Research map / Probabilistic and scientific modeling / Molecules and proteins
InfoGlobe: Local-and-Global Information-Preserving Statistical Manifold Learning for Single-Cell Transcriptomics
Cheng Wang, Jinpu Cai, Chongxiao Mao, Yuxuan Wang, Xinzhu Jiang, Yunhao Qiao, Luqi Yang, Luting Zhou, Qiuyu Lian, Hongyi Xin
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 InfoGlobe Fisher-Rao embedding instead of best baseline | scPHERE · Simulated nested-Multinomial scRNA-seq | Spearman correlation: 0.69 -> 0.88 | Improved |
| use InfoGlobe instead of FlatVI | FlatVI · Simulated nested-Multinomial scRNA-seq | Trustworthiness: 0.75 -> 0.83 | Improved |
| use InfoGlobe instead of FlatVI | FlatVI · Simulated nested-Multinomial scRNA-seq | Continuity: 0.71 -> 0.84 | Improved |
| cluster on InfoGlobe embedding instead of FlatVI embedding | FlatVI · Simulated scRNA-seq, Leiden clustering | ARI: 0.58 -> 0.70 | Improved |
| cluster on InfoGlobe embedding instead of IRVAE embedding | IRVAE · Simulated scRNA-seq, Leiden clustering | V-measure: 0.69 -> 0.69 | No clear effect |
| cluster on InfoGlobe embedding instead of scVI embedding | scVI · Simulated scRNA-seq, Leiden clustering | FMI: 0.80 -> 0.84 | Improved |
| feed InfoGlobe embeddings instead of PCA into SpaGCN | SpaGCN · Breast cancer Visium spatial domain segmentation | ARI: 0.48 -> 0.56 | Improved |
| feed InfoGlobe embeddings instead of PCA into SpaGCN | SpaGCN · Breast cancer Visium spatial domain segmentation | NMI: 0.58 -> 0.62 | Improved |
| use InfoGlobe instead of NMF and GBCD for factorization | NMF/GBCD · Simulated qualitative/quantitative factors | factor recovery | Improved |
| use InfoGlobe instead of NMF and GBCD under removal of two cell types | NMF/GBCD · Simulated stability test | factor stability | Improved |
| use InfoGlobe instead of PCA as PHATE input | PCA+PHATE · T-cell-depleted bone marrow | trajectory quality (qualitative) | Improved |
Closest papers by meaning
- Recovering Manifold Structure Using Ollivier Ricci Curvature (ICLR 2025 · similarity 0.86)
- Enforcing Latent Euclidean Geometry in Single-Cell VAEs for Manifold Interpolation (ICML 2025 · similarity 0.86)
- Approximating mutual information of high-dimensional variables using learned representations (NeurIPS 2024 · similarity 0.85)
- $\texttt{RNAGenScape}$: property-guided, optimized generation of mRNA sequences with manifold Langevin dynamics (NeurIPS 2026 · similarity 0.84)
- Unsupervised Gene-Cell Collective Representation Learning with Optimal Transport (AAAI 2024 · similarity 0.84)
- Preserving DEG Rankings for Gene Discovery in Histology-Based Spatial Gene Expression Prediction (NeurIPS 2026 · 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.
