GEMS: Molecular Structure Elucidation as Learned Search over Isomer Graphs
[Sztuczna inteligencja] Autorzy: Utku Umur Acikalin, Yingheng Wang, Goncalo J. Gouveia i 3 więcej
Identifying small-molecule structures from molecular formulas and tandem mass spectra remains a bottleneck in untargeted metabolomics and natural-product discovery. Even when database retrieval or de novo prediction misses the exact structure, the resulting candidates can provide starting points for exploring nearby structures through a few bond edits. We introduce GEMS (Guided Editing of Molecular Structures), which refines candidates through learned 2-switch bond edits that preserve the molecular formula and each atom's total valence. GEMS uses MIST, a pretrained spectrum-to-fingerprint model, to predict fingerprint probabilities once per spectrum. A neural policy compares each candidate's fingerprint with these predictions, links present features to the atoms and bonds that generate them, and scores all valid edits in one forward pass. The policy is trained on shortest edit paths bet…
- Kategoria arxiv
- cs.AI
- Kategoria
- Sztuczna inteligencja