Research map / Image generation / Autoregressive and latent generation
Flexibility-Aware Geometric Latent Diffusion for Full-Atom Peptide Design
Dongjiang Niu, Xiaofeng Wang, Zhiqiang Wei, Zhen Li
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 PepFGLD (flexibility-aware latent diffusion) instead of PepGLAD | peptide co-design · PepBench | binding energy dG: -13.46 -> -19.86 | Improved |
| use PepFGLD instead of PepGLAD | peptide co-design · PepBDB | binding energy dG: -19.57 -> -18.74 | Hurt |
| use PepFGLD instead of PepGLAD | peptide co-design · PepBench | success rate: 47.12% -> 59.35% | Improved |
| use PepFGLD instead of PepMimic on binding conformation generation | conformation generation · PepBDB | RMSD (Calpha): 8.41 -> 8.86 | Hurt |
| use PepFGLD instead of PepGLAD on binding conformation generation | conformation generation · PepBench | DockQ: 0.558 -> 0.607 | Improved |
| use PepFGLD instead of PepGLAD on high-flexibility peptides | peptide co-design · PepBench High-Flex subset | binding energy dG: -7.11 -> -14.54 | Improved |
| re-evaluate with Prime MM-GBSA instead of PyRosetta | PepFGLD vs PepGLAD · PepBench | binding energy (kcal/mol): -99.73 -> -102.48 | Improved |
| added flexibility modules increase parameters and sampling cost relative to PepGLAD | PepFGLD · PepBench, A100-40G, 40 candidates | sampling time per sample (s): 19.91 -> 26.73 seconds | Hurt |
Closest papers by meaning
- Full-Atom Peptide Design with Geometric Latent Diffusion (NeurIPS 2024 · similarity 0.93)
- Full-Atom Peptide Design based on Multi-modal Flow Matching (ICML 2024 · similarity 0.88)
- Generative Modeling of Full-Atom Protein Conformations using Latent Diffusion on Graph Embeddings (NeurIPS 2025 · similarity 0.88)
- 4D Diffusion for Dynamic Protein Structure Prediction with Reference and Motion Guidance (AAAI 2025 · similarity 0.87)
- Unlocking hidden biomolecular conformational landscapes in diffusion models at inference time (NeurIPS 2025 · similarity 0.86)
- Swallowing the Bitter Pill: Simplified Scalable Conformer Generation (ICML 2024 · similarity 0.86)
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.
