Research map / Probabilistic and scientific modeling / Molecules and proteins
MARS: Markov Molecular Sampling for Multi-objective Drug Discovery
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 |
|---|---|---|---|
| use MARS instead of the strongest baseline | molecular generation · JNK3 | PM: 0.40 -> 0.66 | Helped |
| use MARS instead of the strongest baseline | molecular generation · GSK3β + QED + SA | PM: 0.61 -> 0.68 | Helped |
| use MARS instead of the strongest baseline | molecular generation · JNK3 + QED + SA | PM: 0.43 -> 0.67 | Helped |
| use MARS instead of the strongest baseline | molecular generation · GSK3β + JNK3 + QED + SA | PM: 0.29 -> 0.55 | Helped |
| use an adaptive fragment-editing proposal instead of a random proposal (ablation) | MARS with annealed acceptance · GSK3β + JNK3 | PM: 0.32 -> 0.52 | Helped |
| use an adaptive fragment-editing proposal instead of a random proposal (ablation) | MARS with annealed acceptance · GSK3β + JNK3 + QED + SA | PM: 0.16 -> 0.55 | Helped |
| use annealed acceptance instead of always accepting candidates (ablation) | MARS with adaptive proposal · GSK3β + JNK3 + QED + SA | PM: 0.07 -> 0.55 | Helped |
| use annealed acceptance instead of hill climbing (ablation) | MARS with adaptive proposal · GSK3β + JNK3 + QED + SA | PM: 0.35 -> 0.55 | Helped |
| use hill climbing instead of annealed acceptance (ablation) | MARS with adaptive proposal · GSK3β + JNK3 | PM: 0.52 -> 0.42 | Hurt |
Closest papers by meaning
- InversionGNN: A Dual Path Network for Multi-Property Molecular Optimization (ICLR 2025 · similarity 0.88)
- Empowering Active Learning for 3D Molecular Graphs with Geometric Graph Isomorphism (NeurIPS 2024 · similarity 0.87)
- Multi-Objective Molecular Design Through Learning Latent Pareto Set (AAAI 2025 · similarity 0.86)
- Efficient Evolutionary Search Over Chemical Space with Large Language Models (ICLR 2025 · similarity 0.86)
- Neural Atoms: Propagating Long-range Interaction in Molecular Graphs through Efficient Communication Channel (ICLR 2024 · similarity 0.86)
- On the Scalability of GNNs for Molecular Graphs (NeurIPS 2024 · similarity 0.86)
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.