ScDiVa: Masked Discrete Diffusion for Joint Modeling of Single-Cell Identity and Expression
ScDiVa:用于单细胞身份和表达联合建模的掩码离散扩散
机构 * Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China(中国人民大学人工智能学院) ; School of Statistics, Renmin University of China, Beijing, China(中国人民大学统计学院) ; CRE Life Institute, China(中国CRE生命科学研究院) ; School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China(华中科技大学计算机科学与技术学院) ; School of Mathematics, Jilin University, Changchun, China(吉林大学数学学院) ; Beijing Academy of Artificial Intelligence,Beijing,China(北京人工智能研究院)
AI总结 ScDiVa通过掩码离散扩散模型,联合建模单细胞身份与表达,实现高效去噪与高精度恢复。
Comments 19 pages, 11 figures