CN110689927B - Drug resistance key gene screening method and device, electronic equipment and storage medium - Google Patents
Drug resistance key gene screening method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN110689927B CN110689927B CN201910920777.2A CN201910920777A CN110689927B CN 110689927 B CN110689927 B CN 110689927B CN 201910920777 A CN201910920777 A CN 201910920777A CN 110689927 B CN110689927 B CN 110689927B
- Authority
- CN
- China
- Prior art keywords
- gene
- genes
- network
- regulation
- drug
- 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.)
- Active
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
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Genetics & Genomics (AREA)
- Molecular Biology (AREA)
- Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biotechnology (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a drug resistance key gene screening method, a drug resistance key gene screening device, electronic equipment and a storage medium, and belongs to the field of medicine. The method comprises the steps of obtaining a first transcriptome corresponding to a target character in a drug-resistant cell, and obtaining a second transcriptome corresponding to the target character in a sensitive cell; according to the differential expression of the genes and the interaction relation among the genes, aiming at a first transcriptome, a drug-resistant gene regulation network is obtained, and aiming at a second transcriptome, a sensitive gene regulation network is obtained; obtaining a difference regulation and control network comprising a plurality of nodes according to the difference between the drug-resistant gene regulation and control network and the sensitive gene regulation and control network, wherein each node is used for representing a drug-resistant gene; and calculating the importance value of each node included in the difference regulation and control network, and sequencing the genes according to the importance values of the nodes in the difference regulation and control network so as to determine the drug resistance key genes. The accuracy of the drug resistance key gene obtained by the method is higher.
Description
Technical Field
The application belongs to the field of medicine, and particularly relates to a drug resistance key gene screening method and device, electronic equipment and a storage medium.
Background
The drug resistance of tumor cells to therapeutic drugs is an inevitable event in clinical tumor treatment, which limits the effect of drug therapy and thus affects the cure of cancer, so it is necessary to screen out key drug resistance genes which have a key effect on the drug resistance of tumor cells.
In the existing methods for screening drug resistance key genes based on gene transcriptome data, a gene differential expression analysis method is generally adopted. However, the gene differential expression analysis method only considers the difference of the expression level of the genes and does not consider the interaction between the genes, so that the accuracy of the finally obtained drug resistance key gene is not high.
Disclosure of Invention
In view of the above, an object of the present application is to provide a method, an apparatus, an electronic device, and a storage medium for screening drug resistance key genes, wherein a difference regulation network is obtained based on dynamic changes of genes in a time sequence and interaction relationships between the genes, and finally drug resistance key genes with high accuracy are obtained.
The embodiment of the application is realized as follows:
in a first aspect, the present embodiments provide a method for screening drug resistance key genes, the method including: obtaining a first transcriptome corresponding to a target character in a drug-resistant cell, and obtaining a second transcriptome corresponding to the target character in a sensitive cell; according to the differential expression of the genes and the interaction relation among the genes, aiming at a first transcriptome, a drug-resistant gene regulation network is obtained, and aiming at a second transcriptome, a sensitive gene regulation network is obtained; obtaining a difference regulation and control network comprising a plurality of nodes according to the difference between the drug-resistant gene regulation and control network and the sensitive gene regulation and control network, wherein each node is used for representing a drug-resistant gene; and calculating the importance value of each node included in the difference regulation and control network, sequencing according to the magnitude relation of the obtained multiple importance values, and determining the drug resistance key gene. In the process of screening the drug resistance key genes, not only the dynamic change of genes corresponding to target characters in drug resistant cells and sensitive cells on a time sequence is considered, but also the interaction relationship among the genes is considered, so that the accuracy of finally obtaining the drug resistance key genes is higher.
With reference to the examples of the first aspect, in a possible implementation manner, the obtaining a drug-resistant gene regulatory network for a first transcriptome and a sensitive gene regulatory network for a second transcriptome according to differential expression of genes and an interaction relationship between the genes includes: screening a first group of time-sequence variation genes from the first transcription group and screening a second group of time-sequence variation genes from the second transcription group according to the relation between the maximum expression quantity of the genes in a period of time and a threshold value; respectively calculating the interaction degree between the first group of time sequence change genes and the interaction degree between the second group of time sequence change genes to obtain a first interaction coefficient matrix and a second interaction coefficient matrix; and obtaining the drug-resistant gene regulation and control network according to the first interaction coefficient matrix, and obtaining the sensitive gene regulation and control network according to the second interaction coefficient matrix.
With reference to the example of the first aspect, in a possible implementation manner, the threshold includes a first threshold and a second threshold, and the screening a first set of time-series variation genes from the first transcription set and a second set of time-series variation genes from the second transcription set according to a relationship between a maximum expression amount of the genes in a period of time and the threshold includes:
for a certain gene in the first transcriptome, determining that the gene is the first group of time-series variation genes in the first transcriptome when the maximum expression level of the gene in a certain period of time is greater than the first threshold and the quotient of the gene expression levels of the gene at least at two time points is not less than the second threshold, or when the maximum expression level of the gene in a certain period of time is greater than the first threshold and the quotient of the gene expression levels of the gene at least at two time points is not greater than the reciprocal of the second threshold; and for a certain gene in the second transcriptome, determining the gene as the second group of time-series variation genes in the second transcriptome when the maximum expression level of the gene in a certain period of time is greater than the first threshold and the quotient of the gene expression levels of the gene at least at two time points is not less than the second threshold, or when the maximum expression level of the gene in a certain period of time is greater than the first threshold and the quotient of the gene expression levels of the gene at least at two time points is not greater than the reciprocal of the second threshold.
With reference to the example of the first aspect, in a possible implementation manner, the calculating the degree of interaction between the first group of time-series variation genes and the degree of interaction between the second group of time-series variation genes, respectively, to obtain a first interaction coefficient matrix and a second interaction coefficient matrix includes: construction of a model of the ordinary differential for characterizing the degree of interaction between genes
Wherein the content of the first and second substances,
xirepresents the time-series expression level of the ith gene,
denotes the regulatory factor from Gene j to Gene i, biWhich represents the degradation constant of the polymer,
representing prior information; estimating a regulation coefficient between every two first group of time sequence change genes in the common differential model through an LASSO regression algorithm to obtain a first interaction coefficient matrix; and estimating the regulation and control coefficient between every two second groups of time sequence change genes in the ordinary differential model through the LASSO regression algorithm to obtain the second interaction coefficient matrix.
With reference to the example of the first aspect, in a possible implementation manner, the obtaining a drug-resistant gene regulatory network according to the first interaction coefficient matrix, and obtaining a sensitive gene regulatory network according to the second interaction coefficient matrix includes: screening out a value with remarkable degrees of representation in the first interaction coefficient matrix according to a Bayesian criterion, and determining the value as a first result value, screening out a value with remarkable degrees of representation in the second interaction coefficient matrix according to the Bayesian criterion, and determining the value as a second result value; and representing the two genes related to each first result value by using two nodes, establishing a connection line between the two nodes to obtain the drug-resistant gene regulation and control network, representing the two genes related to each second result value by using two nodes, and establishing a connection line between the two nodes to obtain the sensitive gene regulation and control network.
With reference to the example of the first aspect, in a possible implementation manner, the obtaining a difference regulation network including a plurality of nodes according to a difference between the drug-resistant gene regulation network and the sensitive gene regulation network, where each node is used for characterizing a drug-resistant gene includes: comparing the drug-resistant gene regulation network with the sensitive gene regulation network; and screening out a connecting line which exists in the drug-resistant gene regulation network and does not exist in the sensitive gene regulation network and a node which is associated with the screened connecting line to obtain the difference regulation network.
With reference to the embodiment of the first aspect, in a possible implementation manner, the calculating an importance value of each node included in the difference regulation and control network to obtain a plurality of importance values includes: based on the formula
Calculating an importance value for each node comprised by the difference regulation network, wherein ri HCharacterizing the singular value, r, corresponding to the gene corresponding to the ith node in the adjacency matrix of the Difference regulatory networki SCharacterizing the difference between the network entropy of the gene corresponding to the ith node in the drug-resistant gene regulation network and the network entropy of the gene corresponding to the ith node in the sensitive gene regulation network,
characterizing the adaptive value of the gene corresponding to the ith node in the difference regulation network,
and
respectively shows the difference of the dynamic changes of the gene expression of the gene corresponding to the ith node in sensitive cells and drug-resistant cells,
expressing the gene expression level of the gene corresponding to the ith node at the time point T in the sensitive cell,
and (b) represents the gene expression level of the gene corresponding to the i-th node at the time point T in the drug-resistant cell.
In a second aspect, the present application provides an apparatus for screening drug-resistant key genes, the apparatus including: the acquisition module is used for acquiring a first transcriptome corresponding to a target character in a drug-resistant cell and acquiring a second transcriptome corresponding to the target character in a sensitive cell; the determining module is used for obtaining a drug-resistant gene regulation and control network aiming at the first transcriptome and a sensitive gene regulation and control network aiming at the second transcriptome according to the differential expression of the genes and the interaction relation among the genes; the determining module is further configured to obtain a difference regulation and control network comprising a plurality of nodes according to a difference between the drug-resistant gene regulation and control network and the sensitive gene regulation and control network, wherein each node is used for representing a drug-resistant gene; and the calculating module is also used for calculating the importance value of each node included in the difference regulation and control network, sequencing according to the size relationship of the obtained multiple importance values and determining the drug resistance key gene.
With reference to the second aspect example, in one possible implementation manner, the determining module is configured to screen out a first group of time-series variation genes from the first transcriptome and a second group of time-series variation genes from the second transcriptome according to a relationship between a maximum expression amount of the genes in a period of time and a threshold; respectively calculating the interaction degree between the first group of time sequence change genes and the interaction degree between the second group of time sequence change genes to obtain a first interaction coefficient matrix and a second interaction coefficient matrix; and obtaining the drug-resistant gene regulation and control network according to the first interaction coefficient matrix, and obtaining the sensitive gene regulation and control network according to the second interaction coefficient matrix.
With reference to the second aspect, in a possible implementation manner, the threshold includes a first threshold and a second threshold, and the determining module is configured to, for a gene in the first transcriptome, determine that the gene is the first group of time-series-change genes in the first transcriptome when a maximum expression level of the gene in a certain period of time is greater than the first threshold and a quotient of gene expression levels of the gene at least at two time points is not less than the second threshold, or when the maximum expression level of the gene in a certain period of time is greater than the first threshold and the quotient of gene expression levels of the gene at least at two time points is not greater than an inverse of the second threshold; and for a certain gene in the second transcriptome, determining the gene as the second group of time-series variation genes in the second transcriptome when the maximum expression level of the gene in a certain period of time is greater than the first threshold and the quotient of the gene expression levels of the gene at least at two time points is not less than the second threshold, or when the maximum expression level of the gene in a certain period of time is greater than the first threshold and the quotient of the gene expression levels of the gene at least at two time points is not greater than the reciprocal of the second threshold.
In a possible implementation manner, in combination with the second aspect example, the determining module is configured to construct a constant differential model for characterizing the degree of interaction between genes
Wherein the content of the first and second substances,
xirepresents the time-series expression level of the ith gene,
denotes the regulatory factor from Gene j to Gene i, biWhich represents the degradation constant of the polymer,
representing prior information; estimating a regulation coefficient between every two first group of time sequence change genes in the common differential model through an LASSO regression algorithm to obtain a first interaction coefficient matrix; and estimating the regulation and control coefficient between every two second groups of time sequence change genes in the ordinary differential model through the LASSO regression algorithm to obtain the second interaction coefficient matrix.
With reference to the embodiment of the second aspect, in a possible implementation manner, the determining module is configured to screen out, according to a bayesian criterion, a value with a significant degree of representation in the first interaction coefficient matrix to be determined as a first result value, and screen out, according to the bayesian criterion, a value with a significant degree of representation in the second interaction coefficient matrix to be determined as a second result value; and representing the two genes related to each first result value by using two nodes, establishing a connection line between the two nodes to obtain the drug-resistant gene regulation and control network, representing the two genes related to each second result value by using two nodes, and establishing a connection line between the two nodes to obtain the sensitive gene regulation and control network.
With reference to the second aspect, in one possible implementation manner, the determining module is configured to compare the drug-resistant gene regulatory network with the sensitive gene regulatory network; and screening out a connecting line which exists in the drug-resistant gene regulation network and does not exist in the sensitive gene regulation network and a node which is associated with the screened connecting line to obtain the difference regulation network.
With reference to the second aspect, in one possible implementation manner, the calculating module is configured to base a formula
Calculating an importance value for each node comprised by the difference regulation network, wherein ri HCharacterizing the singular value, r, corresponding to the gene corresponding to the ith node in the adjacency matrix of the Difference regulatory networki SCharacterizing the difference between the network entropy of the gene corresponding to the ith node in the drug-resistant gene regulation network and the network entropy of the gene corresponding to the ith node in the sensitive gene regulation network,
characterizing the adaptive value of the gene corresponding to the ith node in the difference regulation network,
and
respectively shows the difference of the dynamic changes of the gene expression of the gene corresponding to the ith node in sensitive cells and drug-resistant cells,
expressing the gene expression level of the gene corresponding to the ith node at the time point T in the sensitive cell,
and (b) represents the gene expression level of the gene corresponding to the i-th node at the time point T in the drug-resistant cell.
In a third aspect, an embodiment of the present application further provides an electronic device, including: a memory and a processor, the memory and the processor connected; the memory is used for storing programs; the processor calls a program stored in the memory to perform the method of the first aspect embodiment and/or any possible implementation manner of the first aspect embodiment.
In a fourth aspect, the present application further provides a non-volatile computer-readable storage medium (hereinafter, referred to as a storage medium), on which a computer program is stored, where the computer program is executed by a computer to perform the method in the foregoing first aspect and/or any possible implementation manner of the first aspect.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and drawings.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts. The foregoing and other objects, features and advantages of the application will be apparent from the accompanying drawings. Like reference numerals refer to like parts throughout the drawings. The drawings are not intended to be to scale as practical, emphasis instead being placed upon illustrating the subject matter of the present application.
FIG. 1 shows one of the flow charts of the drug resistance key gene screening method provided in the examples of the present application.
FIG. 2 shows a second flowchart of the drug resistance key gene screening method provided in the embodiment of the present application.
Fig. 3A shows a schematic diagram of a sensitive gene regulatory network provided in an embodiment of the present application.
Fig. 3B shows a schematic diagram of a drug-resistant gene regulatory network provided in an embodiment of the present application.
Fig. 4 shows a schematic diagram of a difference regulation network provided in an embodiment of the present application.
Fig. 5 is a block diagram showing a structure of a drug resistance key gene screening apparatus according to an embodiment of the present invention.
Fig. 6 shows a schematic structural diagram of an electronic device provided in an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, relational terms such as "first," "second," and the like may be used solely in the description herein to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Further, the term "and/or" in the present application is only one kind of association relationship describing the associated object, and means that three kinds of relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone.
The embodiment of the application provides a drug resistance key gene screening method, a drug resistance key gene screening device, electronic equipment and a storage medium. The technology can be realized by adopting corresponding software, hardware and a combination of software and hardware. The following describes embodiments of the present application in detail.
The following will describe the drug resistance key gene screening method provided in the present application.
Referring to FIG. 1, the present application provides a method for screening drug resistance key genes. The steps involved will be described below with reference to fig. 1.
Step S110: and obtaining a first transcriptome corresponding to the target character in the drug-resistant cell and obtaining a second transcriptome corresponding to the target character in the sensitive cell.
Wherein, the target character refers to tumor, and the drug-resistant cell refers to tumor cell which generates drug resistance to tumor drug; the sensitive cells refer to tumor cells which are sensitive to tumor drugs and do not generate drug resistance.
The determination of which genomes of the tumor cells lead to tumor production (i.e., there may be more than one gene that leads to tumor production) and whether a tumor cell is a resistant cell or a sensitive cell is not a problem to be solved by the present application.
In this application, it is clear which cells are sensitive and which are resistant before data is obtained. After the above information is clarified, the electronic device obtains the transcriptome in the drug-resistant cell and determines it as a first transcriptome, and obtains the transcriptome in the sensitive cell and determines it as a second transcriptome, respectively.
It is worth noting that for each gene in the transcriptome, the information obtained by the electronic device includes the name of the gene, the amount of gene expression for that gene at various time points over a period of time.
Step S120: according to the differential expression of the genes and the interaction relation among the genes, a drug-resistant gene regulation network is obtained aiming at the first transcriptome, and a sensitive gene regulation network is obtained aiming at the second transcriptome.
Wherein, the differential expression of the genes refers to the difference between the expression levels of the genes of the same gene at different time points.
The interaction relationship between genes directs the interaction between different genes that result in the same trait (e.g., resulting in tumor resistance).
Referring to fig. 2, for step S120, the following steps may be included:
step S121: and screening a first group of time-sequence variation genes from the first transcription group and screening a second group of time-sequence variation genes from the second transcription group according to the relation between the maximum expression quantity of the genes in a period of time and a threshold value.
In the embodiment of the present application, the threshold may include a first threshold ζ and a second threshold δ. Alternatively, the first threshold may be set to 10, and the second threshold may be set to 5.
When a Gene u is selected from among time-series variation genes (TCGs)k(K is 0, 1, …, K, where K represents a time-point number) satisfies at least the following two conditions, the gene can be identified as a time-series-variable gene, as follows.
(a)
(b)
Or
Wherein (a) the characteristic gene ukMaximum gene expression level not less than ζ over a period of time, (b) characterizing gene ukThe quotient of the gene expression levels at least two time points in the above-mentioned period of time is not less than delta or not more than delta
Therefore, when screening a first group of time-series-variable genes for a first transcriptome, it is possible to determine that a certain gene is a first group of time-series-variable genes when the certain gene satisfies the above two conditions by checking each gene in the first transcriptome. When the first group of time-series variation genes is screened for the second transcriptome, each gene in the second transcriptome can be checked, and when a certain gene meets the two conditions, the gene is determined to be the second group of time-series variation genes.
Step S122: and respectively calculating the interaction degree between the first group of time sequence change genes and the interaction degree between the second group of time sequence change genes to obtain a first interaction coefficient matrix and a second interaction coefficient matrix.
After obtaining the TCGs, the degree of interaction between the individual TCGs can be determined by the following method, resulting in an interaction coefficient matrix.
First, the electronic device may construct an Ordinary Differential Equation (ODE) model for characterizing the degree of interaction between genes:
wherein the content of the first and second substances,
xirepresents the time-series expression level, x, of the ith genejRepresents the time-series expression level of the jth gene, L represents the number of TCG genes,
denotes the regulatory factor from Gene j to Gene i, biIndicate descendingThe constant of the solution is calculated,
representing a priori information.
After the above definition, the solution can be based on the idea of regression
By substituting different TCGs into the above model, the control coefficient (i.e., the degree of interaction) between the TCGs is obtained.
Solving for
The procedure of (2) may be as follows.
Approximating derivatives by difference
To obtain
Memo
Wherein x isi(tk) Represents gene xiThe amount of gene expression at time point k, and t is assumed herek+1-tkIs small enough. Thus, the above ODE model can be transformed into the following linear regression form:
suppose Y is (Y)i,k)L×k＝(yi(tk))L×k，X＝(Xj,k)L×k＝(xj(tk))L×k，E＝(eij)L×L，A＝(aij)L×LAnd B ═ diag (B)i) Then the regression form can be written as Y ═ (EoA) X + B + epsilon. Where i and j refer to different genes, k refers to time points, o refers to dot product between matrices, and e ═ e (e ═ e)1,ε2,…,εL)TRepresenting noise in the data.
The parameters in Y ═ (EoA) X + B + epsilon were estimated using LASSO regression:
Therefore, each gene in the first group of time-series-change genes is substituted into the above fi(x1,x2,…,xL) And obtaining each regulation coefficient among the first group of time sequence change genes, and finally determining a first interaction coefficient matrix among the first group of time sequence change genes. Substituting each gene in the second group of time-series variation genes into the fi(x1,x2,…,xL) And obtaining each regulation coefficient among the second group of time sequence change genes, and finally determining a second interaction coefficient matrix among the second group of time sequence change genes.
Substituting the time-series change gene into fi(x1,x2,…,xL) In this case, the number of data points (gene expression levels in time points) for each of the time-series variable genes may be insufficient for the above-described period of time. To solve this problem, as an alternative embodiment, a sliced cubic Hermit interpolation value may be used to interpolate each gene in the above time-series variation genes to obtain more data points, for example, for each gene, 100 uniform points may be obtained through interpolation, and it is ensured that subsequent calculation is obtained as much as possible
The accuracy of (2).The slicing three-time Hermit interpolation is the prior art, and is not described herein again.
Step S123: and obtaining the drug-resistant gene regulation and control network according to the first interaction coefficient matrix, and obtaining the sensitive gene regulation and control network according to the second interaction coefficient matrix.
After the first interaction coefficient matrix is obtained, as an alternative embodiment, two genes involved in each regulatory coefficient included in the first interaction coefficient matrix may be represented by two nodes, and a connection line is established between the two nodes, so as to obtain the drug-resistant gene regulatory network.
Similarly, two genes related to each regulatory coefficient included in the second interaction coefficient matrix can be represented by two nodes, and a connection line is established between the two nodes, so that the sensitive gene regulatory network is obtained.
As shown in fig. 3A and 3B, each node is represented by a dot. Of course, the symbols used to represent the nodes in the figures are merely illustrative, and it will be understood that nodes may be represented by other symbols (e.g., triangles).
As another alternative, a value representing a significant degree of action may be screened from the first interaction coefficient matrix according to a bayesian criterion, and determined as a first result value, then two genes related to each first result value are represented by two nodes, and a connection line is established between the two nodes, and finally, the drug-resistant gene regulation network is obtained.
And similarly, screening a value representing the significant degree of action from the second interaction coefficient matrix according to a Bayesian criterion, determining the value as a second result value, then representing two genes related to each second result value by using two nodes, establishing a connection line between the two nodes, and finally obtaining the sensitive gene regulation network.
The bayesian criterion is prior art and is not described herein again. When the value of a certain regulation coefficient is larger than the action degree threshold value calculated through the Bayesian rule, the action degree representing the regulation coefficient is obvious.
Step S130: and obtaining a difference regulation and control network comprising a plurality of nodes according to the difference between the drug-resistant gene regulation and control network and the sensitive gene regulation and control network, wherein each node is used for representing a drug-resistant gene.
After the drug-resistant gene regulation network and the sensitive gene regulation network are obtained, the drug-resistant gene regulation network and the sensitive gene regulation network can be compared, a connecting line existing in the drug-resistant gene regulation network and not existing in the sensitive gene regulation network and a node associated with the screened connecting line are screened, and the screened connecting line and the node associated with the screened connecting line are the difference regulation network.
For example, when a drug-resistant gene regulatory network present in FIG. 3B and a junction not present in the sensitive gene regulatory network in FIG. 3A and a node associated with the screened junction are screened, the differential regulatory network shown in FIG. 4 can be obtained.
Step S140: and calculating the importance value of each node included in the difference regulation and control network, and sequencing according to the magnitude relation of the obtained multiple importance values to determine the drug resistance key gene.
Wherein, the importance value of each node can be represented by the pivot value, the network entropy and the adaptive value of the gene corresponding to the node in the difference regulation network.
In the following, taking a gene corresponding to a certain node as a gene i as an example, a pivot value, a network entropy and an adaptive value of the gene i in the difference regulation network will be respectively described.
The pivot value of the gene i in the difference regulation network is the singular value (i.e. the eigenvector corresponding to the maximum eigenvalue) corresponding to the gene i in the adjacency matrix of the difference regulation network, and r is usedi HAnd (4) showing.
The network entropy of the gene i in the difference regulation network is the difference between the network entropy of the gene i in the drug-resistant gene regulation network and the network entropy of the gene i in the sensitive gene regulation network, and r is usedi SAnd (4) showing. Wherein, the calculation formula of the network entropy of the gene i in the drug-resistant gene regulation network or the sensitive gene regulation network is
N (i) is the number of neighbor nodes of the node corresponding to the gene i (the node connected with the node A is the neighbor node of the node A),
represents the regulatory factor from gene j to gene i. Thus, the network entropy r of gene i in the differentially regulated networki SIs composed of
Wherein
And
respectively represents the network entropy of the gene i in a sensitive gene regulation network and a drug-resistant gene regulation network.
R is used as the adaptive value of the gene i in the differential regulation networki DAnd (4) showing. Wherein the content of the first and second substances,
and
indicates the difference in the dynamic changes of gene expression of gene i in sensitive cells and drug-resistant cells, respectively.
Expressing the gene expression level of the gene corresponding to the ith node at the time point T in the sensitive cell,
represents a gene corresponding to the i-th node when the time point of the gene in the drug-resistant cell is TDepending on the amount of expression.
Represents the gene expression level of the gene corresponding to the i-th node at the time point of 0 in the sensitive cell,
and (b) represents the gene expression level of the gene corresponding to the i-th node at a time point of 0 in the drug-resistant cell. Wherein the content of the first and second substances,
and
the first and second transcriptomes are acquired in step S110.
After the pivot value, the network entropy and the adaptive value of each gene in the difference regulation network are obtained, the formula can be based on
Calculating the importance value of the gene in the differential regulation network.
After obtaining the importance value corresponding to each gene, as an alternative embodiment, the values according to the importance values may be sorted in descending order, and the genes sorted at the top M position may be determined as the drug resistance key genes. Wherein, M can be set according to actual conditions.
In the method for screening drug resistance key genes provided by the embodiment of the application, in the process of screening the drug resistance key genes, not only the dynamic changes of genes corresponding to target characters in drug resistant cells and sensitive cells in time sequence are considered, but also the interaction relationship between the genes is considered, and the difference regulation and control network of the genes in the drug resistant cells and the sensitive cells is obtained according to the dynamic changes of the genes in time sequence and the interaction relationship between the genes. Therefore, the accuracy of obtaining the drug resistance key gene based on the difference regulation network is higher.
In addition, as shown in fig. 5, the present embodiment further provides a drug resistance key gene screening apparatus 400, and the drug resistance key gene screening apparatus 400 may include: an acquisition module 410, a determination module 420, and a calculation module 430.
An obtaining module 410, configured to obtain a first transcriptome corresponding to a target trait in a drug-resistant cell, and obtain a second transcriptome corresponding to the target trait in a sensitive cell;
a determining module 420, configured to obtain a drug-resistant gene regulation network for the first transcriptome and a sensitive gene regulation network for the second transcriptome according to differential expression of the genes and an interaction relationship between the genes;
the determining module 420 is further configured to obtain a difference regulatory network including a plurality of nodes according to a difference between the drug-resistant gene regulatory network and the sensitive gene regulatory network, where each node is used to characterize a drug-resistant gene;
the calculating module 430 is further configured to calculate an importance value of each node included in the difference regulatory network, and rank according to a magnitude relationship of the obtained multiple importance values, so as to determine a drug resistance key gene.
Optionally, the determining module 420 is configured to screen a first group of time-series variation genes from the first transcription group and a second group of time-series variation genes from the second transcription group according to a relationship between a maximum expression amount of a gene in a period of time and a threshold; respectively calculating the interaction degree between the first group of time sequence change genes and the interaction degree between the second group of time sequence change genes to obtain a first interaction coefficient matrix and a second interaction coefficient matrix; and obtaining the drug-resistant gene regulation and control network according to the first interaction coefficient matrix, and obtaining the sensitive gene regulation and control network according to the second interaction coefficient matrix.
Optionally, the threshold includes a first threshold and a second threshold, and the determining module 420 is configured to determine, for a certain gene in the first transcriptome, that the certain gene is the first group of time-series variation genes in the first transcriptome, when a maximum expression level of the certain gene in a certain period of time is greater than the first threshold and a quotient of gene expression levels of the certain gene at least at two time points is not less than the second threshold, or when the maximum expression level of the certain gene in a certain period of time is greater than the first threshold and a quotient of gene expression levels of the certain gene at least at two time points is not greater than an inverse of the second threshold; and for a certain gene in the second transcriptome, determining the gene as the second group of time-series variation genes in the second transcriptome when the maximum expression level of the gene in a certain period of time is greater than the first threshold and the quotient of the gene expression levels of the gene at least at two time points is not less than the second threshold, or when the maximum expression level of the gene in a certain period of time is greater than the first threshold and the quotient of the gene expression levels of the gene at least at two time points is not greater than the reciprocal of the second threshold.
Optionally, the determining module 420 is used for constructing a constant differential model for characterizing the degree of interaction between genes
Wherein the content of the first and second substances,
xirepresents the time-series expression level of the ith gene, L represents the number of TCG genes,
denotes the regulatory factor from Gene j to Gene i, biWhich represents the degradation constant of the polymer,
representing prior information; estimating a regulation coefficient between every two first group of time sequence change genes in the common differential model through an LASSO regression algorithm to obtain a first interaction coefficient matrix for representing the regulation coefficient; and estimating the regulation and control coefficient between every two second groups of time sequence change genes in the ordinary differential model through the LASSO regression algorithm to obtain a second interaction coefficient matrix for representing the regulation and control coefficient.
Optionally, the determining module 420 is configured to screen out a value with a significant degree of representation in the first interaction coefficient matrix according to a bayesian criterion, and determine the value with the significant degree of representation in the second interaction coefficient matrix according to the bayesian criterion, as a first result value; and representing the two genes related to each first result value by using two nodes, establishing a connection line between the two nodes to obtain the drug-resistant gene regulation and control network, representing the two genes related to each second result value by using two nodes, and establishing a connection line between the two nodes to obtain the sensitive gene regulation and control network.
Optionally, the determining module 420 is configured to compare the drug-resistant gene regulatory network with the sensitive gene regulatory network; and screening out a connecting line which exists in the drug-resistant gene regulation network and does not exist in the sensitive gene regulation network and a node which is associated with the screened connecting line to obtain the difference regulation network.
Optionally, the calculating module 430 is configured to calculate a formula based on the formula
Calculating an importance value for each node comprised by the difference regulation network, wherein ri HCharacterizing the singular value, r, corresponding to the gene corresponding to the ith node in the adjacency matrix of the Difference regulatory networki SCharacterizing the difference between the network entropy of the gene corresponding to the ith node in the drug-resistant gene regulation network and the network entropy of the gene corresponding to the ith node in the sensitive gene regulation network,
characterizing the adaptive value of the gene corresponding to the ith node in the difference regulation network,
and
respectively shows the difference of the dynamic changes of the gene expression of the gene corresponding to the ith node in sensitive cells and drug-resistant cells,
expressing the gene expression level of the gene corresponding to the ith node at the time point T in the sensitive cell,
and (b) represents the gene expression level of the gene corresponding to the i-th node at the time point T in the drug-resistant cell.
The drug resistance key gene screening apparatus 400 provided in the embodiment of the present application has the same implementation principle and technical effect as those of the method embodiments described above, and for brief description, reference may be made to the corresponding contents in the method embodiments described above where no mention is made in the apparatus embodiments.
In addition, the present invention also provides a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a computer, the computer program executes the steps included in the drug resistance key gene screening method.
In addition, please refer to fig. 6, an embodiment of the present application further provides an electronic device 100 for implementing the method and apparatus for screening drug-resistant key genes according to the embodiment of the present application. The electronic Device 100 may be, but is not limited to, a high-performance computer, a workstation, a Personal Computer (PC), a smart phone, a tablet computer, a Mobile Internet Device (MID), a Personal digital assistant, and the like.
Among them, the electronic device 100 may include: processor 110, memory 120, display 130.
It should be noted that the components and structure of electronic device 100 shown in FIG. 6 are exemplary only, and not limiting, and electronic device 100 may have other components and structures as desired.
The processor 110, memory 120, display 130, and other components that may be present in the electronic device 100 are electrically connected to each other, directly or indirectly, to enable the transfer or interaction of data. For example, the processor 110, the memory 120, the display 130, and other components that may be present may be electrically connected to each other via one or more communication buses or signal lines.
The memory 120 is used for storing programs, such as programs corresponding to the drug resistance key gene screening methods presented above or drug resistance key gene screening apparatuses presented later. Optionally, when the memory 120 stores a drug resistance key gene screening device, the drug resistance key gene screening device includes at least one software functional module that can be stored in the memory 120 in the form of software or firmware (firmware).
Alternatively, the software function module included in the drug resistance key gene screening apparatus may also be fixed in an Operating System (OS) of the electronic device 100.
The processor 110 is used to execute executable modules stored in the memory 120, such as software functional modules or computer programs included in the drug resistance key gene screening apparatus. When the processor 110 receives the execution instruction, it may execute the computer program, for example, to perform: obtaining a first transcriptome corresponding to a target character in a drug-resistant cell, and obtaining a second transcriptome corresponding to the target character in a sensitive cell; according to the differential expression of the genes and the interaction relation among the genes, aiming at a first transcriptome, a drug-resistant gene regulation network is obtained, and aiming at a second transcriptome, a sensitive gene regulation network is obtained; obtaining a difference regulation and control network comprising a plurality of nodes according to the difference between the drug-resistant gene regulation and control network and the sensitive gene regulation and control network, wherein each node is used for representing a drug-resistant gene; and calculating the importance value of each node included in the difference regulation and control network, sequencing according to the magnitude relation of the obtained multiple importance values, and determining the drug resistance key gene.
Of course, the method disclosed in any of the embodiments of the present application can be applied to the processor 110, or implemented by the processor 110.
In summary, in the method, the apparatus, the electronic device, and the storage medium for screening drug resistance key genes provided in the embodiments of the present invention, in the process of screening drug resistance key genes, the dynamic changes of genes corresponding to target traits in drug-resistant cells and sensitive cells in time sequence are considered, the interaction relationship between the genes is also considered, and the dynamic changes of the genes in time sequence and the interaction relationship between the genes are considered, so as to obtain a gene difference regulation and control network in drug-resistant cells and sensitive cells. Therefore, the accuracy of obtaining the drug resistance key gene based on the difference regulation network is higher.
It should be noted that, in the present specification, the embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a notebook computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application.
Claims (10)
1. A drug resistance key gene screening method is characterized by comprising the following steps:
obtaining a first transcriptome corresponding to a target character in a drug-resistant cell, and obtaining a second transcriptome corresponding to the target character in a sensitive cell;
according to the differential expression of the genes and the interaction relation among the genes, aiming at a first transcriptome, a drug-resistant gene regulation network is obtained, and aiming at a second transcriptome, a sensitive gene regulation network is obtained;
obtaining a difference regulation and control network comprising a plurality of nodes according to the difference between the drug-resistant gene regulation and control network and the sensitive gene regulation and control network, wherein each node is used for representing a drug-resistant gene;
and calculating the importance value of each node included in the difference regulation and control network, sequencing according to the magnitude relation of the obtained multiple importance values, and determining the drug resistance key gene.
2. The method of claim 1, wherein obtaining a drug-resistant gene regulatory network for a first transcriptome and a sensitive gene regulatory network for a second transcriptome based on differential expression of genes and interaction relationships between genes comprises:
screening a first group of time-sequence variation genes from the first transcription group and screening a second group of time-sequence variation genes from the second transcription group according to the relation between the maximum expression quantity of the genes in a period of time and a threshold value;
respectively calculating the interaction degree between the first group of time sequence change genes and the interaction degree between the second group of time sequence change genes to obtain a first interaction coefficient matrix and a second interaction coefficient matrix;
and obtaining the drug-resistant gene regulation and control network according to the first interaction coefficient matrix, and obtaining the sensitive gene regulation and control network according to the second interaction coefficient matrix.
3. The method of claim 2, wherein the threshold comprises a first threshold and a second threshold, and wherein the screening the first transcriptome for a first set of temporally-variable genes and the screening the second transcriptome for a second set of temporally-variable genes according to a relationship between a maximum expression of the genes over a period of time and the threshold comprises:
for a certain gene in the first transcriptome, determining that the gene is the first group of time-series variation genes in the first transcriptome when the maximum expression level of the gene in a certain period of time is greater than the first threshold and the quotient of the gene expression levels of the gene at least at two time points is not less than the second threshold, or when the maximum expression level of the gene in a certain period of time is greater than the first threshold and the quotient of the gene expression levels of the gene at least at two time points is not greater than the reciprocal of the second threshold;
and for a certain gene in the second transcriptome, determining the gene as the second group of time-series variation genes in the second transcriptome when the maximum expression level of the gene in a certain period of time is greater than the first threshold and the quotient of the gene expression levels of the gene at least at two time points is not less than the second threshold, or when the maximum expression level of the gene in a certain period of time is greater than the first threshold and the quotient of the gene expression levels of the gene at least at two time points is not greater than the reciprocal of the second threshold.
4. The method of claim 2, wherein the calculating the degree of interaction between the first set of time-series variation genes and the degree of interaction between the second set of time-series variation genes to obtain a first interaction coefficient matrix and a second interaction coefficient matrix comprises:
construction of a model of the ordinary differential for characterizing the degree of interaction between genes
Wherein the content of the first and second substances,
xirepresents the time-series expression level of the ith gene, aijDenotes the regulatory factor from Gene j to Gene i, biDenotes the degradation constant, eijRepresenting prior information;
estimating a regulation coefficient between every two first group of time sequence change genes in the common differential model through an LASSO regression algorithm to obtain a first interaction coefficient matrix;
and estimating the regulation and control coefficient between every two second groups of time sequence change genes in the ordinary differential model through the LASSO regression algorithm to obtain the second interaction coefficient matrix.
5. The method of claim 2, wherein obtaining a drug-resistant gene regulatory network from the first interaction coefficient matrix and obtaining a sensitive gene regulatory network from the second interaction coefficient matrix comprises:
screening out a value with remarkable degrees of representation in the first interaction coefficient matrix according to a Bayesian criterion, and determining the value as a first result value, screening out a value with remarkable degrees of representation in the second interaction coefficient matrix according to the Bayesian criterion, and determining the value as a second result value;
and representing the two genes related to each first result value by using two nodes, establishing a connection line between the two nodes to obtain the drug-resistant gene regulation and control network, representing the two genes related to each second result value by using two nodes, and establishing a connection line between the two nodes to obtain the sensitive gene regulation and control network.
6. The method of claim 5, wherein obtaining a difference regulatory network comprising a plurality of nodes based on the difference between the resistance gene regulatory network and the sensitive gene regulatory network, each node being used to characterize a resistance gene comprises:
comparing the drug-resistant gene regulation network with the sensitive gene regulation network;
and screening out a connecting line which exists in the drug-resistant gene regulation network and does not exist in the sensitive gene regulation network and a node which is associated with the screened connecting line to obtain the difference regulation network.
7. The method according to claim 1, wherein the calculating the importance value of each node included in the difference regulation and control network to obtain a plurality of importance values comprises:
based on the formula
Calculating a weight of each node included in the difference regulation networkEssential value, wherein ri HCharacterizing the singular value, r, corresponding to the gene corresponding to the ith node in the adjacency matrix of the Difference regulatory networki SCharacterizing the difference between the network entropy of the gene corresponding to the ith node in the drug-resistant gene regulation network and the network entropy of the gene corresponding to the ith node in the sensitive gene regulation network,
characterizing the adaptive value of the gene corresponding to the ith node in the difference regulation network,
and
respectively shows the difference of the dynamic changes of the gene expression of the gene corresponding to the ith node in sensitive cells and drug-resistant cells,
expressing the gene expression level of the gene corresponding to the ith node at the time point T in the sensitive cell,
and (b) represents the gene expression level of the gene corresponding to the i-th node at the time point T in the drug-resistant cell.
8. A drug resistance key gene screening device, characterized in that the device comprises:
the acquisition module is used for acquiring a first transcriptome corresponding to a target character in a drug-resistant cell and acquiring a second transcriptome corresponding to the target character in a sensitive cell;
the determining module is used for obtaining a drug-resistant gene regulation and control network aiming at the first transcriptome and a sensitive gene regulation and control network aiming at the second transcriptome according to the differential expression of the genes and the interaction relation among the genes;
the determining module is further configured to obtain a difference regulation and control network comprising a plurality of nodes according to a difference between the drug-resistant gene regulation and control network and the sensitive gene regulation and control network, wherein each node is used for representing a drug-resistant gene;
and the calculating module is also used for calculating the importance value of each node included in the difference regulation and control network, sequencing according to the size relationship of the obtained multiple importance values and determining the drug resistance key gene.
9. An electronic device, comprising: a memory and a processor, the memory and the processor connected;
the memory is used for storing programs;
the processor calls a program stored in the memory to perform the method of any of claims 1-7.
10. A storage medium, having stored thereon a computer program which, when executed by a computer, performs the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910920777.2A CN110689927B (en) | 2019-09-26 | 2019-09-26 | Drug resistance key gene screening method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910920777.2A CN110689927B (en) | 2019-09-26 | 2019-09-26 | Drug resistance key gene screening method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110689927A CN110689927A (en) | 2020-01-14 |
| CN110689927B true CN110689927B (en) | 2021-11-23 |
Family
ID=69110479
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910920777.2A Active CN110689927B (en) | 2019-09-26 | 2019-09-26 | Drug resistance key gene screening method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110689927B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111583991B (en) * | 2020-05-06 | 2022-06-21 | 苏州浪潮智能科技有限公司 | Method, system, equipment and medium for gene regulation and control network reconstruction |
| CN113782093B (en) * | 2021-09-16 | 2024-03-05 | 平安科技（深圳）有限公司 | Method and device for acquiring gene expression filling data and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1976699A (en) * | 2004-02-27 | 2007-06-06 | 斯隆－凯特灵癌症研究所 | Synthesis of epothilones, intermediates thereto, analogues and uses thereof |
| CN101466259A (en) * | 2005-05-10 | 2009-06-24 | 孟山都技术有限公司 | Genes and uses for plant improvement |
| CN104415347A (en) * | 2013-08-21 | 2015-03-18 | 中国科学院上海生命科学研究院 | Applications of miRNA-27b in antitumor effect and drug resistance |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090004173A1 (en) * | 2004-05-28 | 2009-01-01 | St. Jude Children's Research Hospital | Diagnosis and Treatment of Drug Resistant Leukemia |
| US20130331294A1 (en) * | 2007-11-09 | 2013-12-12 | Fox Chase Cancer Center | Egfr/nedd9/tgf-beta interactome and methods of use thereof for the identification of agents having efficacy in the treatment of hyperproliferative disorders |
-
2019
- 2019-09-26 CN CN201910920777.2A patent/CN110689927B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1976699A (en) * | 2004-02-27 | 2007-06-06 | 斯隆－凯特灵癌症研究所 | Synthesis of epothilones, intermediates thereto, analogues and uses thereof |
| CN101466259A (en) * | 2005-05-10 | 2009-06-24 | 孟山都技术有限公司 | Genes and uses for plant improvement |
| CN104415347A (en) * | 2013-08-21 | 2015-03-18 | 中国科学院上海生命科学研究院 | Applications of miRNA-27b in antitumor effect and drug resistance |
Non-Patent Citations (2)
| Title |
|---|
| Drug resistance gene identification algorithm for next-generation sequencing data;Guan-Jie Hua et al.;《2014 IEEE International Conference on Bioinformatics and Biomedicine》;20150115;全文 * |
| 基因调控网络的模式挖掘及其在药物筛选中的应用;朱丽达;《中国优秀博硕士学位论文全文数据库(博士)工程科技Ⅰ辑》;20170615;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110689927A (en) | 2020-01-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Huynh-Thu et al. | Combining tree-based and dynamical systems for the inference of gene regulatory networks | |
| CN109460793B (en) | Node classification method, model training method and device | |
| Dean et al. | Parameter estimation for hidden Markov models with intractable likelihoods | |
| Cule et al. | Significance testing in ridge regression for genetic data | |
| Higgins et al. | A re-evaluation of random-effects meta-analysis | |
| CN108537327B (en) | Neural network prediction method and device based on time series BP | |
| JP4697670B2 (en) | Identification data learning system, learning device, identification device, and learning method | |
| KR102251302B1 (en) | Collaborative filtering method, device, server and storage media combined with time factor | |
| CN110807207B (en) | Data processing method and device, electronic equipment and storage medium | |
| CN110689927B (en) | Drug resistance key gene screening method and device, electronic equipment and storage medium | |
| CN109711530B (en) | Landslide prediction method and system | |
| Huque et al. | Spatial regression with covariate measurement error: A semiparametric approach | |
| US10445341B2 (en) | Methods and systems for analyzing datasets | |
| CN111159481B (en) | Edge prediction method and device for graph data and terminal equipment | |
| Shiguemori et al. | Estimation of initial condition in heat conduction by neural network | |
| CN113656699B (en) | User feature vector determining method, related equipment and medium | |
| AU2017235890B2 (en) | Recommending software actions to create an image and recommending images to demonstrate the effects of software actions | |
| Palmer et al. | Modelling cell generation times by using the tempered stable distribution | |
| CN113779380A (en) | Cross-domain recommendation method, device and equipment, and content recommendation method, device and equipment | |
| CN107832578A (en) | Data processing method and device based on situation variation model | |
| Biehler et al. | Saddlepoint approximations of the distribution of the person parameter in the two parameter logistic model | |
| CN111144473A (en) | Training set construction method and device, electronic equipment and computer readable storage medium | |
| CN115860802A (en) | Product value prediction method, device, computer equipment and storage medium | |
| CN116152368A (en) | Font generation method, training method, device and equipment of font generation model | |
| CN110866527A (en) | Image segmentation method and device, electronic equipment and readable storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |