Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308961925> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W4308961925 abstract "Abstract The transcriptome is the most extensive and standardized among all biological data, but its lack of inherent structure impedes the application of deep learning tools. This study resolves the neighborhood relationship of protein-coding genes through uniform manifold approximation and projection (UMAP) of high-quality gene expression data. The resultant transcriptome image is conducive to classification tasks and generative learning. Convolutional neural networks (CNNs) trained with full or partial transcriptome images differentiate normal versus lung squamous cell carcinoma (LUSC) and LUSC versus lung adenocarcinoma (LUAD) with over 96% accuracy, comparable to XGBoost. Meanwhile, the generative adversarial network (GAN) model trained with 93 TcgaTargetGtex transcriptome classes synthesizes highly realistic and diverse tissue/cancer-specific transcriptome images. Comparative analysis of GAN-synthesized LUSC and LUAD transcriptome images show selective retention and enhancement of epithelial identity gene expression in the LUSC transcriptome. Further analyses of synthetic LUSC transcriptomes identify a novel role for mitochondria electron transport complex I expression in LUSC stratification and prognosis. In summary, this study provides an intuitive transcriptome embedding compatible with generative deep learning and realistic transcriptome synthesis. Significance Statement Deep learning is most successful when the subject is structured. This study provides a novel way of converting unstructured gene expression lists to 2D-structured transcriptome portraits that are intuitive and compatible with a generative adversarial network (GAN)-based deep learning. The StyleGAN generator trained with transcriptome portrait libraries synthesizes tissue- and disease-specific transcriptomes with significant diversity. Detailed analyses of the synthetic transcriptomes reveal selective enhancement of clinically significant features not apparent in the original transcriptome. Therefore, transcriptome-image-based generative learning may become a significant source of de novo insight generation." @default.
- W4308961925 created "2022-11-20" @default.
- W4308961925 creator A5043183307 @default.
- W4308961925 date "2022-11-14" @default.
- W4308961925 modified "2023-10-05" @default.
- W4308961925 title "Highly Realistic Whole Transcriptome Synthesis through Generative Adversarial Networks" @default.
- W4308961925 cites W1983157224 @default.
- W4308961925 cites W1984708728 @default.
- W4308961925 cites W2047765648 @default.
- W4308961925 cites W2113310577 @default.
- W4308961925 cites W2124770148 @default.
- W4308961925 cites W2787429377 @default.
- W4308961925 cites W2935703330 @default.
- W4308961925 cites W2949099455 @default.
- W4308961925 cites W2964962196 @default.
- W4308961925 cites W3045864178 @default.
- W4308961925 cites W3098100992 @default.
- W4308961925 cites W3102476541 @default.
- W4308961925 cites W3160196987 @default.
- W4308961925 cites W3177828909 @default.
- W4308961925 cites W3179857518 @default.
- W4308961925 cites W3185358186 @default.
- W4308961925 cites W4285194967 @default.
- W4308961925 cites W4301206121 @default.
- W4308961925 doi "https://doi.org/10.1101/2022.11.10.515980" @default.
- W4308961925 hasPublicationYear "2022" @default.
- W4308961925 type Work @default.
- W4308961925 citedByCount "0" @default.
- W4308961925 crossrefType "posted-content" @default.
- W4308961925 hasAuthorship W4308961925A5043183307 @default.
- W4308961925 hasBestOaLocation W43089619251 @default.
- W4308961925 hasConcept C104317684 @default.
- W4308961925 hasConcept C108583219 @default.
- W4308961925 hasConcept C150194340 @default.
- W4308961925 hasConcept C154945302 @default.
- W4308961925 hasConcept C162317418 @default.
- W4308961925 hasConcept C41008148 @default.
- W4308961925 hasConcept C54355233 @default.
- W4308961925 hasConcept C70721500 @default.
- W4308961925 hasConcept C81363708 @default.
- W4308961925 hasConcept C86803240 @default.
- W4308961925 hasConceptScore W4308961925C104317684 @default.
- W4308961925 hasConceptScore W4308961925C108583219 @default.
- W4308961925 hasConceptScore W4308961925C150194340 @default.
- W4308961925 hasConceptScore W4308961925C154945302 @default.
- W4308961925 hasConceptScore W4308961925C162317418 @default.
- W4308961925 hasConceptScore W4308961925C41008148 @default.
- W4308961925 hasConceptScore W4308961925C54355233 @default.
- W4308961925 hasConceptScore W4308961925C70721500 @default.
- W4308961925 hasConceptScore W4308961925C81363708 @default.
- W4308961925 hasConceptScore W4308961925C86803240 @default.
- W4308961925 hasLocation W43089619251 @default.
- W4308961925 hasLocation W43089619252 @default.
- W4308961925 hasOpenAccess W4308961925 @default.
- W4308961925 hasPrimaryLocation W43089619251 @default.
- W4308961925 hasRelatedWork W2731899572 @default.
- W4308961925 hasRelatedWork W2999805992 @default.
- W4308961925 hasRelatedWork W3011074480 @default.
- W4308961925 hasRelatedWork W3116150086 @default.
- W4308961925 hasRelatedWork W3133861977 @default.
- W4308961925 hasRelatedWork W3166467183 @default.
- W4308961925 hasRelatedWork W4200173597 @default.
- W4308961925 hasRelatedWork W4291897433 @default.
- W4308961925 hasRelatedWork W4312417841 @default.
- W4308961925 hasRelatedWork W4321369474 @default.
- W4308961925 isParatext "false" @default.
- W4308961925 isRetracted "false" @default.
- W4308961925 workType "article" @default.