Matches in SemOpenAlex for { <https://semopenalex.org/work/W4379471241> ?p ?o ?g. }
- W4379471241 endingPage "3314" @default.
- W4379471241 startingPage "3293" @default.
- W4379471241 abstract "Machine learning techniques are excellent to analyze expression data from single cells. These techniques impact all fields ranging from cell annotation and clustering to signature identification. The presented framework evaluates gene selection sets how far they optimally separate defined phenotypes or cell groups. This innovation overcomes the present limitation to objectively and correctly identify a small gene set of high information content regarding separating phenotypes for which corresponding code scripts are provided. The small but meaningful subset of the original genes (or feature space) facilitates human interpretability of the differences of the phenotypes including those found by machine learning results and may even turn correlations between genes and phenotypes into a causal explanation. For the feature selection task, the principal feature analysis is utilized which reduces redundant information while selecting genes that carry the information for separating the phenotypes. In this context, the presented framework shows explainability of unsupervised learning as it reveals cell-type specific signatures. Apart from a Seurat preprocessing tool and the PFA script, the pipeline uses mutual information to balance accuracy and size of the gene set if desired. A validation part to evaluate the gene selection for their information content regarding the separation of the phenotypes is provided as well, binary and multiclass classification of 3 or 4 groups are studied. Results from different single-cell data are presented. In each, only about ten out of more than 30000 genes are identified as carrying the relevant information. The code is provided in a GitHub repository at https://github.com/AC-PHD/Seurat_PFA_pipeline." @default.
- W4379471241 created "2023-06-07" @default.
- W4379471241 creator A5003790616 @default.
- W4379471241 creator A5019736004 @default.
- W4379471241 creator A5031422615 @default.
- W4379471241 creator A5035105283 @default.
- W4379471241 creator A5042261155 @default.
- W4379471241 creator A5086202312 @default.
- W4379471241 date "2023-01-01" @default.
- W4379471241 modified "2023-10-16" @default.
- W4379471241 title "Optimized cell type signatures revealed from single-cell data by combining principal feature analysis, mutual information, and machine learning" @default.
- W4379471241 cites W1968072716 @default.
- W4379471241 cites W2012034410 @default.
- W4379471241 cites W2028681796 @default.
- W4379471241 cites W2035618305 @default.
- W4379471241 cites W2069089843 @default.
- W4379471241 cites W2088986234 @default.
- W4379471241 cites W2091759162 @default.
- W4379471241 cites W2103017472 @default.
- W4379471241 cites W2114104545 @default.
- W4379471241 cites W2130410032 @default.
- W4379471241 cites W2137207158 @default.
- W4379471241 cites W2143426320 @default.
- W4379471241 cites W2154053567 @default.
- W4379471241 cites W2167898988 @default.
- W4379471241 cites W2179438025 @default.
- W4379471241 cites W2214074259 @default.
- W4379471241 cites W2534555913 @default.
- W4379471241 cites W2560285866 @default.
- W4379471241 cites W2773459956 @default.
- W4379471241 cites W2781733423 @default.
- W4379471241 cites W2794480084 @default.
- W4379471241 cites W2817838603 @default.
- W4379471241 cites W2886347923 @default.
- W4379471241 cites W2900044275 @default.
- W4379471241 cites W2901677030 @default.
- W4379471241 cites W2949177718 @default.
- W4379471241 cites W2949237386 @default.
- W4379471241 cites W2950640959 @default.
- W4379471241 cites W2953151710 @default.
- W4379471241 cites W2953251392 @default.
- W4379471241 cites W2961217357 @default.
- W4379471241 cites W2961304458 @default.
- W4379471241 cites W2981122358 @default.
- W4379471241 cites W2988464219 @default.
- W4379471241 cites W2989747508 @default.
- W4379471241 cites W2997280954 @default.
- W4379471241 cites W2999746472 @default.
- W4379471241 cites W3014040695 @default.
- W4379471241 cites W3020212197 @default.
- W4379471241 cites W3039667012 @default.
- W4379471241 cites W3092295864 @default.
- W4379471241 cites W3092982430 @default.
- W4379471241 cites W3093964578 @default.
- W4379471241 cites W3097088191 @default.
- W4379471241 cites W3112600195 @default.
- W4379471241 cites W3114773357 @default.
- W4379471241 cites W3124814274 @default.
- W4379471241 cites W3132827988 @default.
- W4379471241 cites W3157103618 @default.
- W4379471241 cites W3164692211 @default.
- W4379471241 cites W3175752499 @default.
- W4379471241 cites W3216026604 @default.
- W4379471241 cites W4200271898 @default.
- W4379471241 cites W4200397564 @default.
- W4379471241 cites W4200510291 @default.
- W4379471241 cites W4220940711 @default.
- W4379471241 cites W4221010612 @default.
- W4379471241 cites W4229044214 @default.
- W4379471241 cites W4284989442 @default.
- W4379471241 cites W4286471297 @default.
- W4379471241 cites W4308458522 @default.
- W4379471241 doi "https://doi.org/10.1016/j.csbj.2023.06.002" @default.
- W4379471241 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37333862" @default.
- W4379471241 hasPublicationYear "2023" @default.
- W4379471241 type Work @default.
- W4379471241 citedByCount "0" @default.
- W4379471241 crossrefType "journal-article" @default.
- W4379471241 hasAuthorship W4379471241A5003790616 @default.
- W4379471241 hasAuthorship W4379471241A5019736004 @default.
- W4379471241 hasAuthorship W4379471241A5031422615 @default.
- W4379471241 hasAuthorship W4379471241A5035105283 @default.
- W4379471241 hasAuthorship W4379471241A5042261155 @default.
- W4379471241 hasAuthorship W4379471241A5086202312 @default.
- W4379471241 hasBestOaLocation W43794712411 @default.
- W4379471241 hasConcept C111919701 @default.
- W4379471241 hasConcept C119857082 @default.
- W4379471241 hasConcept C124101348 @default.
- W4379471241 hasConcept C138885662 @default.
- W4379471241 hasConcept C148483581 @default.
- W4379471241 hasConcept C151730666 @default.
- W4379471241 hasConcept C152139883 @default.
- W4379471241 hasConcept C153180895 @default.
- W4379471241 hasConcept C154945302 @default.
- W4379471241 hasConcept C177264268 @default.
- W4379471241 hasConcept C199360897 @default.
- W4379471241 hasConcept C2776401178 @default.
- W4379471241 hasConcept C2779343474 @default.