Mohammad Reza Zare Shahneh

This paper introduces SIMBA, a transformer-based model that learns interpretable structural similarity from tandem mass spectra to improve small molecule analog discovery.

This paper introduces MT-GEM and STEP to predict discrete structural transformations in metabolites from MS/MS spectra, achieving significant improvements over existing methods.

The paper develops a drug exposure resource from untargeted metabolomics data to identify medications without clinical records.

ModiFinder localizes structural modification sites in small molecules by aligning MS/MS spectra of known and unknown compounds.