OdoriFy: A conglomerate of artificial intelligence–driven prediction engines for olfactory decoding

Ria Gupta,Aayushi Mittal,Vishesh Agrawal,Sushant Gupta,Krishan Gupta,Rishi Raj Jain,Prakriti Garg,Sanjay Kumar Mohanty,Riya Sogani,Harshit Singh Chhabra,Vishakha Gautam,Tripti Mishra,Debarka Sengupta,Gaurav Ahuja

doi:10.1016/j.jbc.2021.100956

Abstract

The molecular mechanisms of olfaction, or the sense of smell, are relatively underexplored compared with other sensory systems, primarily because of its underlying molecular complexity and the limited availability of dedicated predictive computational tools. Odorant receptors (ORs) allow the detection and discrimination of a myriad of odorant molecules and therefore mediate the first step of the olfactory signaling cascade. To date, odorant (or agonist) information for the majority of these receptors is still unknown, limiting our understanding of their functional relevance in odor-induced behavioral responses. In this study, we introduce OdoriFy, a Web server featuring powerful deep neural network–based prediction engines. OdoriFy enables (1) identification of odorant molecules for wildtype or mutant human ORs (Odor Finder); (2) classification of user-provided chemicals as odorants/nonodorants (Odorant Predictor); (3) identification of responsive ORs for a query odorant (OR Finder); and (4) interaction validation using Odorant–OR Pair Analysis. In addition, OdoriFy provides the rationale behind every prediction it makes by leveraging explainable artificial intelligence. This module highlights the basis of the prediction of odorants/nonodorants at atomic resolution and for the ORs at amino acid levels. A key distinguishing feature of OdoriFy is that it is built on a comprehensive repertoire of manually curated information of human ORs with their known agonists and nonagonists, making it a highly interactive and resource-enriched Web server. Moreover, comparative analysis of OdoriFy predictions with an alternative structure-based ligand interaction method revealed comparable results. OdoriFy is available freely as a web service at https://odorify.ahujalab.iiitd.edu.in/olfy/.

Highlights

Odorant molecules that mediate vital behavioral responses, such as social communication, identification and quality assessment of food [1], and the recognition of prey and predators [2, 3]
OdoriFy is an open-source Web server with deep neural network–based prediction models coupled with explainable artificial intelligence functionalities
To ease user experience in converting their query chemicals into the Simplified MolecularInput Line-Entry System (SMILES) format, OdoriFy provides a direct link to the OPSIN Web server [56]

Summary

Introduction

Odorant molecules that mediate vital behavioral responses, such as social communication, identification and quality assessment of food [1], and the recognition of prey and predators [2, 3]. OdoriFy is capable of identifying agonists for human ORs (Odor Finder), prediction of odorant molecules (Odorant Predictor), identification of responsive ORs for the user-supplied chemicals The output format of OR Finder prediction engine is the same as that of Odorant Predictor, except it provides the FASTA sequences of the predicted cognate ORs against the user queried chemicals and information on the decision-making amino acids of the OR sequences.

Results

Conclusion