Confronting spurious evaluations of computational methods in small molecule mass spectrometry (opens in new tab)

Mass spectrometry-based metabolomics detects thousands of small molecule-associated signals in biological samples, but the vast majority cannot be structurally identified. Mounting interest in this metabolomic 'dark matter' has spurred the development of dozens of machine-learning models for structural annotation of small molecules from their MS/MS spectra. Here, we expose a fundamental flaw in the longstanding paradigm by which these models have been evaluated. We show that a trivial machine...