FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2961661570> ?p ?o ?g. }

• W2961661570 endingPage "i163" @default.
• W2961661570 startingPage "i154" @default.
• W2961661570 abstract "Predictive models are a powerful tool for solving complex problems in computational biology. They are typically designed to predict or classify data coming from the same unknown distribution as the training data. In many real-world settings, however, uncontrolled biological or technical factors can lead to a distribution mismatch between datasets acquired at different times, causing model performance to deteriorate on new data. A common additional obstacle in computational biology is scarce data with many more features than samples. To address these problems, we propose a method for unsupervised domain adaptation that is based on a weighted elastic net. The key idea of our approach is to compare dependencies between inputs in training and test data and to increase the cost of differently behaving features in the elastic net regularization term. In doing so, we encourage the model to assign a higher importance to features that are robust and behave similarly across domains.We evaluate our method both on simulated data with varying degrees of distribution mismatch and on real data, considering the problem of age prediction based on DNA methylation data across multiple tissues. Compared with a non-adaptive standard model, our approach substantially reduces errors on samples with a mismatched distribution. On real data, we achieve far lower errors on cerebellum samples, a tissue which is not part of the training data and poorly predicted by standard models. Our results demonstrate that unsupervised domain adaptation is possible for applications in computational biology, even with many more features than samples.Source code is available at https://github.com/PfeiferLabTue/wenda.Supplementary data are available at Bioinformatics online." @default.
• W2961661570 created "2019-07-23" @default.
• W2961661570 creator A5023259879 @default.
• W2961661570 creator A5048155855 @default.
• W2961661570 creator A5071560628 @default.
• W2961661570 creator A5075567221 @default.
• W2961661570 creator A5076705834 @default.
• W2961661570 date "2019-07-01" @default.
• W2961661570 modified "2023-10-13" @default.
• W2961661570 title "Weighted elastic net for unsupervised domain adaptation with application to age prediction from DNA methylation data" @default.
• W2961661570 cites W1920348529 @default.
• W2961661570 cites W1974047233 @default.
• W2961661570 cites W1982696459 @default.
• W2961661570 cites W1986462247 @default.
• W2961661570 cites W1987180785 @default.
• W2961661570 cites W1997866877 @default.
• W2961661570 cites W2009467617 @default.
• W2961661570 cites W2020541351 @default.
• W2961661570 cites W2029276959 @default.
• W2961661570 cites W2038783315 @default.
• W2961661570 cites W2041290212 @default.
• W2961661570 cites W2056198580 @default.
• W2961661570 cites W2077359776 @default.
• W2961661570 cites W2090054883 @default.
• W2961661570 cites W2096192437 @default.
• W2961661570 cites W2097360283 @default.
• W2961661570 cites W2116117181 @default.
• W2961661570 cites W2117398145 @default.
• W2961661570 cites W2121091193 @default.
• W2961661570 cites W2122825543 @default.
• W2961661570 cites W2125789330 @default.
• W2961661570 cites W2127192982 @default.
• W2961661570 cites W2127431419 @default.
• W2961661570 cites W2128241046 @default.
• W2961661570 cites W2134755636 @default.
• W2961661570 cites W2136691282 @default.
• W2961661570 cites W2149310258 @default.
• W2961661570 cites W2158485828 @default.
• W2961661570 cites W2163327652 @default.
• W2961661570 cites W2165101781 @default.
• W2961661570 cites W2165698076 @default.
• W2961661570 cites W2168880641 @default.
• W2961661570 cites W2413867752 @default.
• W2961661570 cites W2560311853 @default.
• W2961661570 cites W2616090912 @default.
• W2961661570 cites W2730472814 @default.
• W2961661570 cites W2760834325 @default.
• W2961661570 cites W2761275051 @default.
• W2961661570 cites W2951012645 @default.
• W2961661570 cites W2952935243 @default.
• W2961661570 cites W4234698323 @default.
• W2961661570 cites W4294541781 @default.
• W2961661570 doi "https://doi.org/10.1093/bioinformatics/btz338" @default.
• W2961661570 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/6612879" @default.
• W2961661570 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31510704" @default.
• W2961661570 hasPublicationYear "2019" @default.
• W2961661570 type Work @default.
• W2961661570 sameAs 2961661570 @default.
• W2961661570 citedByCount "11" @default.
• W2961661570 countsByYear W29616615702020 @default.
• W2961661570 countsByYear W29616615702021 @default.
• W2961661570 countsByYear W29616615702022 @default.
• W2961661570 countsByYear W29616615702023 @default.
• W2961661570 crossrefType "journal-article" @default.
• W2961661570 hasAuthorship W2961661570A5023259879 @default.
• W2961661570 hasAuthorship W2961661570A5048155855 @default.
• W2961661570 hasAuthorship W2961661570A5071560628 @default.
• W2961661570 hasAuthorship W2961661570A5075567221 @default.
• W2961661570 hasAuthorship W2961661570A5076705834 @default.
• W2961661570 hasBestOaLocation W29616615701 @default.
• W2961661570 hasConcept C111919701 @default.
• W2961661570 hasConcept C119857082 @default.
• W2961661570 hasConcept C124101348 @default.
• W2961661570 hasConcept C139807058 @default.
• W2961661570 hasConcept C148483581 @default.
• W2961661570 hasConcept C154945302 @default.
• W2961661570 hasConcept C16910744 @default.
• W2961661570 hasConcept C169760540 @default.
• W2961661570 hasConcept C177264268 @default.
• W2961661570 hasConcept C199360897 @default.
• W2961661570 hasConcept C201797286 @default.
• W2961661570 hasConcept C203868755 @default.
• W2961661570 hasConcept C2776135515 @default.
• W2961661570 hasConcept C2776760102 @default.
• W2961661570 hasConcept C41008148 @default.
• W2961661570 hasConcept C43126263 @default.
• W2961661570 hasConcept C45804977 @default.
• W2961661570 hasConcept C60644358 @default.
• W2961661570 hasConcept C66024118 @default.
• W2961661570 hasConcept C86803240 @default.
• W2961661570 hasConceptScore W2961661570C111919701 @default.
• W2961661570 hasConceptScore W2961661570C119857082 @default.
• W2961661570 hasConceptScore W2961661570C124101348 @default.
• W2961661570 hasConceptScore W2961661570C139807058 @default.
• W2961661570 hasConceptScore W2961661570C148483581 @default.
• W2961661570 hasConceptScore W2961661570C154945302 @default.
• W2961661570 hasConceptScore W2961661570C16910744 @default.
• W2961661570 hasConceptScore W2961661570C169760540 @default.

• next