FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2962149159> ?p ?o ?g. }

• W2962149159 endingPage "i224" @default.
• W2962149159 startingPage "i218" @default.
• W2962149159 abstract "Motivation: Human genomic datasets often contain sensitive information that limits use and sharing of the data. In particular, simple anonymisation strategies fail to provide sufficient level of protection for genomic data, because the data are inherently identifiable. Differentially private machine learning can help by guaranteeing that the published results do not leak too much information about any individual data point. Recent research has reached promising results on differentially private drug sensitivity prediction using gene expression data. Differentially private learning with genomic data is challenging because it is more difficult to guarantee the privacy in high dimensions. Dimensionality reduction can help, but if the dimension reduction mapping is learned from the data, then it needs to be differentially private too, which can carry a significant privacy cost. Furthermore, the selection of any hyperparameters (such as the target dimensionality) needs to also avoid leaking private information. Results: We study an approach that uses a large public dataset of similar type to learn a compact representation for differentially private learning. We compare three representation learning methods: variational autoencoders, PCA and random projection. We solve two machine learning tasks on gene expression of cancer cell lines: cancer type classification, and drug sensitivity prediction. The experiments demonstrate significant benefit from all representation learning methods with variational autoencoders providing the most accurate predictions most often. Our results significantly improve over previous state-of-the-art in accuracy of differentially private drug sensitivity prediction." @default.
• W2962149159 created "2019-07-23" @default.
• W2962149159 creator A5018305257 @default.
• W2962149159 creator A5058641659 @default.
• W2962149159 creator A5065857131 @default.
• W2962149159 creator A5071329195 @default.
• W2962149159 date "2019-07-01" @default.
• W2962149159 modified "2023-10-16" @default.
• W2962149159 title "Representation transfer for differentially private drug sensitivity prediction" @default.
• W2962149159 cites W1873763122 @default.
• W2962149159 cites W2040228409 @default.
• W2962149159 cites W2108068107 @default.
• W2962149159 cites W2108933868 @default.
• W2962149159 cites W2115358662 @default.
• W2962149159 cites W2122128696 @default.
• W2962149159 cites W2129157759 @default.
• W2962149159 cites W2134167315 @default.
• W2962149159 cites W2136114025 @default.
• W2962149159 cites W2159024459 @default.
• W2962149159 cites W2168610667 @default.
• W2962149159 cites W2812083516 @default.
• W2962149159 cites W2913413968 @default.
• W2962149159 cites W2979473749 @default.
• W2962149159 cites W3100553354 @default.
• W2962149159 cites W4205228770 @default.
• W2962149159 cites W4234726042 @default.
• W2962149159 doi "https://doi.org/10.1093/bioinformatics/btz373" @default.
• W2962149159 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/6612875" @default.
• W2962149159 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31510659" @default.
• W2962149159 hasPublicationYear "2019" @default.
• W2962149159 type Work @default.
• W2962149159 sameAs 2962149159 @default.
• W2962149159 citedByCount "7" @default.
• W2962149159 countsByYear W29621491592021 @default.
• W2962149159 countsByYear W29621491592022 @default.
• W2962149159 countsByYear W29621491592023 @default.
• W2962149159 crossrefType "journal-article" @default.
• W2962149159 hasAuthorship W2962149159A5018305257 @default.
• W2962149159 hasAuthorship W2962149159A5058641659 @default.
• W2962149159 hasAuthorship W2962149159A5065857131 @default.
• W2962149159 hasAuthorship W2962149159A5071329195 @default.
• W2962149159 hasBestOaLocation W29621491591 @default.
• W2962149159 hasConcept C111030470 @default.
• W2962149159 hasConcept C119857082 @default.
• W2962149159 hasConcept C124101348 @default.
• W2962149159 hasConcept C127413603 @default.
• W2962149159 hasConcept C137822555 @default.
• W2962149159 hasConcept C150899416 @default.
• W2962149159 hasConcept C154945302 @default.
• W2962149159 hasConcept C17744445 @default.
• W2962149159 hasConcept C199360897 @default.
• W2962149159 hasConcept C199539241 @default.
• W2962149159 hasConcept C202444582 @default.
• W2962149159 hasConcept C21200559 @default.
• W2962149159 hasConcept C24326235 @default.
• W2962149159 hasConcept C2776359362 @default.
• W2962149159 hasConcept C33676613 @default.
• W2962149159 hasConcept C33923547 @default.
• W2962149159 hasConcept C38652104 @default.
• W2962149159 hasConcept C41008148 @default.
• W2962149159 hasConcept C59404180 @default.
• W2962149159 hasConcept C70518039 @default.
• W2962149159 hasConcept C8642999 @default.
• W2962149159 hasConcept C90559484 @default.
• W2962149159 hasConcept C94625758 @default.
• W2962149159 hasConcept C99221444 @default.
• W2962149159 hasConceptScore W2962149159C111030470 @default.
• W2962149159 hasConceptScore W2962149159C119857082 @default.
• W2962149159 hasConceptScore W2962149159C124101348 @default.
• W2962149159 hasConceptScore W2962149159C127413603 @default.
• W2962149159 hasConceptScore W2962149159C137822555 @default.
• W2962149159 hasConceptScore W2962149159C150899416 @default.
• W2962149159 hasConceptScore W2962149159C154945302 @default.
• W2962149159 hasConceptScore W2962149159C17744445 @default.
• W2962149159 hasConceptScore W2962149159C199360897 @default.
• W2962149159 hasConceptScore W2962149159C199539241 @default.
• W2962149159 hasConceptScore W2962149159C202444582 @default.
• W2962149159 hasConceptScore W2962149159C21200559 @default.
• W2962149159 hasConceptScore W2962149159C24326235 @default.
• W2962149159 hasConceptScore W2962149159C2776359362 @default.
• W2962149159 hasConceptScore W2962149159C33676613 @default.
• W2962149159 hasConceptScore W2962149159C33923547 @default.
• W2962149159 hasConceptScore W2962149159C38652104 @default.
• W2962149159 hasConceptScore W2962149159C41008148 @default.
• W2962149159 hasConceptScore W2962149159C59404180 @default.
• W2962149159 hasConceptScore W2962149159C70518039 @default.
• W2962149159 hasConceptScore W2962149159C8642999 @default.
• W2962149159 hasConceptScore W2962149159C90559484 @default.
• W2962149159 hasConceptScore W2962149159C94625758 @default.
• W2962149159 hasConceptScore W2962149159C99221444 @default.
• W2962149159 hasFunder F4320321108 @default.
• W2962149159 hasIssue "14" @default.
• W2962149159 hasLocation W29621491591 @default.
• W2962149159 hasLocation W29621491592 @default.
• W2962149159 hasLocation W29621491593 @default.
• W2962149159 hasLocation W29621491594 @default.
• W2962149159 hasLocation W29621491595 @default.
• W2962149159 hasLocation W29621491596 @default.

• next