Search

CN-117766054-B - Method and system for generating compound intervention scheme based on pre-training model and application of method and system

CN117766054BCN 117766054 BCN117766054 BCN 117766054BCN-117766054-B

Abstract

The invention discloses a method and a system for generating a compound intervention scheme based on a pre-training model and application thereof, wherein the compound refers to a nutritional supplement, a traditional Chinese medicine, a natural product with a discoverable medicinal value or a new compound for old medicines, and particularly relates to a method and a system for generating a personalized nutritional supplement combined intervention scheme. The compounds can be successfully quantitatively characterized using the methods of the invention, and the methods of the invention can also be applied to direct patient dosing, or clinical nutritional regimens, such as patients infected with novel coronaviruses.

Inventors

  • XIONG JIANGHUI

Assignees

  • 北京深度甲基健康技术有限公司

Dates

Publication Date
20260508
Application Date
20230221

Claims (12)

  1. 1. A method for quantitative characterization of compound effects, the method comprising the steps of: (1) Obtaining a target set of single compounds, wherein the single compounds comprise medicines and nutritional supplements; (2) Acquiring all genes in interaction relation with a single gene, and taking the single gene and all genes in interaction relation as a gene set of a protein interaction network of the single gene; (3) Calculating semo values for a set of targets of the single compound and a set of genes of the protein interaction network of the single gene, the semo values calculated by: semo = , Wherein, the Is the average value of the characteristic values of the target genes, Is the mean value of the characteristic values of the non-target genes, S y 2 is the variance of the characteristic values of target genes, n is the number of target genes, m is the number of non-target genes, the target genes are the intersection of the gene set of the protein interaction network and the target set of the compound, and the non-target genes are genes belonging to the gene set of the protein interaction network but not to the target set of the compound; The semo value is a representation of the quantification of the single compound effect using the protein interaction network of the single gene.
  2. 2. The method according to claim 1, wherein the characteristic value is selected from the group consisting of methylation characteristic value, expression value of a gene.
  3. 3. The method of claim 2, wherein the methylation signature value is an average value of methylation beta values or SIMPO values of all methylation sites of a genomic region.
  4. 4. The method according to claim 3, wherein the methylation characteristic value is an average value of methylation beta values or SIMPO values of all methylation sites of a gene promoter region.
  5. 5. The method according to any one of claims 1 to 4, wherein the number of genes in the gene set of the protein interaction network of a single gene is not less than 20.
  6. 6. A system for quantitative characterization of compound effects, wherein the system implements the method of any one of claims 1-5, the system comprising: The gene acquisition module is used for acquiring a target set of a single compound and a gene set of a protein interaction network of a single gene so as to obtain a target gene and a non-target gene; the data acquisition module is used for acquiring characteristic values of the target genes and the non-target genes for a subject; and a calculation module for calculating semo values based on the characteristic values of the target gene and the non-target gene.
  7. 7. A medium for quantitative characterization of compound effects, the medium comprising a program to implement the method of any one of claims 1-5, the medium comprising: (1) Obtaining a target set of a single compound and a gene set of a protein interaction network of a single gene, thereby obtaining a target gene and a non-target gene; (2) Reading the characteristic values of the target genes and non-target genes of the subject; (3) A semo value is calculated based on the eigenvalues of the target gene and non-target gene.
  8. 8. A method of providing a subject with a compound intervention regimen, characterized in that the method uses a method as claimed in any one of claims 1-5, the method comprising the steps of, (1) Acquiring protein interaction network data and compound target point data; (2) Screening a protein interaction network and compound combination, semo features, based on the protein interaction network data and the compound target data, wherein the protein interaction network and compound combination is that intersection of a gene set of the protein interaction network and a gene set of the compound target is significant; (3) Establishing an evaluation model for the phenotype data based on the semo characteristics of screening by using the phenotype data, wherein the phenotype data is a characteristic value multiplied by a sample matrix; Wherein, the establishment of the evaluation model comprises the following steps: (i) Based on the semo features screened, semo values of semo features in the phenotype data are obtained, and finally a semo feature x sample matrix is obtained; (ii) Obtaining semo features having significant relevance to the phenotype by a machine learning algorithm based on the semo features x sample matrix in step (i); (4) For semo features that have a significant correlation with the phenotype, a semo value for a subject is calculated, and a compound intervention regimen is provided to the subject based on the semo value.
  9. 9. A system for providing a compound intervention regimen for a subject, wherein the system implements the method of claim 8, the system comprising: the data acquirer is used for acquiring protein interaction network data, compound target point data and phenotype data; semo a screener for screening for valid semo features; A computational analyzer for calculating semo values of effective semo features in the phenotype data, obtaining semo features with significant correlation to the phenotype, and providing a compound intervention regimen for the subject based on semo values of semo features with significant correlation to the phenotype.
  10. 10. A medium for providing a compound intervention regimen for a subject, the medium comprising a program to implement the method of claim 8, the medium comprising: (1) Acquiring protein interaction network data, compound target point data and phenotype data; (2) Screening effective semo characteristics; (3) Calculating semo values for effective semo features in the phenotype data, obtaining semo features with significant relevance to the phenotype, and providing a compound intervention regimen for the subject based on semo values for semo features with significant relevance to the phenotype.
  11. 11. A method of providing a compound intervention regimen for a subject infected with a novel coronavirus, wherein the method uses the method of claim 8, Semo features that are positively correlated with the novel coronavirus infection outcome include: The single gene is FUT4, and the compound is L-Alanine; semo features that are negatively related to the novel coronavirus infection outcome include: The single gene is IL6, the compound is L-Tryptophan, and/or The single gene is CXCL8, the compound is Vitamin E, and/or The single gene is ITGA2, the compound is L-Cystine, and/or The single gene is CXCL8, the compound is Calcitriol, and/or The single gene is VCAM1, the compound is L-Citrulline, and/or The single gene is CTSB, the compound is Vitamin A, and/or The single gene is VCAM1, the compound is Spermine, and/or The single gene is ITGAM, the compound is L-Tryptophan, and/or The single gene is ITGA2, the compound is L-Citrulline, and/or The single gene is ITGAM, the compound is Glycine betaine, and/or The single gene is MMP9, the compound is L-ASPARTIC ACID, and/or The single gene is TFRC, the compound is L-Tryptophan, and/or The single gene is LCK, the compound is L-Tyrosine, and/or The single gene is ITGAM, the compound is L-Arginine, and/or The single gene is GZMB, the compound is Vitamin A, and/or The single gene is ITGAM, the compound is L-Isoleucine, and/or The single gene is CXCL8, the compound is L-Tryptophan, and/or The single gene is MMP9, the compound is L-Citrulline, and/or The single gene is ITGAM, the compound is L-Valine, and/or The single gene is MMP9, the compound is L-Tryptophan, and/or The single gene is VCAM1, the compound is Clopidogrel, and/or The single gene is CD40LG, the compound is Niacin, and/or The single gene is CSF2, the compound is Choline, and/or The single gene is IL6, the compound is L-Citrulline, and/or The single gene is IL15, the compound is Vitamin A, and/or The single gene is MMP9, the compound is Glycine betaine, and/or The single gene is MMP2, the compound is Melatonin, and/or The single gene is MMP2, the compound is L-Valine, and/or The single gene is ALB, the compound is N-Acetyl-D-glucosamine, and/or The single gene is MMP2, the compound is Glycine betaine, and/or The single gene is CD40LG, the compound is L-Tryptophan, and/or The single gene is VCAM1, the compound is L-Tryptophan, and/or The single gene is CXCL8, the compound is N-Acetyl-D-glucosamine, and/or The single gene is CSF3, the compound is Calcitriol, and/or The single gene is ITGAM, the compound is L-Citrulline, and/or The single gene is MMP9, the compound is Spermine, and/or The single gene is TLR2, the compound is Lipoic Acid, and/or The single gene is CD40, the compound is Lipoic Acid, and/or The single gene is ITGAM, the compound is Clopidogrel, and/or The single gene is CXCL8, the compound is L-citruline, and/or The single gene is SPI1, the compound is L-Cysteine, and/or The single gene is IL4, the compound is Choline, and/or The single gene is MMP2, the compound is Spermine, and/or The single gene is STAT3, the compound is L-Citrulline, and/or The single gene is ITGAX, the compound is Choline, and/or The single gene is IL4, the compound is Lipoic Acid, and/or The single gene is MMP2, the compound is L-ASPARTIC ACID, and/or The single gene is MMP2, the compound is L-Tryptophan, and/or The single gene is CD8A, the compound is Choline, and/or The single gene is MMP2, the compound is L-Citrulline, and/or The single gene is STAT1, the compound is Lipoic Acid, and/or The single gene is CD8A, and the compound is Lipoic Acid; The novel coronavirus infection outcome is indicative of the efficacy of the subject following treatment with the compound.
  12. 12. A method of providing a compound intervention regimen for a subject infected with a novel coronavirus, wherein the method uses the method of claim 8, The single gene is CD68: semo features that are positively correlated with the novel coronavirus infection outcome include: the compounds are Succinic acid, magnesium, niacin, Semo features that are negatively related to the novel coronavirus infection outcome include: The compound is Lipoic Acid; the single gene is CD4: semo features that are positively correlated with the novel coronavirus infection outcome include: the compound is a compound of Calcium, magnesium which, Semo features that are negatively related to the novel coronavirus infection outcome include: The compound is Tretinoin, calcitriol; The single gene is IL6: semo features that are positively correlated with the novel coronavirus infection outcome include: The compound is a Glycine which is used as a carrier, Semo features that are negatively related to the novel coronavirus infection outcome include: The compound is L-citruline, L-Valine or L-Tryptophan; the single gene is CXCL8: semo features that are negatively related to the novel coronavirus infection outcome include: The compound is Glucosamine, calcitriol, tretinoin, L-Citrulline; the single gene is FOXP3: semo features that are positively correlated with the novel coronavirus infection outcome include: the compound is Vitamin E, succinic acid, magnesium, glutathione; The novel coronavirus infection outcome is indicative of the efficacy of the subject following treatment with the compound.

Description

Method and system for generating compound intervention scheme based on pre-training model and application of method and system Technical Field The invention belongs to the technical field of biology, and particularly relates to a method and a system for generating a compound intervention scheme based on a pre-training model and application thereof. Background The complex relationship between compounds (e.g., drugs, nutritional supplements) and the human immune system, and the concern for single compounds has hampered the study of the role of compounds in the management of novel coronavirus infections. Compounds such as pharmaceuticals and nutritional supplements have a significant impact on the immune system, but experiments to study multiple compounds simultaneously are difficult to perform. Thus, there is a need in the art for a method of providing a compound intervention regimen for a subject. Disclosure of Invention As previously mentioned, there is a need in the art for a method of providing a compound intervention regimen for a subject. The inventor defines semo characteristics formed by combining the PPI network and the compound, calculates the PPI network-compound semo value by detecting the DNA methylation or transcriptome and other histology data of an individual, realizes quantitative characterization of the compound action, analyzes phenotype data by using a quantitative characterization method of the compound action to obtain semo characteristics related to the phenotype, and guides the medication of the subject by using the semo characteristics. Thus, the present invention has been achieved. In a first aspect, the present invention provides a method for quantitative characterization of the effect of a compound, the method comprising the steps of: (1) Obtaining a target set of individual compounds including, but not limited to, pharmaceuticals, nutritional supplements; (2) Acquiring all genes in interaction relation with a single gene, and taking the single gene and all genes in interaction relation as a gene set of a protein interaction network of the single gene; (3) Calculating semo values for a set of targets of the single compound and a set of genes of the protein interaction network of the single gene, the semo values calculated by: Wherein, the Is the average value of the characteristic values of the target genes,The method is characterized in that the method comprises the steps of (1) S x2 is the mean value of characteristic values of non-target genes, S y2 is the variance of the characteristic values of the target genes, n is the number of the target genes, and m is the number of the non-target genes, wherein the target genes are the intersection of a gene set of the protein interaction network and a target set of the compound, and the non-target genes are genes belonging to the gene set of the protein interaction network but not belonging to the target set of the compound; The semo value is a representation of the quantification of the single compound effect using the protein interaction network of the single gene. In a second aspect, the present invention provides a system for quantitative characterization of compound effects, the system implementing the method of the first aspect, the system comprising: The gene acquisition module is used for acquiring a target set of a single compound and a gene set of a protein interaction network of a single gene so as to obtain a target gene and a non-target gene; the data acquisition module is used for acquiring characteristic values of the target genes and the non-target genes for a subject; and a calculation module for calculating semo values based on the characteristic values of the target gene and the non-target gene. In a third aspect, the present invention provides a medium for quantitative characterization of compound effects, the medium comprising a program for carrying out the method of the first aspect, the medium comprising: (1) Obtaining a target set of a single compound and a gene set of a protein interaction network of a single gene, thereby obtaining a target gene and a non-target gene; (2) Reading the characteristic values of the target genes and non-target genes of the subject; (3) A semo value is calculated based on the eigenvalues of the target gene and non-target gene. In a fourth aspect, the present invention provides a method of providing a compound intervention regimen to a subject, the method using the method of the first aspect, the method comprising the steps of: (1) Acquiring protein interaction network data and compound target point data; (2) Screening a protein interaction network and compound combination, semo features, based on the protein interaction network data and the compound target data, wherein the protein interaction network and compound combination is that intersection of a gene set of the protein interaction network and a gene set of the compound target is significant; (3) Establishing an evaluation mod