Research map / Probabilistic and scientific modeling / Molecules and proteins
SurProGenes: Survival Risk-Ordered Representation of Cancer Patients and Genes for the Identification of Prognostic Genes
Junetae Kim, Kyoungsuk Park, Hanseok Jeong, Youngwook KIM, Jeongseon Kim, Sun-Young Kim
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 ACAM (arccosine angle adjustment) to the RCFR model (ablation) | RCFR · TCGA four tumor types, Neg genes | SigRGene mean: 67.50% -> 80.90% (ϑ=3.0) | Mixed |
| Remove similarity-based embedding (SEM) from RCFR AC (ablation) | RCFR AC†3 · TCGA four tumor types, Neg genes | SigRGene mean: 80.90% -> 4.79% | Hurt |
| Remove centroid mechanism (GCM) from RCFR AC (ablation) | RCFR AC†3 · TCGA four tumor types, Neg genes | SigRGene mean: 80.90% -> 59.15% | Hurt |
| Remove gene-oriented risk ordering (GROM) from RCFR (ablation) | RCFR · TCGA four tumor types | SigSurv: 0.146 -> 0.995 | Hurt |
| Add ACAM with ϑ=3.0 across patient dichotomization (RCFR AC†3 vs CFR base) (ablation) | CFR · TCGA four tumor types | SigSurv: 0.590 -> 0.020 | Improved |
| Use centroid-proximal gene selection vs random genes (RCFR AC†3 vs RCFR ACNoCL) across Kn 100-900 (ablation) | RCFR AC†3 · TCGA four tumor types, Kn 100-900 | SigRGene min and mean | Improved |
| Vary ACAM hyperparameter ϑ (1.0, 2.0, 3.0) (ablation) | RCFR AC · TCGA four tumor types | SigSurv and SigRGene: SigSurv 0.033 / 0.014 / 0.020 for ϑ=1/2/3 | Mixed |
Closest papers by meaning
- Multimodal Prototyping for cancer survival prediction (ICML 2024 · similarity 0.83)
- Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction (CVPR 2024 · similarity 0.83)
- WISER: Weak Supervision and Supervised Representation Learning to Improve Drug Response Prediction in Cancer (ICML 2024 · similarity 0.83)
- CA-MLIF: Cross-Attention and Multimodal Low-Rank Interaction Fusion Framework for Tumor Prognostic Prediction (AAAI 2025 · similarity 0.83)
- Robust Multimodal Survival Prediction with Conditional Latent Differentiation Variational AutoEncoder (CVPR 2025 · similarity 0.82)
- GeSubNet: Gene Interaction Inference for Disease Subtype Network Generation (ICLR 2025 · similarity 0.82)
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.
