.png){kind=icon}
返回
scmFormer Integrates Large-Scale Single-Cell Proteomics and Transcriptomics Data by Multi-Task Transformer
.png){kind=icon}
OA
AI
DOI：10.1002/advs.202307835.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Transformer-based models have revolutionized single cell RNA-seq (scRNA-seq) data analysis. However, their applicability is challenged by the complexity and scale of single-cell multi-omics data. Here a novel single-cell multi-modal/multi-task transformer (scmFormer) is proposed to fill up the existing blank of integrating single-cell proteomics with other omics data. Through systematic benchmarking, it is demonstrated that scmFormer excels in integrating large-scale single-cell multimodal data and heterogeneous multi-batch paired multi-omics data, while preserving shared information across batchs and distinct biological information. scmFormer achieves 54.5% higher average F1 score compared to the second method in transferring cell-type labels from single-cell transcriptomics to proteomics data. Using COVID-19 datasets, it is presented that scmFormer successfully integrates over 1.48 million cells on a personal computer. Moreover, it is also proved that scmFormer performs better than existing methods on generating the unmeasured modality and is well-suited for spatial multi-omic data. Thus, scmFormer is a powerful and comprehensive tool for analyzing single-cell multi-omics data. scmFormer, a Transformer-based model, employs multi-task learning for single-cell multi-omics integration and unmeasured data generation. It excels in preserving shared information across diverse datasets, achieving a 54.5% higher average F1 score in cell-type label transfer. Impressively scalable, scmFormer seamlessly integrates millions of cells on personal computers, outperforming existing methods in generating unmeasured modalities and excelling in spatial multi-omic data analysis. image
Keyword:
multi-task leaning
single-cell data generation
single-cell data integration
single-cell multi-omics
single-cell protein
spatial multi-omics
transformer
期刊
IF:
14.1
论文数:
1.8W
被引数:
11.5W
机构
引用论文
High-throughput sequencing of the transcriptome and chromatin accessibility in the same cell.png)
NATURE BIOTECHNOLOGY
OAAI
NATURE BIOTECHNOLOGYIF41.7
OAAI分享收藏Clot lysis time in platelet-rich plasma: Method assessment, comparison with assays in platelet-free and platelet-poor plasmas, and response to tranexamic acidPlatelets
PlateletsIF0
PREAI
分享收藏High-resolution alignment of single-cell and spatial transcriptomes with CytoSPACE单细胞和空间转录组与CytoSPACE的高分辨率比对NATURE BIOTECHNOLOGYOAAI
NATURE BIOTECHNOLOGYIF41.7
OAAI分享收藏Histopathology images predict multi-omics aberrations and prognoses in colorectal cancer patients组织病理学图像预测结直肠癌患者的多组学像差和预后NATURE COMMUNICATIONSOAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏Binding of a 4-Methyl-4-Aza-Steroid to 5α-Reductase of Rat Liver and Prostate Microsomes4-甲基-4-氮杂-类固醇与大鼠肝脏和前列腺微粒体的5 α-还原酶的结合
PREAI
分享收藏
查看更多内容