Regina Barzilay

Machine learning approaches are increasingly being used to aid small-molecule structure elucidation from mass spectrometry data. Surprisingly, however, current models often fail to outperform even simple baseline methods. Here we examine why these approaches fall short and propose strategies to overcome their limitations. You have full access to this article via your institution. The advent of machine learning (ML) has led to transformative breakthroughs in biology.

replying to S. P. J. de Jong & C. A. Russell Nature Medicine https://doi.org/10.1038/s41591-026-04461-z (2026) Retrospective evaluation of influenza vaccine selection is inherently difficult due to the limited number of seasons with available effectiveness data, and the substantial noise in these estimates further compounds the challenge. Given this, reliance on a single evaluation metric is insufficient. Instead, a multifaceted framework is essential.