.
CN202111649901.XA 2021-12-30 2021-12-30 Omics data processing method and device, electronic device and storage medium Pending CN114429786A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111649901.XA CN114429786A (en) 2021-12-30 2021-12-30 Omics data processing method and device, electronic device and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111649901.XA CN114429786A (en) 2021-12-30 2021-12-30 Omics data processing method and device, electronic device and storage medium

Publications (1)

Publication Number Publication Date
CN114429786A true CN114429786A (en) 2022-05-03

Family

ID=81312130

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111649901.XA Pending CN114429786A (en) 2021-12-30 2021-12-30 Omics data processing method and device, electronic device and storage medium

Country Status (1)

Country Link
CN (1) CN114429786A (en)

Similar Documents

Publication Publication Date Title
CN114898811A (en) Training method and device of protein training model, electronic equipment and storage medium
CN112580324A (en) Text error correction method and device, electronic equipment and storage medium
CN113490986A (en) De-noising ATAC-SEQ data using deep learning
CN114420309B (en) Method for establishing medicine synergistic effect prediction model, prediction method and corresponding device
CN112507118A (en) Information classification and extraction method and device and electronic equipment
CN115116559A (en) Method, device, equipment and medium for determining and training atomic coordinates in amino acid
CN114242162A (en) Method for establishing drug synergy prediction model, prediction method and corresponding device
CN113409898B (en) Molecular structure acquisition method and device, electronic equipment and storage medium
CN114781650A (en) Data processing method, device, equipment and storage medium
CN112949433B (en) Method, device and equipment for generating video classification model and storage medium
CN114120452A (en) Living body detection model training method and device, electronic equipment and storage medium
Xu et al. TrichomeYOLO: A Neural Network for Automatic Maize Trichome Counting
CN116959585A (en) Deep learning-based whole genome prediction method
CN114429787B (en) Omics data processing method and device, electronic device and storage medium
CN114429786A (en) Omics data processing method and device, electronic device and storage medium
CN115206421B (en) Drug repositioning method, and repositioning model training method and device
CN116564401A (en) Model training, cell segmentation system, method and storage medium
CN114783597B (en) Method and device for diagnosing multi-class diseases, electronic equipment and storage medium
CN115526882A (en) Medical image classification method, device, equipment and storage medium
CN115579069A (en) Construction method and device of scRNA-Seq cell type annotation database and electronic equipment
CN114461085A (en) Medical input recommendation method, device, equipment and storage medium
CN113408304A (en) Text translation method and device, electronic equipment and storage medium
CN114792573B (en) Drug combination effect prediction method, model training method, device and equipment
CN115497633B (en) Data processing method, device, equipment and storage medium
CN117238368B (en) Molecular genetic marking method and device, and biological individual identification method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination