Research map / Probabilistic and scientific modeling / Molecules and proteins
FlexiFlow: decomposable flow matching for generation of flexible molecular ensemble
Riccardo Tedoldi, Ola Engkvist, Patrick Bryant, Hossein Azizpour, Jon Paul Janet, Alessandro Tibo
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 |
|---|---|---|---|
| increase model size from S to L (10 epochs, 100 NFE) (ablation) | FlexiFlow · QM9 | strain x: 5.63 -> 2.12 | Improved |
| increase model size from S to L (10 epochs, 100 NFE) (ablation) | FlexiFlow · QM9 | strain y: 1.43 -> 0.88 | Improved |
| increase training epochs from 10 to 40 (L, 100 NFE) (ablation) | FlexiFlow · QM9 | strain x: 2.12 -> 0.51 | Improved |
| increase training epochs from 10 to 40 (L, 100 NFE) (ablation) | FlexiFlow · QM9 | strain y: 0.88 -> 0.24 | Improved |
| increase NFE from 100 to 500 (S, 10 epochs) (ablation) | FlexiFlow · QM9 | strain x: 5.63 -> 5.11 | No clear effect |
| increase NFE from 100 to 500 (S, 10 epochs) (ablation) | FlexiFlow · QM9 | strain y: 1.43 -> 1.53 | No clear effect |
| increase NFE from 50 to 500 (S, 10 epochs) (ablation) | FlexiFlow · QM9 | validity: 96.9 -> 94.9 | Hurt |
| train protein-conditioned model with GEOM Drugs flexibility data (ablation) | FlexiFlow · PDBBind ligand generation | strained-energy of top-k y conformers | Improved |
| FlexiFlow vs SemlaFlow on molecule stability | FlexiFlow · GEOM Drugs | molecule stability: 97.3 -> 99.9 | Improved |
| FlexiFlow vs SemlaFlow on validity | FlexiFlow · GEOM Drugs | validity: 93.9 -> 92.0 | Hurt |
Closest papers by meaning
- AlphaFold Meets Flow Matching for Generating Protein Ensembles (ICML 2024 · similarity 0.90)
- Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow (ICML 2025 · similarity 0.90)
- Energy-Based Flow Matching for Generating 3D Molecular Structure (ICML 2025 · similarity 0.90)
- FlexSBDD: Structure-Based Drug Design with Flexible Protein Modeling (NeurIPS 2024 · similarity 0.89)
- Swallowing the Bitter Pill: Simplified Scalable Conformer Generation (ICML 2024 · similarity 0.89)
- FlashMol: High-Quality Molecule Generation in as Few as Four Steps (NeurIPS 2026 · similarity 0.88)
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.
