Recent advances in single-cell chromatin accessibility sequencing(scCAS)technologies have resulted in new insights into the characterization of epigenomic heterogeneity and have increased the need for automatic cell t...Recent advances in single-cell chromatin accessibility sequencing(scCAS)technologies have resulted in new insights into the characterization of epigenomic heterogeneity and have increased the need for automatic cell type annotation.However,existing automatic annotation methods for scCAS data fail to incorporate the reference data and neglect novel cell types,which only exist in a test set.Here,we propose RAINBOW,a reference-guided automatic annotation method based on the contrastive learning framework,which is capable of effectively identifying novel cell types in a test set.By utilizing contrastive learning and incorporating reference data,RAINBOW can effectively characterize the heterogeneity of cell types,thereby facilitating more accurate annotation.With extensive experiments on multiple scCAS datasets,we show the advantages of RAINBOW over state-of-the-art methods in known and novel cell type annotation.We also verify the effectiveness of incorporating reference data during the training process.In addition,we demonstrate the robustness of RAINBOW to data sparsity and number of cell types.Furthermore,RAINBOW provides superior performance in newly sequenced data and can reveal biological implication in downstream analyses.All the results demonstrate the superior performance of RAINBOW in cell type annotation for scCAS data.We anticipate that RAINBOW will offer essential guidance and great assistance in scCAS data analysis.The source codes are available at the GitHub website(BioX-NKU/RAINBOW).展开更多
Single-cell RNA sequencing(scRNA-seq)is revolutionizing the study of complex and dynamic cellular mechanisms.However,cell type annotation remains a main challenge as it largely relies on a priori knowledge and manual ...Single-cell RNA sequencing(scRNA-seq)is revolutionizing the study of complex and dynamic cellular mechanisms.However,cell type annotation remains a main challenge as it largely relies on a priori knowledge and manual curation,which is cumbersome and subjective.The increasing number of scRNA-seq datasets,as well as numerous published genetic studies,has motivated us to build a comprehensive human cell type reference atlas.Here,we present decoding Cell type Specificity(deCS),an automatic cell type annotation method augmented by a comprehensive collection of human cell type expression profiles and marker genes.We used deCS to annotate scRNAseq data from various tissue types and systematically evaluated the annotation accuracy under different conditions,including reference panels,sequencing depth,and feature selection strategies.Our results demonstrate that expanding the references is critical for improving annotation accuracy.Compared to many existing state-of-the-art annotation tools,deCS significantly reduced computation time and increased accuracy.deCS can be integrated into the standard scRNA-seq analytical pipeline to enhance cell type annotation.Finally,we demonstrated the broad utility of deCS to identify trait-cell type associations in 51 human complex traits,providing deep insights into the cellular mechanisms underlying disease pathogenesis.展开更多
基金National Natural Science Foundation of China,Grant/Award Number:62203236Fundamental Research Funds for the Central Universities,Nankai University,Grant/Award Number:63231137。
文摘Recent advances in single-cell chromatin accessibility sequencing(scCAS)technologies have resulted in new insights into the characterization of epigenomic heterogeneity and have increased the need for automatic cell type annotation.However,existing automatic annotation methods for scCAS data fail to incorporate the reference data and neglect novel cell types,which only exist in a test set.Here,we propose RAINBOW,a reference-guided automatic annotation method based on the contrastive learning framework,which is capable of effectively identifying novel cell types in a test set.By utilizing contrastive learning and incorporating reference data,RAINBOW can effectively characterize the heterogeneity of cell types,thereby facilitating more accurate annotation.With extensive experiments on multiple scCAS datasets,we show the advantages of RAINBOW over state-of-the-art methods in known and novel cell type annotation.We also verify the effectiveness of incorporating reference data during the training process.In addition,we demonstrate the robustness of RAINBOW to data sparsity and number of cell types.Furthermore,RAINBOW provides superior performance in newly sequenced data and can reveal biological implication in downstream analyses.All the results demonstrate the superior performance of RAINBOW in cell type annotation for scCAS data.We anticipate that RAINBOW will offer essential guidance and great assistance in scCAS data analysis.The source codes are available at the GitHub website(BioX-NKU/RAINBOW).
基金supported by National Institutes of Health grants(Grant Nos.R01LM012806R,I01DE030122,and R01DE029818)support from Cancer Prevention and Research Institute of Texas(Grant Nos.CPRIT RP180734 and RP210045),United States.
文摘Single-cell RNA sequencing(scRNA-seq)is revolutionizing the study of complex and dynamic cellular mechanisms.However,cell type annotation remains a main challenge as it largely relies on a priori knowledge and manual curation,which is cumbersome and subjective.The increasing number of scRNA-seq datasets,as well as numerous published genetic studies,has motivated us to build a comprehensive human cell type reference atlas.Here,we present decoding Cell type Specificity(deCS),an automatic cell type annotation method augmented by a comprehensive collection of human cell type expression profiles and marker genes.We used deCS to annotate scRNAseq data from various tissue types and systematically evaluated the annotation accuracy under different conditions,including reference panels,sequencing depth,and feature selection strategies.Our results demonstrate that expanding the references is critical for improving annotation accuracy.Compared to many existing state-of-the-art annotation tools,deCS significantly reduced computation time and increased accuracy.deCS can be integrated into the standard scRNA-seq analytical pipeline to enhance cell type annotation.Finally,we demonstrated the broad utility of deCS to identify trait-cell type associations in 51 human complex traits,providing deep insights into the cellular mechanisms underlying disease pathogenesis.
