GEMS: Molecular Structure Identification via Guided Search over Isomer Graphs
In brief
- GEMS refines molecular candidates using AI-guided bond edits to match mass spectra.
- The method leverages mass spectra and formulas to predict and rank the most likely structures.
- Results: Hit@1 of 29.64% on NPLIB1, outperforming prior methods in accuracy and runtime.
GEMS is an AI method for identifying molecular structures from chemical formulas and mass spectra. It refines initial candidates by applying bond edits guided by learned policies. Results show significant improvements over existing approaches on two standard datasets.
This summary gives you the essentials. The full article, its figures and quotes are on cs.AI updates on arXiv.org.
Read the original articleAI-generated summary of the source, checked by rules. Report an error