scEMAIL A source-free and universal cell-type annotation tool
Introduction
We propose a universal annotation framework for scRNA-seq data called scEMAIL, which automatically detects novel cell types without accessing source data during adaptation. For new cell-type identification, a novel cell-type perception module is designed with three steps. First, an expert ensemble system measures uncertainty of each cell from three complementary aspects. Second, based on this measurement, bimodality tests are applied to detect the presence of new cell types. Third, once assured of their presence, an adaptive threshold via manifold mixup is calculated to partition target cells into "known" and "unknown" groups. Model adaptation is then conducted to alleviate the batch effect. We gather multi-order neighborhood messages globally and impose local affinity regularizations on "known" cells. These constraints mitigate wrong classifications of the source model via reliable self-supervised information of neighbors.
Publications
No Publication Information
Credits
- HUI WAN wanhui1997@pku.edu.cn Investigator
School of Mathematical Sciences, Peking University, China
Community Ratings
Usability | Efficiency | Reliability | Rated By |
---|---|---|---|
0 user | |||
Sign in to rate |
Accession | BT007335 |
---|---|
Tool Type | Application |
Category | |
Platforms | Windows |
Technologies | Python3 |
User Interface | |
Latest Release | v1.0 (November 27, 2022) |
Download Count | 511 |
Country/Region | China |
Submitted By | HUI WAN |