Predicate |
Object |
assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_d86855b2452fd30e31e41138c31b8b19 |
classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/C12Q2600-158 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/C12Q1-6876 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/C12Q2600-106 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/C12Q2600-136 |
classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F17-18 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16B40-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16B25-10 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16B25-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16C20-70 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16C20-30 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16B45-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16B40-20 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16B50-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/C12Q1-6869 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16B20-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-048 |
classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G01N33-50 |
filingDate |
2018-10-15-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_069126c7d8d9cbc25d5ac1bc0e3379ae http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_502a0b75a23bee6a8b01cf0ad24ba840 |
publicationDate |
2020-08-19-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber |
EP-3695226-A1 |
titleOfInvention |
Drug repurposing based on deep embeddings of gene expression profiles |
abstract |
This invention relates to a deep learning model that measures functional similarities between compounds based on gene expression data of each compound. The model receives an untagged expression profile for the perturbagen that has been the subject of the query including the number of transcripts of a plurality of genes in a cell affected by the perturbation of the request. The model extracts an integration of the expression profile. Using the integration of the perturbagen that has been the subject of the query and the integrations of known perturbagens, the model determines a set of similarity scores, each indicating a probability that a known perturbagen has a similar effect on the gene expression to that of the perturbagen of the request.nThe probability further defines a prediction that the known perturbagen and the perturbation of the query share pharmacological similarities. The similarity scores are ranked and, from the ranked set, at least one candidate-pertussis is determined to have pharmacological effects similar to those of the perturbation of the request. The model may further be applied to the determination of similarities in the structure and biological protein targets between perturbagens. |
priorityDate |
2017-10-13-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type |
http://data.epo.org/linked-data/def/patent/Publication |