Research map / Probabilistic and scientific modeling / Molecules and proteins
Coarse-Grained Boltzmann Generators
Weilong Chen, Bojun Zhao, Jan Eckwert, Julija Zavadlav
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 |
|---|---|---|---|
| reweight flow proposals with the learned PMF (ablation) | CG-BG · alanine di/tri/hexapeptide, Muller-Brown | free energy profile agreement | Improved |
| learn PMF from explicit solvent data instead of using implicit solvent model | CG-BG reweighting target · alanine dipeptide | JS divergence: 0.0157 -> 0.0048 (vs OBC1) | Improved |
| learn PMF from explicit solvent data instead of implicit solvent | CG-BG · alanine hexapeptide | PMF error: 1.8401 -> 0.3646 | Improved |
| train flow on 10 ns biased WT-MetaD data instead of long unbiased data (ablation) | CG-BG flow, alanine dipeptide Heavy Atom · alanine dipeptide | JS divergence: 0.0048 -> 0.0063 | Hurt |
| use coarser Core Beta mapping instead of Heavy Atom (ablation) | CG-BG · alanine dipeptide | normalized ESS: 0.5112 -> 0.5528 | Improved |
| use coarser Core Beta mapping instead of Heavy Atom (ablation) | CG-BG · alanine dipeptide | PMF error: 0.2005 -> 0.2210 | Hurt |
| use coarser Core Beta mapping instead of Heavy Atom (ablation) | CG-BG · alanine tripeptide | normalized ESS: 0.3201 -> 0.4212 | Improved |
| use Core Beta mapping instead of all-atom solute generation (ablation) | CG-BG · alanine dipeptide | total time (h): 2.80h -> 0.47h | Improved |
| train PMF on long unbiased MD data instead of ESFM biased data (ablation) | CG-BG PMF · alanine dipeptide | phi free-energy metastable populations | Hurt |
Closest papers by meaning
- Scalable Equilibrium Sampling with Sequential Boltzmann Generators (ICML 2025 · similarity 0.91)
- Transferable Boltzmann Generators (NeurIPS 2024 · similarity 0.90)
- Conditional Normalizing Flows for Active Learning of Coarse-Grained Molecular Representations (ICML 2024 · similarity 0.90)
- Temperature-Annealed Boltzmann Generators (ICML 2025 · similarity 0.90)
- BoltzNCE: Learning likelihoods for Boltzmann Generation with Stochastic Interpolants and Noise Contrastive Estimation (NeurIPS 2025 · similarity 0.89)
- Path Gradients after Flow Matching (NeurIPS 2025 · similarity 0.87)
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.
