CN109698029A - A kind of circRNA- disease association prediction technique based on network model - Google Patents
A kind of circRNA- disease association prediction technique based on network model Download PDFInfo
- Publication number
- CN109698029A CN109698029A CN201811580662.5A CN201811580662A CN109698029A CN 109698029 A CN109698029 A CN 109698029A CN 201811580662 A CN201811580662 A CN 201811580662A CN 109698029 A CN109698029 A CN 109698029A
- Authority
- CN
- China
- Prior art keywords
- circrna
- disease
- matrix
- gauss
- disease association
- 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
- 201000010099 disease Diseases 0.000 title claims abstract description 100
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 100
- 238000000034 method Methods 0.000 title claims abstract description 37
- 239000011159 matrix material Substances 0.000 claims abstract description 65
- 230000003993 interaction Effects 0.000 claims abstract description 23
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 claims description 6
- 241000287828 Gallus gallus Species 0.000 claims description 5
- 241000699666 Mus <mouse, genus> Species 0.000 claims description 5
- 238000011524 similarity measure Methods 0.000 claims description 5
- 238000007477 logistic regression Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000002474 experimental method Methods 0.000 description 9
- 238000002790 cross-validation Methods 0.000 description 7
- 108090000623 proteins and genes Proteins 0.000 description 6
- 108091027963 non-coding RNA Proteins 0.000 description 4
- 102000042567 non-coding RNA Human genes 0.000 description 4
- 102000004169 proteins and genes Human genes 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 206010006187 Breast cancer Diseases 0.000 description 3
- 208000026310 Breast neoplasm Diseases 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 206010017758 gastric cancer Diseases 0.000 description 3
- 238000004393 prognosis Methods 0.000 description 3
- 230000001105 regulatory effect Effects 0.000 description 3
- 108091032973 (ribonucleotides)n+m Proteins 0.000 description 2
- 108091028075 Circular RNA Proteins 0.000 description 2
- 206010028980 Neoplasm Diseases 0.000 description 2
- 208000005718 Stomach Neoplasms Diseases 0.000 description 2
- 201000011510 cancer Diseases 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000003550 marker Substances 0.000 description 2
- 201000011549 stomach cancer Diseases 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 108091026815 Competing endogenous RNA (CeRNA) Proteins 0.000 description 1
- 102000004190 Enzymes Human genes 0.000 description 1
- 108090000790 Enzymes Proteins 0.000 description 1
- 101001090713 Homo sapiens L-lactate dehydrogenase A chain Proteins 0.000 description 1
- 102100034671 L-lactate dehydrogenase A chain Human genes 0.000 description 1
- 208000012902 Nervous system disease Diseases 0.000 description 1
- 108091028043 Nucleic acid sequence Proteins 0.000 description 1
- 108091036407 Polyadenylation Proteins 0.000 description 1
- 208000003721 Triple Negative Breast Neoplasms Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000090 biomarker Substances 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 206010012601 diabetes mellitus Diseases 0.000 description 1
- 239000000104 diagnostic biomarker Substances 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 208000010749 gastric carcinoma Diseases 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 108091029119 miR-34a stem-loop Proteins 0.000 description 1
- 238000010208 microarray analysis Methods 0.000 description 1
- 206010061311 nervous system neoplasm Diseases 0.000 description 1
- 238000006116 polymerization reaction Methods 0.000 description 1
- 210000002784 stomach Anatomy 0.000 description 1
- 201000000498 stomach carcinoma Diseases 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 208000022679 triple-negative breast carcinoma Diseases 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- 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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/80—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
Landscapes
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The present invention discloses a kind of circRNA- disease association prediction technique based on network model, which comprises the steps of: 1) obtains circRNA- disease association data set, construct the adjacency matrix A about circRNA- disease association；2) building circRNA Gauss interaction attribute nucleus similarity matrix KC；3) building disease Gauss interaction attribute nucleus similarity matrix KD；4) circRNA- disease association is predicted according to network consistency projection model.This method is at low cost, can improve circRNA- disease association precision of prediction.
Description
Technical field
It is specifically a kind of based on network model the present invention relates to bioinformatics and artificial intelligence crossing domain
CircRNA- disease association prediction technique.
Background technique
It is well known that hereditary information is stored in protein coding gene, this is referred to as the central dogma of molecular biology.
Therefore, RNA is in the intermediary being to be considered only as between DNA sequence dna and its protein encoded in considerable time.Nearest grinds
Study carefully the very small part (about 1.5%) for showing that protein coding gene only accounts for human genome.In other words, more than 98%
Human genome not coded protein sequence.Particularly, it has been observed that the ratio of non-proteinencoding sequences is with biology
Complexity and increase.These facts have challenged the traditional view of above-mentioned RNA.In addition, more and more evidences show
Non-coding RNA (ncRNA) usually plays key effect in various bioprocess.Circular rna (circRNA) is a kind of very heavy
The ncRNA wanted, circRNA molecule form closed circular structure with covalent bond, are a kind of without the end 5' cap and the end 3'
The special endogenous ncRNA of poly (A) tail has the characteristics such as popularity, conservative, tissue specificity and stability.
In the research of recent years, it has been found that circRNA plays important in various bioprocess
Role.Its generation, development process for participating in the diseases such as diabetes, cardiovascular disease, the nervous system disease and tumour, concurrently
Wave important regulating and controlling effect.Numerous studies have shown that circRNA can be used as novel disease clinical diagnosis marker or human diseases
The potential target spot for the treatment of, is widely used in medical diagnosis on disease, treatment and prognosis.A period of time recently closes about circRNA and disease
The research achievement of connection is also more and more, for example, in circRNA and the association study of breast cancer, Huang (Huang X, Xie X,
Wang H,Xiao X,Yang L,Tian Z,Guo X,Zhang L,Tang H,Xie X:PDL1And LDHA act as
ceRNAs in triple negative breast cancer by regulating miR-34a.Journal of
Experimental&Clinical Cancer Research 2017,36 (1): 129.) et al. pass through quantitative reverse transcription-polymerization
Enzyme chain reaction (qRT-PCR), microarray analysis process show that circRNA:circGFRA1 is played in generation, the development of breast cancer
Regulating and controlling effect.Therefore, circGFRA1 can be used as the diagnostic biomarkers and potential target of breast cancer treatment.CircRNA and stomach
In the association study of cancer, Sun (Sun H, Tang W, Rong D, Jin H, Fu K, Zhang W, Liu Z, Cao H, Cao X:
Hsa_circ_0000520,a potential new circular RNA biomarker,is involved in
Gastric carcinoma.Cancer Biomarkers2018,21 (2): 299.) et al. experiments prove that circRNA:
Hsa_circ_0000520 can be used as the Novel marker of gastric cancer and participate in the development of gastric cancer.
In conclusion the association of identification circRNA- disease, is conducive to treatment, diagnosis and the prognosis to disease, thus
Improve and improve the medical level of the mankind.But due to the association of traditional BIOLOGICAL TEST METHODS identification circRNA- disease, no
It only needs to take a substantial amount of time, and waste of manpower and financial resources, therefore there is an urgent need to a kind of efficiently methods to identify
The association of circRNA- disease instructs biomedical research to reduce cost.However, up to the present, very there are no one
Good method goes to solve the problems, such as this.
Summary of the invention
The purpose of the present invention is in view of the deficiencies of the prior art, and provide a kind of circRNA- disease based on network model
Interaction prediction method.This method is at low cost, can improve circRNA- disease association precision of prediction.
Realizing the technical solution of the object of the invention is:
A kind of circRNA- disease association prediction technique based on network model, points unlike the prior art are, including
Following steps:
1) circRNA- disease association data set is obtained, the adjacency matrix A about circRNA- disease association is constructed: from
CircRNADisease database obtains the circRNA- disease association data confirmed through Bioexperiment, due to chicken, mouse species
Associated data amount is less not to have representativeness, we delete the circRNA- disease association data of chicken, mouse species, only retain
The circRNA- disease association data of human species, finally obtain 239 couples of different circRNA and disease association data, wherein
It is related to 34 kinds of kinds of Diseases, 223 kinds of circRNA type, defines D={ d (1), d (2), d (3) ..., d (nd) } to remember nd kind disease
The set of disease, C={ c (1), c (2), c (3) ..., c (nc) } remember the set of nc kind circRNA, build adjacency matrix And×ncTable
The relationship for showing circRNA and disease association data, when disease d (i) and circRNA c (j) are interrelated, A in adjacency matrix A
The value of (i, j) is set as 1；Conversely, the value of A (i, j) is set as 0, unknown association is indicated；
2) building circRNA Gauss interaction attribute nucleus similarity matrix KC: according to the adjacency matrix A of step 1), structure
It builds the similitude that circRNA Gauss interacts between attribute nucleus similarity matrix KC, circRNA and refers to that Gauss interacts
Gauss interaction attribute nucleus Similarity measures such as formula (1) and the formula of attribute nucleus similitude, circRNA c (i) and c (j)
(2) shown in:
KC (c (i), c (j))=exp (- γc||IP(c(i))-IP(c(j))||2) (1),
Wherein, IP (c (i)) and IP (c (j)) respectively indicates the i-th column vector and jth column vector of adjacency matrix A, | | | |
It is the norm for seeking vector, parameter γcIt is defined as the bandwidth of Gauss interaction attribute nucleus, controls the big of KC (c (i), c (j))
It is small, by the Gauss of all circRNA between any two interact attribute nucleus similitude building circRNA similarity matrix KC；
3) building disease Gauss interaction attribute nucleus similarity matrix KD: according to the adjacency matrix A of step 1), disease is constructed
Sick Gauss interaction attribute nucleus similarity matrix KD, the Gauss interaction attribute nucleus similitude between disease d (i) and d (j)
It calculates as shown in formula (3) and formula (4):
KD (d (i), d (j))=exp (- γd||IP(d(i))-IP(d(j))||2 (3),
Wherein, IP (d (i)) and IP (d (j)) respectively indicates the i-th row vector and jth row vector of adjacency matrix A, | | | |
It is the norm for seeking vector, parameter γdIt is defined as the bandwidth of Gauss interaction attribute nucleus, controls the big of KD (d (i), d (j))
It is small, by the Gauss of all diseases between any two interact attribute nucleus similitude building disease similarity matrix KD, in order to improve
Precision of prediction, and logistic regression function processing is carried out as shown in formula (5) to KD:
Wherein parameter c and d are respectively set are as follows: c=-15, d=log (9999)；
4) circRNA- disease association is predicted according to network consistency projection model: firstly, obtaining disease according to formula (6)
Sick space projection score matrix DSPS:
Wherein KDiIt is the i-th row in matrix K D, AjIt is the jth column of matrix A, | Aj| indicate vector AjNorm；
Then, circRNA space projection score matrix CSPS is obtained according to formula (7):
Wherein AiIt is the i-th row of matrix A, KCjIt is matrix K C jth column, | Ai| indicate vector AiNorm,
Finally, being combined according to formula (8) and normalizing DSPS and CSPS:
SPS is final network consistency projection score matrix, measures each pair of circRNA- disease association score, according to
Score, which is ranked up, provides projected relationship, we obtain a final circRNA- disease association prediction score matrix, score
Higher a possibility that showing circRNA- disease association, is bigger, is ranked up according to score, can provide certain disease and
Association possibility ranking between circRNA facilitates field of biomedicine specific aim according to the ranking grade of association possibility
Interaction relationship between certain disease and certain circRNA is studied on ground, so that the early detection and preventing, treating for disease mentions
For helping.
The technical program has the beneficial effect that:
The technical program provides a kind of circRNA- disease association prediction technique based on network model to predict
The incidence relation of circRNA- disease, to facilitate understanding of the mankind to disease mechanisms, the discovery of drug and the treatment of disease,
Diagnosis and prognosis, the method for the technical program predict the incidence relation between circRNA- disease, not complicated linear algebra
The tuning of conversion and parameter, predictablity rate is high, time-consuming short, and reduces huge brought by previous traditional biological experimental method
Big cost, the technical program can implement prediction on the new circRNA of no any known related disease, can also not have
Implement new disease forecasting in the case where any known correlation circRNA.
This method is at low cost, can improve circRNA- disease association precision of prediction.
Detailed description of the invention
Fig. 1 is embodiment method flow schematic diagram；
Fig. 2 is the comparison schematic diagram of embodiment method and other methods under leave one cross validation experiment；
Fig. 3 is the comparison schematic diagram of embodiment method and other methods under 5 folding cross-validation experiments.
Specific embodiment
The content of present invention is further elaborated with reference to the accompanying drawings and examples, but is not limitation of the invention:
Embodiment:
Referring to Fig.1, a kind of circRNA- disease association prediction technique based on network model, includes the following steps:
1) circRNA- disease association data set is obtained, the adjacency matrix A about circRNA- disease association is constructed: from
CircRNADisease database obtains the circRNA- disease association data confirmed through Bioexperiment, due to chicken, mouse species
Associated data amount is less not to have representativeness, we delete the circRNA- disease association data of chicken, mouse species, only retain
The circRNA- disease association data of human species, finally obtain 239 couples of different circRNA and disease association data, wherein
It is related to 34 kinds of kinds of Diseases, 223 kinds of circRNA type, defines D={ d (1), d (2), d (3) ..., d (nd) } to remember nd kind disease
The set of disease, C={ c (1), c (2), c (3) ..., c (nc) } remember the set of nc kind circRNA, build adjacency matrix And×ncTable
The relationship for showing circRNA and disease association data, when disease d (i) and circRNA c (j) are interrelated, A in adjacency matrix A
The value of (i, j) is set as 1；Conversely, the value of A (i, j) is set as 0, unknown association is indicated；
2) building circRNA Gauss interaction attribute nucleus similarity matrix KC: according to the adjacency matrix A of step 1), structure
It builds the similitude that circRNA Gauss interacts between attribute nucleus similarity matrix KC, circRNA and refers to that Gauss interacts
Gauss interaction attribute nucleus Similarity measures such as formula (1) and the formula of attribute nucleus similitude, circRNA c (i) and c (j)
(2) shown in:
KC (c (i), c (j))=exp (- γc||IP(c(i))-IP(c(j))||2) (1),
Wherein, IP (c (i)) and IP (c (j)) respectively indicates the i-th column vector and jth column vector of adjacency matrix A, | | | |
It is the norm for seeking vector, parameter γcIt is defined as the bandwidth of Gauss interaction attribute nucleus, controls the big of KC (c (i), c (j))
It is small, by the Gauss of all circRNA between any two interact attribute nucleus similitude building circRNA similarity matrix KC；
3) building disease Gauss interaction attribute nucleus similarity matrix KD: according to the adjacency matrix A of step 1), disease is constructed
Sick Gauss interacts attribute nucleus similarity matrix KD, and the similitude between disease refers to that the Gauss attribute nucleus that interacts is similar
Property, shown in Gauss interaction attribute nucleus the Similarity measures such as formula (3) and formula (4) between disease d (i) and d (j):
KD (d (i), d (j))=exp (- γd||IP(d(i))-IP(d(j))||2) (3),
Wherein, IP (d (i)) and IP (d (j)) respectively indicates the i-th row vector and jth row vector of adjacency matrix A, | | | |
It is the norm for seeking vector, parameter γdIt is defined as the bandwidth of Gauss interaction attribute nucleus, controls the big of KD (d (i), d (j))
It is small, by the Gauss of all diseases between any two interact attribute nucleus similitude building disease similarity matrix KD, in order to improve
Precision of prediction, and logistic regression function processing is carried out as shown in formula (5) to KD:
Wherein parameter c and d are respectively set are as follows: c=-15, d=log (9999)；
4) circRNA- disease association is predicted according to network consistency projection model: firstly, obtaining disease according to formula (6)
Sick space projection score matrix DSPS:
Wherein KDiIt is the i-th row in matrix K D, AjIt is the jth column of matrix A, | Aj| indicate vector AjNorm；
Then, circRNA space projection score matrix CSPS is obtained according to formula (7):
Wherein AiIt is the i-th row of matrix A, KCjIt is matrix K C jth column, | Ai| indicate vector AiNorm；
Finally, being combined according to formula (8) and normalizing DSPS and CSPS:
SPS is final network consistency projection score matrix, measures each pair of circRNA- disease association score, according to
Score, which is ranked up, provides projected relationship, we obtain a final circRNA- disease association prediction score matrix, score
Higher a possibility that showing circRNA- disease association, is bigger, is ranked up according to score, can provide certain disease and
Association possibility ranking between circRNA facilitates field of biomedicine specific aim according to the ranking grade of association possibility
Interaction relationship between certain disease and certain circRNA is studied on ground, so that the early detection and preventing, treating for disease mentions
For helping.
Verifying: we term it NCPHCDA methods for circRNA- disease association prediction technique in the present embodiment, use
BIRWHCDA method and LRLSHCDA method compare, and have carried out leave one cross validation experiment and 5 folding cross validations respectively
Experiment leaves an associated data as test set in leave one cross validation experiment every time, remaining as training set,
It draws ROC curve and calculates the area under AUC value i.e. ROC curve, AUC value is bigger, and expression model prediction performance is better, such as Fig. 2 institute
Show, the AUC value of the present embodiment method NCPHCDA reaches 0.8655, BIRWHCDA method and LRLSHCDA method is respectively
0.8236 and 0.8175, the AUC value of the present embodiment method is all higher than the AUC value of other two methods；In 5 folding cross-validation experiments
In, data set is randomly divided into 5 groups, wherein one group is used as test set, remaining four groups are used as training set, due to random division data
Rally brings offset issue, repeats 100 5 folding cross-validation experiments, average AUC value is calculated, as shown in figure 3, this reality
Apply that an AUC value of method NCPHCDA reaches 0.8367, BIRWHCDA method and LRLSHCDA method is respectively 0.7967 He
0.8035, AUC value of the AUC value of the present embodiment method still than other two methods is all high, and the value of AUC is higher to be shown to predict mould
Type is better.
Claims (1)
1. a kind of circRNA- disease association prediction technique based on network model, which comprises the steps of:
1) circRNA- disease association data set is obtained, the adjacency matrix A about circRNA- disease association is constructed: from
The circRNA- disease association data confirmed through Bioexperiment are obtained in circRNADisease database, by chicken, mouse species
CircRNA- disease association data delete, only retain human species circRNA- disease association data, obtain 239 pairs of differences
CircRNA and disease association data, be directed to 34 kinds of kinds of Diseases, 223 kinds of circRNA type, define D={ d (1), d
(2), d (3) ..., d (nd) } remember the set of nd kind disease, C={ c (1), c (2), c (3) ..., c (nc) } remembers nc kind
The set of circRNA builds adjacency matrix And×ncThe relationship for indicating circRNA and disease association data, as disease d (i) and
When circRNA c (j) is interrelated, the value of A (i, j) is set as 1 in adjacency matrix A；Conversely, the value of A (i, j) is set as 0, indicate not
The association known；
2) building circRNA Gauss interaction attribute nucleus similarity matrix KC: according to the adjacency matrix A of step 1), building
The similitude that circRNA Gauss interacts between attribute nucleus similarity matrix KC, circRNA refers to that Gauss interacts and belongs to
Property core similitude, the Gauss of circRNA c (i) and c (j) interacts attribute nucleus Similarity measures such as formula (1) and formula (2)
It is shown:
KC (c (i), c (j))=exp (- γc||IP(c(i))-IP(c(j))||2) (1),
Wherein, IP (c (i)) and IP (c (j)) respectively indicates the i-th column vector and jth column vector of adjacency matrix A, | | | | it is to ask
The norm of vector, parameter γcIt is defined as the bandwidth of Gauss interaction attribute nucleus, by the Gauss of all circRNA between any two
The attribute nucleus similitude that interacts constructs circRNA similarity matrix KC；
3) building disease Gauss interaction attribute nucleus similarity matrix KD: according to the adjacency matrix A of step 1), building disease is high
This attribute nucleus similarity matrix KD that interacts, the similitude between disease refer to Gauss interaction attribute nucleus similitude,
Gauss between disease d (i) and d (j) interacts shown in attribute nucleus Similarity measures such as formula (3) and formula (4):
KD (d (i), d (j))=exp (- γd||IP(d(i))-IP(d(j))||2) (3),
Wherein, IP (d (i)) and IP (d (j)) respectively indicates the i-th row vector and jth row vector of adjacency matrix A, | | | it is to ask
The norm of vector, parameter γdIt is defined as the bandwidth of Gauss interaction attribute nucleus, Gauss between any two is mutual by all diseases
Role attribute core similitude constructs disease similarity matrix KD, and carries out logistic regression function processing as shown in formula (5) to KD:
Wherein parameter c and d are respectively set are as follows: c=-15, d=log (9999)；
4) circRNA- disease association is predicted according to network consistency projection model: firstly, obtaining disease sky according to formula (6)
Between project score matrix DSPS:
Wherein KDiIt is the i-th row in matrix K D, AjIt is the jth column of matrix A, | Aj| indicate vector AjNorm,
Then, circRNA space projection score matrix CSPS is obtained according to formula (7):
Wherein AiIt is the i-th row of matrix A, KCjIt is matrix K C jth column, | Ai| indicate vector AiNorm,
Finally, being combined according to formula (8) and normalizing DSPS and CSPS:
SPS is final network consistency projection score matrix, each pair of circRNA- disease association score is measured, according to score
It is ranked up and provides projected relationship.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811580662.5A CN109698029A (en) | 2018-12-24 | 2018-12-24 | A kind of circRNA- disease association prediction technique based on network model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811580662.5A CN109698029A (en) | 2018-12-24 | 2018-12-24 | A kind of circRNA- disease association prediction technique based on network model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109698029A true CN109698029A (en) | 2019-04-30 |
Family
ID=66232084
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811580662.5A Pending CN109698029A (en) | 2018-12-24 | 2018-12-24 | A kind of circRNA- disease association prediction technique based on network model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109698029A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110459264A (en) * | 2019-08-02 | 2019-11-15 | 陕西师范大学 | Based on grad enhancement decision tree prediction circular rna and disease associated method |
| CN110767263A (en) * | 2019-10-18 | 2020-02-07 | 中国人民解放军陆军军医大学 | Non-coding RNA and disease associated prediction method based on sparse subspace learning |
| CN111161796A (en) * | 2019-12-30 | 2020-05-15 | 中南大学 | Method and system for predicting PD potential gene and miRNA |
| CN111540405A (en) * | 2020-04-29 | 2020-08-14 | 新疆大学 | Disease gene prediction method based on rapid network embedding |
| CN111584006A (en) * | 2020-05-06 | 2020-08-25 | 西安交通大学 | Circular RNA identification method based on machine learning strategy |
| CN113241115A (en) * | 2021-03-26 | 2021-08-10 | 广东工业大学 | Depth matrix decomposition-based circular RNA disease correlation prediction method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107610784A (en) * | 2017-09-15 | 2018-01-19 | 中南大学 | A kind of method of predictive microbiology and disease relationship |
| CN108681660A (en) * | 2018-05-07 | 2018-10-19 | 福州大学 | A kind of non-coding RNA based on association rule mining and disease relationship prediction technique |
| CN108920895A (en) * | 2018-06-22 | 2018-11-30 | 中南大学 | A kind of incidence relation prediction technique of circular rna and disease |
-
2018
- 2018-12-24 CN CN201811580662.5A patent/CN109698029A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107610784A (en) * | 2017-09-15 | 2018-01-19 | 中南大学 | A kind of method of predictive microbiology and disease relationship |
| CN108681660A (en) * | 2018-05-07 | 2018-10-19 | 福州大学 | A kind of non-coding RNA based on association rule mining and disease relationship prediction technique |
| CN108920895A (en) * | 2018-06-22 | 2018-11-30 | 中南大学 | A kind of incidence relation prediction technique of circular rna and disease |
Non-Patent Citations (3)
| Title |
|---|
| BMC BIOINFORMATICS: "novel human mircobe-disease association prediction using network consistency projection" * |
| ZOU SHUAI等: "a novel approach for predicting mirobe-disease associations by bi-random walk on the heterogeneous network" * |
| 朱庆祺: "基于异构网络的非编码RNA及微生物与疾病关联预测研究" * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110459264A (en) * | 2019-08-02 | 2019-11-15 | 陕西师范大学 | Based on grad enhancement decision tree prediction circular rna and disease associated method |
| CN110767263A (en) * | 2019-10-18 | 2020-02-07 | 中国人民解放军陆军军医大学 | Non-coding RNA and disease associated prediction method based on sparse subspace learning |
| CN111161796A (en) * | 2019-12-30 | 2020-05-15 | 中南大学 | Method and system for predicting PD potential gene and miRNA |
| CN111161796B (en) * | 2019-12-30 | 2024-04-16 | 中南大学 | Method and system for predicting PD potential gene and miRNA |
| CN111540405A (en) * | 2020-04-29 | 2020-08-14 | 新疆大学 | Disease gene prediction method based on rapid network embedding |
| CN111584006A (en) * | 2020-05-06 | 2020-08-25 | 西安交通大学 | Circular RNA identification method based on machine learning strategy |
| CN111584006B (en) * | 2020-05-06 | 2022-02-22 | 西安交通大学 | Circular RNA identification method based on machine learning strategy |
| CN113241115A (en) * | 2021-03-26 | 2021-08-10 | 广东工业大学 | Depth matrix decomposition-based circular RNA disease correlation prediction method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109698029A (en) | A kind of circRNA- disease association prediction technique based on network model | |
| Guilliams et al. | Liver macrophages in health and disease | |
| Lee et al. | Machine learning on a genome-wide association study to predict late genitourinary toxicity after prostate radiation therapy | |
| Shim et al. | Integrated analysis of single-cell and spatial transcriptomics in keloids: highlights on fibrovascular interactions in keloid pathogenesis | |
| CN103160537B (en) | Application method of long-chain non-coding ribonucleic acid (RNA) gene in preparation of interference inhibitor | |
| Williamson et al. | Medulloblastoma group 3 and 4 tumors comprise a clinically and biologically significant expression continuum reflecting human cerebellar development | |
| Xie et al. | Single-cell sequencing analysis and weighted co-expression network analysis based on public databases identified that TNC is a novel biomarker for keloid | |
| CN103160580A (en) | Application method of long-chain non-coding ribonucleic acid (RNA) gene | |
| MotieGhader et al. | mRNA and microRNA selection for breast cancer molecular subtype stratification using meta-heuristic based algorithms | |
| Fink et al. | Single-cell and spatial mapping Identify cell types and signaling Networks in the human ureter | |
| Chen et al. | Six Glycolysis‐Related Genes as Prognostic Risk Markers Can Predict the Prognosis of Patients with Head and Neck Squamous Cell Carcinoma | |
| Konoshenko et al. | The influence of radical prostatectomy on the expression of cell-free MiRNA | |
| Zhou et al. | Joint masking and self-supervised strategies for inferring small molecule-miRNA associations | |
| Di Silvestre et al. | Proteomics-based network analysis characterizes biological processes and pathways activated by preconditioned mesenchymal stem cells in cardiac repair mechanisms | |
| Sh et al. | CaSee: A lightning transfer-learning model directly used to discriminate cancer/normal cells from scRNA-seq | |
| Ghasemi et al. | MicroRNAs dysregulation as potential biomarkers for early diagnosis of endometriosis | |
| Liu et al. | Multi-omics of extracellular vesicles: An integrative representation of functional mediators and perspectives on lung disease study | |
| Mao et al. | Transcriptomic and machine learning analyses identify hub genes of metabolism and host immune response that are associated with the progression of breast capsular contracture | |
| Wang et al. | Identification and validation of HOXD3 and UNC5C as molecular signatures in keloid based on weighted gene co-expression network analysis | |
| Liu et al. | Contrast-Enhanced Computed Tomography–Based Radiogenomics Analysis for Predicting Prognosis in Gastric Cancer | |
| Su et al. | Prediction of LncRNA-disease associations based on network representation learning | |
| Yuan | Characterizing Transcriptionally-Derived Molecular Subsets of Systemic Sclerosis Using Deep Neural Networks and miRNA Activity Scores | |
| Yan et al. | Acupoint Therapy with Injectable, Pro‐Healing Stem Cell‐Loaded Hydrogel Microspheres Promotes Skin Wound Healing | |
| Li et al. | Identification of subtype-specific master regulatory long non-coding RNAs of gastric cancer through a network-based approach | |
| Sen Puliparambil et al. | A novel algorithm for feature selection using penalized regression with applications to single-cell RNA sequencing data. Biology. 2022 Oct; 11 (10): 1495 |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190430 |
|
| WD01 | Invention patent application deemed withdrawn after publication |