http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110689918-B
Outgoing Links
Predicate | Object |
---|---|
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16B15-20 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16B5-00 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16B15-20 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16B5-00 |
filingDate | 2019-09-24-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
grantDate | 2022-12-09-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationDate | 2022-12-09-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-110689918-B |
titleOfInvention | Method and system for predicting protein tertiary structure |
abstract | The invention provides a method and system for predicting the tertiary structure of a protein, comprising: a step of building a network structure; a step of setting two head outputs; a step of obtaining a distance probability distribution; a step of obtaining an angle probability distribution; a step of constructing a loss function l; obtaining a parameter set step; fitting step; learning step of neural network; prediction result calculation step. The dual-head shared neural network architecture for joint prediction can not only solve the inconsistency of distance and angle prediction, improve the accuracy of angle and distance prediction, but also greatly reduce the calculation time and speed up the prediction speed. |
priorityDate | 2019-09-24-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 19.