Research map / Probabilistic and scientific modeling / Molecules and proteins
Demystifying Multimodal Biomolecular Co-design With Intrinsic Geodesic Coupling
Keyue Qiu, Xintong Wang, Zhilong Zhang, Hao Zhou, Wei-Ying Ma
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 |
|---|---|---|---|
| learn temporal coupling during training instead of random coupling with post-hoc selection (MolPilot) | MolCRAFT-style BFN · CrossDocked SBDD | Vina Score (avg): -6.88 -> -7.16 | Improved |
| learn temporal coupling instead of synchronous coupling (MolCRAFT) | BFN · CrossDocked SBDD | Vina Dock (avg): -7.67 -> -8.32 | Improved |
| learn coupling vs MolPilot on PoseBusters validity | BFN · CrossDocked SBDD | PB-Valid: 95.9% -> 94.3% | No clear effect |
| use random coupling instead of synchronous | TargetDiff · CrossDocked SBDD | Vina Dock (avg): -7.80 -> -8.04 | Improved |
| use random coupling instead of synchronous | TargetDiff · CrossDocked SBDD | PB-Valid: 50.5% -> 58.1% | Hurt |
| freeze a-priori optimal schedule instead of adaptive bilevel optimization (ablation) | GeoCoupling · CrossDocked SBDD (1000 samples) | Vina Score mean: -6.97 -> -7.12 | Improved |
| add adaptive bilevel optimization over fixed schedule (ablation) | GeoCoupling · CrossDocked SBDD (1000 samples) | Connected (%): 91.1 -> 93.5 | Improved |
| add EMA smoothing of learned schedule (ablation) | GeoCoupling · CrossDocked SBDD (1000 samples) | Vina Score mean: -6.50 -> -7.12 | Improved |
| add EMA smoothing of learned schedule (ablation) | GeoCoupling · CrossDocked SBDD (1000 samples) | QED: 0.58 -> 0.54 | No clear effect |
| train with learned coupling instead of applying it post-hoc to MultiFlow (ablation) | GeoCoupling · Unconditional protein co-design | co-designability: 0.74 -> 0.79 | Improved |
| apply learned coupling post-hoc to MultiFlow checkpoint | MultiFlow · Unconditional protein co-design | FS clusters: 0.56 -> 0.73 | Improved |
| use learned coupling for longer proteins | GeoCoupling vs MultiFlow · Protein length 500 | co-designability: < 0.3 -> > 0.6 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MolCRAFT — MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space (ICML 2024) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- BindGPT: A Scalable Framework for 3D Molecular Design via Language Modeling and Reinforcement Learning (AAAI 2025 · similarity 0.85)
- ShEPhERD: Diffusing shape, electrostatics, and pharmacophores for bioisosteric drug design (ICLR 2025 · similarity 0.85)
- Integrating Protein Dynamics into Structure-Based Drug Design via Full-Atom Stochastic Flows (ICLR 2025 · similarity 0.85)
- UniMoMo: Unified Generative Modeling of 3D Molecules for De Novo Binder Design (ICML 2025 · similarity 0.84)
- Elucidating the Design Space of Multimodal Protein Language Models (ICML 2025 · similarity 0.84)
- Piloting Structure-Based Drug Design via Modality-Specific Optimal Schedule (ICML 2025 · 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.
