Research map / Image generation / Autoregressive and latent generation
Spatially Resolved Gene Expression Prediction from Histology Images via Bi-modal Contrastive Learning
Ronald Xie, Kuan Pang, Sai W Chung, Catia Perciani, Sonya MacParland, BO WANG, Gary Bader
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 |
|---|---|---|---|
| use BLEEP instead of best baseline | gene expression prediction · Liver Visium marker genes | avg Pearson correlation: 0.099 -> 0.217 | Improved |
| use BLEEP instead of ST-Net | gene expression prediction · Liver Visium top 50 HEG | avg Pearson correlation: 0.126 -> 0.175 | Improved |
| use BLEEP instead of ST-Net | gene expression prediction · Liver Visium top 50 HVG | avg Pearson correlation: 0.091 -> 0.173 | Improved |
| increase K from 10 to 50 in query-reference imputation (ablation) | BLEEP · Liver Visium marker genes | avg Pearson correlation: 0.179 -> 0.217 | Improved |
| increase K from 50 to 100 (ablation) | BLEEP · Liver Visium top 50 HVG | avg Pearson correlation: 0.175 -> 0.180 | No clear effect |
| increase K from 50 to 100 (ablation) | BLEEP · Liver Visium marker genes | avg Pearson correlation: 0.217 -> 0.215 | No clear effect |
| average top-K profiles instead of using only the single best match (ablation) | BLEEP · Liver Visium marker genes | avg Pearson correlation: 0.079 -> 0.217 | Improved |
| simple average instead of similarity-weighted average of top-K profiles (ablation) | BLEEP · Liver Visium marker genes | avg Pearson correlation: 0.186 -> 0.217 | Improved |
| use smoothed contrastive objective instead of original CLIP objective (ablation) | BLEEP · Liver Visium marker genes | avg Pearson correlation: 0.209 -> 0.217 | Improved |
| use smoothed contrastive objective instead of original CLIP objective (ablation) | BLEEP · Liver Visium top 50 HVG | avg Pearson correlation: 0.165 -> 0.175 | Improved |
| use ResNet50 image encoder instead of pretrained ViT encoders (ablation) | BLEEP · Liver Visium | avg Pearson correlation | Improved |
Closest papers by meaning
- Diffusion Generative Modeling for Spatially Resolved Gene Expression Inference from Histology Images (ICLR 2025 · similarity 0.88)
- Transcriptomics-guided Slide Representation Learning in Computational Pathology (CVPR 2024 · similarity 0.87)
- STimage-1K4M: A histopathology image-gene expression dataset for spatial transcriptomics (NeurIPS 2024 · similarity 0.87)
- Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction (CVPR 2024 · similarity 0.86)
- HEST-1k: A Dataset For Spatial Transcriptomics and Histology Image Analysis (NeurIPS 2024 · similarity 0.85)
- Semantic and Visual Crop-Guided Diffusion Models for Heterogeneous Tissue Synthesis in Histopathology (NeurIPS 2025 · similarity 0.85)
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.
