CN110503158A - A kind of disease associated analysis method of drug based on time factor - Google Patents
A kind of disease associated analysis method of drug based on time factor Download PDFInfo
- Publication number
- CN110503158A CN110503158A CN201910800975.5A CN201910800975A CN110503158A CN 110503158 A CN110503158 A CN 110503158A CN 201910800975 A CN201910800975 A CN 201910800975A CN 110503158 A CN110503158 A CN 110503158A
- Authority
- CN
- China
- Prior art keywords
- disease
- drug
- community
- analysis
- time
- 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
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 122
- 201000010099 disease Diseases 0.000 title claims abstract description 121
- 239000003814 drug Substances 0.000 title claims abstract description 115
- 229940079593 drug Drugs 0.000 title claims abstract description 112
- 238000004458 analytical method Methods 0.000 title claims abstract description 50
- 238000003745 diagnosis Methods 0.000 claims description 11
- 238000010219 correlation analysis Methods 0.000 claims description 9
- 238000000034 method Methods 0.000 claims description 9
- 238000005295 random walk Methods 0.000 claims description 5
- 238000009412 basement excavation Methods 0.000 claims description 3
- 230000002596 correlated effect Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000011160 research Methods 0.000 abstract description 21
- 230000007812 deficiency Effects 0.000 abstract description 3
- 239000000523 sample Substances 0.000 description 7
- 206010061623 Adverse drug reaction Diseases 0.000 description 3
- 208000030453 Drug-Related Side Effects and Adverse reaction Diseases 0.000 description 3
- 230000005012 migration Effects 0.000 description 3
- 238000013508 migration Methods 0.000 description 3
- 108090000623 proteins and genes Proteins 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 206010028980 Neoplasm Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 201000011510 cancer Diseases 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 206010012601 diabetes mellitus Diseases 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 208000002672 hepatitis B Diseases 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000003012 network analysis Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 208000011580 syndromic disease Diseases 0.000 description 1
- 208000019553 vascular disease Diseases 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B45/00—ICT specially adapted for bioinformatics-related data visualisation, e.g. displaying of maps or networks
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/60—ICT specially adapted for the handling or processing of medical references relating to pathologies
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medical Informatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Pharmacology & Pharmacy (AREA)
- Toxicology (AREA)
- Medicinal Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Biophysics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Biotechnology (AREA)
- Probability & Statistics with Applications (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention discloses a kind of disease associated analysis methods of the drug based on time factor, belong to complex network in the applied technical field of diseases analysis.The disease associated analysis method of drug based on time factor of the invention is measured the correlation of drug and disease using patient's number as weight first, then obtains the positive negative correlation between drug and disease by the analysis to patient medication time and Diagnostic Time.The disease associated analysis method of the drug based on time factor of the invention can make up for it the deficiency in disease and drug-associated research, and provide direction for the experimental research studied after drug listing, have good application value.
Description
Technical field
The present invention relates to complex networks in the applied technical field of diseases analysis, specifically provides a kind of based on time factor
The disease associated analysis method of drug.
Background technique
Currently, mainly passing through two ways for the research of drug and disease.First way is the mode of clinical trial,
Which needs researcher to test repeatedly.This not only needs to expend a large amount of manpower and material resources, while also very time-consuming.It is general a kind of
Drug needs to expend from studying to using 10 to 15 years [1].Another way is based on real world data, and utilization is various
Data mining technology carries out drug and disease associated research.With the fast development of computer hardware, complex network, machine
Study, the research of neural network scheduling theory are more complete, increasingly by the welcome of medical field.Wherein, complex network research is benefit
One of the important method of drug and disease relationship research is carried out with real world data.It is complex network drug at home and abroad below
The main application in disease research field.
First, application of the complex network in traditional Chinese medicine research.The application refer to by Chinese medicine data carry out network modelling,
Secondly its characteristic is analyzed, then finds community using community discovery algorithm, and study community one by one.Utilize this
Method has found that hepatitis B syndrome crowd's network has Small-world Characters.
Second, application of the complex network in disease research.In real life, universal common diabetes, cancer, the heart
Vascular diseases etc. are the diseases influenced by environment and genetics.The mutual of protein relevant to such disease is simulated using complex network
Networking network, the abnormal target spot of disease is gone out by network analysis.
Third, application of the complex network in disease and drug-associated research field.Current complex network is in study of disease
With the correlation aspect of drug, it is based primarily upon disease, gene, drug and establishes network.Then it is visited by the analysis to complex network
The distribution characteristics for seeking certain a kind of drug side-effect excavates the correlativity with drug side-effect such as disease, gene.
Genetic factors are added in disease and drug-associated research about complex network, it no doubt can be to a certain extent
Reach the correlation for excavating disease and drug side-effect.However, this method has ignored real world individual patient factor, especially
Disease incidence time and administration time factor.Since drug is to be used by the patient, usually work to entire people rather than certain class disease
Disease, therefore need that individual patient factor is added under study for action.Again because individual all one's life will obtain different diseases in different time sections
Disease, or obtain multiclass disease in the same period, while can also have that same time individual eats multiclass drug or different time is eaten not
The case where similar drugs.Therefore, while network is added in individual factors, time factor is also that cannot be neglected important spy
Sign.
Summary of the invention
Technical assignment of the invention is that in view of the above problems, providing one kind can make up for it disease and drug-associated
Deficiency in research, and the drug disease based on time factor in direction is provided for the experimental research studied after drug listing
Correlation analysis.
To achieve the above object, the present invention provides the following technical scheme that
A kind of disease associated analysis method of drug based on time factor, this method weigh by weight of patient's number first
The correlation of drug and disease is measured, then is obtained between drug and disease just by the analysis to patient medication time and Diagnostic Time
Negative correlation.
Preferably, should disease associated analysis method of drug based on time factor specifically includes the following steps:
S1, drug and disease associated excavation
S11, it establishes complex network: establishing network using drug, disease, patient as node;
S12, heterogeneous network community discovery;
S13, correlation analysis, drug disease correlation of nodes analysis in analysis and community including community's tightness;
S2, drug and the positive and negative correlation analysis of disease
The higher disease of correlation and diagnosis pair are excavated in S21, arrangement;
The positive negative correlation of S22, the remaining drug disease pair of analysis.
Preferably, step S12 heterogeneous network community discovery establishes random walk sequence using the mode of node2vec, make
With the mode training pattern of word2vec, community's division is carried out using clustering algorithm.
Preferably, correlation analysis described in step S13 includes drug disease node in the analysis and community of community's density
The analysis of correlation.
Preferably, the analysis of community's tightness determines the community by calculating the average class spacing in class between sample
The tightness degree of interior nodes, as shown in formula (1)
Wherein, M is community's tightness, and M is smaller, and community's tightness is higher;N is that drug, disease, patient's node are total in community
Number;X is the drug obtained by node2vec algorithm in community, disease, patient's knot vector.
Preferably, the connection that the analysis of drug disease correlation of nodes passes through patient between drug and disease in the community
Number determines that the patient between drug and disease is more, and drug disease correlation of nodes is bigger in community.
Preferably, the higher disease of correlation and diagnosis pair are excavated in step S21 arrangement, have directly for drug and disease
It is associated right.
Preferably, step S22 analyzes the criterion of the positive negative correlation of remaining drug disease pair are as follows:
1) patient takes time of such drug earlier than the medical diagnosis on disease time, and the two time phase difference is in threshold range,
Then there is negative correlation between the drug and disease;
2) time that patient takes such drug is later than the medical diagnosis on disease time, and nothing in the threshold time after administration time
Palindromia then exists between the drug and disease and is positively correlated.
Herein threshold values needs determined according to the curative effect time for being actually related to drug, generally should be within curative effect time.
Compared with prior art, the disease associated analysis method of the drug of the invention based on time factor has following prominent
Out the utility model has the advantages that the disease associated analysis method of the drug based on time factor can analyze in advance that class drug with
The correlation of which class disease is higher, is then made a choice using professional knowledge to analysis result, as the reality studied after listing
It tests Journal of Sex Research and direction is provided, increase the accuracy of experimental research, complex network can made up in disease and drug-associated
While deficiency in research, the beforehand research using real world publishing house is provided for the experimental research in research after drug listing
Study carefully, there is good application value.
Detailed description of the invention
Fig. 1 is the flow chart of the disease associated analysis method of the drug based on time factor of the present invention.
Specific embodiment
Below in conjunction with drawings and examples, to the disease associated analysis method of the drug based on time factor of the invention
It is described in further detail.
Embodiment
The disease associated analysis method of drug based on time factor of the invention, first by using patient's number as weight
Lack individual factor in disease medicament correlation research to indicate that drug and disease associated mode make up complex network
It is insufficient.Secondly, this method probes into drug under the conditions of real world data by the analysis to patient medication time and Diagnostic Time
Positive negative correlation between disease
Below based on python language, specific embodiments of the present invention are illustrated.
As shown in Figure 1, should disease associated analysis method of drug based on time factor specifically includes the following steps:
S1, drug and disease associated excavation.
S11, it establishes complex network: establishing network using drug, disease, patient as node, drug, disease, patient are node
The relationship content for establishing network is as shown in table 1, and drug point attribute, disease point attribute, patient's point attribute are respectively such as table 2, table 3, table 4
It is shown.
Wherein, complex network is established with networkx frame.Before establishing complex network, need to carry out specimen sample.
Sample needs comprehensively when specimen sample, is generally comprehensive hospital and non-special class hospital from sampling mechanism.According to table 1, table 2, table
3, the attribute listed in table 4, samples one by one, and field contents can not be sky, and sampled data must really be effective.
Table 1
Table 2
Serial number | Property Name | Attribute description |
1 | Medicine name | Pharmaceutical standards title |
2 | Drug codes | Drug standards coding |
Table 3
Serial number | Property Name | Attribute description |
1 | Disease name | Disease criterion title |
2 | Disease code | Disease ICD coding |
Table 4
S12, heterogeneous network community discovery.
The analysis of node2vec is carried out using the node2vec packet based on networkx frame.Guarantee the section with homogeney
The vector of point study is closer, forms community to find the stronger node of relevance.I.e. when carrying out node2vec random walk,
Make the strategy of random walk be more biased towards in BFS (range migration) rather than DFS (depth migration).For the situation, migration parameter is set
It is as follows.
Wherein p, q are random walk parameter, and wherein p is Return parameter, and q is In-out parameter.
After obtaining knot vector, model training is carried out using the word2vec function based on Gensim frame, it is therefore an objective to
Node is subjected to vectorization.
It is clustered using the function (such as kmeans) based on cluster in sklearn frame, divides community.It is used herein as
Kmeans cluster can have the requirement for needing to specify community's number in advance, can be configured according to specific sample situation.
S13, correlation analysis, drug disease correlation of nodes analysis in analysis and community including community's tightness.
The analysis of community's tightness determines the close of community's interior nodes by calculating the average class spacing in class between sample
Degree, as shown in formula (1)
Wherein, M is community's tightness, and M is smaller, and community's tightness is higher;N is that drug, disease, patient's node are total in community
Number;X is the drug obtained by node2vec algorithm in community, disease, patient's knot vector.
The calculating that average inter- object distance is carried out to the class gathered, selects inter- object distance smaller, in community more close community
It is analyzed, to reduce computer capacity.It counts in the community filtered out, common connection patient is more and without direct association
Drug and disease node.
S2, drug and the positive and negative correlation analysis of disease
The higher disease of correlation and diagnosis pair are excavated in S21, arrangement, there is pair of direct correlation with disease for drug.
The positive negative correlation of S22, the remaining drug disease pair of analysis.
The criterion of the positive negative correlation of the remaining drug disease pair of the analysis are as follows:
1) patient takes time of such drug earlier than the medical diagnosis on disease time, and the two time phase difference is in threshold range,
Then there is negative correlation between the drug and disease, i.e., such drug may cause such disease.
2) time that patient takes such drug is later than the medical diagnosis on disease time, and nothing in the threshold time after administration time
Palindromia then exists between the drug and disease and is positively correlated, i.e., such drug has a possibility that curing or alleviating such disease.
Embodiment described above, the only present invention more preferably specific embodiment, those skilled in the art is at this
The usual variations and alternatives carried out within the scope of inventive technique scheme should be all included within the scope of the present invention.
Claims (8)
1. a kind of disease associated analysis method of drug based on time factor, it is characterised in that: this method is first with patient
Number be weight measure drug and disease correlations, then by the analysis to patient medication time and Diagnostic Time obtain drug with
Positive negative correlation between disease.
2. the disease associated analysis method of the drug according to claim 1 based on time factor, it is characterised in that: the party
Method specifically includes the following steps:
S1, drug and disease associated excavation
S11, it establishes complex network: establishing network using drug, disease, patient as node;
S12, heterogeneous network community discovery;
S13, correlation analysis, drug disease correlation of nodes analysis in analysis and community including community's tightness;
S2, drug and the positive and negative correlation analysis of disease
The higher disease of correlation and diagnosis pair are excavated in S21, arrangement;
The positive negative correlation of S22, the remaining drug disease pair of analysis.
3. the disease associated analysis method of the drug according to claim 2 based on time factor, it is characterised in that: step
S12 heterogeneous network community discovery establishes random walk sequence using the mode of node2vec, uses the mode training of word2vec
Model carries out community's division using clustering algorithm.
4. the disease associated analysis method of the drug according to claim 3 based on time factor, it is characterised in that: step
Correlation analysis described in S13 includes the analysis of drug disease correlation of nodes in the analysis and community of community's density.
5. the disease associated analysis method of the drug according to claim 4 based on time factor, it is characterised in that: described
The analysis of community's tightness determines the tightness degree of community's interior nodes by calculating the average class spacing in class between sample, such as public
Shown in formula (1)
Wherein, M is community's tightness, and M is smaller, and community's tightness is higher;N is that drug, disease, patient's node are always a in community
Number;X is the drug obtained by node2vec algorithm in community, disease, patient's knot vector.
6. the disease associated analysis method of the drug according to claim 5 based on time factor, it is characterised in that: described
The analysis of drug disease correlation of nodes is determined by the linking number of patient between drug and disease in community, between drug and disease
Patient it is more, drug disease correlation of nodes is bigger in community.
7. the disease associated analysis method of the drug according to claim 6 based on time factor, it is characterised in that: step
The higher disease of correlation and diagnosis pair are excavated in S21 arrangement, there is pair of direct correlation with disease for drug.
8. the disease associated analysis method of the drug according to claim 7 based on time factor, it is characterised in that: step
S22 analyzes the criterion of the positive negative correlation of remaining drug disease pair are as follows:
1) patient takes time of such drug earlier than the medical diagnosis on disease time, and the two time phase difference then should in threshold range
There is negative correlation between drug and disease;
2) time that patient takes such drug is later than the medical diagnosis on disease time, and without disease in the threshold time after administration time
Recurrence then exists between the drug and disease and is positively correlated.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910800975.5A CN110503158A (en) | 2019-08-28 | 2019-08-28 | A kind of disease associated analysis method of drug based on time factor |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910800975.5A CN110503158A (en) | 2019-08-28 | 2019-08-28 | A kind of disease associated analysis method of drug based on time factor |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110503158A true CN110503158A (en) | 2019-11-26 |
Family
ID=68590137
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910800975.5A Pending CN110503158A (en) | 2019-08-28 | 2019-08-28 | A kind of disease associated analysis method of drug based on time factor |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110503158A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102779142A (en) * | 2011-06-28 | 2012-11-14 | 安徽大学 | Quick community discovery method based on community closeness |
CN104978474A (en) * | 2014-04-11 | 2015-10-14 | 中国中医科学院中医临床基础医学研究所 | Medicine effect evaluating method based on molecular network and medicine effect evaluating system |
CN105653846A (en) * | 2015-12-25 | 2016-06-08 | 中南大学 | Integrated similarity measurement and bi-directional random walk based pharmaceutical relocation method |
WO2017158152A1 (en) * | 2016-03-17 | 2017-09-21 | Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e. V. | Diagnosis of chronic obstructive pulmonary disease (copd) |
CN108109700A (en) * | 2017-12-19 | 2018-06-01 | 中国科学院深圳先进技术研究院 | A kind of chronic disease Drug efficacy evaluation method and apparatus |
CN109411033A (en) * | 2018-11-05 | 2019-03-01 | 杭州师范大学 | A kind of curative effect of medication screening technique based on complex network |
CN109903854A (en) * | 2019-01-25 | 2019-06-18 | 电子科技大学 | A kind of core drug recognition methods based on TCM Literature |
-
2019
- 2019-08-28 CN CN201910800975.5A patent/CN110503158A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102779142A (en) * | 2011-06-28 | 2012-11-14 | 安徽大学 | Quick community discovery method based on community closeness |
CN104978474A (en) * | 2014-04-11 | 2015-10-14 | 中国中医科学院中医临床基础医学研究所 | Medicine effect evaluating method based on molecular network and medicine effect evaluating system |
CN105653846A (en) * | 2015-12-25 | 2016-06-08 | 中南大学 | Integrated similarity measurement and bi-directional random walk based pharmaceutical relocation method |
WO2017158152A1 (en) * | 2016-03-17 | 2017-09-21 | Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e. V. | Diagnosis of chronic obstructive pulmonary disease (copd) |
CN108109700A (en) * | 2017-12-19 | 2018-06-01 | 中国科学院深圳先进技术研究院 | A kind of chronic disease Drug efficacy evaluation method and apparatus |
CN109411033A (en) * | 2018-11-05 | 2019-03-01 | 杭州师范大学 | A kind of curative effect of medication screening technique based on complex network |
CN109903854A (en) * | 2019-01-25 | 2019-06-18 | 电子科技大学 | A kind of core drug recognition methods based on TCM Literature |
Non-Patent Citations (2)
Title |
---|
FAN GONG等: "SMR: Medical Knowledge Graph Embedding for Safe Medicine Recommendation", 《ARXIV:1710.05980》 * |
熊正理等: "基于用户紧密度的在线社会网络社区发现算法", 《计算机工程》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Yang et al. | Risk prediction of diabetes: big data mining with fusion of multifarious physical examination indicators | |
CN105653846B (en) | Drug method for relocating based on integrated similarity measurement and random two-way migration | |
Wilkens et al. | HierS: hierarchical scaffold clustering using topological chemical graphs | |
Veeramah et al. | An early divergence of KhoeSan ancestors from those of other modern humans is supported by an ABC-based analysis of autosomal resequencing data | |
Anzar et al. | NeoMutate: an ensemble machine learning framework for the prediction of somatic mutations in cancer | |
CN109872772B (en) | Method for excavating colorectal cancer radiotherapy specific genes by using weight gene co-expression network | |
Khaing | Data mining based fragmentation and prediction of medical data | |
CN109920547A (en) | A kind of diabetes prediction model construction method based on electronic health record data mining | |
CN110444248A (en) | Cancer Biology molecular marker screening technique and system based on network topology parameters | |
CN109637579B (en) | Tensor random walk-based key protein identification method | |
Zhao et al. | Microbes and complex diseases: from experimental results to computational models | |
Li et al. | Large-scale identification of potential drug targets based on the topological features of human protein–protein interaction network | |
CN105139390A (en) | Image processing method for detecting pulmonary tuberculosis focus in chest X-ray DR film | |
WO2016191340A1 (en) | Discovery and analysis of drug-related side effects | |
Lindblom et al. | Bioinformatics for human genetics: promises and challenges | |
Zhu et al. | TGSA: protein–protein association-based twin graph neural networks for drug response prediction with similarity augmentation | |
Hasan et al. | Design protein-protein interaction network and protein-drug interaction network for common cancer diseases: A bioinformatics approach | |
CN111986814A (en) | Modeling method of lupus nephritis prediction model of lupus erythematosus patient | |
Li et al. | End-to-end interpretable disease–gene association prediction | |
KR101839572B1 (en) | Apparatus Analyzing Disease-related Genes and Method thereof | |
CN110503158A (en) | A kind of disease associated analysis method of drug based on time factor | |
CN108804871A (en) | Key protein matter recognition methods based on maximum neighbours' subnet | |
CN113488119B (en) | Drug small molecule numerical value characteristic structured database and establishment method thereof | |
CN105447337B (en) | A kind of time series data processing method based on dynamic network map analysis | |
CN109492690B (en) | Method for detecting CT image based on convolutional neural network |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191126 |