Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048184046> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W3048184046 abstract "ABSTRACT Deep learning can extract meaningful features from data given enough training examples. Large-scale genomic data are well suited for this class of machine learning algorithms; however, for many of these data the labels are at the level of the sample instead of at the level of the individual genomic measures. Conventional approaches to this data statically featurise and aggregate the measures separately from prediction. We propose to featurise, aggregate, and predict with a single trainable end-to-end model by turning to attention-based multiple instance learning. This allows for direct modelling of instance importance to sample-level classification in addition to trainable encoding strategies of genomic descriptions, such as mutations. We first demonstrate this approach by successfully solving synthetic tasks conventional approaches fail. Subsequently we applied the approach to somatic variants and achieved best-in-class performance when classifying tumour type or microsatellite status, while simultaneously providing an improved level of model explainability. Our results suggest that this framework could lead to biological insights and improve performance on tasks that aggregate information from sets of genomic data." @default.
- W3048184046 created "2020-08-13" @default.
- W3048184046 creator A5007455008 @default.
- W3048184046 creator A5040720823 @default.
- W3048184046 creator A5062308537 @default.
- W3048184046 creator A5074992313 @default.
- W3048184046 date "2020-08-07" @default.
- W3048184046 modified "2023-10-14" @default.
- W3048184046 title "Aggregation Tool for Genomic Concepts (ATGC): A deep learning framework for sparse genomic measures and its application to somatic mutations" @default.
- W3048184046 cites W2010792435 @default.
- W3048184046 cites W2041440766 @default.
- W3048184046 cites W2110119381 @default.
- W3048184046 cites W2111435123 @default.
- W3048184046 cites W2152061559 @default.
- W3048184046 cites W2198606573 @default.
- W3048184046 cites W2262414037 @default.
- W3048184046 cites W2493343568 @default.
- W3048184046 cites W2560886373 @default.
- W3048184046 cites W2567051070 @default.
- W3048184046 cites W2760942750 @default.
- W3048184046 cites W2794804602 @default.
- W3048184046 cites W2795441251 @default.
- W3048184046 cites W2795622837 @default.
- W3048184046 cites W2800388620 @default.
- W3048184046 cites W2805627121 @default.
- W3048184046 cites W2890252047 @default.
- W3048184046 cites W2937319208 @default.
- W3048184046 cites W2951934944 @default.
- W3048184046 cites W2964844385 @default.
- W3048184046 cites W2994737357 @default.
- W3048184046 cites W2995997429 @default.
- W3048184046 cites W3004480399 @default.
- W3048184046 cites W3005188734 @default.
- W3048184046 cites W3008614160 @default.
- W3048184046 cites W3126827997 @default.
- W3048184046 cites W3135547872 @default.
- W3048184046 cites W3159302505 @default.
- W3048184046 cites W3199772305 @default.
- W3048184046 cites W3203838058 @default.
- W3048184046 cites W4221003407 @default.
- W3048184046 cites W4225752857 @default.
- W3048184046 cites W4283362956 @default.
- W3048184046 doi "https://doi.org/10.1101/2020.08.05.237206" @default.
- W3048184046 hasPublicationYear "2020" @default.
- W3048184046 type Work @default.
- W3048184046 sameAs 3048184046 @default.
- W3048184046 citedByCount "2" @default.
- W3048184046 countsByYear W30481840462023 @default.
- W3048184046 crossrefType "posted-content" @default.
- W3048184046 hasAuthorship W3048184046A5007455008 @default.
- W3048184046 hasAuthorship W3048184046A5040720823 @default.
- W3048184046 hasAuthorship W3048184046A5062308537 @default.
- W3048184046 hasAuthorship W3048184046A5074992313 @default.
- W3048184046 hasBestOaLocation W30481840461 @default.
- W3048184046 hasConcept C119857082 @default.
- W3048184046 hasConcept C125411270 @default.
- W3048184046 hasConcept C154945302 @default.
- W3048184046 hasConcept C159985019 @default.
- W3048184046 hasConcept C185592680 @default.
- W3048184046 hasConcept C192562407 @default.
- W3048184046 hasConcept C198531522 @default.
- W3048184046 hasConcept C2777212361 @default.
- W3048184046 hasConcept C41008148 @default.
- W3048184046 hasConcept C43617362 @default.
- W3048184046 hasConcept C4679612 @default.
- W3048184046 hasConceptScore W3048184046C119857082 @default.
- W3048184046 hasConceptScore W3048184046C125411270 @default.
- W3048184046 hasConceptScore W3048184046C154945302 @default.
- W3048184046 hasConceptScore W3048184046C159985019 @default.
- W3048184046 hasConceptScore W3048184046C185592680 @default.
- W3048184046 hasConceptScore W3048184046C192562407 @default.
- W3048184046 hasConceptScore W3048184046C198531522 @default.
- W3048184046 hasConceptScore W3048184046C2777212361 @default.
- W3048184046 hasConceptScore W3048184046C41008148 @default.
- W3048184046 hasConceptScore W3048184046C43617362 @default.
- W3048184046 hasConceptScore W3048184046C4679612 @default.
- W3048184046 hasLocation W30481840461 @default.
- W3048184046 hasOpenAccess W3048184046 @default.
- W3048184046 hasPrimaryLocation W30481840461 @default.
- W3048184046 hasRelatedWork W2389073067 @default.
- W3048184046 hasRelatedWork W2895096066 @default.
- W3048184046 hasRelatedWork W2961085424 @default.
- W3048184046 hasRelatedWork W3046775127 @default.
- W3048184046 hasRelatedWork W4285260836 @default.
- W3048184046 hasRelatedWork W4286629047 @default.
- W3048184046 hasRelatedWork W4306321456 @default.
- W3048184046 hasRelatedWork W4306674287 @default.
- W3048184046 hasRelatedWork W4380203703 @default.
- W3048184046 hasRelatedWork W4224009465 @default.
- W3048184046 isParatext "false" @default.
- W3048184046 isRetracted "false" @default.
- W3048184046 magId "3048184046" @default.
- W3048184046 workType "article" @default.