http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114974405-A
Outgoing Links
| Predicate | Object |
|---|---|
| assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_946c48785286f9a03c170ced2d1aca3a |
| classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/Y02D10-00 |
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16B15-30 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N10-20 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16B15-30 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N10-20 |
| filingDate | 2022-05-07-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_43b3b87571db9b313ec10aa3a76616d4 |
| publicationDate | 2022-08-30-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-114974405-A |
| titleOfInvention | Binding energy prediction method based on quantum GNN |
| abstract | The invention provides a binding energy prediction method based on quantum GNN, belonging to the technical field of quantum computing and biomedicine. Because this method optimizes the model between the GIN and the convolution module in the classical GNN through the quantum circuit, specifically through the quantum MLP in the quantum-classical hybrid GIN, the node eigenvectors after the aggregation of the drug molecules are remapped to obtain the first eigenvector, and then the first eigenvector is obtained. The protein sequence is extracted through the quantum convolutional network to obtain the feature vector of the protein molecule, and finally the predicted binding energy is obtained by splicing the feature vectors of the two. Therefore, using the highly parallel characteristics of quantum, the method provided by the present invention can greatly reduce the parameters of training, save computing resources, and improve the expression ability of data, so that the quantum chip and the electronic chip can work together to predict the binding energy of drug targets. Model. |
| priorityDate | 2022-05-07-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
| Predicate | Subject |
|---|---|
| isDiscussedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID458392451 |
Total number of triples: 15.