Research map / Label-efficient and robust learning / Recognition and long-tail
Evidence-aware Integration and Domain Identification of Spatial Transcriptomics Data
Wei Zhang, Siyu Yi, Lezhi Chen, Yifan Wang, Ziyue Qiao, Yongdao Zhou, Wei Ju
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add diversity-semantics loss (prototype diversity + belief-semantics) (ablation) | PREST · DLPFC 151507 | ARI: 0.62 -> 0.75 | Improved |
| add uncertainty-weighted ZINB reconstruction loss (ablation) | PREST · HBC | ARI: 0.68 -> 0.72 | Improved |
| add uncertainty-weighted spatial regularization loss (ablation) | PREST · DLPFC 151507 | ARI: 0.60 -> 0.75 | Improved |
| use structure-guided cross-attention instead of cross-attention without adjacency (ablation) | PREST fusion · DLPFC 151507 | ARI: 0.54 -> 0.75 | Improved |
| use structure-guided cross-attention instead of additive fusion (ablation) | PREST fusion · MAB | ARI: 0.32 -> 0.43 | Improved |
| apply uncertainty weighting in reconstruction and regularization (ablation) | PREST · DLPFC 151507 | domain identification quality | Improved |
| add Gaussian noise (eps=5) to expression | PREST vs GraphST · MAB | ARI: PREST 0.24 vs GraphST 0.15 | Improved |
| PREST vs GraphST on slice 151673 | domain identification · DLPFC 151673 | ARI: 0.63 -> 0.59 | Hurt |
| spatially-aware methods vs non-spatial SCANPY | domain identification · DLPFC | ARI: SCANPY 0.20 vs PREST 0.75 on 151507 | Improved |
Closest papers by meaning
- Global Context-aware Representation Learning for Spatially Resolved Transcriptomics (ICML 2025 · similarity 0.88)
- SUICA: Learning Super-high Dimensional Sparse Implicit Neural Representations for Spatial Transcriptomics (ICML 2025 · similarity 0.88)
- STINR: Deciphering Spatial Transcriptomics via Implicit Neural Representation (CVPR 2025 · similarity 0.87)
- HEST-1k: A Dataset For Spatial Transcriptomics and Histology Image Analysis (NeurIPS 2024 · similarity 0.87)
- Diffusion Generative Modeling for Spatially Resolved Gene Expression Inference from Histology Images (ICLR 2025 · similarity 0.87)
- Preserving DEG Rankings for Gene Discovery in Histology-Based Spatial Gene Expression Prediction (NeurIPS 2026 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
