Research map / Probabilistic and scientific modeling / Molecules and proteins
3DLinker: An E(3) Equivariant Variational Autoencoder for Molecular Linker Design
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Jointly generate linker graphs and 3D coordinates with E(3)-equivariant features | 3DLinker · ZINC test | Recovered (%): 81.56 -> 93.58 | Helped |
| Jointly generate linker graphs and 3D coordinates with E(3)-equivariant features | 3DLinker · ZINC test | RMSD: 1.356 -> 0.079 | Helped |
| Jointly generate linker graphs and 3D coordinates with E(3)-equivariant features | 3DLinker · ZINC test fragments | SC_RDKit average: 0.675 -> 0.683 | Helped |
| Use the learned latent representation for QED prediction | 3DLinker · ZINC test | QED RMSE: 0.1077 -> 0.0833 | Helped |
| Provide the ground-truth anchor nodes instead of predicting anchors | 3DLinker · ZINC test | Recovered (%): 93.58 -> 94.69 | Helped |
| Add equivariant features (ablation) | 3DLinker · ZINC test | RMSD: 1.352 -> 0.079 | Helped |
| Add equivariant features (ablation) | 3DLinker · ZINC test | Recovered (%): 86.59 -> 93.58 | Helped |
| Add the coordinate update strategy (ablation) | 3DLinker · ZINC test | Recovered (%): 39.94 -> 93.58 | Helped |
| Add the coordinate update strategy (ablation) | 3DLinker · ZINC test | RMSD: 0.399 -> 0.079 | Helped |
| Add the coordinate update strategy (ablation) | 3DLinker · ZINC test fragments | SC_RDKit average: 0.670 -> 0.683 | Helped |
Closest papers by meaning
- Learning Disentangled Equivariant Representation for Explicitly Controllable 3D Molecule Generation (AAAI 2025 · similarity 0.91)
- Manipulating 3D Molecules in a Fixed-Dimensional E(3)-Equivariant Latent Space (NeurIPS 2025 · similarity 0.91)
- Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation (ICLR 2024 · similarity 0.89)
- Lift Your Molecules: Molecular Graph Generation in Latent Euclidean Space (ICLR 2025 · similarity 0.89)
- Molecule Design by Latent Prompt Transformer (NeurIPS 2024 · similarity 0.88)
- Beyond Atoms: Enhancing Molecular Pretrained Representations with 3D Space Modeling (ICML 2025 · 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.