CN112562795A - Method for predicting new application of medicine based on multi-similarity fusion - Google Patents
Method for predicting new application of medicine based on multi-similarity fusion Download PDFInfo
- Publication number
- CN112562795A CN112562795A CN202011418728.8A CN202011418728A CN112562795A CN 112562795 A CN112562795 A CN 112562795A CN 202011418728 A CN202011418728 A CN 202011418728A CN 112562795 A CN112562795 A CN 112562795A
- Authority
- CN
- China
- Prior art keywords
- drug
- disease
- similarity
- calculated
- representing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000003814 drug Substances 0.000 title claims abstract description 245
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000004927 fusion Effects 0.000 title claims abstract description 15
- 229940079593 drug Drugs 0.000 claims abstract description 226
- 201000010099 disease Diseases 0.000 claims abstract description 158
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 158
- 239000000126 substance Substances 0.000 claims abstract description 26
- 238000004364 calculation method Methods 0.000 claims abstract description 24
- 102000038037 druggable proteins Human genes 0.000 claims abstract description 22
- 108091007999 druggable proteins Proteins 0.000 claims abstract description 22
- 230000000694 effects Effects 0.000 claims abstract description 22
- 238000000547 structure data Methods 0.000 claims abstract description 11
- 102000004169 proteins and genes Human genes 0.000 claims description 8
- 108090000623 proteins and genes Proteins 0.000 claims description 8
- 206010061623 Adverse drug reaction Diseases 0.000 claims description 4
- 208000030453 Drug-Related Side Effects and Adverse reaction Diseases 0.000 claims description 4
- 230000001225 therapeutic effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000004071 biological effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009511 drug repositioning Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 229940043263 traditional drug Drugs 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/30—Prediction of properties of chemical compounds, compositions or mixtures
-
- 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
- G16C20/70—Machine learning, data mining or chemometrics
Abstract
The invention discloses a method for predicting new application of a medicine based on multi-similarity fusion, which comprises the following steps: calculating the similarity of the medicines by using the chemical structure data of the medicines; calculating the similarity of the drugs by using the data of the drug target protein; calculating the similarity of the medicines by using the side effect data of the medicines; fusing the calculated drug similarity to obtain fused drug similarity; calculating a drug-disease association prediction value by using the fused drug similarity; calculating a disease similarity using the drug-disease data, and calculating a drug-disease association prediction value based on the disease similarity; and fusing the calculated medicine-disease correlation predicted value to obtain a fused medicine-disease correlation predicted value. The method performs weighted summation on the drug-disease association predicted value obtained by calculation based on the drug similarity and the drug-disease association predicted value obtained by calculation based on the disease similarity to obtain the fused drug-disease association predicted value, and improves the reliability and accuracy of the predicted value.
Description
Technical Field
The invention belongs to the field of medicine application prediction, and particularly relates to a method for predicting new medicine application based on multi-similarity fusion.
Background
Drug relocation (drug repurposing), commonly known as "old drug new use", refers to the relocation of a drug that has already developed an indication by existing technical means to find a new indication. Since the concept of drug relocation was proposed, scholars at home and abroad put great efforts on the research in this field. Chiang et al propose a view to treat drug relocation from a disease perspective, and consider two diseases similar when they can be treated with multiple identical drugs. If one drug has a treatment effect on only one disease, the drug is considered to have a potential treatment relation on the other disease, and can be used as a candidate drug for treating the disease. The chemical structure of the drug is considered to be a measure of the similarity between drugs, and Dudley et al suggest that the chemical properties of the drug are closely related to its therapeutic effect, and that there is a quantitative relationship between the chemical structure and the biological activity of the drug, so the chemical structure of the drug is the research direction for drug relocation. The drug target protein is a key factor for treating diseases by drugs, and drugs containing similar target proteins can have similar effects, so that the target protein can be used as a research angle for measuring the similarity of the drugs in drug relocation. Also, similar to the therapeutic effect of drugs on diseases, side effects produced by drugs provide phenotypic characteristics of humans, and thus studies of drug relocation from the side effect point of view of drugs are also feasible. Although the traditional drug relocation algorithm based on collaborative filtering has certain effects, the traditional method still has great progress space, and the traditional method is to conduct drug relocation research from one or two of multiple angles, which may cause deviation of predicted values.
Disclosure of Invention
The invention aims to solve the problems, and provides a method for predicting the new application of a medicine based on multi-similarity fusion, which respectively calculates the similarity of the medicine by using the chemical structure of the medicine, the target protein of the medicine and the side effect data of the medicine, then weights and sums the obtained similarity of the medicine to obtain the similarity of the fused medicine, calculates the obtained medicine-disease associated predicted value based on the similarity of the fused medicine, and avoids the problem of deviation of the medicine to the predicted value of the disease by depending on a single data source; and calculating the disease similarity by using the valley coefficient, calculating the drug-disease correlation predicted value based on the disease similarity, and performing weighted summation on the drug-disease correlation predicted value calculated based on the drug similarity to obtain the predicted value of the fused drug to the disease, so that the reliability of the predicted value is improved.
The technical scheme of the invention is a method for predicting the new application of a medicament based on multi-similarity fusion, which comprises the following steps,
step 1: calculating the similarity of the medicines by using the chemical structure data of the medicines;
step 2: calculating the similarity of the drugs by using the data of the drug target protein;
and step 3: calculating the similarity of the medicines by using the side effect data of the medicines;
and 4, step 4: fusing the drug similarity obtained by calculation in the step 1-3 to obtain fused drug similarity;
and 5: calculating a drug-disease association prediction value by using the fused drug similarity;
step 6: calculating a disease similarity using the drug-disease data, and calculating a drug-disease association prediction value based on the disease similarity;
and 7: and (5) fusing the predicted values in the steps (5) and (6) to obtain a fused drug-disease associated predicted value.
In step 4, the calculation formula of the fused drug similarity is as follows:
simd＝αsims+βsimp+γsimf
in the formula simdRepresenting the drug similarity, sim, of drug a and drug b obtained by fusionsRepresenting the drug similarity, sim, of drug a and drug b calculated using the drug chemical structure datapRepresenting the drug similarity, sim, of drug a and drug b calculated using drug target protein datafThe drug similarity of the drug a and the drug b calculated using the drug target protein data is expressed, α, β, and γ represent the weights of the drug similarity calculated using the drug chemical structure, the drug target protein, and the drug target protein data, respectively, and α + β + γ is 1.
In step 5, the formula for calculating the drug-disease associated predictive value is as follows:
in the formula
A predicted value representing the efficacy of drug a on disease q calculated using drug similarity; sim (D)a,Db) Denotes the drug a
Drug similarity to drug b, T is the neighbor set of drug a,
representing calculated drugs based on drug disease data
a mean value of the drug-disease correspondence values for all diseases,
means, s, representing the mean value of the drug-disease correspondence relationship values of drug b and all the diseases calculated based on the drug disease datab,qRepresents the drug-disease correspondence value of drug b to disease q.
In step 6, calculating the disease similarity by using the valley coefficient, wherein the calculation formula is as follows:
in the formula sim (I)q,Iy) Indicates the disease similarity of disease q and disease y, IqDenotes the amount of drug which can treat disease q, IyRepresents the amount of drug that can treat disease y, | IqyI denotes the number of drugs which can treat disease q and disease y simultaneously, sim (I)q,Iy) Has a value in the interval [0,1 ]]And (4) the following steps.
In step 6, the calculation formula for calculating the drug-disease association prediction value based on the disease similarity is as follows:
in the formula
A predicted value representing the efficacy of drug a on disease q calculated using the disease similarity; sim (I)q,Iy) Representing disease similarity between disease q and disease y, T is the neighbor set of disease q, sa,yA drug-disease correspondence value representing drug a and disease y.
In step 7, the calculation formula of the fused drug-disease association prediction value is as follows
In the formula PaqThe predicted value of the drug-disease association of the fused drug a and the disease q,
a predicted value representing the efficacy of drug a on disease q calculated using the disease similarity;
a predicted value representing the efficacy of drug a on disease q calculated using drug similarity; omega1、ω2Weight, ω, representing predicted values of drug-disease association calculated using the disease similarity and drug similarity, respectively1+ω2＝1。
Compared with the prior art, the invention has the beneficial effects that:
1) the method performs weighted summation on the drug-disease association predicted value obtained by calculation based on the drug similarity and the drug-disease association predicted value obtained by calculation based on the disease similarity to obtain the fused predicted value of the drug to the disease, so that the reliability and the accuracy of the predicted value are improved;
2) the method calculates the drug similarity by respectively utilizing the chemical structure of the drug, the drug target protein and the side effect data of the drug, weights are added to obtain the fused drug similarity, and the drug-disease correlation predicted value is calculated based on the fused drug similarity, so that the influence of sparse data and noise data of a single data source on the calculation result is avoided.
3) The disease similarity is calculated by utilizing the valley coefficient, and compared with a cosine similarity calculation method, the method simplifies the calculation complexity under the condition of not influencing the accuracy of the similarity.
Drawings
The invention is further illustrated by the following figures and examples.
Fig. 1 is a schematic diagram of calculating a fused drug-disease association predictive value according to an embodiment of the present invention.
Detailed Description
As shown in FIG. 1, the method for predicting the new application of the drug based on multi-similarity fusion comprises the following steps,
step 1: and calculating the similarity of the medicines by using the chemical structure data of the medicines, wherein the calculation formula is as follows:
in the formula simsRepresenting the similarity of drug a and drug b calculated using the chemical structure data of the drugs, D1aDenotes the number of chemical structures comprised by drug a, D1bRepresents the number of chemical structures contained in the drug b, | D1abI represents the number of identical chemical structures contained in drug a and drug b;
step 2: drug similarity was calculated using drug target protein data as follows:
in the formula simpRepresenting the similarity of drug a and drug b calculated using drug target protein data, D2aIndicates the number of target proteins corresponding to drug a, D2bRepresents the number of target proteins corresponding to the drug b, | D2abI represents the same target egg corresponding to the drug a and the drug bWhite number;
and step 3: and calculating the similarity of the medicaments by using the medicament side effect data, wherein the calculation formula is as follows:
in the formula simfRepresenting the degree of similarity of drug a and drug b calculated using drug side effect data, D3aIndicates the number of side effects of drug a, D3bIndicates the number of side effects, D, produced by drug b3abI represents the number of the same side effects generated by the drug a and the drug b; and 4, step 4: fusing the drug similarity obtained by calculation in the step 1-3 to obtain fused drug similarity, wherein the calculation formula is as follows
simd＝αsims+βsimp+γsimf
In the formula simdRepresenting the drug similarity, sim, of drug a and drug b obtained by fusionsRepresenting the drug similarity, sim, of drug a and drug b calculated using the drug chemical structure datapRepresenting the drug similarity, sim, of drug a and drug b calculated using drug target protein datafThe method comprises the steps of calculating the drug similarity of a drug a and a drug b by using drug target protein data, respectively calculating the weights of the drug similarity by using the drug chemical structure, the drug target protein and the drug target protein data, calculating the values of alpha, beta and gamma by using a heuristic method and taking 0.1 as a step length, and determining a group of weights with optimal effect by multiple experiments. The effect is optimal when alpha is 0.2, beta is 0.4 and gamma is 0.4 by a heuristic method;
and 5: calculating the drug-disease correlation prediction value by using the fused drug similarity, wherein the calculation formula is as follows
In the formula
A predicted value representing the efficacy of drug a on disease q calculated using drug similarity; sim (D)a,Db) Representing the similarity of drug a and drug b, T is the neighbor set of drug a,
represents the average value of the drug-disease correspondence values of the drug a and all the diseases calculated based on the drug disease data,
means, s, representing the mean value of the drug-disease correspondence relationship values of drug b and all the diseases calculated based on the drug disease datab,qA drug-disease correspondence value representing drug b and disease q;
step 6: calculating a disease similarity using the drug-disease data, and calculating a drug-disease association prediction value based on the disease similarity; the calculation of the disease similarity is as follows:
in the formula sim (I)q,Iy) Indicates the disease similarity of disease q and disease y, IqDenotes the amount of drug which can treat disease q, IyRepresents the amount of drug that can treat disease y, | IqyI denotes the number of drugs which can treat disease q and disease y simultaneously, sim (I)q,Iy) Has a value in the interval [0,1 ]]Internal;
calculating the drug-disease correlation prediction value based on the disease similarity, wherein the calculation formula is as follows
In the formula
Shows the effect of drug a on disease q calculated by using the similarity of diseasesThe predicted value of (2); sim (I)q,Iy) Representing disease similarity between disease q and disease y, T is the neighbor set of disease q, sa,yA drug-disease correspondence value representing drug a and disease y.
And 7: fusing the predicted values in the steps 5 and 6 to obtain a fused drug-disease associated predicted value, wherein the calculation formula is as follows
In the formula PaqThe predicted value of the drug-disease association of the fused drug a and the disease q,
a predicted value representing the efficacy of drug a on disease q calculated using the disease similarity;
a predicted value representing the efficacy of drug a on disease q calculated using drug similarity; omega1、ω2Weight, ω, representing predicted values of drug-disease association calculated using the disease similarity and drug similarity, respectively1+ω21, example ω1＝0.6，ω2＝0.4；
In the examples, drug chemical structure data was sampled from the PubChem database, drug target protein data from the UniPort knowledgbase database, and drug side effect data from the SIDER database. The method for fusing the similarity effectively solves the problem that the effective similarity calculated by a single data source is less due to data sparsity.
In the embodiment, the disease similarity is calculated only by considering whether the medicine and the disease have the corresponding treatment relation, but not considering the quality of the treatment effect, so that the disease similarity is performed through a trough coefficient, and compared with methods such as cosine similarity, the method simplifies the complexity of calculation under the condition of not influencing the accuracy of the similarity.
Claims (8)
1. The method for predicting the new application of the medicine based on multi-similarity fusion is characterized by comprising the following steps,
step 1: calculating the similarity of the medicines by using the chemical structure data of the medicines;
step 2: calculating the similarity of the drugs by using the data of the drug target protein;
and step 3: calculating the similarity of the medicines by using the side effect data of the medicines;
and 4, step 4: fusing the drug similarity obtained by calculation in the step 1-3 to obtain fused drug similarity;
and 5: calculating a drug-disease association prediction value by using the fused drug similarity;
step 6: calculating a disease similarity using the drug-disease data, and calculating a drug-disease association prediction value based on the disease similarity;
and 7: and (5) fusing the predicted values in the steps (5) and (6) to obtain a fused drug-disease associated predicted value.
2. The method for predicting the new application of the drug based on the multi-similarity fusion according to claim 1, wherein in the step 1, the drug similarity is calculated by using the chemical structure data of the drug according to the following formula:
in the formula simsRepresenting the drug similarity of drug a and drug b calculated using the drug chemical structure data, D1aDenotes the number of chemical structures comprised by drug a, D1bRepresents the number of chemical structures contained in the drug b, | D1abThe | represents the number of identical chemical structures comprised by drug a and drug b.
3. The method for predicting the new application of the drug based on the multi-similarity fusion as claimed in claim 2, wherein in the step 2, the drug similarity is calculated by using the data of the drug target protein, and the calculation formula is as follows:
in the formula simpRepresenting the drug similarity of drug a and drug b calculated using drug target protein data, D2aIndicates the number of target proteins corresponding to drug a, D2bRepresents the number of target proteins corresponding to the drug b, | D2abThe | represents the number of the same target protein corresponding to the drug a and the drug b.
4. The method for predicting the new application of the drug based on the multi-similarity fusion as claimed in claim 3, wherein in the step 3, the drug similarity is calculated by using the drug side effect data, and the calculation formula is as follows:
in the formula simfRepresenting the drug similarity of drug a and drug b calculated using the drug side effect data, D3aIndicates the number of side effects of drug a, D3bIndicates the number of side effects, D, produced by drug b3abThe | represents the number of the same side effects produced by the drug a and the drug b.
5. The method for predicting the new application of the multi-similarity fusion-based drug according to claim 4, wherein the fused drug similarity in step 4 is calculated by the following formula:
simd＝αsims+βsimp+γsimf
in the formula simdRepresenting the drug similarity, sim, of drug a and drug b obtained by fusionsRepresenting the drug similarity, sim, of drug a and drug b calculated using the drug chemical structure datapRepresenting the drug similarity, sim, of drug a and drug b calculated using drug target protein datafRepresenting drug a and drug b calculated using drug target protein dataα, β, and γ represent weights of the drug similarity calculated using the chemical structure of the drug, the drug target protein, and the drug target protein data, respectively, and α + β + γ is 1.
6. The method for predicting the new application of the drug based on the multi-similarity fusion according to claim 5, wherein in the step 5, the predicted value of the drug-disease association is calculated by the following formula:
in the formula
A predicted value representing the efficacy of drug a on disease q calculated using drug similarity; sim (D)a,Db) Representing the drug similarity of drug a and drug b, T is the neighbor set of drug a,
represents the average value of the drug-disease correspondence values of the drug a and all the diseases calculated based on the drug disease data,
means, s, representing the mean value of the drug-disease correspondence relationship values of drug b and all the diseases calculated based on the drug disease datab,qRepresents the drug-disease correspondence value of drug b to disease q.
7. The method for predicting the new application of the drug based on the multi-similarity fusion according to claim 6, wherein in the step 6, the disease similarity is calculated by the following formula:
in the formula sim (I)q,Iy) Indicates the disease similarity of disease q and disease y, IqDenotes the amount of drug which can treat disease q, IyRepresents the amount of drug that can treat disease y, | IqyL represents the number of drugs that can treat disease q and disease y simultaneously;
the formula for calculating the predictive value of drug-disease association based on disease similarity is as follows:
in the formula
A predicted value representing the efficacy of drug a on disease q calculated using the disease similarity; sim (I)q,Iy) Representing disease similarity between disease q and disease y, T is the neighbor set of disease q, sa,yA drug-disease correspondence value representing drug a and disease y.
8. The method for predicting the new use of a drug based on multi-similarity fusion according to claim 7, wherein the fused drug-disease association prediction value is calculated by the following formula in step 7:
in the formula PaqThe predicted value of the drug-disease association of the fused drug a and the disease q,
a predicted value representing the efficacy of drug a on disease q calculated using the disease similarity;
representing the effect of drug a on disease q calculated using drug similarityPredicting a value; omega1、ω2Weight, ω, representing predicted values of drug-disease association calculated using the disease similarity and drug similarity, respectively1+ω2＝1。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011418728.8A CN112562795A (en) | 2020-12-07 | 2020-12-07 | Method for predicting new application of medicine based on multi-similarity fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011418728.8A CN112562795A (en) | 2020-12-07 | 2020-12-07 | Method for predicting new application of medicine based on multi-similarity fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112562795A true CN112562795A (en) | 2021-03-26 |
Family
ID=75059326
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011418728.8A Pending CN112562795A (en) | 2020-12-07 | 2020-12-07 | Method for predicting new application of medicine based on multi-similarity fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112562795A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105653846A (en) * | 2015-12-25 | 2016-06-08 | 中南大学 | Integrated similarity measurement and bi-directional random walk based pharmaceutical relocation method |
| CN107506591A (en) * | 2017-08-28 | 2017-12-22 | 中南大学 | A kind of medicine method for relocating based on multivariate information fusion and random walk model |
| CN109712678A (en) * | 2018-12-12 | 2019-05-03 | 中国人民解放军军事科学院军事医学研究院 | Relationship Prediction method, apparatus and electronic equipment |
| CN111951886A (en) * | 2019-05-17 | 2020-11-17 | 天津科技大学 | Drug relocation prediction method based on Bayesian inductive matrix completion |
-
2020
- 2020-12-07 CN CN202011418728.8A patent/CN112562795A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105653846A (en) * | 2015-12-25 | 2016-06-08 | 中南大学 | Integrated similarity measurement and bi-directional random walk based pharmaceutical relocation method |
| CN107506591A (en) * | 2017-08-28 | 2017-12-22 | 中南大学 | A kind of medicine method for relocating based on multivariate information fusion and random walk model |
| CN109712678A (en) * | 2018-12-12 | 2019-05-03 | 中国人民解放军军事科学院军事医学研究院 | Relationship Prediction method, apparatus and electronic equipment |
| CN111951886A (en) * | 2019-05-17 | 2020-11-17 | 天津科技大学 | Drug relocation prediction method based on Bayesian inductive matrix completion |
Non-Patent Citations (2)
| Title |
|---|
| PENG CHEN等: "A Drug Repositioning Algorithm Based on Deep Auto-Encoder and Adaptive Fusion", 《RESEARCH SQUARE》 * |
| 林耀进等: "基于协同过滤的药物重定位算法", 《南京大学学报（自然科学）》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pousset et al. | A 22-year follow-up study of long-term cardiac outcome and predictors of survival in Friedreich ataxia | |
| Cuthbert et al. | Toward the future of psychiatric diagnosis: the seven pillars of RDoC | |
| Sohn et al. | Phase I/II clinical trial of enzyme replacement therapy with idursulfase beta in patients with mucopolysaccharidosis II (Hunter syndrome) | |
| US20180039726A1 (en) | Computer based system for predicting treatment outcomes | |
| Nyati et al. | TH1 and TH2 response to Campylobacter jejuni antigen in Guillain-Barre syndrome | |
| Yasnitsky et al. | Artificial neural networks for obtaining new medical knowledge: diagnostics and prediction of cardiovascular disease progression | |
| Pogoryelova et al. | Phenotypic stratification and genotype–phenotype correlation in a heterogeneous, international cohort of GNE myopathy patients: first report from the GNE myopathy disease monitoring program, registry portion | |
| Lewis et al. | Use of biotelemetry to define physiology-based deterioration thresholds in a murine cecal ligation and puncture model of sepsis | |
| US20070083333A1 (en) | Modeling of systemic inflammatory response to infection | |
| Chaikittisilpa et al. | Characterizing the relationship between systemic inflammatory response syndrome and early cardiac dysfunction in traumatic brain injury | |
| CN108034708B (en) | System for determining individual effectiveness of tripterygium glycosides tablet in treating rheumatoid arthritis through expression quantity of multiple mRNA | |
| Komaroff | Can infections cause Alzheimer disease? | |
| CN108647484B (en) | Medicine relation prediction method based on multivariate information integration and least square method | |
| Roman et al. | Spotlight on brodalumab in the treatment of moderate-to-severe plaque psoriasis: design, development, and potential place in therapy | |
| CN111863181A (en) | Medicine recommendation method and device, computer equipment and storage medium | |
| CN109558493A (en) | A kind of disease similarity calculating method based on disease ontology | |
| Hecker et al. | Integrative modeling of transcriptional regulation in response to antirheumatic therapy | |
| Phillips et al. | Calcium antagonists for Duchenne muscular dystrophy | |
| Song et al. | Intracranial pressure patterns and neurological outcomes in out-of-hospital cardiac arrest survivors after targeted temperature management: a retrospective observational study | |
| Zhao et al. | Evaluation of quality of life using ASQoL questionnaire in patients with ankylosing spondylitis in a Chinese population | |
| Ørbo et al. | Cortical thickness and cognitive performance after out-of-hospital cardiac arrest | |
| Vijayalakshmi et al. | Predicting Hepatitis B to be acute or chronic in an infected person using machine learning algorithm | |
| Liao et al. | Comparative efficacy of Intra-articular injection, physical therapy, and combined treatments on pain, function, and sarcopenia indices in knee osteoarthritis: a network Meta-analysis of randomized controlled trials | |
| CN112562795A (en) | Method for predicting new application of medicine based on multi-similarity fusion | |
| Mercuri et al. | Potential role of ustekinumab in the treatment of chronic plaque psoriasis |
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: 20210326 |