http://rdf.ncbi.nlm.nih.gov/pubchem/patent/RU-2745733-C1
Outgoing Links
| Predicate | Object |
|---|---|
| assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_1cb98082561173e3872367ac6ed34be6 |
| classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16B50-10 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16B30-00 |
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-082 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-084 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16B20-20 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16B30-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16B30-10 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16B40-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16B40-20 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-02 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16B50-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-02 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16B40-20 |
| filingDate | 2019-07-09-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| grantDate | 2021-03-31-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_c2cce894b937a0229e94a83b3d2fb8c3 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_b453ee3f30ae5bfd4faf260dd4f6cd9a http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_7ccebcf793067b8408f04c4b41a84fcb |
| publicationDate | 2021-03-31-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | RU-2745733-C1 |
| titleOfInvention | A deep learning frame for identifying sequence patterns that cause sequence specific errors (sse) |
| abstract | FIELD: computing.SUBSTANCE: invention relates in particular to computers and digital data processing systems related to artificial intelligence. The technical result is achieved by processing the superimposed samples with a convolutional neural network and based on the detection of nucleotide patterns in the superimposed samples by convolutional neural network filters, generating classification scores for the likelihood that the specified variant nucleotide in each of the superimposed samples is a true variant or a false variant; outputting distributions of classification points generated by a pre-trained subsystem of the filter of options for the repetition factors of the corresponding repeating patterns; and indicating, based on the threshold, a subset of classification scores in said distributions as indicating false classifications of variants and classifications of repetitive patterns that are associated with this subset of classification scores that indicate false classifications of variants as causing sequence-specific errors.EFFECT: technical result consists in minimizing training errors of the convolutional neural network.25 cl, 21 dwg |
| priorityDate | 2018-07-11-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 37.