Research map / Probabilistic and scientific modeling / Molecules and proteins
MSAnchor: De Novo Molecular Generation from Mass Spectrometry Data with Anchor-Extended Molecular Scaffolds
Xiaohan Qin, Chao Wang, Zhengyang Zhou, Linjiang Chen, Wenjie Du, Yang Wang
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 |
|---|---|---|---|
| replace Murcko scaffold with AEMS (anchor points) (ablation) | MSAnchor · MassSpecGym | Top-1 accuracy: 2.28% -> 2.68% | Improved |
| add anchor-specific side-chain priors (ablation) | MSAnchor · MassSpecGym | Top-1 accuracy: 2.35% -> 2.68% | Improved |
| add Conditional Information Bottleneck module (ablation) | MSAnchor · MassSpecGym | Top-1 accuracy: 2.44% -> 2.68% | Improved |
| use ground-truth molecular formula instead of predicted (ablation) | MSAnchor · MassSpecGym | Top-1 accuracy: 1.72% -> 2.68% | Improved |
| MSAnchor vs DiffMS | DiffMS · CANOPUS | Top-1 accuracy: 8.34% -> 8.51% | Improved |
| MSAnchor vs DiffMS | DiffMS · CANOPUS | Top-10 accuracy: 15.44% -> 16.90% | Improved |
| MSAnchor vs DiffMS | DiffMS · MassSpecGym | Top-1 accuracy: 2.30% -> 2.68% | Improved |
| AEMS vs Murcko scaffold search space (ablation) | MSAnchor · PubChem candidate search | fraction of matching candidates: 21.4% -> 3.5% | 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.
- DiffMS — DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra (ICML 2025) · better on 10 of 10 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
- MADGEN: Mass-Spec attends to De Novo Molecular generation (ICLR 2025 · similarity 0.91)
- MS-BART: Unified Modeling of Mass Spectra and Molecules for Structure Elucidation (NeurIPS 2025 · similarity 0.90)
- MassSpecGym: A benchmark for the discovery and identification of molecules (NeurIPS 2024 · similarity 0.88)
- GLACIER: Rethinking Mass Spectrum Prediction as an Object Detection Problem (NeurIPS 2026 · similarity 0.86)
- DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra (ICML 2025 · similarity 0.85)
- Unraveling Molecular Structure: A Multimodal Spectroscopic Dataset for Chemistry (NeurIPS 2024 · similarity 0.85)
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.
