| Predicate |
Object |
| assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_4bd24d0edc441a277cf5d128b2c97b31 |
| classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/C12Q2600-154 |
| classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16B20-00
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/G16H50-20
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16H70-60
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/C12Q1-6869
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/C12Q1-6886
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-04
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16B5-20 |
| classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16B40-00
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16H70-60
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16B5-20 |
| filingDate |
2021-03-29-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_2e3dfdddd9e21262586ddfee65276dbe
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_66318464959f741081ebcdf3309c744d
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_f383dd2577d09f3c2a96b39df7d444ee |
| publicationDate |
2021-10-07-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber |
US-2021313006-A1 |
| titleOfInvention |
Cancer Classification with Genomic Region Modeling |
| abstract |
Methods and systems for detecting cancer and/or determining a cancer tissue of origin are disclosed. Fragments are grouped into genomic regions, wherein a region model is trained for each genomic region. Fragments are input into the region models, and the outputs are used to generate a feature vector for cancer classification. In one embodiment, the region models are shallow neural networks configured to generate a score indicating a likelihood that a fragment is derived from a cancer biological sample. The feature vector is determined based on counts of fragments having scores above threshold scores for the various genomic regions. In another embodiment, the regions models are configured to generate a region embedding for an input methylation embedding of a fragment. The region embeddings are pooled by region and then pooled again to generate the feature vector. |
| isCitedBy |
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115064211-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-2023164665-A1
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114373502-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-2023102142-A1 |
| priorityDate |
2020-03-31-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type |
http://data.epo.org/linked-data/def/patent/Publication |