Matches in SemOpenAlex for { <https://semopenalex.org/work/W2893702256> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W2893702256 abstract "Author(s): Durbin, Kenneth James | Advisor(s): Stuart, Josh | Abstract: In this work, I examine the use of low-level feature classifiers to enhance the performance of clinically relevant gene expression classifiers. In other machine learning domains, notably machine vision, recognizing higher level or more abstract concepts by using lower level or more concrete feature classifiers is a common motif. For example, a classifier to recognize images of “parties” might usefully first have sub-classifiers to recognize concrete elements commonly found in parties: indoors, people, party hats, cake, candles, banners, confetti, etc. The output of these low level feature classifiers can be supplied to an overall “party” classifier to assign a label. Image pixels are far removed from an abstract concept like “party,” so training classifiers for these more concretely defined sub-concepts is a way to bridge this semantic gap. Moreover, there may be many more training examples available for the lower level concepts (e.g. people) than the target (e.g. party), allowing one to utilize the robustness that comes from plentiful data. I hypothesize that there is a similar semantic gap between gene expression levels and clinically relevant gene expression classification targets, such as survival prognosis or drug sensitivity for tumor types, and that these clinically relevant classification tasks can benefit from decomposition into classifiers for more concrete concepts, such as tissue type, chromatin state, mutations, and gene essentiality. I will present a series of experiments that show modest but real improvements from the use of low-level feature classifiers in several gene expression prediction tasks. I will also present a series of tools developed for this work including wekaMine (a large-scale model selection and feature-building pipeline), viewtab (a “big data” spreadsheet), csvsql (a program to allow arbitrary SQL queries on csv/tab files), and SamplePsychic (a web application to apply a suite of feature classifiers to gene expression samples and explore the results)." @default.
- W2893702256 created "2018-10-05" @default.
- W2893702256 creator A5050547204 @default.
- W2893702256 date "2018-01-01" @default.
- W2893702256 modified "2023-09-24" @default.
- W2893702256 title "Improving Clinically Relevant Classification of Gene Expression Datasets Using Attribute Classifiers as Features" @default.
- W2893702256 hasPublicationYear "2018" @default.
- W2893702256 type Work @default.
- W2893702256 sameAs 2893702256 @default.
- W2893702256 citedByCount "0" @default.
- W2893702256 crossrefType "journal-article" @default.
- W2893702256 hasAuthorship W2893702256A5050547204 @default.
- W2893702256 hasConcept C104317684 @default.
- W2893702256 hasConcept C106135958 @default.
- W2893702256 hasConcept C119857082 @default.
- W2893702256 hasConcept C138885662 @default.
- W2893702256 hasConcept C153180895 @default.
- W2893702256 hasConcept C154945302 @default.
- W2893702256 hasConcept C2776401178 @default.
- W2893702256 hasConcept C41008148 @default.
- W2893702256 hasConcept C41895202 @default.
- W2893702256 hasConcept C55493867 @default.
- W2893702256 hasConcept C63479239 @default.
- W2893702256 hasConcept C86803240 @default.
- W2893702256 hasConcept C95623464 @default.
- W2893702256 hasConceptScore W2893702256C104317684 @default.
- W2893702256 hasConceptScore W2893702256C106135958 @default.
- W2893702256 hasConceptScore W2893702256C119857082 @default.
- W2893702256 hasConceptScore W2893702256C138885662 @default.
- W2893702256 hasConceptScore W2893702256C153180895 @default.
- W2893702256 hasConceptScore W2893702256C154945302 @default.
- W2893702256 hasConceptScore W2893702256C2776401178 @default.
- W2893702256 hasConceptScore W2893702256C41008148 @default.
- W2893702256 hasConceptScore W2893702256C41895202 @default.
- W2893702256 hasConceptScore W2893702256C55493867 @default.
- W2893702256 hasConceptScore W2893702256C63479239 @default.
- W2893702256 hasConceptScore W2893702256C86803240 @default.
- W2893702256 hasConceptScore W2893702256C95623464 @default.
- W2893702256 hasLocation W28937022561 @default.
- W2893702256 hasOpenAccess W2893702256 @default.
- W2893702256 hasPrimaryLocation W28937022561 @default.
- W2893702256 hasRelatedWork W1998752042 @default.
- W2893702256 hasRelatedWork W1999236014 @default.
- W2893702256 hasRelatedWork W2023161323 @default.
- W2893702256 hasRelatedWork W2026974139 @default.
- W2893702256 hasRelatedWork W2031173026 @default.
- W2893702256 hasRelatedWork W2090026354 @default.
- W2893702256 hasRelatedWork W2578983297 @default.
- W2893702256 hasRelatedWork W2592183144 @default.
- W2893702256 hasRelatedWork W2599331200 @default.
- W2893702256 hasRelatedWork W2741956870 @default.
- W2893702256 hasRelatedWork W2743529343 @default.
- W2893702256 hasRelatedWork W2757513300 @default.
- W2893702256 hasRelatedWork W2790343611 @default.
- W2893702256 hasRelatedWork W2894448360 @default.
- W2893702256 hasRelatedWork W2936772191 @default.
- W2893702256 hasRelatedWork W2985206888 @default.
- W2893702256 hasRelatedWork W2993303751 @default.
- W2893702256 hasRelatedWork W3149729257 @default.
- W2893702256 hasRelatedWork W3178115463 @default.
- W2893702256 hasRelatedWork W944409021 @default.
- W2893702256 isParatext "false" @default.
- W2893702256 isRetracted "false" @default.
- W2893702256 magId "2893702256" @default.
- W2893702256 workType "article" @default.