FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384695598> ?p ?o ?g. }

• W4384695598 abstract "ABSTRACT Machine Learning models have been frequently used in transcriptome analyses. Particularly, Representation Learning (RL), e.g., autoencoders, are effective in learning critical representations in noisy data. However, learned representations, e.g., the “latent variables” in an autoencoder, are difficult to interpret, not to mention prioritizing essential genes for functional follow-up. In contrast, in traditional analyses, one may identify important genes such as Differentially Expressed (DiffEx), Differentially Co-Expressed (DiffCoEx), and Hub genes. Intuitively, the complex gene-gene interactions may be beyond the capture of marginal effects (DiffEx) or correlations (DiffCoEx and Hub), indicating the need of powerful RL models. However, the lack of interpretability and individual target genes is an obstacle for RL’s broad use in practice. To facilitate interpretable analysis and gene-identification using RL, we propose “Critical genes”, defined as genes that contribute highly to learned representations (e.g., latent variables in an autoencoder). As a proof-of-concept, supported by eXplainable Artificial Intelligence (XAI), we implemented eXplainable Autoencoder for Critical genes (XA4C) that quantifies each gene’s contribution to latent variables, based on which Critical genes are prioritized. Applying XA4C to gene expression data in six cancers showed that Critical genes capture essential pathways underlying cancers. Remarkably, Critical genes has little overlap with Hub or DiffEx genes, however, has a higher enrichment in a comprehensive disease gene database (DisGeNET), evidencing its potential to disclose massive unknown biology . As an example, we discovered five Critical genes sitting in the center of Lysine degradation (hsa00310) pathway, displaying distinct interaction patterns in tumor and normal tissues. In conclusion, XA4C facilitates explainable analysis using RL and Critical genes discovered by explainable RL empowers the study of complex interactions. Author Summary We propose a gene expression data analysis tool, XA4C, which builds an eXplainable Autoencoder to reveal Critical genes. XA4C disentangles the black box of the neural network of an autoencoder by providing each gene’s contribution to the latent variables in the autoencoder. Next, a gene’s ability to contribute to the latent variables is used to define the importance of this gene, based on which XA4C prioritizes “Critical genes”. Notably, we discovered that Critical genes enjoy two properties: (1) Their overlap with traditional differentially expressed genes and hub genes are poor, suggesting that they indeed brought novel insights into transcriptome data that cannot be captured by traditional analysis. (2) The enrichment of Critical genes in a comprehensive disease gene database (DisGeNET) is higher than differentially expressed or hub genes, evidencing their strong relevance to disease pathology. Therefore, we conclude that XA4C can reveal an additional landscape of gene expression data." @default.
• W4384695598 created "2023-07-20" @default.
• W4384695598 creator A5011968094 @default.
• W4384695598 creator A5012401410 @default.
• W4384695598 creator A5027271308 @default.
• W4384695598 creator A5033305169 @default.
• W4384695598 creator A5062572974 @default.
• W4384695598 creator A5092493981 @default.
• W4384695598 date "2023-07-17" @default.
• W4384695598 modified "2023-09-25" @default.
• W4384695598 title "XA4C: eXplainable representation learning via Autoencoders revealing Critical genes" @default.
• W4384695598 cites W1537947034 @default.
• W4384695598 cites W1923068721 @default.
• W4384695598 cites W1966327575 @default.
• W4384695598 cites W1986911601 @default.
• W4384695598 cites W2034543587 @default.
• W4384695598 cites W2064769568 @default.
• W4384695598 cites W2095898243 @default.
• W4384695598 cites W2109521384 @default.
• W4384695598 cites W2119034410 @default.
• W4384695598 cites W2126652700 @default.
• W4384695598 cites W2128728535 @default.
• W4384695598 cites W2144086069 @default.
• W4384695598 cites W2158485828 @default.
• W4384695598 cites W2166574880 @default.
• W4384695598 cites W2179438025 @default.
• W4384695598 cites W2487898712 @default.
• W4384695598 cites W2561960501 @default.
• W4384695598 cites W2791235391 @default.
• W4384695598 cites W2809388839 @default.
• W4384695598 cites W2891597765 @default.
• W4384695598 cites W2945183595 @default.
• W4384695598 cites W2946173685 @default.
• W4384695598 cites W2951381561 @default.
• W4384695598 cites W2995523160 @default.
• W4384695598 cites W3006265958 @default.
• W4384695598 cites W3016178978 @default.
• W4384695598 cites W3081106993 @default.
• W4384695598 cites W3092136373 @default.
• W4384695598 cites W3097649106 @default.
• W4384695598 cites W3130814454 @default.
• W4384695598 cites W3195201018 @default.
• W4384695598 cites W3196807348 @default.
• W4384695598 cites W3200632075 @default.
• W4384695598 doi "https://doi.org/10.1101/2023.07.16.549209" @default.
• W4384695598 hasPublicationYear "2023" @default.
• W4384695598 type Work @default.
• W4384695598 citedByCount "0" @default.
• W4384695598 crossrefType "posted-content" @default.
• W4384695598 hasAuthorship W4384695598A5011968094 @default.
• W4384695598 hasAuthorship W4384695598A5012401410 @default.
• W4384695598 hasAuthorship W4384695598A5027271308 @default.
• W4384695598 hasAuthorship W4384695598A5033305169 @default.
• W4384695598 hasAuthorship W4384695598A5062572974 @default.
• W4384695598 hasAuthorship W4384695598A5092493981 @default.
• W4384695598 hasBestOaLocation W43846955981 @default.
• W4384695598 hasConcept C101738243 @default.
• W4384695598 hasConcept C104317684 @default.
• W4384695598 hasConcept C108583219 @default.
• W4384695598 hasConcept C116834253 @default.
• W4384695598 hasConcept C119857082 @default.
• W4384695598 hasConcept C145741570 @default.
• W4384695598 hasConcept C150194340 @default.
• W4384695598 hasConcept C154945302 @default.
• W4384695598 hasConcept C162317418 @default.
• W4384695598 hasConcept C17744445 @default.
• W4384695598 hasConcept C199539241 @default.
• W4384695598 hasConcept C2776359362 @default.
• W4384695598 hasConcept C2781067378 @default.
• W4384695598 hasConcept C41008148 @default.
• W4384695598 hasConcept C54355233 @default.
• W4384695598 hasConcept C59822182 @default.
• W4384695598 hasConcept C67339327 @default.
• W4384695598 hasConcept C70721500 @default.
• W4384695598 hasConcept C86803240 @default.
• W4384695598 hasConcept C94625758 @default.
• W4384695598 hasConceptScore W4384695598C101738243 @default.
• W4384695598 hasConceptScore W4384695598C104317684 @default.
• W4384695598 hasConceptScore W4384695598C108583219 @default.
• W4384695598 hasConceptScore W4384695598C116834253 @default.
• W4384695598 hasConceptScore W4384695598C119857082 @default.
• W4384695598 hasConceptScore W4384695598C145741570 @default.
• W4384695598 hasConceptScore W4384695598C150194340 @default.
• W4384695598 hasConceptScore W4384695598C154945302 @default.
• W4384695598 hasConceptScore W4384695598C162317418 @default.
• W4384695598 hasConceptScore W4384695598C17744445 @default.
• W4384695598 hasConceptScore W4384695598C199539241 @default.
• W4384695598 hasConceptScore W4384695598C2776359362 @default.
• W4384695598 hasConceptScore W4384695598C2781067378 @default.
• W4384695598 hasConceptScore W4384695598C41008148 @default.
• W4384695598 hasConceptScore W4384695598C54355233 @default.
• W4384695598 hasConceptScore W4384695598C59822182 @default.
• W4384695598 hasConceptScore W4384695598C67339327 @default.
• W4384695598 hasConceptScore W4384695598C70721500 @default.
• W4384695598 hasConceptScore W4384695598C86803240 @default.
• W4384695598 hasConceptScore W4384695598C94625758 @default.
• W4384695598 hasLocation W43846955981 @default.
• W4384695598 hasOpenAccess W4384695598 @default.
• W4384695598 hasPrimaryLocation W43846955981 @default.
• W4384695598 hasRelatedWork W2669956259 @default.

• next