DECODE: deep learning-based common deconvolution framework for various omics data - PubMed
6 hours ago
- #deep learning
- #omics data
- #deconvolution
- DECODE is a deep learning-based deconvolution framework for various omics data.
- It estimates cell-type abundances from tissue-level data, enabling cellular analysis of large cohorts.
- DECODE is universal and can be applied to transcriptomic, proteomic, and metabolomic data.
- It outperforms state-of-the-art methods across different omics data, donors, and disease conditions.
- DECODE is robust and can accurately deconvolve cell types even with incomplete reference single-cell data.
- The framework integrates diverse multiomics tissue datasets at the cellular level.
- DECODE fills the gap in metabolomics deconvolution.