CN113611372A - Method and system for predicting drug effect fitting of effective ingredients of traditional Chinese medicine prescription - Google Patents
Method and system for predicting drug effect fitting of effective ingredients of traditional Chinese medicine prescription Download PDFInfo
- Publication number
- CN113611372A CN113611372A CN202111018496.1A CN202111018496A CN113611372A CN 113611372 A CN113611372 A CN 113611372A CN 202111018496 A CN202111018496 A CN 202111018496A CN 113611372 A CN113611372 A CN 113611372A
- Authority
- CN
- China
- Prior art keywords
- sub
- similarity score
- monomer component
- chinese medicine
- monomer
- 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
Links
- 239000003814 drug Substances 0.000 title claims abstract description 92
- 238000000034 method Methods 0.000 title claims abstract description 78
- 230000000857 drug effect Effects 0.000 title claims abstract description 36
- 239000004615 ingredient Substances 0.000 title claims abstract description 14
- 239000000178 monomer Substances 0.000 claims abstract description 179
- 238000012216 screening Methods 0.000 claims abstract description 37
- 239000004480 active ingredient Substances 0.000 claims abstract description 25
- 230000003285 pharmacodynamic effect Effects 0.000 claims abstract description 24
- 238000004364 calculation method Methods 0.000 claims description 43
- 108090000623 proteins and genes Proteins 0.000 claims description 41
- 238000012545 processing Methods 0.000 claims description 10
- 229940079593 drug Drugs 0.000 claims description 6
- 239000000203 mixture Substances 0.000 claims description 5
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 238000005303 weighing Methods 0.000 claims description 3
- 238000002360 preparation method Methods 0.000 claims description 2
- 238000009472 formulation Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 15
- 238000011160 research Methods 0.000 abstract description 9
- 230000009471 action Effects 0.000 abstract description 8
- 230000007246 mechanism Effects 0.000 abstract description 8
- 201000010099 disease Diseases 0.000 abstract description 6
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract description 6
- 230000001737 promoting effect Effects 0.000 abstract description 4
- 239000000126 substance Substances 0.000 abstract description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 35
- 230000008827 biological function Effects 0.000 description 7
- 241000411851 herbal medicine Species 0.000 description 7
- 230000000144 pharmacologic effect Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000019491 signal transduction Effects 0.000 description 3
- 239000000243 solution Substances 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000010201 enrichment analysis Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 231100001231 less toxic Toxicity 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000002332 oil field water Substances 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 208000011580 syndromic disease Diseases 0.000 description 1
- 230000002195 synergetic effect Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/20—Identification of molecular entities, parts thereof or of chemical compositions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/50—Molecular design, e.g. of drugs
Landscapes
- Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Crystallography & Structural Chemistry (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medicinal Chemistry (AREA)
- Pharmacology & Pharmacy (AREA)
- Medicines Containing Plant Substances (AREA)
Abstract
The invention belongs to the technical field of Chinese medicine efficacy prediction, in particular to a method and a system for predicting the drug effect fitting of active ingredients of a Chinese medicine prescription, which determine the score of the drug effect fitting degree of each monomer ingredient of the Chinese medicine prescription through comprehensive analysis of model prediction of the drug effect fitting degree based on the pretreatment of drug effect grading screening of each monomer ingredient of the Chinese medicine prescription and solve the problems that in the prior art, the research on the action mechanism of the Chinese medicine prescription involves a large number of complex molecules and changes of related signal paths due to complex and diverse ingredients and drug effect substances, so that the potential monomer active ingredients in the Chinese medicine prescription are comprehensively clarified from a molecular level system and the providing scientific basis for the treatment effect of related diseases has important significance, the method has the beneficial technical effects of digitalizing the pharmacodynamic characteristics of multiple components and multiple targets and analyzing the comprehensive indexes of the effects and having important practical significance for promoting the modernization research of the traditional Chinese medicine.
Description
Technical Field
The invention belongs to the technical field of traditional Chinese medicine efficacy prediction, and particularly relates to a method and a system for predicting the drug efficacy of active ingredients of a traditional Chinese medicine prescription through fitting.
Background
In China, thousands of years of traditional Chinese herbal medicines have attracted more and more attention in the field of clinical treatment by virtue of the overall treatment appearance, unique clinical curative effect, less toxic and side effects and multi-component and multi-target pharmacodynamic characteristics. However, because the ingredients in the Chinese herbal medicine formula are complex and various, and the drug effect substance is complex in basis, the research on the action mechanism of the Chinese herbal medicine formula involves a large number of complex molecules and changes of related signal paths. Therefore, the molecular level system, the comprehensive elucidation of the potential monomer effective components in the Chinese medicine prescription and the scientific basis for the treatment effect of the relevant diseases remain one of the key problems to be solved urgently in the traditional Chinese medicine field at present;
in recent years, with the cross fusion of modern emerging disciplines such as 'system biology' and 'bioinformatics' and ancient traditional Chinese medicine and pharmacology, a brand new discipline of 'traditional Chinese medicine network pharmacology' is brought forward. At present, a series of research methods of 'traditional Chinese medicine network pharmacology' are created and applied, wherein the research methods comprise traditional Chinese medicine component target spectrum and active monomer component prediction, disease target prediction, common mode block analysis of medicine-target-disease, large-scale screening and analysis of traditional Chinese medicine component multi-target synergistic effect and the like based on a network platform; the new methods can disclose potential pharmacological mechanisms of the traditional Chinese medicine prescription and corresponding components from a systematic level, provide powerful tools for accelerating the research and development of the traditional Chinese medicine, and have strong promotion effect on the traditional Chinese medicine from empirical medicine to syndrome-based medicine;
in the prior art, because the components in the Chinese herbal medicine formula are complex and various and the drug effect substance is complex in basis, the research on the action mechanism of the Chinese herbal medicine formula relates to the change of a large number of complex molecules and related signal paths, so that the potential monomer effective components in the Chinese herbal medicine formula are comprehensively clarified from a molecular level system, and the problem of having important significance for providing scientific basis for the treatment effect of related diseases is solved.
Disclosure of Invention
The invention provides a method and a system for predicting the drug effect fitting of active ingredients of a traditional Chinese medicine prescription, aiming at solving the problems that in the prior art, due to the complex and various ingredients and complex drug effect substance basis in the traditional Chinese medicine prescription, the research on the action mechanism of the traditional Chinese medicine prescription relates to the change of a large number of complex molecules and related signal paths, so that the potential monomer active ingredients in the traditional Chinese medicine prescription are comprehensively clarified from a molecular level system, and the problem that the potential monomer active ingredients have important significance for providing scientific basis for the treatment effect of related diseases is solved.
The technical problem solved by the invention is realized by adopting the following technical scheme: a method for predicting the drug effect of active ingredients of a traditional Chinese medicine prescription by fitting comprises the following steps:
and (3) determining the pharmacodynamic fit degree score of each monomer component of the Chinese medicinal formula through comprehensive analysis of pharmacodynamic fit degree model prediction based on the pretreatment of pharmacodynamic grading screening of each monomer component of the Chinese medicinal formula.
Further, the pretreatment of the drug effect grading screening of each monomer component of the traditional Chinese medicine formula comprises the following steps:
determining a first updating sub-table of corresponding monomer components by a first screening method based on the general table of the traditional Chinese medicine formula and the corresponding monomer component sub-table;
based on the corresponding first updated sub-tables of the monomer components, determining corresponding first similarity scores between the general table of the traditional Chinese medicine prescription and the corresponding first updated sub-tables of the monomer components by a first similarity score calculation method;
a second updated sub-table of corresponding monomer components is determined by a second screening method based on the corresponding first updated sub-table of monomer components.
And determining corresponding second similarity scores between the general table of the Chinese medicinal formula and the corresponding second updated sub-tables of the monomer components by a second similarity score calculation method based on the corresponding second updated sub-tables of the monomer components.
Further, the comprehensive analysis of the pharmacodynamic fitness model prediction comprises:
based on the corresponding second updated sub-table of the monomer components, determining corresponding index weight of the monomer components between the general table of the traditional Chinese medicine formula and the corresponding second updated sub-table of the monomer components by a prediction entropy weight method;
and determining the fitting degree score between the traditional Chinese medicine formula general table and the corresponding monomer component table by a corresponding monomer component comprehensive index calculation method based on the corresponding monomer component index weight, the first similarity score and the second similarity score.
Further, the first screening method comprises:
and if the monomer component significance value of the corresponding monomer component sub-table is greater than 0.05, deleting the monomer component record with the corresponding significance value of greater than 0.05 to form a corresponding monomer component first updating sub-table.
Further, the first similarity score calculating method includes determining a first similarity score by a first similarity score function, where the first similarity score function includes:
α=T’/T；
the alpha is a first similarity score;
the T' is the number of the same item names of the corresponding monomer ingredient table and the traditional Chinese medicine general table;
and T is the number of the item names of the Chinese medicinal prescription general table.
Further, the second screening method comprises:
if the entry names of the general table of the Chinese medicinal formulae are different from the entry names of the corresponding monomer component sub-tables, deleting the monomer component records with the different entry names to form corresponding monomer component second updating sub-tables.
Further, the second similarity score calculation method includes determining a second similarity score by a second similarity score function, the second similarity score function including:
β=G’/G；
beta is a second similarity score;
g' is the number of corresponding specific genes recorded by the monomer components in the corresponding monomer component table;
g is the number of corresponding specific genes in a general table of Chinese medicinal formulas;
further, the prediction entropy weight method comprises:
based on the standardized corresponding monomer component second updating sub-table, determining corresponding sub-value information entropy through an information entropy processing function, and determining monomer component index weight through a weight calculation function based on the sub-value information entropy;
the information entropy processing function comprises:
said Y isijThe numerical value of the corresponding similarity score;
the P isijThe alpha value is the cumulative average of the first similarity score;
said EjAnd dividing the corresponding sub-value information entropy for the corresponding similarity.
The weight calculation function is a function including:
said EiThe sub-value information entropy corresponding to the first similarity score;
the W isiAnd weighing the monomer component indexes corresponding to the corresponding sub-value information entropies.
Further, the monomer component comprehensive index calculation method comprises the following steps: determining a fitness score by a monomer component comprehensive index function, wherein the monomer component comprehensive index function comprises:
S=W1xα+ W2xβ；
the alpha is a first similarity score;
beta is a second similarity score;
the W is1A weight that is a first similarity score;
the W is2A weight that is a second similarity score;
and S is a monomer component comprehensive index.
A Chinese medicinal prescription effective component drug effect fitting prediction system comprises:
the Chinese medicinal prescription active ingredient drug effect fitting module: the method is applied to the fitting prediction method of the drug effect of the effective components of the traditional Chinese medicine formula.
The beneficial technical effects are as follows:
the method adopts pretreatment based on pharmacodynamic grading screening of each monomer component of the traditional Chinese medicine prescription, and determines the pharmacodynamic fitting degree score of each monomer component of the traditional Chinese medicine prescription through comprehensive analysis of pharmacodynamic fitting degree model prediction, and because the model simultaneously brings related elements such as 'specific item', 'gene name participating under the item' and 'significance of the item' into consideration by jointly applying relevant technical means of traditional Chinese medicine network pharmacology and bioinformatics and combining relevant concepts of enrichment analysis, the method aims to screen potential monomer effective components similar to the overall action of the traditional Chinese medicine prescription in the aspects of biological function and pharmacological mechanism from the traditional Chinese medicine prescription, thereby providing a virtual research technical means for promoting the modernization of the traditional Chinese medicine; in the field, a model relating to the degree of matching between a traditional Chinese medicine prescription and the efficacy of an active ingredient is recently reported; the scheme is that the pharmacodynamic grading screening of each monomer component of the traditional Chinese medicine is carried out, the data preprocessing is mainly carried out on the basis of the general table of the traditional Chinese medicine and the corresponding monomer component sub-table, and the fitting degree score is determined by a comprehensive index calculation method including a prediction entropy weight method according to the preprocessed data.
Drawings
FIG. 1 is a flow chart of the method for predicting the drug effect of the active ingredients of the Chinese medicinal composition by fitting.
Detailed Description
The invention is further described below with reference to the accompanying drawings:
in the figure:
s101, determining a first updating sub-table of corresponding monomer components by a first screening method based on a general table of the traditional Chinese medicine formula and a sub-table of the corresponding monomer components;
s102, determining corresponding first similarity scores between the general table of the traditional Chinese medicine prescription and the corresponding first updated sub-tables of the monomer components by a first similarity score calculation method based on the corresponding first updated sub-tables of the monomer components;
s103, determining a second updated sublist of the corresponding monomer components through a second screening method based on the first updated sublist of the corresponding monomer components;
s104, determining corresponding second similarity scores between the general Chinese medicine formula table and the corresponding second updated sub-tables of the monomer components by a second similarity score calculation method based on the corresponding second updated sub-tables of the monomer components;
s105, determining corresponding monomer component index weights between the general table of the traditional Chinese medicine formula and the corresponding second updated sub-table of the monomer components by a prediction entropy weight method based on the corresponding second updated sub-table of the monomer components;
s106, determining the fitting degree score between the traditional Chinese medicine formula general table and the corresponding monomer component table through a corresponding monomer component comprehensive index calculation method based on the corresponding monomer component index weight, the first similarity score and the second similarity score.
Example (b):
in this embodiment: as shown in fig. 1, a method for predicting the drug effect of active ingredients of a Chinese medicinal composition by fitting comprises the following steps:
and (3) determining the pharmacodynamic fit degree score of each monomer component of the Chinese medicinal formula through comprehensive analysis of pharmacodynamic fit degree model prediction based on the pretreatment of pharmacodynamic grading screening of each monomer component of the Chinese medicinal formula.
Because the model is a comprehensive analysis based on the prediction of a pharmacodynamic fitting degree model, related technical means of network pharmacology and bioinformatics of the traditional Chinese medicine are jointly applied, and related concepts of enrichment analysis are combined, related elements such as 'specific items', 'gene names participating in the items', and 'significance of the items' are simultaneously brought into consideration, and the model aims to screen potential monomer effective components similar to the overall effect of the traditional Chinese medicine in terms of biological functions and pharmacological mechanisms from the traditional Chinese medicine, thereby providing a virtual research technical means for promoting the modernization of the traditional Chinese medicine; in the field, a model relating to the degree of matching between a traditional Chinese medicine prescription and the efficacy of an active ingredient is recently reported; the scheme is that the pharmacodynamic grading screening of each monomer component of the traditional Chinese medicine is carried out, the data preprocessing is mainly carried out on the basis of the general table of the traditional Chinese medicine and the corresponding monomer component sub-table, and the fitting degree score is determined by a comprehensive index calculation method including a prediction entropy weight method according to the preprocessed data.
The pretreatment of the drug effect grading screening of each monomer component of the traditional Chinese medicine prescription comprises the following steps:
determining a first updating sub-table S101 of corresponding monomer components by a first screening method based on the general table of the traditional Chinese medicine formula and the corresponding monomer component sub-table;
based on the corresponding first updated sub-table of the monomer components, determining corresponding first similarity values between the general table of the traditional Chinese medicine prescription and the corresponding first updated sub-table of the monomer components by a first similarity value calculation method S102;
determining a corresponding second updated sub-table of monomer components by a second screening method based on the corresponding first updated sub-table of monomer components S103;
and determining corresponding second similarity score S104 between the general table of the Chinese medicinal formula and the corresponding second updated sub-table of the monomer components by a second similarity score calculation method based on the corresponding second updated sub-table of the monomer components.
The pretreatment of the drug effect grading screening of each monomer component of the traditional Chinese medicine prescription comprises the following steps: determining a first updating sub-table of corresponding monomer components by a first screening method based on the general table of the traditional Chinese medicine formula and the corresponding monomer component sub-table; based on the corresponding first updated sub-tables of the monomer components, determining corresponding first similarity scores between the general table of the traditional Chinese medicine prescription and the corresponding first updated sub-tables of the monomer components by a first similarity score calculation method; a second updated sub-table of corresponding monomer components is determined by a second screening method based on the corresponding first updated sub-table of monomer components. And determining corresponding second similarity scores between the general table of the traditional Chinese medicine and the corresponding second updating sub-tables of the monomer components by a second similarity score calculation method based on the corresponding second updating sub-tables of the monomer components, wherein the general table and the sub-tables are arranged into a first column to be specific item names (Terms), the second column is specific gene (Genes) names participating under the items, and the third column is significance values (P-Value) of the items, and the tables are called by the model program. By this procedure, entries (term) with P-Value greater than 0.05 in each table are first culled. Then, respectively calculating similarity scores alpha of term and the total table in each sub-table, further screening out term which is the same as the total table in each sub-table, and entering the next round of calculation, in other words, the total table can be thought of as a 'roster', the roster has n rows and 3 columns (matrix of n multiplied by 3), the first column is the significance value of the item, the second column is the specific item name, and the third column is the specific gene; the method comprises the following steps that (1) a student registration sub-table and a roster general table are assumed to exist, the sub-table can be understood as summary of characteristics of a student, and the general table can be understood as standard answers of two classes (term is assumed to be language, and gene is mathematics) in an examination; the first step is that all rows with P larger than 0.05 in the two tables are deleted, which is equivalent to updating each table once; the second step is that aiming at the two updated tables, the score alpha of the student about term (language) is calculated, namely the term number of the sub-table which is the same as the total table is divided by the term number of the total table; and the third step is to delete all rows with different terms in the sub-tables and the general table, only the rows with the same terms are reserved, which is equivalent to updating the two tables again, so as to carry out the next calculation.
The comprehensive analysis of the pharmacodynamic fitness model prediction comprises:
based on the corresponding second updated sub-table of the monomer components, determining corresponding index weights of the monomer components between the general table of the Chinese medicinal formula and the corresponding second updated sub-table of the monomer components by a prediction entropy weight method S105;
and determining the fitting degree score S106 between the traditional Chinese medicine formula general table and the corresponding monomer component table by a corresponding monomer component comprehensive index calculation method based on the corresponding monomer component index weight, the first similarity score and the second similarity score.
The comprehensive analysis of the pharmacodynamic fitness model prediction comprises the following steps: based on the corresponding second updated sub-table of the monomer components, determining corresponding index weight of the monomer components between the general table of the traditional Chinese medicine formula and the corresponding second updated sub-table of the monomer components by a prediction entropy weight method; based on the corresponding monomer component index weight, the first similarity score and the second similarity score, the fitting degree score between the traditional Chinese medicine formula general table and the corresponding monomer component sub-table is determined by a corresponding monomer component comprehensive index calculation method, as the fourth step is to calculate the score beta of the gene (mathematics), namely, the updated sub-table and the updated general table are subjected to related gene comparison, the calculation method is exemplified by: now that the contents of the sub-table and the total table relation term are the same, then in the first row, let the gene of the sub-table in the row be abc, and the gene of the total table in the row be abcd, then β 1 of the "row" is 3/4; in the second row, assuming that the gene of the sub-table in the row is abcd and the gene of the total table in the row is abc, the β 2 of the "row" is 5/3. Finally, calculating the average value of the beta of each row to be used as the final beta value (mathematical achievement) of the student; the fifth step is to calculate the weights (w 1 and w 2) of the two subjects of language and mathematics, and to determine the weights by an entropy weight method so as to finally calculate the weighted average performance of the students. After the language achievement (α), the mathematical achievement (β) and the weights (W1 and W2) of the two subjects of each student (sub-table) are obtained, the overall achievement (weighted average achievement) of each student (sub-table) is obtained from the formula (W1 × α + W2 ×) and the prediction of the whole model is completed.
The first screening method comprises:
and if the monomer component significance value of the corresponding monomer component sub-table is greater than 0.05, deleting the monomer component record with the corresponding significance value of greater than 0.05 to form a corresponding monomer component first updating sub-table.
The first screening method comprises the following steps: if the monomer component significance value of the corresponding monomer component sub-table is greater than 0.05, deleting the monomer component record with the corresponding significance value of greater than 0.05 to form a corresponding monomer component first updating sub-table, and deleting all rows with P greater than 0.05 in the two tables in the first step, which is equivalent to updating each table once;
the first similarity score calculating method comprises the step of determining a first similarity score through a first similarity score function, wherein the first similarity score function comprises the following steps:
α=T’/T；
the alpha is a first similarity score;
the T' is the number of the same item names of the corresponding monomer ingredient table and the traditional Chinese medicine general table;
and T is the number of the item names of the Chinese medicinal prescription general table.
Since the method for calculating the first similarity score comprises the step of determining the first similarity score through a first similarity score function, the first similarity score function comprises the following steps: α = T'/T; the alpha is a first similarity score; the T' is the number of the same item names of the corresponding monomer ingredient table and the traditional Chinese medicine general table; the value of T is the number of the entry names of the general table of the chinese medicine formulae, and since the score α of the student with respect to term (language) is calculated for the two updated tables, i.e., the score α of the similarity between term and the general table in each sub-table is calculated, the score α of the similarity is calculated for term and the general table. In a biological sense, "term" may then refer to both the specific biological function involved in the selected drug and the molecular signaling pathway involved in its regulation. Generally, drugs will have similar pharmacological effects if they participate in similar biological functions or molecular signaling pathways. Therefore, in the first screening process, the index of "term" is considered in an important way, the selected monomer is compared with the prescription at this level, and the purpose is to screen out items with the same action as the prescription in terms of biological function and signal path from a macroscopic view, so that the method has very important purpose and action for further locking potential effective monomer components.
The second screening method comprises:
if the entry names of the general table of the Chinese medicinal formulae are different from the entry names of the corresponding monomer component sub-tables, deleting the monomer component records with the different entry names to form corresponding monomer component second updating sub-tables.
The second screening method comprises the following steps: if the entry names of the Chinese medicinal prescription general table are different from the entry names of the corresponding monomer component sub-tables, deleting the monomer component records with different entry names to form corresponding monomer component second updating sub-tables, and entering the next round of calculation due to the fact that term which is the same as the general table in each sub-table is screened out, namely deleting all rows which are different from term in the sub-tables and the general table, only keeping the rows of the same term, namely updating the two tables by 'again', and further carrying out the next data processing;
the second similarity score calculation method includes determining a second similarity score by a second similarity score function, the second similarity score function including:
β=G’/G；
beta is a second similarity score;
g' is the number of corresponding specific genes recorded by the monomer components in the corresponding monomer component table;
g is the number of corresponding specific genes in a general table of Chinese medicinal formulas;
the second similarity score calculation method comprises the step of determining the second similarity score through a second similarity score function, wherein the second similarity score function comprises the following steps: β = G'/G; since the calculation of the similarity score β for the gene name (gene) was performed for the selected sublets. The calculation method of the beta comprises the following steps: assuming that the name (gene) of the gene involved in a particular entry (term) of a certain sub-table is abc and the name (gene) of the gene involved in the term in the general table is abcd, the similarity score is 3/4; assuming that the gene in a term of a sub-table is abcde and the gene of the term of the general table is abc, the similarity score is 5/3. And calculating the similarity score of each term and averaging to finally obtain the similarity score beta of the sublist, wherein the similarity score beta is another important parameter in model prediction. Thus, in a biological sense, "gene" refers to all genes involved in a particular biological function or molecular signaling pathway. Generally, when the drug acts, the expression level of the relevant target gene is regulated and changed. Therefore, in the second screening process, the index of the gene is included, and the selected monomer is compared with the prescription in the aspect from a microscopic angle, so that the name and the number of the genes participating in the same "term" are screened and compared from the term "with the same biological function and signal path, and the important purpose and effect are achieved for further carrying out drug effect fitting.
The prediction entropy weight method comprises the following steps:
based on the standardized corresponding monomer component second updating sub-table, determining corresponding sub-value information entropy through an information entropy processing function, and determining monomer component index weight through a weight calculation function based on the sub-value information entropy;
the information entropy processing function comprises:
said Y isijThe numerical value of the corresponding similarity score;
the P isijThe alpha value is the cumulative average of the first similarity score;
said EjAnd dividing the corresponding sub-value information entropy for the corresponding similarity.
The weight calculation function is a function including:
said EiThe sub-value information entropy corresponding to the first similarity score;
the W isiAnd weighing the monomer component indexes corresponding to the corresponding sub-value information entropies.
The adoption of the prediction entropy weight method comprises the following steps: based on the standardized corresponding monomer component second updating sub-table, determining corresponding sub-value information entropy through an information entropy processing function, and determining monomer component index weight through a weight calculation function based on the sub-value information entropy;
the information entropy processing function comprises:
the weight calculation function is a function including:
the entropy weight method comprises the following steps: assuming that five sub-tables (five students) are provided, the respective Chinese (alpha) and mathematics (beta) scores of the five sub-tables are known, (1) the score values of two grades of all students are subjected to standardization processing to respectively calculate 'information entropy' of two grades of Chinese and mathematics, and the calculation method is as follows:
y in the above formulai,jIs the score of each student after standardization;
then, the weight of each family is obtained according to the following formula;
the monomer component comprehensive index calculation method comprises the following steps: determining a fitness score by a monomer component comprehensive index function, wherein the monomer component comprehensive index function comprises:
S=W1xα+ W2xβ；
the alpha is a first similarity score;
beta is a second similarity score;
the W is1Is the first similarityA weight of the score;
the W is2A weight that is a second similarity score;
and S is a monomer component comprehensive index.
The method for calculating the comprehensive index of the monomer components comprises the following steps: determining a fitness score by a monomer component comprehensive index function, wherein the monomer component comprehensive index function comprises: s = W1x α + W2x β; the alpha is a first similarity score; beta is a second similarity score; w1 is the weight of the first similarity score; w2 is the weight of the second similarity score; for example, after obtaining the language achievement (α), the mathematical achievement (β) and the weights (W1 and W2) of the subjects in each sub-table, the overall achievement (weighted average achievement) of each student (sub-table) is obtained according to the formula (W1 × α + W2 ×).
A Chinese medicinal prescription effective component drug effect fitting prediction system comprises:
the Chinese medicinal prescription active ingredient drug effect fitting module: the method is used for realizing the fitting prediction method of the drug effects of the effective components of the traditional Chinese medicine formula.
Meanwhile, the invention also provides a Chinese medicinal prescription active ingredient drug effect fitting prediction system, which utilizes the application of the Chinese medicinal prescription active ingredient drug effect fitting prediction method, and the model mainly carries out program operation in a Python language environment, and has the advantages of strong function, simple and convenient operation, and convenient implementation and prediction.
The working principle is as follows:
the pretreatment of the patent through the drug effect grading screening of each monomer component of the traditional Chinese medicine prescription comprises the following steps: determining a first updating sub-table of corresponding monomer components by a first screening method based on the general table of the traditional Chinese medicine formula and the corresponding monomer component sub-table; based on the corresponding first updated sub-tables of the monomer components, determining corresponding first similarity scores between the general table of the traditional Chinese medicine prescription and the corresponding first updated sub-tables of the monomer components by a first similarity score calculation method; a second updated sub-table of corresponding monomer components is determined by a second screening method based on the corresponding first updated sub-table of monomer components. And determining corresponding second similarity scores between the general table of the traditional Chinese medicine and the corresponding second updating sub-tables of the monomer components by a second similarity score calculation method based on the corresponding second updating sub-tables of the monomer components, wherein the general table and the sub-tables are arranged into a first column to be specific item names (Terms), the second column is specific gene (Genes) names participating under the items, and the third column is significance values (P-Value) of the items, and the tables are called by the model program. By this procedure, entries (term) with P-Value greater than 0.05 in each table are first culled. Then, respectively calculating similarity scores alpha of term and the total table in each sub-table, further screening out term which is the same as the total table in each sub-table, and entering the next round of calculation, in other words, the total table can be thought of as a 'roster', the roster has n rows and 3 columns (matrix of n multiplied by 3), the first column is the significance value of the item, the second column is the specific item name, and the third column is the specific gene; the method comprises the following steps that (1) a student registration sub-table and a roster general table are assumed to exist, the sub-table can be understood as summary of characteristics of a student, and the general table can be understood as standard answers of two classes (term is assumed to be language, and gene is mathematics) in an examination; the first step is that all rows with P larger than 0.05 in the two tables are deleted, which is equivalent to updating each table once; the second step is that aiming at the two updated tables, the score alpha of the student about term (language) is calculated, namely the term number of the sub-table which is the same as the total table is divided by the term number of the total table; and the third step is to delete all rows with different terms in the sub-tables and the general table, only the rows with the same terms are reserved, which is equivalent to updating the two tables again, so as to carry out the next calculation. The comprehensive analysis of the pharmacodynamic fitness model prediction comprises: based on the corresponding second updated sub-table of the monomer components, determining corresponding index weight of the monomer components between the general table of the traditional Chinese medicine formula and the corresponding second updated sub-table of the monomer components by a prediction entropy weight method; based on the corresponding monomer component index weight, the first similarity score and the second similarity score, the fitting degree score between the traditional Chinese medicine formula general table and the corresponding monomer component sub-table is determined by a corresponding monomer component comprehensive index calculation method, as the fourth step is to calculate the score beta of the gene (mathematics), namely, the updated sub-table and the updated general table are subjected to related gene comparison, the calculation method is exemplified by: now that the contents of the sub-table and the total table relation term are the same, then in the first row, let the gene of the sub-table in the row be abc, and the gene of the total table in the row be abcd, then β 1 of the "row" is 3/4; in the second row, assuming that the gene of the sub-table in the row is abcd and the gene of the total table in the row is abc, the β 2 of the "row" is 5/3. Finally, calculating the average value of the beta of each row to be used as the final beta value (mathematical achievement) of the student; the fifth step is to calculate the weights (w 1 and w 2) of the two subjects of language and mathematics, and to determine the weights by an entropy weight method so as to finally calculate the weighted average performance of the students. After the language achievement (α), the mathematical achievement (β) and the weights (W1 and W2) of the two subjects of each student (sub-table) are obtained, the overall achievement (weighted average achievement) of each student (sub-table) is obtained from the formula (W1 × α + W2 ×) and the prediction of the whole model is completed. The water distributor is a bidirectional wireless communication remote control split type intelligent water distributor, can realize that a pipe column of an oil field water injection well completes water distribution and tests various functions, solves the problems of complex and various components and complex drug effect material basis in the formula of Chinese herbal medicines in the prior art, thereby leading the research on the action mechanism of the traditional Chinese medicine preparation to involve the change of a large number of complex molecules and related signal paths, therefore, potential monomer active ingredients in the traditional Chinese medicine formula are comprehensively elucidated from a molecular level system, the prediction model combines the traditional Chinese medicine principle with a big data method model, digitalizes the multi-component and multi-target pharmacodynamic characteristics, analyzes the comprehensive indexes of the effects, and has an important practical beneficial technical effect on promoting the modernization research of the traditional Chinese medicine.
The technical solutions of the present invention or similar technical solutions designed by those skilled in the art based on the teachings of the technical solutions of the present invention are all within the scope of the present invention to achieve the above technical effects.
Claims (10)
1. A method for predicting the drug effect fitting of effective ingredients of a traditional Chinese medicine is characterized by comprising the following steps:
and (3) determining the pharmacodynamic fit degree score of each monomer component of the Chinese medicinal formula through comprehensive analysis of pharmacodynamic fit degree model prediction based on the pretreatment of pharmacodynamic grading screening of each monomer component of the Chinese medicinal formula.
2. The method for predicting the drug effect fitting of the active ingredients of the Chinese medicinal prescription according to claim 1, wherein the pretreatment of the drug effect grading screening of the monomer ingredients of the Chinese medicinal prescription comprises:
determining a first updating sub-table of corresponding monomer components by a first screening method based on the general table of the traditional Chinese medicine formula and the corresponding monomer component sub-table;
based on the corresponding first updated sub-tables of the monomer components, determining corresponding first similarity scores between the general table of the traditional Chinese medicine prescription and the corresponding first updated sub-tables of the monomer components by a first similarity score calculation method;
determining a second updated sub-table of the corresponding monomer components by a second screening method based on the first updated sub-table of the corresponding monomer components;
and determining corresponding second similarity scores between the general table of the Chinese medicinal formula and the corresponding second updated sub-tables of the monomer components by a second similarity score calculation method based on the corresponding second updated sub-tables of the monomer components.
3. The method for predicting the pharmacodynamic fit of an active ingredient of a Chinese medicinal formulation according to claim 2, wherein the comprehensive analysis of the pharmacodynamic fit model prediction comprises:
based on the corresponding second updated sub-table of the monomer components, determining corresponding index weight of the monomer components between the general table of the traditional Chinese medicine formula and the corresponding second updated sub-table of the monomer components by a prediction entropy weight method;
and determining the fitting degree score between the traditional Chinese medicine formula general table and the corresponding monomer component table by a corresponding monomer component comprehensive index calculation method based on the corresponding monomer component index weight, the first similarity score and the second similarity score.
4. The method for predicting the drug efficacy of the active ingredients of the Chinese medicinal composition according to claim 3, wherein the first screening method comprises:
and if the monomer component significance value of the corresponding monomer component sub-table is greater than 0.05, deleting the monomer component record with the corresponding significance value of greater than 0.05 to form a corresponding monomer component first updating sub-table.
5. The method of claim 3, wherein the first similarity score calculating method comprises determining a first similarity score using a first similarity score function, the first similarity score function comprising:
α=T’/T；
the alpha is a first similarity score;
the T' is the number of the same item names of the corresponding monomer ingredient table and the traditional Chinese medicine general table;
and T is the number of the item names of the Chinese medicinal prescription general table.
6. The method for predicting the drug efficacy of the active ingredients of the Chinese medicinal composition according to claim 3, wherein the second screening method comprises:
if the entry names of the general table of the Chinese medicinal formulae are different from the entry names of the corresponding monomer component sub-tables, deleting the monomer component records with the different entry names to form corresponding monomer component second updating sub-tables.
7. The method of claim 3, wherein the second similarity score is calculated by determining a second similarity score using a second similarity score function, the second similarity score function comprising:
β=G’/G；
beta is a second similarity score;
g' is the number of corresponding specific genes recorded by the monomer components in the corresponding monomer component table;
and G is the number of corresponding specific genes in a general table of Chinese medicinal formulas.
8. The fit prediction method for the drug effects of the active ingredients of the Chinese medicinal preparation according to claim 3, wherein the entropy weight prediction method comprises:
based on the standardized corresponding monomer component second updating sub-table, determining corresponding sub-value information entropy through an information entropy processing function, and determining monomer component index weight through a weight calculation function based on the sub-value information entropy;
the information entropy processing function comprises:
said Y isijThe numerical value of the corresponding similarity score;
the P isijThe alpha value is the cumulative average of the first similarity score;
said EjCorresponding sub-value information entropies are respectively taken as corresponding similarity scores;
the weight calculation function is a function including:
said EiThe sub-value information entropy corresponding to the first similarity score;
the W isiAnd weighing the monomer component indexes corresponding to the corresponding sub-value information entropies.
9. The method for predicting the drug effect of the active ingredients of the Chinese medicinal prescription according to claim 3, wherein the method for calculating the comprehensive index of the monomer ingredients comprises the following steps: determining a fitness score by a monomer component comprehensive index function, wherein the monomer component comprehensive index function comprises:
S=W1xα+ W2xβ；
the alpha is a first similarity score;
beta is a second similarity score;
the W is1A weight that is a first similarity score;
the W is2A weight that is a second similarity score;
and S is a monomer component comprehensive index.
10. A Chinese medicinal prescription active ingredient drug effect fitting prediction system is characterized by comprising:
the Chinese medicinal prescription active ingredient drug effect fitting module: the application of the method for predicting the drug effect fitting of the active ingredients of the Chinese medicinal formulae disclosed in claims 1-10 is realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111018496.1A CN113611372A (en) | 2021-09-01 | 2021-09-01 | Method and system for predicting drug effect fitting of effective ingredients of traditional Chinese medicine prescription |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111018496.1A CN113611372A (en) | 2021-09-01 | 2021-09-01 | Method and system for predicting drug effect fitting of effective ingredients of traditional Chinese medicine prescription |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113611372A true CN113611372A (en) | 2021-11-05 |
Family
ID=78342483
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111018496.1A Pending CN113611372A (en) | 2021-09-01 | 2021-09-01 | Method and system for predicting drug effect fitting of effective ingredients of traditional Chinese medicine prescription |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113611372A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101046831A (en) * | 2006-03-31 | 2007-10-03 | 上海中医药大学 | Setting, computing method of Chinese medicine multi-component PK-PD combined mathematical module and software fit |
| CN101615222A (en) * | 2008-06-23 | 2009-12-30 | 中国医学科学院放射医学研究所 | A kind of Chinese prescription designing technique based on the Chinese medicine effective component group |
| CN104992077A (en) * | 2015-05-25 | 2015-10-21 | 江苏康缘药业股份有限公司 | Traditional Chinese medicine biological information processing method, apparatus and system |
| CN106485086A (en) * | 2016-10-19 | 2017-03-08 | 大连大学 | Human body composition Forecasting Methodology based on AIC and improvement entropy assessment |
| CN110533342A (en) * | 2019-09-04 | 2019-12-03 | 上海丙晟科技有限公司 | A kind of market shops evaluation method based on big data |
| CN111370140A (en) * | 2020-03-03 | 2020-07-03 | 杭州师范大学 | Node similarity-based Kmeans traditional Chinese medicine efficacy clustering method |
| CN112063708A (en) * | 2020-09-11 | 2020-12-11 | 成都中医药大学 | Method for screening active compound from traditional Chinese medicine and agent |
-
2021
- 2021-09-01 CN CN202111018496.1A patent/CN113611372A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101046831A (en) * | 2006-03-31 | 2007-10-03 | 上海中医药大学 | Setting, computing method of Chinese medicine multi-component PK-PD combined mathematical module and software fit |
| CN101615222A (en) * | 2008-06-23 | 2009-12-30 | 中国医学科学院放射医学研究所 | A kind of Chinese prescription designing technique based on the Chinese medicine effective component group |
| CN104992077A (en) * | 2015-05-25 | 2015-10-21 | 江苏康缘药业股份有限公司 | Traditional Chinese medicine biological information processing method, apparatus and system |
| CN106485086A (en) * | 2016-10-19 | 2017-03-08 | 大连大学 | Human body composition Forecasting Methodology based on AIC and improvement entropy assessment |
| CN110533342A (en) * | 2019-09-04 | 2019-12-03 | 上海丙晟科技有限公司 | A kind of market shops evaluation method based on big data |
| CN111370140A (en) * | 2020-03-03 | 2020-07-03 | 杭州师范大学 | Node similarity-based Kmeans traditional Chinese medicine efficacy clustering method |
| CN112063708A (en) * | 2020-09-11 | 2020-12-11 | 成都中医药大学 | Method for screening active compound from traditional Chinese medicine and agent |
Non-Patent Citations (1)
| Title |
|---|
| 王耘等: "利用网络药理学方法探讨针对新型冠状病毒肺炎以ACE2 为治疗靶点的5 味中药的作用机制和组分配伍", 中草药, vol. 51, no. 18, 30 September 2020 (2020-09-30), pages 4691 - 4694 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mu et al. | Potential compound from herbal food of Rhizoma Polygonati for treatment of COVID-19 analyzed by network pharmacology: Viral and cancer signaling mechanisms | |
| Farnsworth | The role of ethnopharmacology in drug development | |
| CN101441682A (en) | Biological information analysis platform of Chinese medicine effective substance mechanism and analysis method thereof | |
| Gaudillière | Better prepared than synthesized: Adolf Butenandt, Schering Ag and the transformation of sex steroids into drugs (1930–1946) | |
| CN102634450A (en) | Biological chip-based antidepressant drug curative effect risk evaluating system and application thereof | |
| Zhou et al. | Assessment of pulmonary infectious disease treatment with Mongolian medicine formulae based on data mining, network pharmacology and molecular docking | |
| CN113611372A (en) | Method and system for predicting drug effect fitting of effective ingredients of traditional Chinese medicine prescription | |
| Kong et al. | The current status and challenges of establishment and utilization of medical big data in China | |
| Perl et al. | The cohesive metaschema: a higher-level abstraction of the UMLS Semantic Network | |
| CN109545276B (en) | Drug discovery method based on epigenome and application thereof | |
| CN106266230A (en) | A kind of Chinese medicinal components compatibility optimization method based on uniform Design and artificial neural network | |
| US20040260721A1 (en) | Methods and systems for creation of a coherence database | |
| CN115691832A (en) | Method for analyzing anti-vitiligo action mechanism of galangin and application thereof | |
| CN115472236A (en) | Method for determining, characterizing and evaluating pharmacodynamic substances by utilizing imprinting template component cluster dynamics and thermodynamic equilibrium principle | |
| Li et al. | Systematic understanding of mechanism of Yi-Qi-Huo-Xue decoction against intracerebral hemorrhagic stroke using a network pharmacology approach | |
| CN113436727B (en) | Method for scoring cure probability of potential treatment plan based on patient detection information | |
| CN110211634A (en) | A kind of method of multiple groups data aggregate analysis | |
| Das et al. | Rice knowledge management portal for technology dissemination: a case study for Haryana, Punjab and Uttarakhand States | |
| Zhang et al. | Analysis of temporal expression profiles after sciatic nerve injury by bioinformatic method | |
| Guo et al. | Exploration in the mechanism of Zhisou san for the treatment of cough variant asthma based on network pharmacology | |
| Lin et al. | Clustering and the design of preference-assessment surveys in healthcare. | |
| Chun-Hong et al. | A new experimental design for screening Chinese medicine formula | |
| CN116087394B (en) | Screening method and application of liquorice honey-fried synergistic active ingredient | |
| Ekwall et al. | Standardization and validation | |
| CN114283902A (en) | Screening method and screening system for pharmaceutical composition and electronic 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 |