Unravelling the human taste receptor interactome: machine learning and molecular modelling insights into protein-protein interactions

Abstract The understanding of the molecular mechanisms that drive taste perception can have broad implications for public health. This study aims to expand the understanding of taste receptor-associated molecular pathways by resolving the taste receptor interactome. To this end, we propose a compreh...

Full description

Saved in:
Bibliographic Details
Main Authors: Harry Zaverdas, Filip Stojceski, Rocío Romero-Zaliz, Lampros Androutsos, Pantelis Makrygiannis, Lorenzo Pallante, Vanessa Martos, Gianvito Grasso, Marco A. Deriu, Konstantinos Theofilatos, Seferina Mavroudi
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:npj Science of Food
Online Access:https://doi.org/10.1038/s41538-025-00478-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849238255209283584
author Harry Zaverdas
Filip Stojceski
Rocío Romero-Zaliz
Lampros Androutsos
Pantelis Makrygiannis
Lorenzo Pallante
Vanessa Martos
Gianvito Grasso
Marco A. Deriu
Konstantinos Theofilatos
Seferina Mavroudi
author_facet Harry Zaverdas
Filip Stojceski
Rocío Romero-Zaliz
Lampros Androutsos
Pantelis Makrygiannis
Lorenzo Pallante
Vanessa Martos
Gianvito Grasso
Marco A. Deriu
Konstantinos Theofilatos
Seferina Mavroudi
author_sort Harry Zaverdas
collection DOAJ
description Abstract The understanding of the molecular mechanisms that drive taste perception can have broad implications for public health. This study aims to expand the understanding of taste receptor-associated molecular pathways by resolving the taste receptor interactome. To this end, we propose a comprehensive machine learning approach to accurately predict and quantify protein-protein interactions using an ensemble evolutionary algorithm. 1,647,374 positive and 894,213 negative experimentally verified protein-protein interactions were mined and characterized using 61 functional orthology, sequence, co-expression and structural features. The binary classifier significantly improved the accuracy of existing methods, reconstructing the full taste receptor interactome and was combined with a regressor that estimates the binding strength of positive interactions. Molecular dynamics investigation of top-scoring protein-protein interactions verified novel interactions of TAS2R41. The reconstructed TR interactome can catalyze the study of molecular pathophysiological mechanisms related to taste, the development of flavorsome nutrient-dense food products and the identification of personalized nutrition markers.
format Article
id doaj-art-d439cde5ffac4e16b8ba295eb0abb50c
institution Kabale University
issn 2396-8370
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series npj Science of Food
spelling doaj-art-d439cde5ffac4e16b8ba295eb0abb50c2025-08-20T04:01:42ZengNature Portfolionpj Science of Food2396-83702025-07-019111610.1038/s41538-025-00478-9Unravelling the human taste receptor interactome: machine learning and molecular modelling insights into protein-protein interactionsHarry Zaverdas0Filip Stojceski1Rocío Romero-Zaliz2Lampros Androutsos3Pantelis Makrygiannis4Lorenzo Pallante5Vanessa Martos6Gianvito Grasso7Marco A. Deriu8Konstantinos Theofilatos9Seferina Mavroudi10InSyBio PCDalle Molle Institute for Artificial Intelligence USI-SUPSI, Polo universitario Lugano—Campus EstDepartment of Computer Science and AI, Research Center in Information and Communication Technologies (CITIC), Andalusian Research Institute on Data Science and Computational Intelligence (DaSCI), University of GranadaInSyBio PCInSyBio PCPolitoBIOMedLab, Department of Mechanical and Aerospace Engineering, Politecnico di TorinoDepartment of Plant Physiology, University of GranadaDalle Molle Institute for Artificial Intelligence USI-SUPSI, Polo universitario Lugano—Campus EstPolitoBIOMedLab, Department of Mechanical and Aerospace Engineering, Politecnico di TorinoSchool of Cardiovascular and Metabolic Medicine & Sciences, King’s College LondonDepartment of Nursing, School of Health Rehabilitation Sciences, University of PatrasAbstract The understanding of the molecular mechanisms that drive taste perception can have broad implications for public health. This study aims to expand the understanding of taste receptor-associated molecular pathways by resolving the taste receptor interactome. To this end, we propose a comprehensive machine learning approach to accurately predict and quantify protein-protein interactions using an ensemble evolutionary algorithm. 1,647,374 positive and 894,213 negative experimentally verified protein-protein interactions were mined and characterized using 61 functional orthology, sequence, co-expression and structural features. The binary classifier significantly improved the accuracy of existing methods, reconstructing the full taste receptor interactome and was combined with a regressor that estimates the binding strength of positive interactions. Molecular dynamics investigation of top-scoring protein-protein interactions verified novel interactions of TAS2R41. The reconstructed TR interactome can catalyze the study of molecular pathophysiological mechanisms related to taste, the development of flavorsome nutrient-dense food products and the identification of personalized nutrition markers.https://doi.org/10.1038/s41538-025-00478-9
spellingShingle Harry Zaverdas
Filip Stojceski
Rocío Romero-Zaliz
Lampros Androutsos
Pantelis Makrygiannis
Lorenzo Pallante
Vanessa Martos
Gianvito Grasso
Marco A. Deriu
Konstantinos Theofilatos
Seferina Mavroudi
Unravelling the human taste receptor interactome: machine learning and molecular modelling insights into protein-protein interactions
npj Science of Food
title Unravelling the human taste receptor interactome: machine learning and molecular modelling insights into protein-protein interactions
title_full Unravelling the human taste receptor interactome: machine learning and molecular modelling insights into protein-protein interactions
title_fullStr Unravelling the human taste receptor interactome: machine learning and molecular modelling insights into protein-protein interactions
title_full_unstemmed Unravelling the human taste receptor interactome: machine learning and molecular modelling insights into protein-protein interactions
title_short Unravelling the human taste receptor interactome: machine learning and molecular modelling insights into protein-protein interactions
title_sort unravelling the human taste receptor interactome machine learning and molecular modelling insights into protein protein interactions
url https://doi.org/10.1038/s41538-025-00478-9
work_keys_str_mv AT harryzaverdas unravellingthehumantastereceptorinteractomemachinelearningandmolecularmodellinginsightsintoproteinproteininteractions
AT filipstojceski unravellingthehumantastereceptorinteractomemachinelearningandmolecularmodellinginsightsintoproteinproteininteractions
AT rocioromerozaliz unravellingthehumantastereceptorinteractomemachinelearningandmolecularmodellinginsightsintoproteinproteininteractions
AT lamprosandroutsos unravellingthehumantastereceptorinteractomemachinelearningandmolecularmodellinginsightsintoproteinproteininteractions
AT pantelismakrygiannis unravellingthehumantastereceptorinteractomemachinelearningandmolecularmodellinginsightsintoproteinproteininteractions
AT lorenzopallante unravellingthehumantastereceptorinteractomemachinelearningandmolecularmodellinginsightsintoproteinproteininteractions
AT vanessamartos unravellingthehumantastereceptorinteractomemachinelearningandmolecularmodellinginsightsintoproteinproteininteractions
AT gianvitograsso unravellingthehumantastereceptorinteractomemachinelearningandmolecularmodellinginsightsintoproteinproteininteractions
AT marcoaderiu unravellingthehumantastereceptorinteractomemachinelearningandmolecularmodellinginsightsintoproteinproteininteractions
AT konstantinostheofilatos unravellingthehumantastereceptorinteractomemachinelearningandmolecularmodellinginsightsintoproteinproteininteractions
AT seferinamavroudi unravellingthehumantastereceptorinteractomemachinelearningandmolecularmodellinginsightsintoproteinproteininteractions