FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4297243391> ?p ?o ?g. }

• W4297243391 endingPage "866" @default.
• W4297243391 startingPage "852" @default.
• W4297243391 abstract "Annotating cell types on the basis of single-cell RNA-seq data is a prerequisite for research on disease progress and tumour microenvironments. Here we show that existing annotation methods typically suffer from a lack of curated marker gene lists, improper handling of batch effects and difficulty in leveraging the latent gene–gene interaction information, impairing their generalization and robustness. We developed a pretrained deep neural network-based model, single-cell bidirectional encoder representations from transformers (scBERT), to overcome the challenges. Following BERT’s approach to pretraining and fine-tuning, scBERT attains a general understanding of gene–gene interactions by being pretrained on huge amounts of unlabelled scRNA-seq data; it is then transferred to the cell type annotation task of unseen and user-specific scRNA-seq data for supervised fine-tuning. Extensive and rigorous benchmark studies validated the superior performance of scBERT on cell type annotation, novel cell type discovery, robustness to batch effects and model interpretability. Cell type annotation is a core task for single cell RNA-sequencing, but current bioinformatic tools struggle with some of the underlying challenges, including high dimensionality, data sparsity, batch effects and a lack of labels. In a self-supervised approach, a transformer model called scBERT is pretrained on millions of unlabelled public single cell RNA-seq data and then fine-tuned with a small number of labelled samples for cell annotation tasks." @default.
• W4297243391 created "2022-09-28" @default.
• W4297243391 creator A5002661071 @default.
• W4297243391 creator A5025671045 @default.
• W4297243391 creator A5046695536 @default.
• W4297243391 creator A5052842216 @default.
• W4297243391 creator A5060712149 @default.
• W4297243391 creator A5068865316 @default.
• W4297243391 creator A5074094490 @default.
• W4297243391 creator A5089823903 @default.
• W4297243391 date "2022-09-26" @default.
• W4297243391 modified "2023-10-18" @default.
• W4297243391 title "scBERT as a large-scale pretrained deep language model for cell type annotation of single-cell RNA-seq data" @default.
• W4297243391 cites W1967327758 @default.
• W4297243391 cites W1980867644 @default.
• W4297243391 cites W2114055879 @default.
• W4297243391 cites W2137460766 @default.
• W4297243391 cites W2523369352 @default.
• W4297243391 cites W2523419694 @default.
• W4297243391 cites W2523620612 @default.
• W4297243391 cites W2526262591 @default.
• W4297243391 cites W2763420753 @default.
• W4297243391 cites W2794521141 @default.
• W4297243391 cites W2796170779 @default.
• W4297243391 cites W2801443765 @default.
• W4297243391 cites W2894662039 @default.
• W4297243391 cites W2894687190 @default.
• W4297243391 cites W2895456557 @default.
• W4297243391 cites W2896518632 @default.
• W4297243391 cites W2899224111 @default.
• W4297243391 cites W2899728356 @default.
• W4297243391 cites W2907514116 @default.
• W4297243391 cites W2916020270 @default.
• W4297243391 cites W2931036699 @default.
• W4297243391 cites W2951506174 @default.
• W4297243391 cites W2951737297 @default.
• W4297243391 cites W2952631022 @default.
• W4297243391 cites W2959295202 @default.
• W4297243391 cites W2964643116 @default.
• W4297243391 cites W2968352143 @default.
• W4297243391 cites W2971398276 @default.
• W4297243391 cites W2971653850 @default.
• W4297243391 cites W2984629040 @default.
• W4297243391 cites W2995410603 @default.
• W4297243391 cites W2998840182 @default.
• W4297243391 cites W3002417351 @default.
• W4297243391 cites W3009609875 @default.
• W4297243391 cites W3021135130 @default.
• W4297243391 cites W3024842005 @default.
• W4297243391 cites W3025989739 @default.
• W4297243391 cites W3035231859 @default.
• W4297243391 cites W3041129226 @default.
• W4297243391 cites W3044352330 @default.
• W4297243391 cites W3088401235 @default.
• W4297243391 cites W3105982350 @default.
• W4297243391 cites W3112976705 @default.
• W4297243391 cites W3117771127 @default.
• W4297243391 cites W3119774682 @default.
• W4297243391 cites W3124814274 @default.
• W4297243391 cites W3130453114 @default.
• W4297243391 cites W3132715010 @default.
• W4297243391 cites W3157103618 @default.
• W4297243391 cites W3164692211 @default.
• W4297243391 cites W4210984920 @default.
• W4297243391 cites W4241350782 @default.
• W4297243391 cites W4283726509 @default.
• W4297243391 doi "https://doi.org/10.1038/s42256-022-00534-z" @default.
• W4297243391 hasPublicationYear "2022" @default.
• W4297243391 type Work @default.
• W4297243391 citedByCount "35" @default.
• W4297243391 countsByYear W42972433912022 @default.
• W4297243391 countsByYear W42972433912023 @default.
• W4297243391 crossrefType "journal-article" @default.
• W4297243391 hasAuthorship W4297243391A5002661071 @default.
• W4297243391 hasAuthorship W4297243391A5025671045 @default.
• W4297243391 hasAuthorship W4297243391A5046695536 @default.
• W4297243391 hasAuthorship W4297243391A5052842216 @default.
• W4297243391 hasAuthorship W4297243391A5060712149 @default.
• W4297243391 hasAuthorship W4297243391A5068865316 @default.
• W4297243391 hasAuthorship W4297243391A5074094490 @default.
• W4297243391 hasAuthorship W4297243391A5089823903 @default.
• W4297243391 hasBestOaLocation W42972433911 @default.
• W4297243391 hasConcept C104317684 @default.
• W4297243391 hasConcept C108583219 @default.
• W4297243391 hasConcept C111919701 @default.
• W4297243391 hasConcept C118505674 @default.
• W4297243391 hasConcept C119857082 @default.
• W4297243391 hasConcept C138958017 @default.
• W4297243391 hasConcept C154945302 @default.
• W4297243391 hasConcept C199360897 @default.
• W4297243391 hasConcept C22019652 @default.
• W4297243391 hasConcept C2776321320 @default.
• W4297243391 hasConcept C2781067378 @default.
• W4297243391 hasConcept C41008148 @default.
• W4297243391 hasConcept C50644808 @default.
• W4297243391 hasConcept C54355233 @default.
• W4297243391 hasConcept C63479239 @default.
• W4297243391 hasConcept C70721500 @default.

• next