Deep cross-omics cycle attention model for joint analysis of single-cell multi-omics data

We proposed DCCA for accurately dissecting the cellular heterogeneity on joint-profiling multi-omics data from the same individual cell by transferring representation between each other.本研究提出了深度典型相关分析（Deep Canonical Correlation Analysis，简称DCCA），可通过同一单细胞多组学联合分析数据间的相互表征迁移，实现对其中细胞异质性的精准解析。