FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2095900670> ?p ?o ?g. }

• W2095900670 abstract "Quantitative phenotypes emerge everywhere in systems biology and biomedicine due to a direct interest for quantitative traits, or to high individual variability that makes hard or impossible to classify samples into distinct categories, often the case with complex common diseases. Machine learning approaches to genotype-phenotype mapping may significantly improve Genome-Wide Association Studies (GWAS) results by explicitly focusing on predictivity and optimal feature selection in a multivariate setting. It is however essential that stringent and well documented Data Analysis Protocols (DAP) are used to control sources of variability and ensure reproducibility of results. We present a genome-to-phenotype pipeline of machine learning modules for quantitative phenotype prediction. The pipeline can be applied for the direct use of whole-genome information in functional studies. As a realistic example, the problem of fitting complex phenotypic traits in heterogeneous stock mice from single nucleotide polymorphims (SNPs) is here considered.The core element in the pipeline is the L1L2 regularization method based on the naïve elastic net. The method gives at the same time a regression model and a dimensionality reduction procedure suitable for correlated features. Model and SNP markers are selected through a DAP originally developed in the MAQC-II collaborative initiative of the U.S. FDA for the identification of clinical biomarkers from microarray data. The L1L2 approach is compared with standard Support Vector Regression (SVR) and with Recursive Jump Monte Carlo Markov Chain (MCMC). Algebraic indicators of stability of partial lists are used for model selection; the final panel of markers is obtained by a procedure at the chromosome scale, termed 'saturation', to recover SNPs in Linkage Disequilibrium with those selected.With respect to both MCMC and SVR, comparable accuracies are obtained by the L1L2 pipeline. Good agreement is also found between SNPs selected by the L1L2 algorithms and candidate loci previously identified by a standard GWAS. The combination of L1L2-based feature selection with a saturation procedure tackles the issue of neglecting highly correlated features that affects many feature selection algorithms.The L1L2 pipeline has proven effective in terms of marker selection and prediction accuracy. This study indicates that machine learning techniques may support quantitative phenotype prediction, provided that adequate DAPs are employed to control bias in model selection." @default.
• W2095900670 created "2016-06-24" @default.
• W2095900670 creator A5018526524 @default.
• W2095900670 creator A5072609433 @default.
• W2095900670 creator A5090829168 @default.
• W2095900670 date "2010-10-01" @default.
• W2095900670 modified "2023-10-09" @default.
• W2095900670 title "A machine learning pipeline for quantitative phenotype prediction from genotype data" @default.
• W2095900670 cites W1964357740 @default.
• W2095900670 cites W1979916898 @default.
• W2095900670 cites W1982220354 @default.
• W2095900670 cites W1988276885 @default.
• W2095900670 cites W1991415175 @default.
• W2095900670 cites W1999132491 @default.
• W2095900670 cites W2014347464 @default.
• W2095900670 cites W2019586039 @default.
• W2095900670 cites W2027042196 @default.
• W2095900670 cites W2042308063 @default.
• W2095900670 cites W2086702905 @default.
• W2095900670 cites W2088738061 @default.
• W2095900670 cites W2107956883 @default.
• W2095900670 cites W2122825543 @default.
• W2095900670 cites W2137118273 @default.
• W2095900670 cites W2140192325 @default.
• W2095900670 cites W2152905639 @default.
• W2095900670 cites W2162683818 @default.
• W2095900670 cites W2165374837 @default.
• W2095900670 cites W2168466769 @default.
• W2095900670 doi "https://doi.org/10.1186/1471-2105-11-s8-s3" @default.
• W2095900670 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/2966290" @default.
• W2095900670 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/21034428" @default.
• W2095900670 hasPublicationYear "2010" @default.
• W2095900670 type Work @default.
• W2095900670 sameAs 2095900670 @default.
• W2095900670 citedByCount "18" @default.
• W2095900670 countsByYear W20959006702012 @default.
• W2095900670 countsByYear W20959006702014 @default.
• W2095900670 countsByYear W20959006702015 @default.
• W2095900670 countsByYear W20959006702016 @default.
• W2095900670 countsByYear W20959006702018 @default.
• W2095900670 countsByYear W20959006702019 @default.
• W2095900670 countsByYear W20959006702020 @default.
• W2095900670 countsByYear W20959006702021 @default.
• W2095900670 countsByYear W20959006702022 @default.
• W2095900670 crossrefType "journal-article" @default.
• W2095900670 hasAuthorship W2095900670A5018526524 @default.
• W2095900670 hasAuthorship W2095900670A5072609433 @default.
• W2095900670 hasAuthorship W2095900670A5090829168 @default.
• W2095900670 hasBestOaLocation W20959006701 @default.
• W2095900670 hasConcept C107673813 @default.
• W2095900670 hasConcept C111350023 @default.
• W2095900670 hasConcept C119857082 @default.
• W2095900670 hasConcept C12267149 @default.
• W2095900670 hasConcept C124101348 @default.
• W2095900670 hasConcept C148483581 @default.
• W2095900670 hasConcept C154945302 @default.
• W2095900670 hasConcept C199360897 @default.
• W2095900670 hasConcept C41008148 @default.
• W2095900670 hasConcept C43521106 @default.
• W2095900670 hasConcept C70518039 @default.
• W2095900670 hasConcept C70721500 @default.
• W2095900670 hasConcept C86803240 @default.
• W2095900670 hasConceptScore W2095900670C107673813 @default.
• W2095900670 hasConceptScore W2095900670C111350023 @default.
• W2095900670 hasConceptScore W2095900670C119857082 @default.
• W2095900670 hasConceptScore W2095900670C12267149 @default.
• W2095900670 hasConceptScore W2095900670C124101348 @default.
• W2095900670 hasConceptScore W2095900670C148483581 @default.
• W2095900670 hasConceptScore W2095900670C154945302 @default.
• W2095900670 hasConceptScore W2095900670C199360897 @default.
• W2095900670 hasConceptScore W2095900670C41008148 @default.
• W2095900670 hasConceptScore W2095900670C43521106 @default.
• W2095900670 hasConceptScore W2095900670C70518039 @default.
• W2095900670 hasConceptScore W2095900670C70721500 @default.
• W2095900670 hasConceptScore W2095900670C86803240 @default.
• W2095900670 hasIssue "S8" @default.
• W2095900670 hasLocation W20959006701 @default.
• W2095900670 hasLocation W20959006702 @default.
• W2095900670 hasLocation W20959006703 @default.
• W2095900670 hasLocation W20959006704 @default.
• W2095900670 hasLocation W20959006705 @default.
• W2095900670 hasOpenAccess W2095900670 @default.
• W2095900670 hasPrimaryLocation W20959006701 @default.
• W2095900670 hasRelatedWork W177481468 @default.
• W2095900670 hasRelatedWork W1996541855 @default.
• W2095900670 hasRelatedWork W2735962158 @default.
• W2095900670 hasRelatedWork W3034132578 @default.
• W2095900670 hasRelatedWork W3165907317 @default.
• W2095900670 hasRelatedWork W3195168932 @default.
• W2095900670 hasRelatedWork W3200179079 @default.
• W2095900670 hasRelatedWork W4288767684 @default.
• W2095900670 hasRelatedWork W4293525103 @default.
• W2095900670 hasRelatedWork W2345184372 @default.
• W2095900670 hasVolume "11" @default.
• W2095900670 isParatext "false" @default.
• W2095900670 isRetracted "false" @default.
• W2095900670 magId "2095900670" @default.
• W2095900670 workType "article" @default.