Research map / Probabilistic and scientific modeling / Molecules and proteins
Constrained Molecule Generation Modelled Using the Grammar Constraint
David Saikali, Gilles Pesant
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 belief-propagation marginals (CPBP) instead of domWDeg search | CP model of SMILES generation · 81 constrained molecule instances | instances solved: 52 -> 72 | Improved |
| use belief-propagation marginals (CPBP) instead of domWDeg search | CP model of SMILES generation · 81 constrained molecule instances | average failed nodes: 333.2 -> 8.1 | Improved |
| use belief-propagation marginals (CPBP) instead of domWDeg search | CP model of SMILES generation · 81 constrained molecule instances | average time (s): 231.2 -> 175.3 | Improved |
| add the weighted counting algorithm for the CFG constraint to CPBP (ablation) | CPBP · 81 constrained molecule instances | instances solved: 49 -> 72 | Improved |
| add the weighted counting algorithm for the CFG constraint to CPBP (ablation) | CPBP · 81 constrained molecule instances | backtrack-free generations: 3 -> 25 | Improved |
| add the weighted counting algorithm for the CFG constraint to CPBP (ablation) | CPBP · 81 constrained molecule instances | average failed nodes: 9.9 -> 8.1 | Improved |
| add the weighted counting algorithm for the CFG constraint to CPBP (ablation) | CPBP · 81 constrained molecule instances | average time (s): 298.2 -> 175.3 | Improved |
| use belief propagation guidance instead of classical CP | CP model of SMILES generation · 81 constrained molecule instances | slope of time versus search effort | Mixed |
Closest papers by meaning
- Procedural Synthesis of Synthesizable Molecules (ICLR 2025 · similarity 0.89)
- Representing Molecules as Random Walks Over Interpretable Grammars (ICML 2024 · similarity 0.88)
- Efficient Evolutionary Search Over Chemical Space with Large Language Models (ICLR 2025 · similarity 0.88)
- Domain-Agnostic Molecular Generation with Chemical Feedback (ICLR 2024 · similarity 0.88)
- Foundation Molecular Grammar: Multi-Modal Foundation Models Induce Interpretable Molecular Graph Languages (ICML 2025 · similarity 0.88)
- Molecular Optimization Model with Patentability Constraint (AAAI 2024 · 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.
