http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113903399-A
Outgoing Links
| Predicate | Object |
|---|---|
| assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_08dde60e3e0ca1e6ffaa5143e5c8477a |
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16B40-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16B35-20 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/C12P21-06 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/C12P21-06 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16B40-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16B35-20 |
| filingDate | 2021-08-26-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_37b7c805ce30677047dbb0f7cf847bc0 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_957360955daf6fdf2e00cec8b93fe29a http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_0f390d16837364a8fa11947ad2fe940b http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_ad40c56d4bf62d21b4f8b1fd77e2a5f0 |
| publicationDate | 2022-01-07-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-113903399-A |
| titleOfInvention | Method for high-throughput screening of food-borne antihypertensive peptides |
| abstract | The invention provides a method for high-throughput screening of food-borne antihypertensive peptides, which comprises the following steps: 1) collecting data on polypeptides known to have a potential for pressure reduction as positive samples; 2) randomly extracting the same amount of polypeptides from a protein database as a negative sample, and 3) extracting polypeptide sequence characteristics by adopting a pseudo-amino acid composition method; 4) establishing a antihypertensive peptide protBERT deep migration learning model; 5) evaluating the deep learning model by adopting a quintuplet cross verification method; 6) extracting protein from food, hydrolyzing the obtained protein with protease to obtain hydrolyzed peptide; 7) and (3) determining the amino acid sequence of the obtained food-borne hydrolyzed peptide, and inputting the amino acid sequence into a deep learning model for predicting the antihypertensive function. According to the method provided by the invention, a antihypertensive peptide prediction model is established by adopting a method of a protBERT deep migration learning model, and the deep learning model is evaluated through two indexes, namely Accuracy index and ROC index, so that the stability of the model is effectively ensured, and the identification and analysis capability of the model can be visually displayed. |
| isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-116564416-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-116564416-B |
| priorityDate | 2021-08-26-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 59.