CN111785334B - Drug combination key factor data mining method and system - Google Patents
Drug combination key factor data mining method and system Download PDFInfo
- Publication number
- CN111785334B CN111785334B CN202010655590.7A CN202010655590A CN111785334B CN 111785334 B CN111785334 B CN 111785334B CN 202010655590 A CN202010655590 A CN 202010655590A CN 111785334 B CN111785334 B CN 111785334B
- Authority
- CN
- China
- Prior art keywords
- key factor
- factor data
- population
- fitness
- data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 35
- 239000000890 drug combination Substances 0.000 title claims abstract description 34
- 238000007418 data mining Methods 0.000 title claims abstract description 20
- 239000003814 drug Substances 0.000 claims abstract description 47
- 229940079593 drug Drugs 0.000 claims abstract description 37
- 206010067484 Adverse reaction Diseases 0.000 claims abstract description 32
- 230000006838 adverse reaction Effects 0.000 claims abstract description 32
- 230000002068 genetic effect Effects 0.000 claims abstract description 8
- 230000009466 transformation Effects 0.000 claims description 18
- 230000006798 recombination Effects 0.000 claims description 15
- 238000005215 recombination Methods 0.000 claims description 15
- 238000004458 analytical method Methods 0.000 claims description 14
- 230000008859 change Effects 0.000 claims description 11
- 230000004083 survival effect Effects 0.000 claims description 11
- 108090000623 proteins and genes Proteins 0.000 claims description 7
- 239000000725 suspension Substances 0.000 claims description 7
- 230000035772 mutation Effects 0.000 claims description 6
- 238000005065 mining Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000000546 chi-square test Methods 0.000 claims description 3
- 238000013075 data extraction Methods 0.000 claims description 3
- 238000010353 genetic engineering Methods 0.000 claims description 3
- 238000001325 log-rank test Methods 0.000 claims description 3
- 230000010076 replication Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 11
- 238000001647 drug administration Methods 0.000 abstract description 8
- 230000008569 process Effects 0.000 abstract description 5
- 231100000331 toxic Toxicity 0.000 abstract description 4
- 230000002588 toxic effect Effects 0.000 abstract description 4
- 238000006243 chemical reaction Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 19
- 229940108949 paclitaxel injection Drugs 0.000 description 8
- 241001533159 Brucea javanica Species 0.000 description 5
- 235000010889 Rhus javanica Nutrition 0.000 description 5
- 239000000839 emulsion Substances 0.000 description 5
- 229940090044 injection Drugs 0.000 description 5
- 239000007924 injection Substances 0.000 description 5
- 238000002347 injection Methods 0.000 description 5
- 230000003993 interaction Effects 0.000 description 5
- 210000000265 leukocyte Anatomy 0.000 description 4
- 238000004820 blood count Methods 0.000 description 3
- 230000014509 gene expression Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000011282 treatment Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000000144 pharmacologic effect Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 241000260732 Buteo regalis Species 0.000 description 1
- 206010013710 Drug interaction Diseases 0.000 description 1
- 241001166737 Menticirrhus nasus Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 239000004480 active ingredient Substances 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 238000011260 co-administration Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003285 pharmacodynamic effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
- 230000002110 toxicologic effect Effects 0.000 description 1
- 231100000027 toxicology Toxicity 0.000 description 1
- 229940126680 traditional chinese medicines Drugs 0.000 description 1
- 238000011269 treatment regimen Methods 0.000 description 1
- 229940126673 western medicines Drugs 0.000 description 1
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
- G16C20/50—Molecular design, e.g. of drugs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computing Systems (AREA)
- Chemical & Material Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Pharmacology & Pharmacy (AREA)
- Data Mining & Analysis (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Medicinal Chemistry (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Crystallography & Structural Chemistry (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to a drug combination key factor data mining method and system, comprising the following steps: s1, establishing an initial population comprising a plurality of individuals according to drug use data, wherein each individual represents a function of a group of key factor data and adverse reaction rate; s2, calculating the fitness of each individual, selecting a preset number of individuals according to the ranking order of the fitness from high to low, and carrying out genetic operation on the sub-population consisting of the individuals to obtain a new population; s3, calculating the fitness of each individual in the new population, judging whether the new population meets the requirements, and if so, outputting the function of the key factor data and the adverse reaction rate corresponding to the individual with the highest fitness in the new population; otherwise, returning to the step S2 to acquire a new population again; s4, setting key factor data of drug combination according to the output function. The method can be used for determining the efficacy and adverse reaction of drug combination more rapidly and accurately, evaluating the drug administration process and relieving the toxic and side effects caused by the mutual reaction between drugs.
Description
Technical Field
The invention relates to a method and a system for mining key factor data of drug combination, belonging to the technical field of drug application.
Background
The combination of two or more drugs is used for achieving the purpose of treatment, and the result is mainly to increase the curative effect of the drugs or to reduce the toxic and side effects of the drugs. The combination of medicines is based on the basic principle of improving the curative effect and/or reducing adverse reactions. When combined, interactions of the drugs include interactions that affect pharmacokinetics and interactions that affect pharmacodynamics. However, since the medicines are of various kinds and the interactions among the medicines are related to many factors, the selection of key factors such as the administration sequence, the administration interval, the administration dosage of the combined medicines, the administration frequency change and the like in the process of combining the medicines can determine the combination result of the medicines to a certain extent. If the key factors are reasonably selected, the advantages of the combination of the medicines can be brought into play to the maximum; conversely, the therapeutic effect may be reduced or even unpredictable damage may occur, and serious adverse reactions may occur. Especially, the combination of the traditional Chinese medicine and the western medicine is more and more common at present, and the traditional Chinese medicine has the characteristics of multiple components and multiple targets, so that the medicine has different effects on the treatment effect of symptoms in the compatibility application of single medicine and different prescriptions for a specific medicine. In addition, the basic theories of the traditional Chinese medicine and the western medicine have great differences, and the effective components, pharmacokinetics, drug interaction, pharmacological research, toxicological research and the like of many Chinese patent medicines are incomplete, so that the pharmacological property and the compatibility taboo of the combined medicine cannot be comprehensively and systematically mastered clinically. Therefore, how to reasonably select parameters of key factors of drug combination in a complex drug administration process becomes a non-negligible problem.
At present, the research on the problem mainly adopts integration of real data with reliable sources on the basis of descriptive statistics to form relevant large database resources for data mining analysis. However, the existing related data mining method has relatively low inspection efficiency, has different limitations, and is a technical problem which needs to be solved in the field, namely how to develop a data mining algorithm with high sensitivity and specificity, quickly and effectively explore the hidden internal rule of combined medication, mine valuable combined medication information, ensure medication safety and provide reference for verification, induction and expansion of related treatment strategies.
Disclosure of Invention
Aiming at the technical problems, the invention aims to provide a drug combination key factor data mining method and system, which are used for determining the efficacy and adverse reaction of drug combination by using a gene expression programming algorithm, have high sensitivity and specificity and accurate results, ensure that the drug combination administration mode is more reasonable, and reduce the possibility of adverse reaction generated by drug combination.
In order to achieve the above purpose, the invention provides a drug combination key factor data mining method, which comprises the following steps: s1, establishing an initial population comprising a plurality of individuals according to drug use data, wherein each individual represents a function of a group of key factor data and adverse reaction rate; s2, calculating the fitness of each individual, selecting a preset number of individuals according to the ranking order of the fitness from high to low, and carrying out genetic operation on the sub-population consisting of the individuals to obtain a new population; s3, calculating the fitness of each individual in the new population, judging whether the new population meets the requirements, and if so, outputting the function of the key factor data and the adverse reaction rate corresponding to the individual with the highest fitness in the new population; otherwise, returning to the step S2 to acquire a new population again; s4, setting key factor data of drug combination according to the output function.
Further, key factors include: the type of drug (Chinese/Western), the order of administration, the interval of administration, the dosage of administration, the frequency of administration and the interval of time.
Further, each individual includes a two-dimensional vector composed of a biochemical index and time, the two-dimensional vector is mapped to a complex space, wherein the biochemical index is a real part, the time is an imaginary part, and the key factor data is subjected to function operation according to the two-dimensional phasors in the complex space to calculate the fitness of the individual.
Further, genetic manipulation in S2 includes selection, replication, mutation, inversion, transformation, recombination, random constant mutation, and random constant transformation.
Further, the transformation includes IS transformation, RIS transformation, and gene transformation; recombination includes single-point recombination, two-point recombination and gene recombination.
Further, the method for judging whether the new population meets the requirements in S3 is as follows: increasing the value of any biochemical index in the two-dimensional vector, keeping the key factor data unchanged, judging whether the change value of the occurrence rate of the adverse reaction exceeds a threshold value, and if the change value of the occurrence rate of the adverse reaction does not exceed the threshold value, determining the population at the moment as a final output population; if the change value of the occurrence rate of the adverse reaction exceeds the threshold value, the step S2 is returned.
Further, the optimal combination of drugs is assessed by survival analysis and/or trend score matching methods.
Further, the survival analysis method comprises the following steps: inputting data, analyzing the data type, identifying the data as classified data or continuous data, grouping and calculating the classified data, calculating the suspension value of each row of continuous data, and obtaining the optimal grouping mode and suspension value by chi-square test or logrank test to generate a survival analysis graph.
Further, the tendency value scoring and matching method comprises the following steps: inputting data, scoring tendency, selecting a column to be analyzed, filling a control group, selecting one-to-one matching or one-to-many matching, generating a matching result, and displaying the matching result.
The invention also discloses a drug combination key factor data mining system, which comprises: the data extraction module is used for establishing an initial population comprising a plurality of individuals according to the drug use data, wherein each individual represents a function of a group of key factor data and adverse reaction rate; the new population generation module is used for calculating the fitness of each individual, selecting a preset number of individuals according to the ranking sequence of the fitness from high to low, and carrying out genetic operation on the sub population formed by the individuals to obtain a new population; the judging module is used for calculating the fitness of each individual in the new population, judging whether the new population meets the requirements, and outputting the function of the key factor data and the adverse reaction rate corresponding to the individual with the highest fitness in the new population if the new population meets the requirements; otherwise, returning to the step S2 to acquire a new population again; and the result output module is used for setting key factor data of the drug combination according to the output function.
Due to the adoption of the technical scheme, the invention has the following advantages: 1. the gene expression programming algorithm is used for determining the efficacy and adverse reaction of drug combination, the result is more accurate, the drug administration process is evaluated, the drug combination using problems of drug combination such as the change of the drug administration sequence, the drug administration interval, the drug administration dosage and the drug administration frequency are more reasonable, and a better treatment effect is achieved; 2. the toxic and side effects caused by the mutual reaction between medicines are reduced, and the safety of the medicine is improved; 3. the method is particularly suitable for the combination of traditional Chinese medicines and western medicines with complex components and undefined active ingredients.
Drawings
FIG. 1 is a flow chart of a method of drug combination in an embodiment of the invention.
Detailed Description
The present invention will be described in detail with reference to specific examples thereof in order to better understand the technical direction of the present invention by those skilled in the art. It should be understood, however, that the detailed description is presented only to provide a better understanding of the invention, and should not be taken to limit the invention. In the description of the present invention, it is to be understood that the terminology used is for the purpose of description only and is not to be interpreted as indicating or implying relative importance.
Example 1
The embodiment provides a drug combination key factor data mining method, which comprises the following steps:
s1, establishing an initial population comprising a plurality of individuals according to drug use data, wherein each individual represents a function of a group of key factor data and adverse reaction rate;
s2, calculating the fitness of each individual, selecting a preset number of individuals according to the ranking order of the fitness from high to low, and carrying out genetic operation on the sub-population consisting of the individuals to obtain a new population;
s3, calculating the fitness of each individual in the new population, judging whether the new population meets the requirements, and if so, outputting the function of the key factor data and the adverse reaction rate corresponding to the individual with the highest fitness in the new population; otherwise, returning to the step S2 to acquire a new population again;
s4, setting key factor data of drug combination according to the output function.
Key factors in this embodiment include: the type of drug (Chinese/Western), the order of administration, the interval of administration, the dosage of administration, the frequency of administration and the interval of time.
The gene expression programming algorithm (GEP) is one of genetic evolution algorithms, and has been well applied in multiple fields such as complex function mining, data classification, time sequence prediction and the like in recent years, which shows that the GEP algorithm is an effective complex function mining method. In the embodiment, the GEP algorithm is applied to analysis of curative effect and adverse reaction of drug combination, the result is more accurate, the drug administration process is evaluated, and toxic and side effects caused by interaction among drugs are reduced.
In step S1 of this embodiment, first, data is extracted from drug use data, and the data is required to be converted into a data type capable of boolean operations, which includes boolean types and number types. The boolean type may be a custom type, but is typically default to True/False. Second, GEM parameters are adjusted according to the data amount and data type, including but not limited to gene length, maximum iteration number, random number range, etc.
Each individual comprises a two-dimensional vector consisting of a biochemical index and time, the two-dimensional vector is mapped to a complex space, the biochemical index is a real part, the time is an imaginary part, and the key factor data is subjected to function operation according to the two-dimensional phasors in the complex space to calculate the fitness of the individual. In order to meet the complex function operation requirement, operations corresponding to the real part and the imaginary part are defined in the present embodiment, for example, the real part of a=1+1j and the real part of b=2+2j are larger than the operation, i.e. groter_real (a, B) =groter (a.real, b.real) =groter (1, 2) =false), and the operations of other functions can be similarly deduced. The functional operations in this embodiment include, but are not limited to and, or, greater than and less than operations.
Genetic manipulation in step S2 includes selection, replication, mutation, inversion, transformation, recombination, random constant mutation, and random constant transformation. Wherein the transformation includes IS transformation, RIS transformation and gene transformation; recombination includes single-point recombination, two-point recombination and gene recombination.
The method for judging whether the new population meets the requirements in the step S3 is as follows: increasing the value of any biochemical index in the two-dimensional vector, keeping the key factor data unchanged, judging whether the change value of the occurrence rate of the adverse reaction exceeds a threshold value, and if the change value of the occurrence rate of the adverse reaction does not exceed the threshold value, determining the population at the moment as a final output population; if the change value of the occurrence rate of the adverse reaction exceeds the threshold value, the step S2 is returned.
In step S4, key factor data mined according to the output function is displayed through a table, that is, screening conditions, a threshold value, a validity improvement degree, an effective data amount and an evaluation value of the mining result, and a user selects the required effective data according to requirements.
To further evaluate the best combination of drugs, this example evaluates them by survival analysis methods and/or trend score matching methods.
The survival analysis method comprises the following steps: the method comprises the steps of inputting data, selecting a column needing to be subjected to survival analysis according to the input data, analyzing the data type, identifying the data as classified data or continuous data, modifying the classified result by a user or optimizing the classified result through an algorithm model, performing grouping calculation on the classified data after determining that the modified result is correct, performing suspension value calculation on each column of continuous data, obtaining an optimal grouping mode and suspension value by chi-square test or log-rank test, generating a graph according to the analysis result, marking the optimal grouping mode or suspension value point, and checking a survival curve corresponding to the corresponding grouping mode. After confirming that the grouping mode is correct, selecting to export a survival analysis graph.
The tendency value scoring and matching method comprises the following steps: selecting security analysis, inputting data to be analyzed, scoring tendency, selecting columns to be analyzed, simultaneously filling a control group, selecting one-to-one matching or one-to-many matching, simultaneously modifying corresponding configuration parameters, generating a matching result, and displaying the matching result in HTML (hypertext markup language) preferably. In addition, other manners of displaying, such as directly displaying in the form of a table, a picture, or the like, may be adopted.
Example two
Based on the same inventive concept, the embodiment also discloses a drug combination key factor data mining system, which comprises:
the data extraction module is used for establishing an initial population comprising a plurality of individuals according to the drug use data, wherein each individual represents a function of a group of key factor data and adverse reaction rate;
the new population generation module is used for calculating the fitness of each individual, selecting a preset number of individuals according to the ranking sequence of the fitness from high to low, and carrying out genetic operation on the sub population formed by the individuals to obtain a new population;
the judging module is used for calculating the fitness of each individual in the new population, judging whether the new population meets the requirements, and outputting the function of the key factor data and the adverse reaction rate corresponding to the individual with the highest fitness in the new population if the new population meets the requirements; otherwise, returning to the step S2 to acquire a new population again;
and the result output module is used for setting key factor data of the drug combination according to the output function.
Example III
In order to verify the effect of the data mining method and system in the invention, the technical scheme of the invention is obtained by comparing the incidence rate of adverse reaction under the condition that the brucea javanica oil emulsion injection and the paclitaxel injection are used together with the paclitaxel injection aloneValidity of the protocol. Wherein the adverse reaction rate is represented by abnormal white blood cell count. In this embodiment, drug ydzyr is used to represent a single dose of the brucea javanica oil emulsion injection; the drug YDZYR_time_suffix is used for representing the administration time of the brucea javanica oil emulsion injection; drug zsc is used to represent single dose of paclitaxel injection, drug zsc_time_suffix is used to represent time of administration of paclitaxel injection, WBC is used to represent white blood cell count. Normal values for white blood cell count are: 4-10*10 9 and/L.
Wherein, parameters of the paclitaxel injection used alone are shown in table 1:
TABLE 1 parameters for paclitaxel injection alone
Parameters of the brucea javanica oil emulsion injection and paclitaxel injection combined use condition are shown in table 2.
TABLE 2 parameters in the case of Co-administration of brucea javanica oil emulsion injection and paclitaxel injection
The result of chi-square verification of the above data is shown in table 3.
TABLE 3 results of chi-square verification
Wherein df is the degree of freedom. The concomitance probability P is a progressive Sig (bilateral) value corresponding to the Pearson chi-square, which is 0.014 and less than 0.05, which shows that the two experimental results have significant differences, and proves that the technical scheme is feasible.
The foregoing is merely a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes or substitutions should be covered in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (9)
1. The drug combination key factor data mining method is characterized by comprising the following steps of:
s1, establishing an initial population comprising a plurality of individuals according to drug use data, wherein each individual represents a function of a group of key factor data and adverse reaction rate;
s2, calculating the fitness of each individual according to the function, arranging the individuals from high to low according to the fitness, selecting a sub population consisting of the individuals with high fitness in the individuals, and carrying out genetic operation on the sub population to obtain a new population;
s3, calculating the fitness of each individual in the new population, judging whether the new population meets the requirements, and if so, outputting the function of the key factor data and the adverse reaction rate corresponding to the individual with the highest fitness in the new population; otherwise, returning to the step S2 to acquire a new population again;
s4, setting key factor data of drug combination according to the function output in the step S3;
each initial population of the individual comprises a two-dimensional vector composed of a biochemical index and time, the two-dimensional vector is mapped to a complex space, the biochemical index is a real part, the time is an imaginary part, and the key factor data are subjected to function operation according to the two-dimensional vector in the complex space so as to calculate the fitness of the individual.
2. The drug combination key factor data mining method of claim 1, wherein the key factors include: drug type, order of administration, interval of administration, dose of administration, frequency of administration, and time interval.
3. The drug combination key factor data mining method according to claim 2, wherein the genetic manipulation in S2 includes selection, replication, mutation, inversion, transformation, recombination, random constant mutation, and random constant transformation.
4. The drug combination key factor data mining method according to claim 3, wherein the transformation includes IS transformation, RIS transformation and gene transformation; the recombination includes single-point recombination, two-point recombination and gene recombination.
5. The method for mining pharmaceutical combination key factor data according to claim 1, wherein the method for determining whether the new population meets the requirement in S3 is as follows: the value of any biological index in the two-dimensional vector is improved, the key factor data is unchanged, whether the change value of the occurrence rate of the adverse reaction at the moment exceeds a threshold value is judged, and if the change value of the occurrence rate of the adverse reaction at the moment does not exceed the threshold value, the population at the moment is the final output population; if the change value of the occurrence rate of the adverse reaction exceeds the threshold value, the step S2 is returned.
6. The drug combination key factor data mining method according to any of claims 1 to 5, wherein the optimal combination of drugs is assessed by survival analysis and/or trend score matching.
7. The drug combination key factor data mining method according to claim 6, wherein the survival analysis method comprises the following steps: inputting data, analyzing the data type, identifying the data as classified data or continuous data, carrying out grouping calculation on the classified data, carrying out suspension value calculation on each row of continuous data, obtaining an optimal grouping mode and suspension value by chi-square test or logrank test, and generating a survival analysis graph.
8. The drug combination key factor data mining method according to claim 6, wherein the trend value score matching method comprises the following steps: inputting data, scoring the tendency of the data, selecting a column to be analyzed, filling a control group, selecting one-to-one matching or one-to-many matching, generating a matching result, and displaying the matching result.
9. A drug combination key factor data mining system, comprising:
the data extraction module is used for establishing an initial population comprising a plurality of individuals according to the drug use data, wherein each individual represents a function of a group of key factor data and adverse reaction rate;
the new population generation module is used for calculating the fitness of each individual, selecting a sub population consisting of individuals with high fitness in the individuals according to the sequence arrangement of the fitness from high to low, and carrying out genetic operation on the sub population to obtain a new population;
the judging module is used for calculating the fitness of each individual in the new population, judging whether the new population meets the requirements, and outputting the function of the key factor data and the adverse reaction rate corresponding to the individual with the highest fitness in the new population if the new population meets the requirements; otherwise, returning to the step S2 to acquire a new population again;
the result output module is used for setting key factor data of the drug combination according to the output function;
each initial population of the individual comprises a two-dimensional vector composed of a biochemical index and time, the two-dimensional vector is mapped to a complex space, the biochemical index is a real part, the time is an imaginary part, and the key factor data are subjected to function operation according to the two-dimensional vector in the complex space so as to calculate the fitness of the individual.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010655590.7A CN111785334B (en) | 2020-07-09 | 2020-07-09 | Drug combination key factor data mining method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010655590.7A CN111785334B (en) | 2020-07-09 | 2020-07-09 | Drug combination key factor data mining method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111785334A CN111785334A (en) | 2020-10-16 |
| CN111785334B true CN111785334B (en) | 2024-02-06 |
Family
ID=72759279
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010655590.7A Active CN111785334B (en) | 2020-07-09 | 2020-07-09 | Drug combination key factor data mining method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111785334B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118412142A (en) * | 2024-06-19 | 2024-07-30 | 浙江大学 | Software robot system for real world research and operation method |
| CN118737311A (en) * | 2024-09-03 | 2024-10-01 | 艾伟拓(江苏)医药科技有限公司 | Compatibility method of dimethylaminobutyric acid and diiodomethyl ester |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016112025A1 (en) * | 2015-01-05 | 2016-07-14 | Children's Hospital Medical Center | System and method for data mining very large drugs and clinical effects databases |
| WO2017100794A1 (en) * | 2015-12-12 | 2017-06-15 | Cipherome, Inc. | Computer-implemented evaluaton of drug safety for a population |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7127436B2 (en) * | 2002-03-18 | 2006-10-24 | Motorola, Inc. | Gene expression programming algorithm |
-
2020
- 2020-07-09 CN CN202010655590.7A patent/CN111785334B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016112025A1 (en) * | 2015-01-05 | 2016-07-14 | Children's Hospital Medical Center | System and method for data mining very large drugs and clinical effects databases |
| WO2017100794A1 (en) * | 2015-12-12 | 2017-06-15 | Cipherome, Inc. | Computer-implemented evaluaton of drug safety for a population |
Non-Patent Citations (6)
| Title |
|---|
| A Method for Mining Infrequent Causal Associations and Its Application in Finding Adverse Drug Reaction Signal Pairs;Yanqing Ji等;《IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING》;第25卷(第4期);第721-733页 * |
| 基于多维数据挖掘的穿琥宁注射液致药品不良反应发生规律的研究;崔盈盈;吴嘉瑞;张丹;谭迪;张晓朦;张冰;;中国医院用药评价与分析(第12期);全文 * |
| 基于数据挖掘的清开灵注射剂不良反应流行病学特点研究;崔盈盈;吴嘉瑞;刘施;谭迪;张丹;张冰;;药物流行病学杂志(第06期);全文 * |
| 基于种群密集度的GEP算法挖掘药物不良反应;姜玥 等;《计算机应用研究》;第32卷(第10期);参见第2-3节 * |
| 我院105例多西紫杉醇不良反应报告分析;江彦;傅彦妍;宋洪涛;;中国药房(第26期);全文 * |
| 重症监护病房149例药师干预用药分析及药学监护表评价;段丽芳 等;《中国临床药学杂志》;第19卷(第6期);参见第2-3节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111785334A (en) | 2020-10-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111785334B (en) | Drug combination key factor data mining method and system | |
| Chang et al. | Malaria life cycle intensifies both natural selection and random genetic drift | |
| Naumova et al. | Epigenetic patterns modulate the connection between developmental dynamics of parenting and offspring psychosocial adjustment | |
| CN102822834B (en) | Computer-based system for predicting treatment outcome | |
| Merrall et al. | Mortality of those who attended drug services in Scotland 1996–2006: record-linkage study | |
| Zhao et al. | The relationship between shyness and aggression: The multiple mediation of peer victimization and security and the moderation of parent–child attachment | |
| Pearcy et al. | Genome-scale metabolic models and machine learning reveal genetic determinants of antibiotic resistance in Escherichia coli and unravel the underlying metabolic adaptation mechanisms | |
| CN106708959A (en) | Combination drug recognition and ranking method based on medical literature database | |
| Farkhad et al. | Insights on the implications of COVID-19 mitigation measures for mental health | |
| Yu et al. | Predicting adverse drug events in Chinese pediatric inpatients with the associated risk factors: a machine learning study | |
| Michaud et al. | Real‐world adherence to oral methotrexate measured electronically in patients with established rheumatoid arthritis | |
| Tosca et al. | Modeling approaches for reducing safety-related attrition in drug discovery and development: a review on myelotoxicity, immunotoxicity, cardiovascular toxicity, and liver toxicity | |
| Chun et al. | Pharmacological and non-pharmacological treatments for insomnia: A protocol for a systematic review and network meta-analysis | |
| Fischer-Holzhausen et al. | Hormonal regulation of ovarian follicle growth in humans: Model-based exploration of cycle variability and parameter sensitivities | |
| Sobhan et al. | Explainable machine learning to identify patient-specific biomarkers for lung cancer | |
| Chu et al. | Integrated network analysis reveals potentially novel molecular mechanisms and therapeutic targets of refractory epilepsies | |
| Leiby | Growth curve mixture models | |
| Taguchi et al. | Novel method for the prediction of drug-drug Interaction based on gene expression profiles | |
| Johnston et al. | A two‐stage adaptive clinical trial design with data‐driven subgroup identification at interim analysis | |
| Sun et al. | Chinese Patent Medicine as Adjuvant for Mild‐to‐Moderate Active Ulcerative Colitis: A Network Meta‐Analysis of Randomized Controlled Trials | |
| Eisenstein | Ranking the risk of heart disease. | |
| Coburn et al. | Cross-disease spillover from research funding: Evidence from four diseases | |
| Zhang et al. | Systematic investigation on interactions for HIV drug resistance and cross-resistance among protease inhibitors | |
| Zhang et al. | Exploring the potential of direct-to-consumer genomic test data for predicting adverse drug events | |
| Soltantabar et al. | Case–control matching‐guided exposure‐efficacy relationship for avelumab in patients with urothelial carcinoma |
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 |