Batch Integration
Cross-source consensus on Batch Integration from 1 sources and 6 claims.
1 sources · 6 claims
How it works
Benefits
Comparisons
Highlighted claims
- On the Stuart dataset, scpFormer achieved AvgBIO 0.795, higher than ComBat and Harmony. — scpFormer: A Foundation Model for Unified Representation and Integration of the Single-Cell Proteomics
- On the Zheng dataset, scpFormer achieved the best reported overall balance with AvgBIO 0.724 and AvgBATCH 0.911. — scpFormer: A Foundation Model for Unified Representation and Integration of the Single-Cell Proteomics
- scpFormer adds adversarial domain adaptation and an Elastic Cell Similarity contrastive loss for integration-specific training. — scpFormer: A Foundation Model for Unified Representation and Integration of the Single-Cell Proteomics
- For clustering and batch integration, scpFormer extracts the CLS representation with bidirectional attention over shared proteins. — scpFormer: A Foundation Model for Unified Representation and Integration of the Single-Cell Proteomics
- The article says Harmony overcorrected biological structure on the Zheng dataset. — scpFormer: A Foundation Model for Unified Representation and Integration of the Single-Cell Proteomics
- The integration results are interpreted as preserving immunophenotypic boundaries while handling nonlinear batch structure. — scpFormer: A Foundation Model for Unified Representation and Integration of the Single-Cell Proteomics