| Popis: |
Imaging mass spectrometry enables spatial metabolomics, yet metabolites can be assigned only to a fraction of the data generated. METASPACE-ML is a machine learning-based approach addressing this challenge. Integrating new scores and computationally-efficient False Discovery Rate estimation, trained and evaluated on 444 representative datasets from 44 groups, METASPACE-ML surpasses the rule-based predecessor in precision, coverage, and computational efficiency. Our work helps illuminate dark matter in spatial metabolomics with machine learning. |
