Research map / Graph learning / Graph self-supervised learning
MuSe-GNN: Learning Unified Gene Representation From Multimodal Biological Graph Data
Tianyu Liu, Yuge Wang, Zhitao Ying, Hongyu Zhao
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 MuSe-GNN instead of the strongest listed baseline | gene representation learning · Heart | Avg Score: 0.64 -> 0.77 | Improved |
| Use MuSe-GNN instead of the strongest listed baseline | gene representation learning · Lung | Avg Score: 0.48 -> 0.96 | Improved |
| Use MuSe-GNN instead of the strongest listed baseline | gene representation learning · Liver | Avg Score: 0.58 -> 0.92 | Improved |
| Use MuSe-GNN instead of the strongest listed baseline | gene representation learning · Kidney | Avg Score: 0.62 -> 0.89 | Improved |
| Use MuSe-GNN instead of the strongest listed baseline | gene representation learning · Thymus | Avg Score: 0.58 -> 0.89 | Improved |
| Use MuSe-GNN instead of the strongest listed baseline | gene representation learning · Spleen | Avg Score: 0.58 -> 0.94 | Improved |
| Use MuSe-GNN instead of the strongest listed baseline | gene representation learning · Pancreas | Avg Score: 0.56 -> 0.80 | Improved |
| Use MuSe-GNN instead of the strongest listed baseline | gene representation learning · Cerebrum | Avg Score: 0.62 -> 0.95 | Improved |
| Use MuSe-GNN instead of the strongest listed baseline | gene representation learning · Cerebellum | Avg Score: 0.61 -> 0.90 | Improved |
| Use MuSe-GNN instead of the strongest listed baseline | gene representation learning · PBMC | Avg Score: 0.58 -> 0.92 | Improved |
| Add CosSim and InfoNCE losses (ablation) | MuSe-GNN · All tissues | Avg Score: 0.25 -> 0.96 | Improved |
| Add CosSim loss (ablation) | MuSe-GNN · All tissues | Avg Score: 0.25 -> 0.71 | Improved |
Closest papers by meaning
- Prot2Text: Multimodal Protein’s Function Generation with GNNs and Transformers (AAAI 2024 · similarity 0.86)
- Multi-modal Topology-embedded Graph Learning for Spatially Resolved Genes Prediction from Pathology Images with Prior Gene Similarity Information (CVPR 2025 · similarity 0.86)
- ProtGO: Function-Guided Protein Modeling for Unified Representation Learning (NeurIPS 2024 · similarity 0.86)
- GeSubNet: Gene Interaction Inference for Disease Subtype Network Generation (ICLR 2025 · similarity 0.85)
- OgBench: A Framework for Evaluating Graph Neural Networks on Omics Data (NeurIPS 2026 · similarity 0.85)
- MERGE: Multi-faceted Hierarchical Graph-based GNN for Gene Expression Prediction from Whole Slide Histopathology Images (CVPR 2025 · similarity 0.84)
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.
