BitterMatch: recommendation systems for matching molecules with bitter taste receptors

• DOI: 10.1186/s13321-022-00612-9
• Publication Date: 2022-07-07T14:08:59Z
• Authors: Eitan Margulis; Yuli Slavutsky; Tatjana Lang; Maik Behrens; Yuval Benjamini; Masha Y. Niv
• Keywords: Taste receptor; Bitter Taste

Bitterness is an aversive cue elicited by thousands of chemically diverse compounds. Bitter taste may prevent consumption foods and jeopardize drug compliance. The G protein-coupled receptors for bitter taste, TAS2Rs, have species-dependent number subtypes varying expression levels in extraoral tissues. Molecular recognition TAS2R physiologically important, presents a challenging case study ligand-receptor matchmaking. Inspired hybrid recommendation systems, we developed new set similarity features, created the BitterMatch algorithm that predicts associations ligands to with ~ 80% precision at 50% recall. Associations several compounds were tested in-vitro, resulting 42% encouraging performance was achieved including receptor properties integrating experimentally determined chemical ligand-to-ligand similarities.BitterMatch can predict off-targets drugs, identify novel guide flavor design. features capture information regarding molecules their receptors, which could inform various chemoinformatic tasks. Inclusion neighbor-informed similarities improves as experimental data mounts, provides generalizable framework molecule-biotarget matching.