Back

Learning interpretable structural similarity from tandem mass spectra for small molecule analog discovery

Piedrahita Giraldo, J. S.; Da Silva, K. M.; Zare Shahneh, M. R.; Wang, M.; Laukens, K.; De Vijlder, T.; Bittremieux, W.

2026-06-23 bioinformatics
10.64898/2026.06.17.733050 bioRxiv
Show abstract

Analog discovery remains a central bottleneck in mass spectrometry-based untargeted metabolomics, as conventional spectral similarity scores poorly reflect molecular structure. We introduce SIMBA, a transformer-based model that infers two interpretable graph-based distances, maximum common edge subgraph and substructure edit distance, directly from tandem mass spectra. SIMBA consistently retrieves structurally closer analogs than existing methods, enabling structure-aware small molecule identification beyond exact spectral matching.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.