FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3199688452> ?p ?o ?g. }

• W3199688452 endingPage "104850" @default.
• W3199688452 startingPage "104850" @default.
• W3199688452 abstract "Deep learning neural networks have improved performance in many cancer informatics problems, including breast cancer subtype classification. However, many networks experience underspecificationwheremultiplecombinationsofparametersachievesimilarperformance, bothin training and validation. Additionally, certain parameter combinations may perform poorly when the test distribution differs from the training distribution. Embedding prior knowledge from the literature may address this issue by boosting predictive models that provide crucial, in-depth information about a given disease. Breast cancer research provides a wealth of such knowledge, particularly in the form of subtype biomarkers and genetic signatures. In this study, we draw on past research on breast cancer subtype biomarkers, label propagation, and neural graph machines to present a novel methodology for embedding knowledge into machine learning systems. We embed prior knowledge into the loss function in the form of inter-subject distances derived from a well-known published breast cancer signature. Our results show that this methodology reduces predictor variability on state-of-the-art deep learning architectures and increases predictor consistency leading to improved interpretation. We find that pathway enrichment analysis is more consistent after embedding knowledge. This novel method applies to a broad range of existing studies and predictive models. Our method moves the traditional synthesis of predictive models from an arbitrary assignment of weights to genes toward a more biologically meaningful approach of incorporating knowledge." @default.
• W3199688452 created "2021-09-27" @default.
• W3199688452 creator A5004031300 @default.
• W3199688452 creator A5007961778 @default.
• W3199688452 creator A5025667244 @default.
• W3199688452 creator A5037851388 @default.
• W3199688452 creator A5056564396 @default.
• W3199688452 date "2021-11-01" @default.
• W3199688452 modified "2023-09-24" @default.
• W3199688452 title "Reducing variability of breast cancer subtype predictors by grounding deep learning models in prior knowledge" @default.
• W3199688452 cites W1985066050 @default.
• W3199688452 cites W1985078733 @default.
• W3199688452 cites W2005895632 @default.
• W3199688452 cites W2018020283 @default.
• W3199688452 cites W2022406334 @default.
• W3199688452 cites W2029965175 @default.
• W3199688452 cites W2032794174 @default.
• W3199688452 cites W2032964150 @default.
• W3199688452 cites W2034269086 @default.
• W3199688452 cites W2053918119 @default.
• W3199688452 cites W2058198205 @default.
• W3199688452 cites W2087689337 @default.
• W3199688452 cites W2096918186 @default.
• W3199688452 cites W2102461795 @default.
• W3199688452 cites W2110256992 @default.
• W3199688452 cites W2111568097 @default.
• W3199688452 cites W2114505219 @default.
• W3199688452 cites W2117692326 @default.
• W3199688452 cites W2117810384 @default.
• W3199688452 cites W2118143278 @default.
• W3199688452 cites W2119277134 @default.
• W3199688452 cites W2119568183 @default.
• W3199688452 cites W2137028370 @default.
• W3199688452 cites W2148418222 @default.
• W3199688452 cites W2162491741 @default.
• W3199688452 cites W2221443338 @default.
• W3199688452 cites W2262414037 @default.
• W3199688452 cites W2419558864 @default.
• W3199688452 cites W2462877134 @default.
• W3199688452 cites W2483024785 @default.
• W3199688452 cites W2589778279 @default.
• W3199688452 cites W2624021832 @default.
• W3199688452 cites W2750268731 @default.
• W3199688452 cites W2808686685 @default.
• W3199688452 cites W2916583781 @default.
• W3199688452 cites W2950595506 @default.
• W3199688452 cites W2951091426 @default.
• W3199688452 cites W2958196506 @default.
• W3199688452 cites W2980183989 @default.
• W3199688452 cites W2981121978 @default.
• W3199688452 cites W2982580298 @default.
• W3199688452 cites W2990290777 @default.
• W3199688452 cites W3000045279 @default.
• W3199688452 cites W3043374725 @default.
• W3199688452 cites W3047040425 @default.
• W3199688452 cites W3048227392 @default.
• W3199688452 cites W3080717832 @default.
• W3199688452 cites W3096093869 @default.
• W3199688452 cites W3097703873 @default.
• W3199688452 cites W4239678514 @default.
• W3199688452 cites W779403461 @default.
• W3199688452 doi "https://doi.org/10.1016/j.compbiomed.2021.104850" @default.
• W3199688452 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34536702" @default.
• W3199688452 hasPublicationYear "2021" @default.
• W3199688452 type Work @default.
• W3199688452 sameAs 3199688452 @default.
• W3199688452 citedByCount "3" @default.
• W3199688452 countsByYear W31996884522022 @default.
• W3199688452 crossrefType "journal-article" @default.
• W3199688452 hasAuthorship W3199688452A5004031300 @default.
• W3199688452 hasAuthorship W3199688452A5007961778 @default.
• W3199688452 hasAuthorship W3199688452A5025667244 @default.
• W3199688452 hasAuthorship W3199688452A5037851388 @default.
• W3199688452 hasAuthorship W3199688452A5056564396 @default.
• W3199688452 hasBestOaLocation W31996884521 @default.
• W3199688452 hasConcept C108583219 @default.
• W3199688452 hasConcept C119857082 @default.
• W3199688452 hasConcept C121608353 @default.
• W3199688452 hasConcept C126322002 @default.
• W3199688452 hasConcept C154945302 @default.
• W3199688452 hasConcept C2776436953 @default.
• W3199688452 hasConcept C41008148 @default.
• W3199688452 hasConcept C41608201 @default.
• W3199688452 hasConcept C46686674 @default.
• W3199688452 hasConcept C50644808 @default.
• W3199688452 hasConcept C530470458 @default.
• W3199688452 hasConcept C71924100 @default.
• W3199688452 hasConceptScore W3199688452C108583219 @default.
• W3199688452 hasConceptScore W3199688452C119857082 @default.
• W3199688452 hasConceptScore W3199688452C121608353 @default.
• W3199688452 hasConceptScore W3199688452C126322002 @default.
• W3199688452 hasConceptScore W3199688452C154945302 @default.
• W3199688452 hasConceptScore W3199688452C2776436953 @default.
• W3199688452 hasConceptScore W3199688452C41008148 @default.
• W3199688452 hasConceptScore W3199688452C41608201 @default.
• W3199688452 hasConceptScore W3199688452C46686674 @default.
• W3199688452 hasConceptScore W3199688452C50644808 @default.
• W3199688452 hasConceptScore W3199688452C530470458 @default.

• next