Machine learning decodes chemical features to identify novel agonists of a moth odorant receptor

Abstract

Odorant receptors expressed at the peripheral olfactory organs are key proteins for animal volatile sensing. Although they determine the odor space of a given species, their functional characterization is a long process and remains limited. To date, machine learning virtual screening has been used to predict new ligands for such receptors in both mammals and insects, using chemical features of known ligands. In insects, such approach is yet limited to Diptera, whereas insect odorant receptors are known to be highly divergent between orders. Here, we extend this strategy to a Lepidoptera receptor, SlitOR25, involved in the recognition of attractive odorants in the crop pest Spodoptera littoralis larvae. Virtual screening of 3 million molecules predicted 32 purchasable ones whose function has been systematically tested on SlitOR25, revealing 11 novel agonists with a success rate of 28%. Our results show that Support Vector Machine optimizes the discovery of novel agonists and expands the chemical space of a Lepidoptera OR. More, it opens up structure-function relationship analyses through a comparison of the agonist chemical structures. This proof-of-concept in a crop pest could ultimately enable the identification of OR agonists or antagonists, capable of modifying olfactory behaviors in a context of biocontrol.

Reverse chemical ecology in a moth: machine learning on odorant receptors identifies new behaviorally active agonists

“…However, we did not investigate their behavioral activity. Anyhow, the chemical structures of the newly identified SlitOR25 agonists precluded their use for pest control, as most agonists were fluorinated compounds that cannot be used in the field [ 20 ].…”

“…To reach these objectives, we focused on the broadly tuned receptors SlitOR24 and SlitOR25 [ 21 ], whose activation has been linked to larvae attraction [ 22 ] and that were thus highly relevant for a reverse chemical ecology strategy. More, SlitOR25 has been used to establish the machine learning proof-of-concept on Lepidoptera ORs [ 20 ], and the data acquired (additional ligands) are perfectly suited to be used for model improvement.…”

Machine Learning Assisted Approach for Finding Novel High Activity Agonists of Human Ectopic Olfactory Receptors

“…A correlation filter was applied to reduce the collinearity among the descriptors [ 37 ]. The threshold value for the correlation coefficient ( r ) was set to 0.95 as previously setup for OR1A1 and OR2W1 features [ 14 ] and for the moth odorant receptor [ 38 ]. Afterwards, three different methods were used for feature selection including a wrapper method: recursive feature elimination, a filter method: Gini, and an embedded method: random forest feature selection, were applied for selection of relevant subset of molecular descriptors.…”

Bitter Taste and Olfactory Receptors: Beyond Chemical Sensing in the Tongue and the Nose

“…As in the case of bitter tastants, machine learning approaches have also been developed for odorants (Lötsch et al 2019 ). These algorithms aim at predicting either new ligand-receptor pairs (Liu et al 2011 ; Audouze et al 2014 ; Bushdid et al 2018 ; Caballero-Vidal et al 2020 ; Cong et al 2020 ) or smells (Keller et al 2017 ; Poivet et al 2018 ; Nozaki and Nakamoto 2018 ; Chacko et al 2020 ; Sharma et al 2021 ), based on chemical features of the odorants.…”