Cong Xiaojing, Ren Wenwen, Pacalon Jody, Xu Rui, Xu Lun, Li Xuewen, de March Claire A, Matsunami Hiroaki, Yu Hongmeng, Yu Yiqun, Golebiowski Jérôme
Université Côte d'Azur, CNRS, Institut de Chimie de Nice UMR7272, Nice 06108, France.
Institutes of Biomedical Sciences, Fudan University, Shanghai 200031, People's Republic of China.
ACS Cent Sci. 2022 Mar 23;8(3):379-387. doi: 10.1021/acscentsci.1c01495. Epub 2022 Feb 18.
G protein-coupled receptors (GPCRs) conserve common structural folds and activation mechanisms, yet their ligand spectra and functions are highly diverse. This work investigated how the amino-acid sequences of olfactory receptors (ORs)-the largest GPCR family-encode diversified responses to various ligands. We established a proteochemometric (PCM) model based on OR sequence similarities and ligand physicochemical features to predict OR responses to odorants using supervised machine learning. The PCM model was constructed with the aid of site-directed mutagenesis, functional assays, and molecular simulations. We found that the ligand selectivity of the ORs is mostly encoded in the residues up to 8 Å around the orthosteric pocket. Subsequent predictions using Random Forest (RF) showed a hit rate of up to 58%, as assessed by functional assays of 111 ORs and 7 odorants of distinct scaffolds. Sixty-four new OR-odorant pairs were discovered, and 25 ORs were deorphanized here. The best model demonstrated a 56% deorphanization rate. The PCM-RF approach will accelerate OR-odorant mapping and OR deorphanization.
G蛋白偶联受体（GPCRs）具有保守的共同结构折叠和激活机制，但其配体谱和功能却高度多样。这项工作研究了嗅觉受体（ORs）——最大的GPCR家族——的氨基酸序列是如何编码对各种配体的多样化反应的。我们基于OR序列相似性和配体物理化学特征建立了一个蛋白质化学计量学（PCM）模型，以使用监督机器学习来预测OR对气味剂的反应。PCM模型是借助定点诱变、功能测定和分子模拟构建的。我们发现，ORs的配体选择性大多编码在正构口袋周围高达8埃的残基中。随后使用随机森林（RF）进行的预测显示，通过对111种ORs和7种不同支架的气味剂进行功能测定评估，命中率高达58%。发现了64对新的OR-气味剂对，并且在此使25种ORs不再是孤儿受体。最佳模型显示出56%的非孤儿受体鉴定率。PCM-RF方法将加速OR-气味剂图谱绘制和OR非孤儿受体鉴定。
