Functions of olfactory receptors are decoded from their sequence
Cong, X.; Ren, W.; Pacalon, J.; de March, C. A.; Xu, L.; Matsunami, H.; Yu, Y.; Golebiowski, J.
Show abstract
G protein-coupled receptors (GPCRs) conserve common structural folds and activation mechanisms, yet their ligand spectra and functions are highly diversified. This work investigated how the functional variations in olfactory GPCRs (ORs)-the largest GPCR family-are encoded in the primary sequence. With the aid of site-directed mutagenesis and molecular simulations, we built machine learning models to predict OR-ligand pairs as well as basal activity of ORs. In vitro functional assay confirmed 20 new OR-odorant pairs, including 9 orphan ORs. Residues around the odorant-binding pocket dictate the odorant selectivity/specificity of the ORs. Residues that encode the varied basal activities of the ORs were found to mostly surround the conserved motifs as well as the binding pocket. The machine learning approach, which is readily applicable to mammalian OR families, will accelerate OR-odorant mapping and the decoding of combinatorial OR codes for odors.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- HTRF-based identification of small molecules targeting SARS-CoV-2 E protein interaction with ZO-1 PDZ2 93%
- A new kinetic method for measuring agonist efficacy and ligand bias using high resolution biosensors and a kinetic data analysis framework 93%
- Structural basis of SALM3 dimerization and synaptic adhesion complex formation with PTPσ 92%
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
- Small-molecule modulators of TRMT2A decrease PolyQ aggregation and PolyQ-induced cell death 94%
- Systematic Investigation of Machine Learning on Limited Data: A Study on Predicting Protein-Protein Binding Strength 92%
- C. perfringens enterotoxin-claudin pore complex: Models for structure, mechanism of pore assembly and cation permeability 92%
"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.