biostudies-literatureUnknown5(1)Campana PAMetabolites regulate activity of proteins and thereby affect cellular processes in all organisms. Despite extensive efforts to catalogue the metabolite-protein interactome in different organisms by employing experimental and computational approaches, the coverage of such interactions remains fragmented, particularly for eukaryotes. Here, we make use of two most comprehensive collections, BioSnap and STITCH, of metabolite-protein interactions from seven eukaryotes as gold standards to train a deep learning model that relies on self- and cross-attention over protein sequences. This innovative protein-centric approach results in interaction-specific features derived from protein sequence alone. In addition, we designed and assessed a first double-blind evaluation protocol for metabolite-proteNAR genomics and bioinformaticslqad008https://www.ebi.ac.uk/biostudies/studies/S-EPMC9887643biostudies-literatureSelf- and cross-attention accurately predicts metabolite-protein interactions.PMC9887643Nikoloski ZCampana PAfalseSelf- and cross-attention accurately predicts metabolite-protein interactions.Metabolites regulate activity of proteins and thereby affect cellular processes in all organisms. Despite extensive efforts to catalogue the metabolite-protein interactome in different organisms by employing experimental and computational approaches, the coverage of such interactions remains fragmented, particularly for eukaryotes. Here, we make use of two most comprehensive collections, BioSnap and STITCH, of metabolite-protein interactions from seven eukaryotes as gold standards to train a deep learning model that relies on self- and cross-attention over protein sequences. This innovative protein-centric approach results in interaction-specific features derived from protein sequence alone. In addition, we designed and assessed a first double-blind evaluation protocol for metabolite-prote2023-01-01T00:00:00Z2023 Mar2026-03-17T15:26:21.236Z2025-04-06T15:43:35.185ZS-EPMC98876433673340010.1093/nargab/lqad008